Pedestrian crossing decisions can be explained by bounded optimal decision-making under noisy visual perception

This paper presents a model of pedestrian crossing decisions based on the theory of computational rationality. It is assumed that crossing decisions are boundedly optimal, with bounds on optimality arising from human cognitive constraints. While previous models of pedestrian behaviour have been either ‘black-box’ machine learning models or mechanistic models with explicit assumptions about cognitive factors, we combine both approaches. Specifically, we mechanistically model noisy human visual perception and model reward considering human constraints in crossing, but we use reinforcement learning to learn boundedly optimal behaviour policy. The model reproduces a larger number of known empirical phenomena than previous models, in particular: (1) the effect of the time to arrival of an approaching vehicle on whether the pedestrian accepts the gap, the effect of the vehicle’s speed on both (2) gap acceptance and (3) pedestrian timing of crossing in front of yielding vehicles, and (4) the effect on this crossing timing of the stopping distance of the yielding vehicle. Notably, our findings suggest that behaviours previously framed as ’biases’ in decision-making, such as speed-dependent gap acceptance, might instead be a product of rational adaptation to the constraints of visual perception. Our approach also permits fitting the parameters of cognitive constraints and rewards per individual to better account for individual differences, achieving good quantitative alignment with experimental data. To conclude, by leveraging both RL and mechanistic modelling, our model offers novel insights into pedestrian behaviour and may provide a useful foundation for more accurate and scalable pedestrian models. • A novel pedestrian model based on the computational rationality framework. • The model reproduces more empirical phenomena than existing models. • Pedestrian ‘biases’ can be understood as rational adaptations to human limitations. • Conditioning reinforcement learning policy on non-policy parameters is effective. • This work provides a foundation for more scalable pedestrian models.