Publications

Reliability modeling for perception systems in autonomous vehicles: A recursive event-triggering point process approach

Published in ‘Transportation Research Part C: Emerging Technologies’, 2024

Abstract

Ensuring the reliability of sensor-fusion-based perception systems is crucial for the safe deployment of autonomous vehicles. Such systems function through a sequence of interconnected stages, where errors in upstream stages may propagate to downstream stages and trigger additional errors. The cross-stage error propagation conceptually exists and makes errors in different stages, not independent, posing model challenges, estimation challenges, and data challenges for reliability modeling. The existing methods cannot be applied to address all these challenges. Thus, this paper presents a recursive event-triggering point process to explicitly consider the error propagation based on the simulated data. The data are simulated from a proposed error injection framework, which can generate various errors from a sequence of interconnected stages in a perception system. The latent and probabilistic error propagation information is incorporated into a modified expectation–maximization (EM) algorithm for parameter estimation. The numerical and physics-based simulation case studies demonstrate the prediction accuracy and interpretability of the proposed modeling methodology.

Key Contributions

• Automated driving system development
• Proposes recursive event-triggering point process
• Develops modified EM estimation algorithm
• Presents simulation error injection framework
• Differentiates primary and propagated errors
• Models redundant multi-module perception systems

Download paper

Citation

Inside Out: Emotion GaRage Vol. V

Published in ‘Adjunct Proceedings of the 16th International Conference on Automotive User Interfaces and Interactive Vehicular Applications’, 2024

Abstract

The rapid advancement of automated vehicles has aroused the curiosity of researchers in the automotive field. Understanding the emotional aspects of this technology is critical to improving human-vehicle interactions. The topics of the proposed workshop will be expanded from internal to external empathetic interface designs of automated vehicles. The workshop will gather researchers and practitioners to brainstorm and design affective internal and external interfaces for automated vehicles, targeting specific use cases within the social context. During the workshop, participants will use an affective design tool and generative AI to prototype affective interface designs in automated vehicles. With this creative approach, we aim to expand the knowledge of affective eHMIs in addition to in-vehicle designs and understand social factors that contribute to the user perceptions of automated vehicles.

Key Contributions

• Emotional and affective computing
• Expands focus to external vehicle interfaces
• Aims to create design guidelines
• Addresses social context and ethical issues
• Prototype affective interface designs

Download paper

Citation

RSS Demonstrator: a Tool for User Experience Interactions with Automated Driving Safety Models

Published in ‘Adjunct Proceedings of the 15th International Conference on Automotive User Interfaces and Interactive Vehicular Applications’, 2023

Abstract

Safety Assurance remains a challenge for the large-scale deployment of Automated Driving Systems (ADS). Safety models monitor the performance of the ADS. Most safety models are validated both in simulation and during on-road tests. However, first-hand experiences and analysis of ADS safety models are not easily accessible to the general research community. This paper introduces the RSS driving demonstrator an open-source simulation tool that enables first-hand experience of the Responsibility Sensitive Safety (RSS) safety model proposed by Intel and Mobileye and adopted by several Automotive Industry standards and regulatory frameworks. The RSS demonstrator enables first-hand interactions and experience of ADS safety model restrictions in both automated and manual driving conditions. As a User Experience (UX) tool, it provides quantitative safety metrics and flexible user interaction features. The results indicate it served to both evangelize the RSS ADS safety model with laymen population and is a versatile tool for Automotive UX development.

Key Contributions

• Safety analysis and validation
• User experience design and evaluation
• Automated driving system development
• Tool development and demonstration
• Human-computer interaction design

Download paper

Citation

“Play Your Anger”: A report on the empathic in-vehicle interface workshop

Published in ‘Adjunct Proceedings of the 15th International Conference on Automotive User Interfaces and Interactive Vehicular Applications’, 2023

Abstract

Empathic in-vehicle interfaces are critical in improving user safety and experiences. There has been much research on how to estimate drivers’ affective states, whereas little research has investigated intervention methods that mitigate potential impacts from the driver’s affective states on their driving performance and user experiences. To enhance the development of in-vehicle interfaces considering emotional aspects, we have organized a workshop series to gather automotive user interface experts to discuss this topic at the International ACM Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutoUI). The present paper focuses particularly on the intervention methods created by the experts and proposes design recommendations for future empathic in-vehicle interfaces. We hope this work can spark lively discussions on the importance of drivers’ affective states in their user experience of automated vehicles and pose the right direction.

Key Contributions

• Presents novel empathic interface prototypes.
• Offers expert-driven design recommendations.
• Addresses anger, frustration, and fear.
• Details a three-phase design process.
• Focuses on specific intervention methods.

Download paper

Citation

Emotion GaRage Vol. IV: Creating empathic in-vehicle interfaces with generative AIs for automated vehicle contexts

Published in ‘Proceedings of ACM’s Automotive UI 2023’, ACM 2023

Abstract

This workshop aims to design advanced empathic user interfaces for in-vehicle displays, particularly for high-level automated vehicles (SAE level 3 or higher). Incorporating model-based approaches for understanding human emotion regulation, it seeks to enhance the user-vehicle interaction. A unique aspect of this workshop is the integration of generative artificial intelligence (AI) tools in the design process. The workshop will explore generative AI’s potential in crafting contextual responses and its impact on user experience and interface design. The agenda includes brainstorming on various driving scenarios, developing emotion-oriented intervention methods, and rapid prototyping with AI tools. The anticipated outcome includes practical prototypes of affective user interfaces and insights on the role of AI in designing human-machine interactions. Through this workshop, we hope to contribute to making automated driving more accessible and enjoyable.

Key Contributions

• Automated driving system development
• Emotional and affective computing
• Designs advanced empathic user interfaces
• Integrates generative AI in design process
• Applies model-based emotion regulation methods

Download paper

Citation

Application of Responsibility-Sensitive Safety in Areas with Limited Visibility: Occlusions in RSS

Published in ‘2023 IEEE 26th International Conference on Intelligent Transportation Systems’, IEEE 2023

Abstract

Areas of limited visibility are common in day-to-day traffic: be it static buildings, parked vehicles, traffic participants blocking the vehicle’s line of sight, harsh weather conditions or just narrow curves that impede the automated driving sensor suite to inspect the road ahead. Autonomous vehicles have to be able to safely cope with this kind of constraints. The Responsibility-Sensitive Safety model (RSS) demands vehicles to exercise caution with respect to occlusions and to consider also occluded road agents. This paper provides a concrete implementation of how occlusions in RSS can be addressed and investigates the balance between safety and usefulness of the model when a reasonably foreseeable behavior of occluded road agents is assumed. We perform occlusion experiments in urban as well as on highway scenarios with the driving simulation platform CARLA applying different parameterization of the agents kinematic properties and the safety model parameters to analyse and judge the consequences with respect to safe driving and overcautious driving behaviors.

Key Contributions

• Safety analysis and validation
• Implements occlusion handling with artificial vehicles
• Evaluates approach in urban/highway scenarios
• Shows aggressive parameters can reduce usability
• Analyzes real-world data for assumptions
• Demonstrates collision mitigation via simulation

Download paper

Citation

White Paper-Literature Review on Kinematic Properties of Road Users for Use on Safety-Related Models for Automated Driving Systems

Published in IEEE Standards, 2022

Abstract

This document presents a review of relevant literature (e.g., standards, regulations, and scientific publications) that investigated kinematic behavior of road users. This review is intended to serve as a key contribution to the Automated Driving Systems (ADS) research and industry communities, as well as to current standardization efforts, such as IEEE Std 2846, IEEE Standard for Assumptions in Safety-Related Models for Automated Driving Systems.

Key Contributions

• Literature review road actors kinematic behavior
• Systematic data organization of kinematic parameter values
• Kinematic data contextualization
• Research gap analysis

Download paper

Citation

User experience design in the era of automated driving

Published in Journal Name, 2023

Abstract

This book is dedicated to user experience design for automated driving to address humane aspects of automated driving, e.g., workload, safety, trust, ethics, and acceptance. Automated driving has experienced a major development boost in recent years. However, most of the research and implementation has been technology-driven, rather than human-centered. The levels of automated driving have been poorly defined and inconsistently used. A variety of application scenarios and restrictions has been ambiguous. Also, it deals with human factors, design practices and methods, as well as applications, such as multimodal infotainment, virtual reality, augmented reality, and interactions in and outside users. This book aims at 1) providing engineers, designers, and practitioners with a broad overview of the state-of-the-art user experience research in automated driving to speed-up the implementation of automated vehicles and 2) helping researchers and students benefit from various perspectives and approaches to generate new research ideas and conduct more integrated research.

Key Contributions

• State-of-the-art UX Design in Automated Driving
• Foundational theory compilation
• UX design methods and frameworks
• Interface application and case studies

Download paper

Citation

Special Issue

Published in ‘MDPI Sensors’, 2022

Abstract

Connected and automated driving technologies have the potential to revolutionize transportation by facilitating mobility services to a wider population, improving safety and traffic efficiency. Automated driving technology is expected to reduce the number of accidents caused by human error and avert deadly crashes, ensure mobility for all, including old and impaired individuals, allow the human driver to perform alternative (secondary) tasks, increase traffic flow efficiency, reduce fuel consumption, and lower emissions.

