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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sun, Jian, Jiang, Xiyan, Zhao, Xiaocong, Wang, Jie, Hang, Peng, Li, Zirui
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914467210592256
author Sun, Jian
Jiang, Xiyan
Zhao, Xiaocong
Wang, Jie
Hang, Peng
Li, Zirui
author_facet Sun, Jian
Jiang, Xiyan
Zhao, Xiaocong
Wang, Jie
Hang, Peng
Li, Zirui
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_10806
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Adaptive Bounded-Rationality Modeling of Early-Stage Takeover in Shared-Control Driving
Sun, Jian
Jiang, Xiyan
Zhao, Xiaocong
Wang, Jie
Hang, Peng
Li, Zirui
Human-Computer Interaction
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.
title Adaptive Bounded-Rationality Modeling of Early-Stage Takeover in Shared-Control Driving
topic Human-Computer Interaction
url https://arxiv.org/abs/2604.10806