Communication timing improves in-car agent interactions and reduces interruptions
When2Talk: When Should a Proactive In-Car Agent Talk?
Human-Computer InteractionComputer Vision and Pattern Recognition
Summary
Automated cars can use in-car agents that talk to passengers to explain what the car is doing. The authors found that if these agents speak only when important and consider what the passenger is doing, people feel less interrupted and find the communication more appropriate. They tested two ways: one that talks about every event immediately, and another that chooses when to talk or stay silent based on the situation. The results showed that selective talking leads to better experiences without reducing trust in the car system.
What this means in practice
- •For automotive user interface designers: Design in-car communication systems that decide when to notify passengers based on importance and passenger state to reduce interruptions.
- •For virtual reality developers: Simulate passenger experiences with adaptive in-car agent communication to test user responses before deployment in real vehicles.
Authors
Kaiser Hamid, Peihang Li, Nade Liang
Abstract
Proactive in-cabin agents can help passengers understand automated-vehicle (AV) behavior, but communicating every ride event may introduce unnecessary interruptions. We investigated how communication should adapt to event priority and passenger activity. In a mixed-methods within-subject study, 41 participants rode as passenger in a VR simulated fully-automated vehicle. We compared an event-triggered (ET) policy that communicated immediately at every event with a context-sensitive (CS) policy that selected \textit{Immediate}, \textit{Delayed}, or \textit{Silent} communications. CS increased communication appropriateness and substantially reduced perceived interruption. Perceived trust did not differ between policies, although baselines dispositional trust differentiated communication preferences. Findings highlight event consequence, passenger activity, continuing information value, and confirmation need as key considerations for selective in-cabin communication.