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.

Deep learning (DL) has shown state-of-the-art performance in trajectory prediction, which is critical to safe navigation in autonomous driving (AD). However, most DL-based methods suffer from catastrophic forgetting, where adapting to a new distribution may cause significant performance degradation in previously learned ones. Such inability to retain learned knowledge limits their applicability in the real world, where AD systems need to operate across varying scenarios with dynamic distributions. As revealed by neuroscience, the hippocampal circuit plays a crucial role in memory replay, effectively reconstructing learned knowledge based on limited resources. Inspired by this, we propose a hippocampal circuit-inspired continual learning method (H2C) for trajectory prediction across varying scenarios. H2C retains prior knowledge by selectively recalling a small subset of learned samples. First, two complementary strategies are developed to select the subset to represent learned knowledge. Specifically, one strategy maximizes inter-sample diversity to represent the distinctive knowledge, and the other estimates the overall knowledge by equiprobable sampling. Then, H2C updates via a memory replay loss function calculated by these selected samples to retain knowledge while learning new data. Experiments based on various scenarios from the INTERACTION dataset are designed to evaluate H2C. Experimental results show that H2C reduces catastrophic forgetting of DL baselines by 22.71% on average in a task-free manner, without relying on manually informed distributional shifts. The implementation is available at https://github.com/BIT-Jack/H2C-lifelong.

Autonomous vehicles (AV) are consistently criticized for their inadequacies in harmoniously interacting with human-driven vehicles (HV), primarily attributed to the lack of sociality, a key human trait that balances individual and group rewards. Understanding sociality is essential for smooth AV navigation but remains challenging. To address this, we propose a Game-Theoretic Inverse Reinforcement Learning (GT-IRL) approach to quantify individualized sociality in driving interaction. Our approach identifies the sociality-preference parameters of a pre-designed reward function that integrates the ego agent’s rewards and the group rewards shared by all the interacting agents. Instead of presuming an agent is propelled by the maximization of its own rewards, the game-theoretical mechanism is utilized within the IRL structure to capture the fact that human drivers take into account others’ interests. We validated our method using human driving data from an unprotected left-turn scenario. The results demonstrate that the proposed GT-IRL outperforms state-of-the-art methods in better reproducing the evolution of the left-turn interaction at both semantic and trajectory levels. Additionally, cross-dataset analysis reveals variations in sociality due to geographical differences (China vs. the U.S.) and the nature of the interacting entities (AV vs. HV or HV vs. HV).

Interacting with human road users is one of the most challenging tasks for autonomous vehicles. For congruent driving behaviors, it is essential to recognize and comprehend sociality, encompassing both implicit social norms and individualized social preferences of human drivers. To understand and quantify the complex sociality in driving interactions, we propose a Virtual-Game-based Interaction Model (VGIM) that is parameterized by a social preference measurement, Interaction Preference Value (IPV). The IPV is designed to capture the driver’s relative inclination towards individual rewards over group rewards. A method for identifying IPV from observed driving trajectory is also developed, with which we assessed human drivers’ IPV using driving data recorded in a typical interactive driving scenario, the unprotected left turn. Our findings reveal that (1) human drivers exhibit particular social preference patterns while undertaking specific tasks, such as turning left or proceeding straight; (2) competitive actions could be strategically conducted by human drivers in order to coordinate with others. Finally, we discuss the potential of learning sociality-aware navigation from human demonstrations by incorporating a rule-based humanlike IPV expressing strategy into VGIM and optimization-based motion planners. Simulation experiments demonstrate that (1) IPV identification improves the motion prediction performance in interactive driving scenarios and (2) the dynamic IPV expressing strategy extracted from human driving data makes it possible to reproduce humanlike coordination patterns in the driving interaction.

Interacting with other vehicles while ensuring safety is a routine task for human drivers, but it can pose a challenge for autonomous vehicles. To address this challenge, we derived a generic utility term of interaction activeness (UTIA) from the driving interaction formulation which considers the rationality of interacting counterparts. Our research shows that incorporating UTIA as a supplementary utility term can improve the active interaction capability of both sampling-based and game-theoretic baseline motion planners without compromising safety. Through simulation experiments, we observed that on average, incorporating the weighted UTIA into the utility function of baseline planners can result in an 8.8% increase in the success rate of exiting a highway within a set distance.