Characterizing Driver Interactions with Autonomous Vehicles via Response Maps

2026-06-25

AI Summary

This study addresses socially compatible cooperative driving by investigating how human drivers respond to the behaviors of autonomous vehicles. Drawing on the concept of response mapping from game theory and leveraging empirical data from driving simulator experiments, the authors model human reactions as a linear feedback policy over a coupled state space. This work pioneers the application of response mapping to human–autonomous vehicle interaction modeling, revealing distinct behavioral patterns in human responses to autonomous yielding, non-yielding, and reactive strategies. The proposed framework effectively captures the mapping between human acceleration responses and autonomous vehicle actions, demonstrating that different autonomous driving strategies exert significant and measurable influences on human driving behavior.

Abstract

Understanding human responses to autonomous vehicle (AV) behaviors is essential for socially aware interaction, which is crucial for socially compatible navigation in shared traffic environments. We characterize human driving responses in interactions with AVs as feedback laws over the coupled state space of the human driven vehicle and the AV. We model the human driver's actions using a response map, a concept based in game theory, and employ a linear representation to capture driver behaviors as a function of AV behaviors, based on empirical data from a driving simulator study. Our results show that 1) human driver acceleration behavior can be captured using response maps, and 2) human driver responses differ significantly with respect to AV behaviors of yielding, non-yielding, and responsive to the human driver.

Problem

• human-vehicle interaction
• autonomous vehicles
• response maps
• socially compatible navigation
• driving behavior

Innovation

• response maps
• human-AV interaction
• game theory
• socially aware navigation
• driving simulator