Adaptive Bounded-Rationality Modeling of Early-Stage Takeover in Shared-Control Driving

2026-04-12

AI Summary

This study addresses the challenge of predicting unstable or hazardous driver behavior during the initial phase of autonomous-to-manual vehicle takeover, where rapid shifts in cognitive state impair reliable control. To overcome the limitations of existing models, the authors propose an explainable driver model grounded in bounded rationality, integrating cognitive constraints into a reinforcement learning framework. Cognitive parameters are inferred online from observed driving behavior using particle filtering, enabling real-time capture of fluctuations in risk perception. Validation through eye-tracking data and a vehicle-in-the-loop experiment with 41 participants demonstrates that the model predicts risky takeover actions earlier and more comprehensively than non-adaptive baselines. Moreover, the inferred cognitive parameters exhibit strong alignment with eye-movement metrics, significantly enhancing both takeover safety and model interpretability.

Technology Category

• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Human drivers' control quality in the first seconds after a handover is critical to shared-driving safety; potentially unsafe steering or pedal inputs therefore require detection and correction by the automated vehicle's safety-fallback system. Yet performance in this window is vulnerable because cognitive states fluctuate rapidly, causing purely rationality-driven, cognition-unaware models to miss early control dynamics. We present an interpretable driver model grounded in bounded rationality with online adaptation that predicts early-stage control quality. We encode boundedness by embedding cognitive constraints in reinforcement learning and adapt latent cognitive parameters in real time via particle filtering from observations of driver actions. In a vehicle-in-the-loop study (n=41), we evaluated predictive performance and physiological validity. The adaptive model not only anticipated hazardous takeovers with higher coverage and longer lead times than non-adaptive baselines but also demonstrated strong alignment between inferred cognitive parameters and real-time eye-tracking metrics. These results confirm that the model captures genuine fluctuations in driver risk perception, enabling timely and cognitively grounded assistance.

Problem

• shared-control driving
• takeover
• bounded rationality
• cognitive state
• driver modeling

Innovation

• bounded rationality
• online adaptation
• reinforcement learning
• particle filtering
• shared-control driving