Driven by these goals, humankind is experiencing an exponential growth in vehicle automation taking over the monitoring of surroundings and vehicle control tasks from human drivers in a quest towards full autonomy. Connected and automated vehicles are equipped with multimodal sensors that allow continuous perception and monitoring of driving tasks to assist drivers in lower levels of SAE automation or to fully take control of driving tasks under full SAE automation. Numerous sensors, both inside and outside vehicles, allow the detection and identification of oncoming obstacles, the determination of their velocity, and the prediction of future behaviours to avoid potential collisions. Each sensor has its own strengths and weaknesses in terms of range, accuracy, energy consumption. and sensitivity towards external conditions such as weather and light. Automated vehicles usually rely on a mix of signals to improve operational reliability and robustness under the dynamic external conditions of real-world deployments. Generally, we can divide external AV sensors into two major groups: active and passive. Active sensors generate an active signal (electromagnetic or light) transmitted to the external environment to analyse its reflection (e.g., radar, lidar), whereas passive sensors just record the information from the environment (e.g., camera). Additionally, there have been advances in intelligent transportation infrastructure to monitor road users, perform predictive analytics, and facilitate collaborative perception services and remote vehicle control.

The increasing commercial availability of conditional automation (SAE level 3) and the incoming Robotaxi services (SAE Level 4) have also resulted in an increase in in-cabin monitoring sensors dedicated to monitoring driver and passenger behaviours. Multimodal in-cabin monitoring systems are crucial enablers for successfully managing automated vehicle operations. These systems enable the detection of the driver/passenger’s physiological state and activity to assess their readiness to take over control of the vehicle if required as well as to monitor their safety. Driving monitoring solutions provide information on occupants’ fatigue, distraction, discomfort, and stress. Furthermore, they can help to verify that automation is used properly by evaluating engagement in the driving monitoring task or the inherent risk of the non-driving tasks.

This Special issue aims to collect original theoretical or empirical articles on different sensing technologies, solutions, and applications for automated vehicles.

Key Contributions

• Research methodology development
• Experimental design and analysis
• Technical implementation and validation

Download paper

Citation

Quantifying Error Propagation in Multi-Stage Perception System of Autonomous Vehicles via Physics-Based Simulation

Published in Proceedings of the IEEE 2022 Winter Simulation Conference, IEEE 2023

Abstract

Ensuring the safety of autonomous vehicle (AV) relies on accurate prediction of error occurrences in its perception system. Due to the inter-stage functional dependence, the error occurred at a certain stage may be propagated to the following stage and generate extra errors. To quantify the error propagation, this paper adopts the physics-based simulation, which enables fault injection at different stages of an AV perception system to generate error event data for error propagation modeling. A multi -stage Hawkes process (MSHP) is proposed to predict the error occurrences in each stage, with error propagation represented as a latent triggering mechanism. With explicitly considering the error propagation mechanism, the proposed outperforms benchmark methods in predicting error occurrence in a physics-based simulation of a multistage AV perception system. The proposed two-step likelihood-based algorithm accurately estimates the model coefficients in a numerical simulation case study.

Key Contributions

• Integrated simulation and modeling framework
• Fault-injection simulation for data generation
• Statistical error propagation modeling
• Model parameter estimation algorithm
• Model validation and performance benchmarking

Download paper

Citation

IEEE Standard for Assumptions in Safety-Related Models for Automated Driving Systems

Abstract

This standard applies to road vehicles. It defines a minimum set of reasonable assumptions and foreseeable scenarios that shall be considered in the development of safety related models that are part of an automated driving system (ADS). Scope: This standard applies to road vehicles. For a set of scenarios, a minimum set of assumptions regarding reasonably foreseeable behaviors of other road users are defined that shall be considered in the development of safety-related models for automated driving systems (ADS). This standard further defines a list of attributes common to contributed safety-related models and methods to help verify whether a safety-related model takes the minimum set of assumptions into consideration. An informative annex instantiates several examples of how the proposed minimum set of assumptions could be employed in ADS development. Sources of uncertainty, such as prediction or perception errors, are out of scope to this standard. This standard does not guarantee the safety of the overall system in all scenarios. Purpose: Government and Industry alike need an open, transparent, and technology-neutral standard that provides guidance useful for evaluating the performance of an ADS. This guidance consists of a minimum set of assumptions with bounds on reasonably foreseeable behaviors of other road users used in the development of safety-related models.

Key Contributions

• Minimum assumption definition for ADAS
• Reasonable Foreseeable scenario specification
• Technology-neutral evaluation guidance
• Model verification methodology

Download paper

BibTeX

@ARTICLE{9761121, author={}, journal={IEEE Std 2846-2022}, title={IEEE Standard for Assumptions in Safety-Related Models for Automated Driving Systems}, year={2022}, volume={}, number={}, pages={1-59}, keywords={IEEE Standards;Autonomous vehicles;Vehicle safety;Autonomous driving;Vehicle driving;Data privacy;Decision making;ADS;ADS-operated vehicle;automated driving system;assumption;automated vehicle;autonomous vehicles;AV;decision-making;IEEE 2846}, doi={10.1109/IEEESTD.2022.9761121}}

Empathic vehicle design: Use cases and design directions from two workshops

Published in ‘Proceedings of ACM’s Computer Human Interaction Conference (CHI)’, ACM 2022

Abstract

Empathic vehicles are expected to improve user experience in automated vehicles and to help increase user acceptance of technology. However, little is known about potential real-world implementations and designs using empathic interfaces in vehicles with higher levels of automation. Given advances in affect detection and emotion mitigation, we conducted two workshops (N1 =24, N2 = 22, Ntotal = 46) on the design of empathic vehicles and their potential utility in a variety of applications. This paper recapitulates key opportunities in the design and application of empathetic interfaces in automated vehicles which emerged from the two workshops hosted at the ACM AutoUI conferences.

Key Contributions

• Emphathetic HMI design in Automotive
• Generative AI prototyping
• Workshop organization and community building

Download paper

Citation

Emotion GaRage Vol. III: A Workshop on Affective In-Vehicle Display Applications

Published in ‘Adjunct Proceedings of the 14th International Conference on Automotive User Interfaces and Interactive Vehicular Applications’, ACM 2022

Abstract

Empathic in-vehicle interfaces can address driver affect and mitigate decreases in driving performance and behavior that are associated with emotional states. Empathic vehicles can detect and employ a variety of intervention modalities to change user affect and improve user experience. Challenges remain in the implementation of such strategies, as a broader established view of practical intervention modalities and strategies is still absent. Therefore, we propose a workshop that aims to bring together researchers and practitioners interested in affective interfaces and in-vehicle technologies as a forum for the development of displays and alternatives suitable to various use case situations in current and future vehicle states. During the workshop, we will focus on a common set of use cases and generate approaches that can suit different user groups. By the end of this workshop, researchers will create a design flowchart for in-vehicle affective display designers when creating displays for an empathic vehicle.

Key Contributions

• HCI Interaction Design
• Emotional and affective computing
• HCI Prototyping
• Workshop organization and community building

Download paper

Citation

Driver emotions in automated vehicles

Abstract

There is little doubt that driving generates emotional responses, whether that’s the joy of freedom, the boredom of stop-and-go traffic or anger towards unsafe maneuvers. In this chapter we provide an overview of emotion research applied to the automotive context and highlight the impact of emotional states in varying levels of driving automation. We review the most critical research findings on the impact of emotional states in driving performance including reaction time and take-over readiness. We also discuss the application of emotion regulation strategies related to the driving task. Finally, we analyze the research challenges still present for robust emotional classification and personalization in their application to in-vehicle interactions. This technology offers great potential for the development of emotionally-aware in-cabin driver assistants which will play a critical role in the future of automated driving user experience development.

Key Contributions

• Foundational theory compilation
• UX design methods and frameworks
• Interface application and case studies
• Academia-industry knowledge transfer
• Holistic user-centered design advocacy

Download paper

Citation

To err is human: The role of human derived safety metrics in an age of automated vehicles

Published in ‘SAE Technical Paper’, SAE 2021

Abstract

As industry races to complete technical development of automated driving systems (ADS), important questions are being raised about how to measure the safety of such systems and the overall safety of Automated Vehicles (AVs). Traffic safety engineers have for decades utilized metrics to assess the safety of human drivers and measurements such as Time To Collision (TTC) and Time Headway (THW) have proven to be a useful indicator of increased risk of an accident for human drivers. But what if we can do better with AVs? Are human driving derived risk metrics meaningful for a self-driving vehicle? Recently, the Institute for Automated Mobility (IAM) published a set of metrics defined specifically for self-driving vehicles that provide a thorough assessment of the safety of an AV. While humans must use estimation and cautious judgement to make decisions, AVs can use precise measurement techniques via sensors and correlate multiple sources of data in real time. Utilizing information such as the reaction time of the ADS, the braking capability of the AV and more, the IAM proposed metrics allow for the assessment of the safety of an AV to be accurately measured, not as a notion of approximated risk, but as a binary calculation of safety. In this paper we analyze, compare and contrast human driving, risk-oriented safety metrics with the more definitive metrics proposed for AVs. We answer important questions about the necessary evolution of human derived metrics to ensure they are meaningful in the assessment of the safety of an AV, as well as whether novel metrics proposed for AVs can be used to better understand and assess the safety performance of AVs when compared to historical safety measures. Our research proves that AV-based assessment metrics can provide better insight into the safety of both AVs and human drivers.

