Robot like in-vehicle agent for a level 3 automated car

Zeng, X., Alam, M. S., Bazilinskyy, P.

(2025)

ABSTRACT With the rapid development of automotive technology and artificial intelligence, in-vehicle agents have great potential to solve the challenges of explaining the status of the system and the intentions of an automated vehicle. A robot-like in-vehicle agent was designed and developed to explore the in-vehicle agent communicating through gestures and facial expressions with a driver in a SAE Level 3 automated vehicle. An experiment with 12 participants was conducted to evaluate the prototype. The results showed that facial expression and gesture interactions can reduce workload (NASA TLX mean scores: baseline = 33%, facial expressions = 23%, gestures = 18%) and increase usefulness and satisfaction. In general, gestures were preferred by 7 of 12 participants due to their practicality and earlier signal timing, while facial expressions were preferred by the remaining 5 participants for their emotional and aesthetic appeal. These findings highlight the distinct advantages of gesture-based interactions for functional communication and facial expressions for emotional connection in automated driving scenarios.