The Safety Challenge of World Models for Embodied AI Agents: A Review

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Baraldi, Lorenzo, Zeng, Zifan, Zhang, Chongzhe, Nayak, Aradhana, Zhu, Hongbo, Liu, Feng, Zhang, Qunli, Wang, Peng, Liu, Shiming, Hu, Zheng, Cangelosi, Angelo
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909829525667840
author Baraldi, Lorenzo
Zeng, Zifan
Zhang, Chongzhe
Nayak, Aradhana
Zhu, Hongbo
Liu, Feng
Zhang, Qunli
Wang, Peng
Liu, Shiming
Hu, Zheng
Cangelosi, Angelo
Baraldi, Lorenzo
author_facet Baraldi, Lorenzo
Zeng, Zifan
Zhang, Chongzhe
Nayak, Aradhana
Zhu, Hongbo
Liu, Feng
Zhang, Qunli
Wang, Peng
Liu, Shiming
Hu, Zheng
Cangelosi, Angelo
Baraldi, Lorenzo
contents The rapid progress in embodied artificial intelligence has highlighted the necessity for more advanced and integrated models that can perceive, interpret, and predict environmental dynamics. In this context, World Models (WMs) have been introduced to provide embodied agents with the abilities to anticipate future environmental states and fill in knowledge gaps, thereby enhancing agents' ability to plan and execute actions. However, when dealing with embodied agents it is fundamental to ensure that predictions are safe for both the agent and the environment. In this article, we conduct a comprehensive literature review of World Models in the domains of autonomous driving and robotics, with a specific focus on the safety implications of scene and control generation tasks. Our review is complemented by an empirical analysis, wherein we collect and examine predictions from state-of-the-art models, identify and categorize common faults (herein referred to as pathologies), and provide a quantitative evaluation of the results.
format Preprint
id arxiv_https___arxiv_org_abs_2510_05865
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Safety Challenge of World Models for Embodied AI Agents: A Review
Baraldi, Lorenzo
Zeng, Zifan
Zhang, Chongzhe
Nayak, Aradhana
Zhu, Hongbo
Liu, Feng
Zhang, Qunli
Wang, Peng
Liu, Shiming
Hu, Zheng
Cangelosi, Angelo
Baraldi, Lorenzo
Artificial Intelligence
Computer Vision and Pattern Recognition
Robotics
The rapid progress in embodied artificial intelligence has highlighted the necessity for more advanced and integrated models that can perceive, interpret, and predict environmental dynamics. In this context, World Models (WMs) have been introduced to provide embodied agents with the abilities to anticipate future environmental states and fill in knowledge gaps, thereby enhancing agents' ability to plan and execute actions. However, when dealing with embodied agents it is fundamental to ensure that predictions are safe for both the agent and the environment. In this article, we conduct a comprehensive literature review of World Models in the domains of autonomous driving and robotics, with a specific focus on the safety implications of scene and control generation tasks. Our review is complemented by an empirical analysis, wherein we collect and examine predictions from state-of-the-art models, identify and categorize common faults (herein referred to as pathologies), and provide a quantitative evaluation of the results.
title The Safety Challenge of World Models for Embodied AI Agents: A Review
topic Artificial Intelligence
Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2510.05865