Key Contributions

• Safety analysis and validation
• Automated driving system development

Download paper

Citation

On responsibility sensitive safety in car-following situations-a parameter analysis on german highways

Published in Proceedings of the IEEE Intelligent Vehicles Symposium (IV), IEEE 2021

Abstract

The need for safety in automated driving is undisputed. Since automated vehicles are expected to reduce the number of fatalities in road traffic significantly, hundreds of millions of test kilometers would be required for statistical safety validation [1]. Physics-based safety verification approaches are promising in order to reduce this validation effort. Towards this goal, Mobileye introduced the concept of Responsibility-Sensitive Safety (RSS). In RSS, bounds for the reasonable worst-case behavior of traffic participants are assumed to be given, such as the reaction time or the maximum deceleration. These parameters have a crucial effect on the applicability of the approach: choosing conservative parameters likely hinders traffic flow, while the opposite could lead to collisions, as the assumptions are violated. Thus, in this work, we focus on finding reasonable parameters of RSS. Based on the physical limits, legal requirements and human driving behavior, we propose scopes and parameter sets that allow for a sound safety verification while not hindering traffic flow. Furthermore, we present an approach that explains seemingly frequent human drivers’ RSS violations on highways and may lead to a useful extension of RSS.

Key Contributions

• Safety analysis and validation
• Automated driving system development
• Verification and validation methods
• Parameter Analysis

Download paper

Citation

MISO-V: Misbehavior detection for collective perception services in vehicular communications

Published in ‘Proceedings of IEEE Intelligent Transportation Systems Conference 2021’, IEEE 2021

Abstract

Recently, Collective Perception Messages (CPM) that carry additional information about the surrounding environment beyond Basic Safety Messages (BSM) or Cooperative Awareness Messages (CAM) have been proposed to increase the situational awareness for Connected and Automated Vehicles (CAV) in Intelligent Transportation Systems. However, blindly trusting perception information from neighbors that cannot be locally verified is dangerous given the safety impact that erroneous or malicious information might have. This paper addresses the data trust challenge of CPMs, proposing a misbehavior detection scheme called MISO- V (Multiple Independent Sources of Observations over V2X) that leverages the inherently overlapping nature of the perception observations from multiple vehicles to verify the semantic correctness of the V2X data and improve the data trust and robustness of V2X systems. CPM-enabled CAVs are implemented and MISO-V performance is evaluated in CARLA-based simulation tool, where falsified V2X packets presenting a ghost car are injected in a suburban T-junction scenario with other cars. The results show that MISO- V is very effective in detecting the ghost car attacks and removing the impact of such misbehavior from influencing the receiver and offers a conservative and sensible approach towards trustworthy Collective Perception Services for CAVs.

Key Contributions

• Research methodology development
• Experimental design and analysis
• Technical implementation and validation

Download paper

Citation

PURSS: Towards Perceptual Uncertainty Aware Responsibility Sensitive Safety with ML.

Published in ‘Proceedings of 2020 AAAI Conference’, AAAI 2020

Abstract

Automated driving is an ML-intensive problem and its safety depends on the integrity of perception as well as planning and control. Responsibility Sensitive Safety (RSS) is a recent approach to promote safe planning and control that relies on perfect perception; however, perceptual uncertainty is always present, and this causes the possibility of misperceptions that can lead an autonomous vehicle to allow unsafe actions. In this position paper, we sketch a novel proposal for a formal model of perception coupled with RSS to help mitigate the impact of misperception by using information about perceptual uncertainty. The approach expresses uncertainty as imprecise perceptions that are consumed by RSS and cause it to limit actions to those that support safe behaviour given the perceptual uncertainty. We illustrate our approach using examples and discuss its implications and limitations.

Key Contributions

• Safety analysis and validation

Download paper

Citation

How safe is safe enough? Automatic safety constraints boundary estimation for decision-making in automated vehicles

Published in Proceedings of IEEE Intelligent Vehicle Symposium 2020, IEEE 2020.

Abstract

The determination of safety assurances for automated driving vehicles is one of the most critical challenges in the industry today. Several behavioral safety models for automated driving have been proposed recently and standards discussions are on the way. In this paper we present a method to automatically explore the performance of automated vehicle (AV) safety models utilizing robustness of Metric Temporal Logic (MTL) specifications as a continuous metric of safety. We present a case study of the Responsibility Sensitive Safety model (RSS), introducing a safety evaluation pipeline based on the CARLA driving simulator, RSS and a set of safety-critical driving scenarios. Our method automatically extracts safety relevant profiles for these scenarios providing practical parametric boundaries for implementation. Furthermore, we evaluate the trade-offs between safety and utility within the safe RSS parameter space through a proposed naturalistic benchmark challenge that we open-sourced. We analyze different RSS parameter configurations including assertive and more conservative settings, extracted by our specification-driven framework. Our results show that while maintaining the safety boundaries, the extracted RSS configuration for assertive driving behavior achieves the highest utility.

Key Contributions

• Safety boundary estimation framework
• Parametric and non-parametric estimation methods
• Simulation-based data generation and validation
• Real-world data application and analysis
• Systematic safety parameter definition

Download paper

Citation

Evaluation of responsibility-sensitive safety (rss) model based on human-in-the-loop driving simulation

Published in In proceedings of the 2020 IEEE 23rd International Conference on Intelligent Transportation Systems, IEEE 2020.

Abstract

Safety is an important challenge in the development of automated vehicles (AVs). To help with the challenge of achieving higher safety in the decision making of AVs, Intel and Mobileye have proposed a parameterized model named Responsibility-Sensitive Safety (RSS). Previous studies have demonstrated that RSS has the potential to improve the safety performance of automated vehicles. However, RSS could lead to a considerable car-following distance depending on the parameter values chosen for the model, which could reduce traffic efficiency. To improve the efficiency of RSS applied to Adaptive Cruise Control (ACC) systems, previous work proposed an efficiency-optimal (referred as “Efficiency-optimal RSS”) variation of the RSS model that involves different triggering conditions of a proper response. Therefore, in this paper a human-in-the-loop driving simulation experiment was conducted to evaluate the performance and acceptance of different safety methods. The RSS model and the efficiencyoptimal variant were embedded in an ACC system based on Model Predictive Control (MPC) algorithm. Two car-following scenarios with a sudden deceleration of lead vehicle at various time headways were simulated to evaluate the human perception and response of the different models. Results show that the original RSS model improves subjective safety judgment of human drivers. While the Efficiency-optimal RSS variant has a lower subjective safety score when compared to original RSS, it significantly reduces driver’s emergency braking reactions when compare to an ACC only system.

Key Contributions

• Human-in-the-loop evaluation framework
• Comparative performance analysis (RSS vs. Human)
• Safety model parameter sensitivity analysis
• Empirical validation of a formal safety model
• Simulation-based model calibration methodology

Download paper

Citation

Emotion GaRage Vol. II A Workshop on Affective In-Vehicle Display Design

Published in ‘Proceedings of 12th International Conference in Automotive User Interfaces and Interactive Vehicular Applications’, 2020

Abstract

Driver performance and behavior can be partially predicated based on one’s emotional state. Through ascertaining the emotional state of passengers and employing various mitigation strategies, empathic cars can show potential in improving user experience and driving performance. Challenges remain in the implementation of such strategies, as individual differences play a large role in mediating the effect of affective intervention. Therefore, we propose a workshop that aims to bring together researchers and practitioners interested in affective interfaces and in-vehicle technologies as a forum for the development of targeted emotion intervention methods. During the workshop, we will focus on a common set of use cases and generate approaches that can suit different user groups. By the end of this short workshop, researchers will determine ideal intervention methods for prospective user groups. This will be achieved through the method of insight combination to generate and discuss ideas.

Key Contributions

• Affective Computing in Automotive
• Emotion-Aware HMI Design
• Community Building

Download paper

Citation

Auto-UI Global Perspectives

Published in ACM IX Interaction Journal, 2020

Abstract

ACM SIGCHI Auto-UI is a growing community, but one in which some continents were less involved than expected and hoped for. For the 2019 conference in Utrecht, the Netherlands, we made various targeted attempts to grow and diversify our international community, with support from the ACM SIGCHI Development Fund. Our efforts resulted in a growth in the number of Asian participants, which made up almost 20 percent of the attendees. In this blog, we briefly reflect on our initiatives and on a panel discussion focusing on research topics that matter more globally to the Auto-UI field.

Key Contributions

• Research methodology development
• Experimental design and analysis
• Technical implementation and validation

Download paper

Citation

Agents, environments, scenarios: A framework for examining models and simulations of human-vehicle interaction

Published in ‘Transportation research interdisciplinary perspectives’, 2020

Abstract

This paper provides a framework for examining human-vehicle interactions with respect to three dimensions that can involve models or simulations: the agents, the environments, and the scenarios. Agents are considered on a spectrum from human to artificial actors. Environments are considered on a spectrum from simulated to real. Scenarios are considered on a spectrum from constrained to unconstrained. It is argued that these three dimensions capture key differences in research approaches within the field of human-vehicle interaction, and that explicitly situating research and discussions within this framework will allow researchers to better compare and contrast research outcomes and contributions. The framework is used to locate different disciplines in the community with respect to one another, and to identify areas which are as-yet unexplored.

