ConAI: AI-based conversational agents that support drivers´ understanding of ADAS and enhance traffic safety

Purpose and goal

Many truck drivers struggle to understand and use Advanced Driver Assistance Systems (ADAS, SAE Level 2), often learning through trial and error, which can lead to misuse or system deactivation. This project explores how AI-based conversational agents can make ADAS more explainable and support learning before, during, and after driving. This paves the way for safer and more frequent use of ADAS among a broader and more diverse group of truck drivers.

Expected effects and result

The results a) insights into the learning strategies truck drivers use to understand how ADAS works, b) conceptualization of at least 3 learning strategies based on AI-driven conversation, c) at least one prototype implemented in a simulated or real truck, d) insights into how AI-based conversational agents are perceived by truck drivers and their impact on ADAS usage, and e) one scientific publication contributing to a doctoral dissertation.

Planned approach and implementation

The project follows a design thinking methodology and is structured around its main phases: Empathize, Define, Ideate, Prototype, and Test. This approach ensures that the developed concept solutions are deeply rooted in real user needs. The project is divided into six work packages: 1) Project management, 2) Understanding driver needs and design requirements, 3) Concept development, 4) Prototype development, 5) User tests and analysis, and 6) Communication and dissemination of results.