English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Understanding the interaction between different road users is critical forroad safety and automated vehicles (AVs). Existing mathematical models on thistopic have been proposed based mostly on either cognitive or machine learning(ML) approaches. However, current cognitive models are incapable of simulatingroad user trajectories in general scenarios, and ML models lack a focus on themechanisms generating the behavior and take a high-level perspective which cancause failures to capture important human-like behaviors. Here, we develop amodel of human pedestrian crossing decisions based on computationalrationality, an approach using deep reinforcement learning (RL) to learnboundedly optimal behavior policies given human constraints, in our case amodel of the limited human visual system. We show that the proposed combinedcognitive-RL model captures human-like patterns of gap acceptance and crossinginitiation time. Interestingly, our model's decisions are sensitive to not onlythe time gap, but also the speed of the approaching vehicle, something whichhas been described as a "bias" in human gap acceptance behavior. However, ourresults suggest that this is instead a rational adaption to human perceptuallimitations. Moreover, we demonstrate an approach to accounting for individualdifferences in computational rationality models, by conditioning the RL policyon the parameters of the human constraints. Our results demonstrate thefeasibility of generating more human-like road user behavior by combining RLwith cognitive models.

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