Key Contributions

• Human-computer interaction design
• Dimensions of simulation models
• Automated Driving Development

Download paper

Citation

Towards standardization of AV safety: C++ library for responsibility sensitive safety

Published in ‘Proceedings of the IEEE Intelligent Vehicle Symposium 2019’, IEEE 2019

Abstract

The need for safety in Automated Driving (AD) is becoming increasingly critical with the accelerating deployment of this technology. Beyond functional safety, industry must guarantee the operational safety of automated vehicles. Towards that end, Mobileye introduced the Responsibility Sensitive Safety (RSS), a model-based approach to Safety [1]. In this paper we expand upon this work introducing the C++ Library for Responsibility Sensitive Safety, an open source executable that implements a subset of RSS. We provide architectural details to integrate the C++ Library for Responsibility Sensitive Safety with AD Software pipelines as safety module overseeing decision making of driving policies. We illustrate this application with an example integration with the Baidu Apollo AD stack and simulator, [2] and [3], that provides safety validation of the planning module. Furthermore, we show how the C++ Library for Responsibility Sensitive Safety can be used to explore the usefulness of the RSS model through parameter exploration and analysis on minimum safe longitudinal distance, (dmin), considering different weather conditions. We also compare these results with half-of-speed rule followed in some parts of the world. We expect that the C++ Library for Responsibility Sensitive Safety becomes a critical component of future tools for formal verification, testing and validation of AD safety and that it helps bootstrap the AD research efforts towards standardization of safety.

Key Contributions

• Safety analysis and validation
• Standardized C++ library implementation
• Modular software architecture design
• Verification and validation methodology
• Open-source safety model deployment

Download paper

Citation

The SKYNIVI experience: evoking startle and frustration in dyads and single drivers

Published in ‘Proceedings of the IEEE International Conference in Intelligent Transportations Systems 2019’, IEEE 2019

Abstract

To study naturalistic in-cabin emotion we developed SKYNIVI, a modified open source driving simulator, with scenarios designed to elicit startle and frustration. We target generating these emotions because we believe that by detecting these it will be possible for autonomous vehicles to learn to drive better. We show how to use SKYNIVI to develop datasets that capture naturalistic emotions in drivers and passengers for algorithmic development. We recruited 51 participants as dyads and single drivers to participate in two different scenarios. We show that we were able to evoke hundreds of instances of our target emotions in this cohort and present an analysis of factors we found to impact emotional expression including: scenario design , demographic factors, personality and baseline affect . We find that having a second person in the vehicle impacts observed expressions of emotion even when no difference in baseline affect is reported.

Key Contributions

• Research methodology development
• Experimental design and analysis
• Technical implementation and validation

Download paper

Citation

Object-level perception sharing among connected vehicles

Published in Proceedings of 2019 IEEE Intelligent Transportation Systems Conference (ITSC), IEEE 2023

Abstract

Advances in vehicular communication technologies have made Connected Vehicles (CVs) a near-term reality. Compared to models where vehicles rely solely on their own perception to sense and make decision on the environment, CVs have the potential to allow information sharing among vehicles to improve sensing and decision making collectively. A first concrete step towards this goal is enabling vehicles to share perception-related information, to overcome limitations of their respective sensors (e.g., partial awareness due to occlusions). Sharing processed information vs raw sensor data has the advantage of reducing the amount of data to be transmitted, and the required computation burden at the receiver side.This paper proposes an approach to enable object-level sharing among vehicles. Following state-of-the-art object-level management techniques, we developed a two-layer architecture that handles object tracking and fusion from dynamic remote sources of information. We implemented our approach and showed that it can achieve realistic performance, and robustness both in terms of quality of information and computation.

Key Contributions

• Proposes two-layer object fusion architecture
• Defines connected vehicles as virtual sensors
• Dynamically manages vehicles entering/leaving range
• uses objects using distance-based clustering
• Evaluates system accuracy and scalability

Download paper

Citation

Human–vehicle cooperation in automated driving: A multidisciplinary review and appraisal

Published in ‘International Journal of Human Computer Interaction’, Elsevier 2019

Abstract

To draw a comprehensive and cohesive understanding of human–vehicle cooperation in automated driving, a review is made on key studies in human–robot interaction and human factors. Throughout this article, insight is provided into how human drivers and vehicle systems interplay and influence each other. The limitations of technology-centered taxonomies of automation are discussed and the benefits of accounting for human agents are examined. The contributions of machine learning to automated driving and how critical models in human-system cooperation can inform the design of a more symbiotic relationship between driver and vehicle are investigated. Challenges in the human element to enable the safe introduction of road automation are also discussed. Particularly, the unintended consequences of vehicle automation on driver’s workload, situation awareness and trust are examined, and the social interactions between driver, vehicle, and other road users are investigated. This review will help professionals shape future directions for safer and more efficient and effective human–vehicle cooperation.

Key Contributions

• Critiques technology-centered automation taxonomies
• Promotes human-centered automation design.
• Analyzes automation’s impact on drivers
• Reviews machine learning for cooperation
• Examines social human-vehicle interactions

Download paper

Citation

Human-system cooperation in automated driving

Published in ‘International Journal of Human Computer Interaction’, Elsevier 2019

Abstract

To draw a comprehensive and cohesive understanding of human–vehicle cooperation in automated driving, a review is made on key studies in human–robot interaction and human factors. Throughout this article, insight is provided into how human drivers and vehicle systems interplay and influence each other. The limitations of technology-centered taxonomies of automation are discussed and the benefits of accounting for human agents are examined. The contributions of machine learning to automated driving and how critical models in human-system cooperation can inform the design of a more symbiotic relationship between driver and vehicle are investigated. Challenges in the human element to enable the safe introduction of road automation are also discussed. Particularly, the unintended consequences of vehicle automation on driver’s workload, situation awareness and trust are examined, and the social interactions between driver, vehicle, and other road users are investigated. This review will help professionals shape future directions for safer and more efficient and effective human–vehicle cooperation.

Key Contributions

• Critiques technology-centered automation taxonomies
• Promotes human-centered automation design.
• Analyzes automation’s impact on drivers
• Reviews machine learning for cooperation
• Examines social human-vehicle interactions

Download paper

Citation

Design of a misbehavior detection system for objects based shared perception V2X applications

Published in ‘IEEE Intelligent Transportation Systems Conference’, IEEE 2019

Abstract

The recent trend of integrating vehicular communications with advanced sensors installed on vehicles, enables Connected and Autonomous Vehicles (CAVs) to share their own driving information as well as perception information, such as a list of perceived objects (e.g., dynamic obstacles such as vehicles, pedestrians, and cyclists, and static obstacles). This has the potential to improve driving safety by expanding collective perception of vehicles. However, adversaries may also populate false information to other Connected Vehicles (CVs) via Vehicle-to-Vehicle (V2V) communications. This paper investigates the security aspects of mixed deployment of CAVs, CVs and legacy vehicles, and in particular with regards to misbehavior detection. We provide a generic design framework that is independent from the specific algorithms of the underlying perception system, and can be used to implement a practical Misbehavior Detection System (MDS). We analyze the MDS framework w.r.t. a ghost vehicle attack. While no computing system can be completely secure, we believe this work would help the industry to develop a practical MDS design within a common framework while allowing individual techniques to mature and evolve over time with future academic research.

Key Contributions

• Proposes a generic misbehavior detection framework
• Divides detection into local/collaborative components
• Categorizes four levels of anomaly detection
• Defines Unobservability and Undecidability concepts
• Defines conditions for successful attacks

Download paper

Citation

2nd special session on solving the automated vehicle safety assurance challenge

Published in Proceedings of the 2019 International Conference on Intelligent Transportation Systems (ITSC), IEEE 2019

Abstract

The scientific knowledge and tools for the mass deployment of Automated Vehicles (AVs) are maturing rapidly, as evidenced by the wide deployment of AV test fleets worldwide. These vehicles have the potential to produce tremendous economic and societal benefits including greatly reduced traffic accidents, injuries, and congestion, and to make less expensive, more flexible and more productive transportation available to all. But one challenge looms above all others in the race to full vehicle automation; solving the AV Safety Assurance challenge. Automated transportation is not just a product, but an industry. And it is as an industry that we must together solve this challenge. We invite researchers, automakers, technology companies, and government regulators to come together to develop a holistic model to define and measure AV Safety. In this special session we present papers that provide contributions to the definition, applicability and standardization of AV safety assurance, including methods for the development of metrics, benchmarks and evangelisation of AV Safety Assurances to users and the public. This session continues the open discussion started in 2018 ITSC with the goal of making AV Safety a reality. The session will consist of high quality paper presentations as well as a panel discussion with some of the most relevant figures of the AV industry.

Key Contributions

• Common AV safety definition
• Fosters collaboration between industry and academia
• Seeks to specify AV safety standards
• Gathers a universal view on safety

Download paper

Citation

Workshop on designing highly automated driving systems as radical innovation

Published in Adjunct Proceedings of the 10th International ACM Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutomotiveUI ’18), ACM 2018

Abstract

Automated driving systems (ADS), especially in higher levels of automation, seem to be the new focus of innovation regarding future mobility. Technological achievements of traveling automation open up new challenges for road traffic. Existing automotive research focuses on problem solving and observational approaches including users and their imagination of the future of mobility to analyze acceptance and user experience of “incremental” (step-wised improved) innovations. On the other hand, “radical” (something new, enabled by technology or meaning change) innovations extensively increase product quality leaping over incremental innovation. This workshop aims to challenge the current research approaches to automated driving against “trying to improve sitting in a horse carriage” and discuss how we can design “radical” innovations for ADS beyond the “horse carriage”. Within this interactive workshop, we will utilize a design thinking approach to refocus on underlying problems that ADSs originally aim to solve and generate ideas for radical innovations.

