Realistic pedestrian-driver interaction modelling using multi-agent RL with human perceptual-motor constraints

TL;DR

This paper introduces a multi-agent reinforcement learning framework that incorporates visual and motor constraints to realistically simulate pedestrian-driver interactions, improving behavioral authenticity without large datasets.

Contribution

It presents a novel multi-agent RL model integrating perceptual-motor constraints, enhancing realism in pedestrian-driver interaction simulations compared to prior rule-based or black-box models.

Findings

Combined visual and motor constraints improve interaction realism.

Motor constraints produce smoother, human-like movements.

Model outperforms supervised behavioral cloning in data-limited scenarios.

Abstract

Modelling pedestrian-driver interactions is critical for understanding human road user behaviour and developing safe autonomous vehicle systems. Existing approaches often rely on rule-based logic, game-theoretic models, or 'black-box' machine learning methods. However, these models typically lack flexibility or overlook the underlying mechanisms, such as sensory and motor constraints, which shape how pedestrians and drivers perceive and act in interactive scenarios. In this study, we propose a multi-agent reinforcement learning (RL) framework that integrates both visual and motor constraints of pedestrian and driver agents. Using a real-world dataset from an unsignalised pedestrian crossing, we evaluate four model variants, one without constraints, two with either motor or visual constraints, and one with both, across behavioural metrics of interaction realism. Results show that the combined model with both visual and motor constraints performs best. Motor constraints lead to smoother movements that resemble human speed adjustments during crossing interactions. The addition of visual constraints introduces perceptual uncertainty and field-of-view limitations, leading the agents to exhibit more cautious and variable behaviour, such as less abrupt deceleration. In this data-limited setting, our model outperforms a supervised behavioural cloning model, demonstrating that our approach can be effective without large training datasets. Finally, our framework accounts for individual differences by modelling parameters controlling the human constraints as population-level distributions, a perspective that has not been explored in previous work on pedestrian-vehicle interaction modelling. Overall, our work demonstrates that multi-agent RL with human constraints is a promising modelling approach for simulating realistic road user interactions.