Safety of Embodied Navigation: A Survey
Zixia Wang, Jia Hu, Ronghui Mu

TL;DR
This survey analyzes safety challenges in embodied navigation, discussing attack strategies, defenses, evaluation methods, and future research directions to develop safer, more reliable embodied AI systems in real-world environments.
Contribution
It provides a comprehensive overview of safety issues, mitigation techniques, evaluation metrics, and future research directions in embodied navigation safety.
Findings
Identifies key attack methods and defense strategies.
Reviews existing evaluation datasets and metrics.
Highlights unresolved safety challenges and future research needs.
Abstract
As large language models (LLMs) continue to advance and gain influence, the development of embodied AI has accelerated, drawing significant attention, particularly in navigation scenarios. Embodied navigation requires an agent to perceive, interact with, and adapt to its environment while moving toward a specified target in unfamiliar settings. However, the integration of embodied navigation into critical applications raises substantial safety concerns. Given their deployment in dynamic, real-world environments, ensuring the safety of such systems is critical. This survey provides a comprehensive analysis of safety in embodied navigation from multiple perspectives, encompassing attack strategies, defense mechanisms, and evaluation methodologies. Beyond conducting a comprehensive examination of existing safety challenges, mitigation technologies, and various datasets and metrics that…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMaritime Navigation and Safety · Social Robot Interaction and HRI · Evacuation and Crowd Dynamics