Key Contributions

• Critiques incremental innovation in ADS research
• Promotes designing ADS as radical innovation
• Applies a design thinking approach
• Utilizes rapid prototyping for radical ideas
• Refocuses on problems ADS should solve

Download paper

Citation

Towards understanding emotional reactions of driver-passenger dyads in automated driving

Published in Proceedings of the 13th IEEE International Conference on Automatic Face & Gesture Recognition, IEEE 2018

Abstract

Automated driving has the potential to reduce the amount of fatal crashes, lighten the burden of commutes, and democratize mobility access to wider populations. But delegation of control to automation is not without issues. One of the foreseen drawbacks is that users might experience negative emotional reactions to unanticipated or unexplainable automated maneuvers. In this paper we present a novel method to induce targeted emotional reactions, frustration and startle, in simulated automated driving environments. We describe the data collection process for 17 driver - passenger dyads and discuss the data labelling method for generating reliable novel emotion datasets. This contribution is a foundational methodology towards expanding emotional understanding in automated vehicles, a critical skill for building long-term trusted experiences.

Key Contributions

• Presents method to induce driver emotions
• Studies emotional reactions of driver-passenger dyads
• Develops a reliable emotion labeling process
• Achieves expert consensus on emotion labels
• Provides methodology for emotional understanding

Download paper

Citation

Theo, take a right… uh… left: Conversational Route Negotiations with Autonomous Driving Assistants

Published in Adjunct Proceedings of the 10th International ACM Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutomotiveUI ’18), ACM 2018

Abstract

We foresee conversational driver assistants playing a crucial role in automated driving interactions. In this video we present a study of user interactions with an in-vehicle agent, “Theo”, under SAE Level 4 automated driving. We use a remote Wizard-of-Oz setup where participants, sitting in a driving simulator, experience real-life video footage transmitted from a vehicle in the neighborhood and interact with Theo to instruct the vehicle where to go. We configured Theo to present 3 levels of conversational abilities (terse, verbose and helpful). We show the results of 9 participants tasked to negotiate destinations and route changes. Voice interaction was reported as preferred means of communication with Theo. There was a clear preference for talkative assistants which were perceived more responsive and intelligent. We highlight challenging interactions for users such as vehicle maneuvers in parking areas and specifying drop off points and interesting associations between the agent performance and the automated vehicle abilities.

Key Contributions

• Automated driving system development
• Pioneers a remote AI Wizard-of-Oz setup
• Tests three conversational agent styles
• Finds user preference for talkative agents
• Identifies challenging user interaction scenarios
• Links agent performance to perceived safety

Download paper

Citation

“Peace of Mind”, An Experiential Safety Framework for Automated Driving Technology Interactions

Published in Proceedings of the 2018 21st International Conference on Intelligent Transportation Systems (ITSC), IEEE 2018

Abstract

Current automated driving systems assume drivers continuously monitor the vehicle. Meanwhile, fully automated vehicles aim at not requiring human intervention for their safely operation. The industry is currently debating how these novel systems can be certified under functional safety standards. In this paper, we argue that the current safety picture is not comprehensive enough, since it alienates users. We propose experiential safety as a complement to existing functional safety and to develop a framework for experiential safety interactions between the user and automation in automated driving environments. To support the experiential safety design model, we provide an overview of the user-centered research on experiential automation safety, which includes results from online surveys, personal interviews, and gamified group workshops. We explore current user behaviors by focusing on what makes them feel safe as drivers and passengers, and how unexpected events and automation responses might impact their perception of safety. Among the highlighted results, we show how mismatched expectations and unexpected behaviors from autonomous vehicles can lead to frustration and compromised trust. We also show how automation feedback to the user can generate stress and anxiety if not properly configured and how a cooperative relationship between automation and the driver leads to more satisfying driving experiences. Finally, we present guidelines for the experiential safety to be applied by automotive engineers and designers in their development of automated driving technologies.

Key Contributions

• Proposes an experiential safety concept for AVs
• Develops a novel gamified workshop method
• Presents an experiential safety framework
• Defines user-lenses and machine-lenses guidelines
• Finds collaborative feedback improves user emotion

Download paper

Citation

Emotional GaRage: A workshop on in-car emotion recognition and regulation

Published in ‘Adjunct Proceedings of the 10th International ACM Conference on Automotive User Interfaces and Interactive Vehicular Applications AutomotiveUI 2018’, ACM 2018

Abstract

In-car emotion detection and regulation have become an emerging and important branch of research within the automotive domain. Different emotional states can greatly influence human driving performance and user experience both in manual and automated driving conditions. The monitoring and regulation of relevant emotional states is therefore important to avoid critical driving scenarios with the human driver being in charge, and to ensure comfort and acceptance in autonomous driving. In this workshop we want to discuss the empathic user interface research to address challenges and opportunities and to reveal new research directions for future work. This workshop provides a forum for exchange and discussion on empathic user interfaces, including methods for emotion recognition and regulation, empathic automotive human-machine interaction design, user evaluation and measurements, and subsequent improvement of autonomous driving experience.

Key Contributions

• Discusses empathic in-car user interfaces
• Identifies critical scenarios and emotions
• Explores emotion recognition and regulation methods
• Uses 4mat system for workshop structure
• Creates roadmap for future research

Download paper

Citation

Chairs

Published in ‘Adjunct Proceedings of the 10th International Conference on Automotive User Interfaces and Interactive Vehicular Applications’, 2018

Abstract

Abstract not yet available.

Key Contributions

• Research methodology development
• Experimental design and analysis
• Technical implementation and validation

Download paper

AutomotiveUI

Published in ‘Automotive UI 2018’, 2018

Abstract

Abstract not yet available.

Key Contributions

• Research methodology development
• Experimental design and analysis
• Technical implementation and validation

Download paper

ARV 2018: 2nd Workshop on Augmented Reality for Intelligent Vehicles

Published in ‘Adjunct Proceedings of the 10th International ACM Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutomotiveUI ’18)’, ACM 2018

Abstract

Augmented reality (AR) has the potential to improve road safety, support more immersive (non-) driving related activities, and finally enhance driving experience. AR may also be the enabling technology to help on the transition towards automated driving. However, augmented reality still faces a number of technical challenges when applied in vehicles, and also several human factors issues need to be solved. In this workshop, we will discuss potential and constraints as well as impact, role, and adequacy of AR in driving applications. The primary goal of this workshop is to define a research agenda for the use of AR in intelligent vehicles within the next 3 to 5 years.

Key Contributions

• Workshop organization and community building
• Defines a 3-5 year collaborative research agenda
• Identifies four key AR problem fields
• Discusses practical usage of AR devices
• Outlines research challenges and hypotheses

Download paper

Citation

An international survey on automated and electric vehicles: Austria, Germany, South Korea, and USA

Published in ‘Springer Natural Digital Human Modelling’, Springer 2018

Abstract

As development of automated vehicles and adoption of electric vehicles continue to grow, there is an increasing interest in the public opinions on these technologies. We conducted an international online survey to gather information about people’s hopes and concerns for automated and electric vehicles from a total of 866 people from four countries – Austria, Germany, South Korea, and USA. Results revealed some differences across countries in the perceptions of automated and electric vehicles. However, differences between the same countries have shrunk compared to our previous survey completed in 2012. Results are discussed with limitations and future work.

Key Contributions

• Automated driving system development
• Electric Vehicles
• International Trends

Download paper

Citation

Workshop on user-centered design for automated driving systems

Published in Proceedings of the 9th International Conference on Automotive User Interfaces and Interactive Vehicular Applications, ACM 2017

Abstract

Automated driving systems (ADS) are mainly regarded from an innovation and technology-centered perspective. In academia, as well as in industry, there is a concentration on technical issues to maintain competitiveness while aspects like acceptance, trust and user experience are widely under-researched. However, the “human factor” is critical for a comprehensive establishment of ADS technology on the market. We believe that there is a need to focus on a user-centered design (UCD) perspective to bring ADS innovation to a next level and to achieve a wide acceptance in society. In this workshop we want to discuss special requirements of UCD applied to ADS, to address challenges and opportunities and to reveal new research fields for future work.

Key Contributions

• Proposes migration-tolerant ATC display concept
• Advocates for stepwise functionality introduction
• Compares small versus large integration steps
• Measures usability, learnability, and acceptance

Download paper

Citation

Towards Adaptive Ambient In-Vehicle Displays and Interactions: Insights and Design Guidelines from the 2015 AutomotiveUI Dedicated Workshop

Published in ‘Automotive User Interfaces: Creating Interactive Experiences in the Car’, ACM 2017

Abstract

Informing a driver of a vehicle’s changing state and environment is a major challenge that grows with the introduction of in-vehicle assistant and infotainment systems. Even in the age of automation, the human will need to be in the loop for monitoring, taking over control, or making decisions. In these cases, poorly designed systems could lead to needless attentional demands imparted on the driver, taking it away from the primary driving task. Existing systems are offering simple and often unspecific alerts, leaving the human with the demanding task of identifying, localizing, and understanding the problem. Ideally, such systems should communicate information in a way that conveys its relevance and urgency. Specifically, information useful to promote driver safety should be conveyed as effective calls for action, while information not pertaining to safety (therefore less important) should be conveyed in ways that do not jeopardize driver attention. Adaptive ambient displays and peripheral interactions have the potential to provide superior solutions and could serve to unobtrusively present information, to shift the driver’s attention according to changing task demands, or enable a driver to react without losing the focus on the primary task. In order to build a common understanding across researchers and practitioners from different fields, we held a Workshop on Adaptive Ambient In-Vehicle Displays and Interactions at the AutomotiveUI`15 conference. In this chapter, we discuss the outcomes of this workshop, provide examples of possible applications now or in the future and conclude with challenges in developing or using adaptive ambient interactions.

