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

TL;DR

This paper introduces an adaptive, interpretable driver model based on bounded rationality, capable of predicting early-stage control quality during handovers in shared-driving, improving safety and aligning with physiological data.

Contribution

The novel model incorporates bounded rationality with online adaptation, outperforming non-adaptive baselines in predicting hazardous takeovers and capturing cognitive fluctuations.

Findings

Adaptive model predicts hazardous takeovers with higher coverage and longer lead times.

Model's inferred cognitive parameters strongly correlate with eye-tracking metrics.

Real-time adaptation improves early-stage control quality prediction.

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.