Agentic driving changes how cars and humans interact and trust each other

Human-Aware Agentic Driving: Rethinking Driver State, Trust, and Intervention

Human-Computer Interaction

Summary

Self-driving cars that can think ahead, explain their moves, and talk adaptively to drivers might change how people pay attention and trust these cars. The authors looked at how these smart interactions affect when a person takes over control and how drivers understand and rely on these vehicles. They found that while some existing ideas about driver attention and warnings still apply, new challenges arise because the car can actively shape driver behavior. They suggest future research should study the effects of interventions, develop joint designs for interaction and driving decisions, and ensure these systems keep working well over time.

What this means in practice

  • For automotive engineers: Design car systems that adapt driving actions based on driver trust and state to improve safety and driver understanding in semi-automated vehicles.
  • For human factors teams: Develop adaptive driver alerts and interactions that maintain appropriate human reliance and timely intervention during automated driving.

A position paper. It proposes an approach and reports no results.

Authors

Lu Feng

Abstract

Agentic driving brings goal-directed reasoning, memory, tools, and adaptive interaction into automated vehicles. A vehicle can clarify a request, explain a maneuver, or prepare a driver to take control, then adapt its next action to the response. These capabilities make the vehicle an active participant in shaping the human behavior it observes. We examine how agentic interaction affects driver-state inference, trust and reliance, and human intervention in conditional automation. Established findings on attention, takeover prediction, trust-aware planning, and adaptive warnings provide useful foundations, but their applicability depends on how observations are elicited and how assistance changes the driving task. We distinguish what remains applicable, what changes under flexible interaction, and what remains unresolved across these three areas. The analysis identifies three research priorities: establishing the effects of interventions, jointly designing interaction and driving policies, and maintaining useful adaptation across repeated use and system changes. Progress should be measured through driver comprehension, appropriate reliance, and the ability to perform the required driving action in time.
View PDFOpen arXiv