Key Contributions

• Workshop organization and community building
• Human-computer interaction design

Download paper

Citation

The insight–prototype–product cycle best practices and processes to iteratively advance in-vehicle interactive experiences development

Published in Automotive User Interfaces: Creating Interactive Experiences in the Car, Springer Book, Springer 2017

Abstract

In-vehicle experiences are made up mainly of mundane small moments, repeated practices, and taken-for-granted decisions that make up daily experiences in and around private passenger vehicles. Understanding what those experiences are for drivers around the world presents an opportunity for designing novel interactive experiences, technologies, and user interfaces for vehicles. In this chapter, we present a set of tools, methodologies, and practices that will help reader create a holistic design space for future mobility. Transitioning between ethnography, insights, prototyping, experience design, and requirements decomposition is a challenging task even for experienced UX professionals. This chapter provides guidance in this matter with practical examples.

Key Contributions

• Ethnographic research methods for Automotive System Development
• Rapid prototyping methods for Automotive Functions
• Experience Design mapping to product specifications
• Product Development evaluation and validation
• Product Success metrics

Download paper

Citation

Socializing under the influence of distracted driving: a study of the effects of in-vehicle and outside-of-the-vehicle communication while driving

Published in ‘Springer Nature Advances in Human Aspects of Transportation’, Springer 2017

Abstract

Advancements of in-vehicle technologies and the development of mobile applications that keep a driver connected in a driving environment have caused an increasingly dangerous safety concern. Distracted driving has gained the attention of legislators and governments globally. Countries have constituted bans that partially or fully forbid drivers from using gadgets while driving, especially hindering out-of-the-vehicle communications. This paper introduces Voiceing™, a voice-activated application meant to improve social communications in the car, serving as a safe alternative to distracted driving. Other modalities of interaction such as texting, in-vehicle conversations and outside-of-the-vehicle conversation have been measured and compared with Voiceing™ investigating effects on driver’s performance, cognitive load and user acceptance. Results from this study suggest that Voiceing™ is a safer alternative than in-vehicle interactions with humans. Results also show that natural speech interaction of in-vehicle applications and the inclusion of context awareness help improve driving performance while interacting with a vehicle system.

Key Contributions

• Introduces Voiceing™ a voice-activated application
• Compares various in-car communication methods
• Measures performance, cognitive load, acceptance
• Voiceing™ is safer than human interactions
• Natural speech improves driving performance

Download paper

Citation

Skyline: A Platform Towards Scalable UX-Centric In-Vehicle HMI Development

Published in ‘International Journal of Mobile Human Computer Interaction (IJMHCI)’, 2017

Abstract

This paper describes the research and development process of an in-vehicle user experience using Skyline, an automotive prototyping platform created in Intel Labs to empower interaction designers and user experience researches to rapidly and iteratively develop and test in-vehicle user experience concepts. The paper describes the hardware and software components of Skyline in depth and how to configure them to suit individual researcher needs. The paper also presents a case study to exemplify the design making process that Skyline enables. From ideation to use-case creation, prototyping and validation through user assessment, the paper showcases the benefits of capturing early qualitative user feedback as support for rapid prototyping walking through a study titled Agency vs. Control and the associated interactions inside the cockpit. Ten defined use-cases are developed and integrated into a hero scenario in Skyline. High fidelity HMI concepts are tested and validated over the course of six months with feedback from a total of fifty users.

Key Contributions

• Automotive HMI Prototyping
• Rapid HCI User Interface Design
• Evaluation Methods

Download paper

Citation

Driver in the loop: Best practices in automotive sensing and feedback mechanisms

Published in ‘Automotive user interfaces: creating interactive experiences in the car’, 2017

Abstract

Given the rapid advancement of technologies in the automotive domain, driver–vehicle interaction has recently become more and more complicated. The amount of research applied to the vehicle cockpit is increasing, with the advent of (highly) automated driving, as the range of interaction that is possible in a driving vehicle expands. However, as opportunities increase, so does the number of challenges that automotive user experience designers and researchers will face. This chapter focuses on the instrumentation of sensing and displaying techniques and technologies to make better user experience while driving. In the driver–vehicle interaction loop, the vehicle can sense driver states, analyze, estimate, and model the data, and then display it through the appropriate channels for intervention purposes. To improve the interaction, a huge number of new/affordable sensing (EEG, fNIRS, IR imaging) and feedback (head-up displays, auditory feedback, tactile arrays, etc.) techniques have been introduced. However, little research has attempted to investigate this area in a systematic way. This chapter provides an overview of recent advances of input and output modalities to be used for timely, appropriate driver–vehicle interaction. After outlining relevant background, we provide information on the best-known practices for input and output modalities based on the exchange results from the workshop on practical experiences for measuring and modeling drivers and driver–vehicle interactions at AutomotiveUI 2015. This chapter can help answer research questions on how to instrument a driving simulator or realistic study to gather data and how to place interaction outputs to enable appropriate driver interactions.

Key Contributions

• Research methodology development
• Experimental design and analysis
• Technical implementation and validation

Download paper

Citation

9th International Conference on Automotive User Interfaces and Interactive Vehicular Applications: Adjunct Proceedings

Published in ‘Proceeding of Automotive UI 2017’, ACM 2017

Abstract

Abstract not yet available.

Key Contributions

• Research methodology development
• Experimental design and analysis
• Technical implementation and validation

Download paper

BibTeX

Autonomous hmi made easy: Prototyping reactive in-cabin aware hmis

Published in ‘Adjunct Proceedings of the 8th International Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutomotiveUI ’16)’, ACM 2016

Abstract

Automotive user experiences can be increasingly personalized and adaptive thanks to advances in in-vehicle sensors and user modelling but current automotive software development frameworks still require large software development efforts to create custom interaction solutions. In this paper we propose a novel system architecture aimed at supporting automotive researchers and designers by simplifying the prototyping process towards novel adaptive user interfaces. We describe the integration of RealSense sensors and the Context Sensing SDK with the Skyline driving simulator framework. The combination of these tools allows rapid prototyping of in-cabin context aware interactions. The paper presents two use cases of in-cabin-aware prototypes, a user profile loading interface that recognizes identities and occupant roles and an L4 to L3 take-over control interface using RealSense and Context sensing APIs to detect in-vehicle events and Skyline to present real-time adaptive warning interfaces. The resulting experiences are core components of an intelligent ADAS framework for research of IVI personalization and highly automated collaborative driving.

Key Contributions

• Automated driving system development
• Proposes architecture integrating Skyline and sensors
• Simplifies prototyping of adaptive HMIs
• Demonstrates automatic user profile recognition
• Prototypes context-aware take-over interface
• Integrates sensor SDKs with HMI platform

Download paper

Citation

Automotive user interfaces in the age of automation (Dagstuhl Seminar 16262)

Published in Dagstuhl Reports, Dagtsuhl 2016

Abstract

The next big change in the automotive domain will be the move towards automated and semi-automated driving. We can expect an increasing level of autonomous driving in the coming years, resulting in new opportunities for the car as an infotainment platform when standard driving tasks will be automated. This change also comes with a number of challenges to automotive user interfaces. Core challenges for the assistance system and the user interface will be distributing tasks between the assistance system and the driver, the re-engagement of drivers in semi-automated driving back to the driving task, and collaborative driving in which cars collectively work together (e.g., platoons). Overall, in the coming years we will need to design interfaces and applications that make driving safe while enabling communication, work, and play in human-operated vehicles. This Dagstuhl seminar brought together researchers from human computer interaction, cognitive psychology, human factors psychology and also from automotive industry and OEMs to discuss the new interface paradigms for (semi-)automated driving.

Key Contributions

• Identifies three core research challenges
• Explores future non-driving in-car activities
• Analyzes the take-over/handover problem
• Proposes methods for calibrating trust
• Creates framework for classifying research methods

Download paper

Citation

1st workshop on situational awareness in semi-automated vehicles

Published in Adjunct Proceedings of the 8th International Conference on Automotive User Interfaces and Interactive Vehicular Applications, ACM 2016

Abstract

This workshop will focus on the problem of occupant and vehicle situational awareness with respect to automated vehicles when the driver must take over control. It will explore the future of fully automated and mixed traffic situations where vehicles are assumed to be operating at level 3 or above. In this case, all critical driving functions will be handled by the vehicle with the possibility of transitions between manual and automated driving modes at any time. This creates a driver environment where, unlike manual driving, there is no direct intrinsic motivation for the driver to be aware of the traffic situation at all times. Therefore, it is highly likely that when such a transition occurs, the driver will not be able to transition either safely or within an appropriate period of time. This workshop will address this challenge by inviting experts and practitioners from the automotive and related domains to explore concepts and solutions to increase, maintain and transfer situational awareness in semi-automated vehicles.

Key Contributions

• Addresses driver situational awareness problem
• Focuses on take-over and handover situations
• Explores shared situational awareness concepts
• Applies Endsley’s model of SA
• Considers long-term driver deskilling effects

Download paper

Citation

1st workshop on ethically inspired user interfaces for automated driving

Published in * Adjunct Proceedings of the 8th International Conference on Automotive User Interfaces and Interactive Vehicular Applications*, ACM 2016

Abstract

On July 1st 2016, the first automated vehicle fatality became headline news [9] and caused a nationwide wave of concern. Now we have at least one situation in which a controlled automated vehicle system failed to detect a life threatening situation. The question still remains: How can an autonomous system make ethical decisions that involve human lives? Control negotiation strategies require prior encoding of ethical conventions into decision making algorithms, which is not at all an easy task – especially considering that actually coming up with ethically sound decision strategies in the first place is often very difficult, even for human agents. This workshop seeks to provide a forum for experts across different backgrounds to voice and formalize the ethical aspects of automotive user interfaces in the context of automated driving. The goal is to derive working principles that will guide shared decision-making between human drivers and their automated vehicles.

