Metraipolis › archive › dc_247dabb145f1

A Human-Like Pedestrian Model for Automated Driving Simulations — arXiv:2609.29175

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.29175
License (as archived)
CC0-1.0
Archived
2026-10-08T05:25:26.596Z
SHA-256 of the archived text
387961ac7db7434729819243ea53f9cf9e937e3b74d6d5e926f42cc1a7bc6578
Stable URL of this page
https://metraipolis.com/documento/dc_247dabb145f1

How to cite

A Human-Like Pedestrian Model for Automated Driving Simulations — arXiv:2609.29175 — arXiv (en), https://arxiv.org/abs/2609.29175 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_247dabb145f1 (Metraipolis archive dc_247dabb145f1, sha256 387961ac7db7434729819243ea53f9cf9e937e3b74d6d5e926f42cc1a7bc6578)
BibTeX
@misc{dc247dabb145f1,
  title = {A Human-Like Pedestrian Model for Automated Driving Simulations — arXiv:2609.29175},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.29175},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_247dabb145f1; sha256 387961ac7db7434729819243ea53f9cf9e937e3b74d6d5e926f42cc1a7bc6578},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29175. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Automated vehicles must be able to interact with pedestrians safely and efficiently across diverse traffic situations. Although driving simulators offer a scalable testbed for learning such capabilities, existing theory-inspired pedestrian models are narrow in scope and limited to go/no-go crossing decisions in single-lane settings. While data-driven approaches can predict pedestrian behavior in complex situations, they lack sufficient observations in rare, safety-critical scenarios. Here, we propose an approach to training pedestrian models in simulators so that learned policies generate demonstrably human-like behavior in realistic, complex traffic scenarios, including multiple lanes, heavy traffic, and dangerous driving styles. Our technical contribution is a novel definition of pedestrian-vehicle interaction as a partially observable Markov decision process (POMDP) with theory-grounded perceptual, cognitive, and motor constraints. It accounts for the highly adaptive nature of human behavior in traffic and simulates how people adjust their responses according to perceived danger, time pressure, and the complexity of the situation. When trained via deep reinforcement learning (RL) with domain randomization in a simulator, the model reproduces the broadest range of empirical findings shown so far on human crossing behavior, including gap acceptance, yielding acceptance, hesitation, and evasive speed adjustment. We show that learned policies transfer to unseen traffic environments, and can be further adapted to local traffic norms with finetuning. Together, these results establish a blueprint for simulator-ready pedestrian models that can support the development and evaluation of automated driving systems.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.HC).
Categorie arXiv: Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2609.29175 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T04:50:17.667Z dalla pagina https://arxiv.org/catchup/cs.HC/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).