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