Key Contributions

• Discusses ethical dilemmas in automated driving
• Analyzes the limits of Asimov’s Automation Laws
• Questions human vs. machine decision-making
• Addresses cultural differences in moral norms
• Seeks to formalize ethics for algorithms

Download paper

Citation

Workshop on Practical Experiences in Measuring and Modeling Drivers and Driver-Vehicle Interactions

Published in Proceedings of Automotive UI 2015, ACM 2015

Abstract

The search term “driver-vehicle interaction study” results in2,690 Google Scholar hits of research papers published inthe past 5 years (2010-2015). This huge number clearlypoints out the problem that researchers (particularly, new tothis field) are exposed to, namely that many decisionsregarding the setting, (e.g., lab/field, low-/high-fidelitysimulator, within/between subjects, sample size, biasedsubject, learning effect, sensor technology, mobilehardware, synchronization issues, briefing, etc.) have to beestablished early in the design phase without the referenceof principled guidelines and best practices to support themin identifying the optimal solution to answer their researchquestion of interest. This workshop invites a) people activein the field to share their experiences in executing studies tomeasure driver behavior or vehicle conditions (driver-vehicle interactions), and b) young researchers to draftresearch questions, present their problems, and discusspossible solutions with the other participants.

Key Contributions

• Addresses lack of research best practices
• Focuses on modeling driver, driving, interactions
• Connects new and experienced researchers
• Reviews sensors for user modeling
• Discusses experimental methods and settings

Download paper

Citation

Workshop on Adaptive Ambient In-Vehicle Displays and Interactions

Published in Proceedings of Automotive UI 2015, ACM 2015

Abstract

A major challenge in today’s as well as future driving is to keep drivers informed about the vehicle’s state and the environment. Today’s assistant and infotainment systems compete for the drivers’ attention and may even distract them from the primary driving task. Further, with an increase in automation, the vehicle needs to be able to communicate information with different urgency levels. While some information are not important and should never distract a driver from important tasks, there are also calls for action, which a driver should not be able to ignore. We believe in adaptive ambient displays and peripheral interaction as one possible way to unobtrusively present information while being able to switch the driver’s attention if needed. In this workshop the focus lies in exchange of best known methods and discussion on challenges and potentials for this kind of interaction in today’s scenarios as well as in future mixed or full autonomous traffic. The central objective of this workshop is to bring together researchers from different domains and discuss radical, innovative, and engaging ideas and a future landscape for research in this area.

Key Contributions

• Proposes workshop on adaptive ambient displays
• Focuses on ambient and peripheral interaction
• Addresses managing driver attention shifts
• Considers non- to fully-autonomous driving
• Fosters interdisciplinary discussion on UIs.

Download paper

Citation

Skyline: a rapid prototyping driving simulator for user experience

Published in ‘AutomotiveUI 2015’, 2015

Abstract

The search term “driver-vehicle interaction study” results in 2,690 Google Scholar hits of research papers published in the past 5 years (2010-2015). This huge number clearly points out the problem that researchers (particularly, new to this field) are exposed to, namely that many decisions regarding the setting, (e.g., lab/field, low-/high-fidelity simulator, within/between subjects, sample size, biased subject, learning effect, sensor technology, mobile hardware, synchronization issues, briefing, etc.) have to be established early in the design phase without the reference of principled guidelines and best practices to support the min identifying the optimal solution to answer their research question of interest. This workshop invites a) people activein the field to share their experiences in executing studies to measure driver behavior or vehicle conditions (driver-vehicle interactions), and b) young researchers to draft research questions, present their problems, and discuss possible solutions with the other participants.

Key Contributions

• Addresses lack of research best practices
• Focuses on modeling driver, driving, interactions
• Connects new and experienced researchers
• Reviews sensors for user modeling
• Discusses experimental methods and settings

Download paper

Citation

Report on the in-vehicle auditory interactions workshop: Taxonomy, challenges, and approaches

Published in ‘Adjunct Proceedings AutomotiveUI ’15’, ACM 2015

Abstract

As driving is mainly a visual task, auditory displays play a critical role for in-vehicle interactions. To improve invehicle auditory interactions to the advanced level, auditory display researchers and automotive user interface researchers came together to discuss this timely topic at an in-vehicle auditory interactions workshop at the International Conference on Auditory Display (ICAD). The present paper reports discussion outcomes from the workshop for more discussions at the AutoUI conference.

Key Contributions

• Workshop organization and community building
• Designed sounds for automated driving take-overs
• Proposed interactive music for eco-driving
• Considered auditory displays for passengers
• Taxonomized auditory collision warning issues
• Bridged auditory and automotive UI communities

Download paper

Citation

Prototyping adaptive automotive UX: A design pedagogy approach

Published in ‘Extended Proceedings of the 7th International Conference on Automotive User’, 2015

Abstract

This paper outlines and evaluates experiential prototyping for emerging vehicle UX design within a pedagogical framework. Drawing from studio experience, we discuss the learnings, options and risks that in-vehicle UX designers face in prototyping realtime, adaptive user interfaces, and suggest methods and solutions for designers wishing to expand their creative practice.

Key Contributions

• Presents a novel pedagogical framework for UX
• Applies “design thinking through making”
• Outlines low-tech experiential prototyping methods
• Advocates for Minimum Viable Prototypes
• Identifies risks in UX prototyping

Download paper

Citation

Help on the road: Effects of vehicle manual consultation in driving performance across modalities

Published in ‘International journal of human-computer studies’, Elsevier 2015

Abstract

The growing advancements of in-vehicle electronics and the intrusion of consumer electronics in the vehicle cockpit have increased the complexity of in-car experiences. Therefore, vehicle manuals are needed, now more than ever, to provide information and guidance. Automakers have extended user assistance through multimedia, integrated manuals, online services and telephonic assistance. However, no driver-centric interfaces have been created to provide vehicle documentation assistance effectively. Drivers are expected to interrupt the driving experience in order to find vehicle information in a paper manual. This paper compares the effects on driving performance and cognitive load when consulting a manual in a simulated driving environment through various conditions. These conditions consist of interacting with a voice activated vehicle manual called the Voice User Help, an on-board multimedia manual, a passenger, and a call center. Results suggest that any kind of interaction to access information while driving has an impact on the driver׳s attention based on a decrease in driving performance and increase of cognitive load. However, amongst all modalities, voice interfaces seem to be the better option for consulting information while driving. Also, and under some circumstances, interaction with a conversational manual system appears to be safer than human-to-human communication.

Key Contributions

• Compared manual consultation methods while driving
• Measured effects on driver performance
• Assessed cognitive load across modalities
• Found voice interfaces safer overall
• Showed manual interfaces cause inattention

Download paper

Citation

The Social Car: Socially-inspired Mechanisms for Future Mobility Services

Published in ‘Pervasive and Mobile Computing’, 2014

Abstract

Research on next generation automotive ICT is challenged by the complex interactions of technological advancements and the social nature of individuals using and adopting technology. Traffic in the future will no longer be considered as a network of individually behaving “dumb” cars, but rather as the entirety of social interactions between its entities. Successful application of collective, socially inspired driving mechanisms requires to understand how socially-inspired vehicles (i.e., driver-car pairs) could make use of their social habitus, composed from (past and present) driving behavior, social interactions with pedestrians, vehicles, infrastructure, etc., and drivers’ vital states when exposed to other road participants in live traffic. In response to this emerging research direction, the aim of this workshop is to achieve a common understanding of the symbiosis between drivers, cars, and infrastructure from a global point of view (referred to as “collective driving”). In particular, this workshop is expected to provoke an active debate on the adequacy of the concept of socializing cars, addressing questions such as who can communicate what, when, how, and why?

Key Contributions

• Research methodology development
• Experimental design and analysis
• Technical implementation and validation

Download paper

Citation

Social, natural, and peripheral interactions: Together and separate

Published in ‘Proceedings of AutomotiveUI 2014’, 2014

Abstract

A major challenge in the future of traffic is to understand how “socially-aware vehicles” could be making use of their social habitus, formed by any information that can be inferred from past and present social relations, social interactions, and a driver’s social state when exposed to other participants in real, live traffic. The aim of this workshop in recognition of this challenge is to advance on a common understanding of the symbiosis between drivers, cars, and the infrastructure. The central objective of the workshop is to provoke an active debate on the adequacy of the concept of social, natural, and peripheral interaction, addressing questions such as “who can communicate what”, “when”, “how”, and “why”? To tackle these questions, we would like to collect different, radical, innovative, versatile, and engaging works that challenge or re-imagine human interactions in the near future automobile space.

