Modeling human road crossing decisions as reward maximization with visual perception limitations

TL;DR

This paper presents a computational model combining cognitive science and deep reinforcement learning to simulate human pedestrian crossing decisions, accounting for visual perception limitations and individual differences, improving realism over prior models.

Contribution

The study introduces a novel cognitive-RL hybrid model that captures human-like crossing behaviors and adapts to individual perceptual constraints, advancing the modeling of road user interactions.

Findings

The model replicates human gap acceptance and crossing times.

Decisions are influenced by vehicle speed, reflecting human biases.

Individual differences can be incorporated via model conditioning.

Abstract

Understanding the interaction between different road users is critical for road safety and automated vehicles (AVs). Existing mathematical models on this topic have been proposed based mostly on either cognitive or machine learning (ML) approaches. However, current cognitive models are incapable of simulating road user trajectories in general scenarios, and ML models lack a focus on the mechanisms generating the behavior and take a high-level perspective which can cause failures to capture important human-like behaviors. Here, we develop a model of human pedestrian crossing decisions based on computational rationality, an approach using deep reinforcement learning (RL) to learn boundedly optimal behavior policies given human constraints, in our case a model of the limited human visual system. We show that the proposed combined cognitive-RL model captures human-like patterns of gap acceptance and crossing initiation time. Interestingly, our model's decisions are sensitive to not only the time gap, but also the speed of the approaching vehicle, something which has been described as a "bias" in human gap acceptance behavior. However, our results suggest that this is instead a rational adaption to human perceptual limitations. Moreover, we demonstrate an approach to accounting for individual differences in computational rationality models, by conditioning the RL policy on the parameters of the human constraints. Our results demonstrate the feasibility of generating more human-like road user behavior by combining RL with cognitive models.