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

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.

Automated summary

Understanding the interaction between different road users is crucial for road safety and automated vehicles. Existing mathematical models on this topic have been mostly proposed based on cognitive or machine learning approaches. However, current cognitive models fail to simulate road user trajectories in general scenarios, while machine learning models lack a focus on the mechanisms generating behavior and may not capture important human-like behaviors. In this study, we develop a computational rationality model using deep reinforcement learning to capture human pedestrian crossing decisions, considering the limited human visual system. Our results demonstrate that the proposed cognitive-reinforcement learning model replicates human-like patterns of gap acceptance and crossing initiation time, providing new insights into road user behavior.