Key Contributions

• Human-computer interaction design

Download paper

Citation

Response to Letter by Padulo and Ardigò

Published in Jouarnal or Ergonomics, Taylor & Francis 2012

Abstract

Abstract not available

Key Contributions

Not available

Download paper

Citation

The voice user help, a smart vehicle assistant for the elderly

Published in Proceedings of the International Conference on Ubiquitous Computing and Ambient Intelligence, Springer 2012

Abstract

The rapid advancement of vehicular technologies has resulted in an exponential increase of new vehicle functions road assistance and connected vehicles services. Vehicle manuals are designed to provide support and information about the use and maintenance of these features. However, current vehicle user manuals do not allow looking for information under driving conditions. This paper presents the Voice User Help, a smart voice-operated system that utilizes natural language understanding and emotional adaptive interfaces to assist drivers when looking for vehicle information with minimal effect on their driving performance. Additionally, the system presents an opportunity for elder drivers to reduce the learning curve of new in-vehicle technologies and improve efficiency. Results on user acceptance of the Voice User Help, as well as cognitive load and driver distraction effects generated during a simulated drive indicate that the Voice User help is an extremely desirable feature and potentially safe application since it did not significantly decrement driving performance. Furthermore preliminary results on adaptive voice interfaces using emotion recognition indicate that personalization of the interaction will be able to palliate possible negative effects that happen during system error recovery.

Key Contributions

• Developed voice-operated vehicle help system
• Aimed to assist elderly drivers
• Evaluated driver distraction and usability
• Integrated emotion recognition for adaptation
• Created a VUH-specific emotional taxonomy

Download paper

Citation

Evaluating the ergonomics of BCI devices for research and experimentation

Published in Journal of Ergonomics, Taylor & Francis Online 2012

Abstract

The use of brain computer interface (BCI) devices in research and applications has exploded in recent years. Applications such as lie detectors that use functional magnetic resonance imaging (fMRI) to video games controlled using electroencephalography (EEG) are currently in use. These developments, coupled with the emergence of inexpensive commercial BCI headsets, such as the Emotiv EPOC ( http://emotiv.com/index.php) and the Neurosky MindWave, have also highlighted the need of performing basic ergonomics research since such devices have usability issues, such as comfort during prolonged use, and reduced performance for individuals with common physical attributes, such as long or coarse hair. This paper examines the feasibility of using consumer BCIs in scientific research. In particular, we compare user comfort, experiment preparation time, signal reliability and ease of use in light of individual differences among subjects for two commercially available hardware devices, the Emotiv EPOC and the Neurosky MindWave. Based on these results, we suggest some basic considerations for selecting a commercial BCI for research and experimentation.

Statement of Relevance: Despite increased usage, few studies have examined the usability of commercial BCI hardware. This study assesses usability and experimentation factors of two commercial BCI models, for the purpose of creating basic guidelines for increased usability. Finding that more sensors can be less comfortable and accurate than devices with fewer sensors.

Key Contributions

• BCI evaluation
• BCI Signal Limitation Modelling
• Practical Use recommendations

Download paper

Citation

Emotional Adaptive Vehicle User Interfaces, Moderating negative effects of failed technology interactions while driving

Published in ‘Adjunct Proceedings of the 4th International Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutomotiveUI 2012)’, 2012

Abstract

Automotive Natural User Interfaces have the potential to increase user experience providing intuitive interactions for drivers. However, in the complex setting of a driving vehicle, failed interactions with in-vehicle technology can lead to frustration and put drivers in a dangerous situation. This paper evaluates the possibility of applying emotion recognition to vehicular spoken dialogue systems in order to adapt the dialog strategies, in error recovery scenarios. An emotional taxonomy is developed for the interactions with a conversational vehicular application, the Voice User Help. The positive results of the performance of VUH emotion recognizer support the creation of real-time classification of the user emotional state, which serves as basis to emotional reappraisal dialog strategies that mitigate negative effects on the driver’s cognitive load and driver performance.

Key Contributions

• Developed the Voice User Help system
• Created a VUH-specific emotional taxonomy
• Built a real-time emotion recognizer
• Proposed adaptive emotional dialog strategies
• Used emotion for error recovery

Download paper

Citation

Contribution to the development of intelligent conversational assistants in automotive environments

Published in EHU Scientific Production Portal, EHU 2012

Abstract

This thesis presents the design and development of the Conversational Automotive Assistant, Voice User Help, a conversational system based on the question-answer paradigm and designed to consult vehicle documentation while driving. This work compiles research in the fields of technical documentation, information retrieval, natural language processing, vehicle user interface design, user experience, and affective computing with the goal of creating an adaptive and dynamic assistant that modifies its conversational behavior depending on the user’s emotional state.

Key Contributions

• Conversational Asistant for In-cabin Automotive Applications
• Information Retrieval Algorithms
• Human-Computer Interaction Voice Interfaces
• Automotive Context-aware Affective Computing

Download paper

Citation

AutoNUI: 2nd Workshop on Automotive Natural User Interfaces

Published in ‘Adjunct Proceedings of the 4th International Conference on Automotive User Interfaces, ACM 2012

Abstract

Natural user interfaces—generally based on gesture and speech interaction—are an increasingly hot topic in research and are already being applied in a multitude of commercial products. Most use cases currently involve consumer electronics devices like smart phones, tablets, TV sets, game consoles, or large-screen tabletop computers.Motivated by the latest results in those areas, our vision is to apply natural user interfaces, for example gesture and conversational speech interaction, to the automotive domain as well. This integration might on one hand reduce driver distraction in certain cases and on the other hand might allow the design of new user experiences for infotainment and entertainment systems. The goal of this workshop is to explore the design space of natural multi-modal automotive user interfaces and to continue the fruitful discussions held at the 1st Workshop on Automotive Natural User Interfaces from AutomotiveUI ’11 in Salzburg, Austria. We would like to analyze where and how new interaction techniques can be integrated into the car.

Key Contributions

• Workshop organization and community building

Download paper

Citation

iHelp, the Ubiquitous Vehicle User Help

Published in Proceedings of Interact 2011, 2011

Abstract

Voice-interfaced, in-vehicle assistance includes receiving a Voice-based query from a user in the vehicle, and then determining at least one of a user emotional state, user expertise level and speech recognition confidence level associated with the Voice-based query. A text-based query may then be derived from the Voice-based query, and used to search a help database for answers corresponding to the Voice-based query. At least one response is then provided to the user in the form of Voice-based assistance in accordance with at least one of the user emotional state, user expertise level and speech recognition confidence level.

Key Contributions

• Voice-interfaced user help
• Conversational dialogue management
• Prototype development

Download paper

Citation

Designing driver centric natural voice user interfaces

Published in Adjunct Proceedings of the 3rd International Conference on Automotive User Interfaces and Interactive Vehicular Applications, 2011

Abstract

The current growth of automotive electronics aims toextend vehicle functionality and information access. Thispaper explores the application of Natural Voice UserInterfaces as a preferred interaction modality with in-vehicle technologies to lower driver distraction effects andimprove the user experience. The benefits and risks ofnatural speech interactions are evaluated in order topropose a driver-centric design guideline based on previousresearch. The paper concludes that driving scenarios canprofit considerably from systems that apply natural speechinterfaces to allow the driver to access information.

Key Contributions

• Natural Voice Interaction
• Voice-interfaced user help system design
• Conversational Dialogue Managment
• Context-aware system and architecture vision

Download paper

Citation

Autonui a workshop on automotive natural user interfaces

Published in ‘Proceedings of AutomotiveUI 2011’, ACM 2011

Abstract

Natural user interfaces by means of gesture and speech interaction have become a hot topic in research as well as already for real products. Most use cases currently center around consumer electronics devices like smart phones, TV sets, gaming, or other large screens like tabletops. Motivated by the latest results in those areas, our vision is to apply natural user interfaces like gesture and speech interaction to the automotive domain as well. This integration might on one hand reduce driver distraction in certain cases and on the other hand allow to design new experiences for operating infotainment and entertainment systems. The goal of this workshop is to explore the design space of natural multi-modal automotive user interfaces. We would like to analyze where and how new interaction techniques can be integrated into the car.

Key Contributions

• Natural User Interfaces in Automotive
• Workshop organization and community building

Download paper

Citation

Are educational video games all they are cracked up to be

Published in ‘International Journal of Learning Technology’, 2011

Abstract

This paper investigates the benefits of learning from educational video games compared to learning by reading from a text document. The participants were exposed to Lewis and Clark expedition via a video game or text document. During the learning task, playing the game or reading, participants wore a Brain Computer Interface (BCI) device to gather their level of engagement. After the learning sessions, post-experiment questionnaires were used to assess the amount of information retained after each session. The results of this study suggests that the educational video games might not be significantly engaging, and also that learning by reading a handout may be better for retaining information. Furthermore, this paper briefly discusses the BCI device, and how it can be used to measure engagement of the participants.

Key Contributions

• Research methodology development
• Experimental design and analysis
• Technical implementation and validation

Download paper

Citation

Voice interfaced vehicle user help

Published in Proceedings of the 10th International Conference on Automotive User Interfaces and Interactive Vehicular Applications, 2010

Abstract

Manuals were designed to provide support and information about the usage and maintenance of the vehicle. In many cases user’s manuals are the driver’s only guidance. However, lack of clarity and efficiency of manuals lead to user dissatisfaction. In vehicles this problem is even more crucial given that driving a motor vehicle is, for many people, the most complex and potentially dangerous task they will perform during their lifetime. In this paper we present a voice interfaced driver manual that can potentially fix the deficiencies of its alternatives. In addition we aim to provide a case for the integration of such technology in a vehicle to reduce driver distraction, increase driver satisfaction, and manual usability, while also benefiting Original Equipment Manufacturers (OEMs) in lowering costs and reducing the documentation process.

Key Contributions

• Voice-interfaced user help system design
• Conversational query methodology
• Dynamic voice user interface architecture
• Prototype development and database design
• Context-aware system and architecture vision

Download paper

Citation