Safe Embodied AI for Long-horizon Tasks: A Cross-layer Analysis of Robotic Manipulation
- URL: http://arxiv.org/abs/2606.05660v1
- Date: Thu, 04 Jun 2026 03:43:09 GMT
- Title: Safe Embodied AI for Long-horizon Tasks: A Cross-layer Analysis of Robotic Manipulation
- Abstract summary: Embodied AI systems are increasingly expected to reason and act over extended horizons in physical environments.<n>Although safe embodied AI has attracted substantial attention, the literature remains fragmented across planning, policy design, and runtime execution.<n>This survey provides a structured review of safety in long-horizon robotic manipulation from an embodied AI perspective.
- Score: 34.70550511647954
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Embodied AI systems are increasingly expected to reason and act over extended horizons in physical environments. This growing capability brings safety to the foreground, because failures in the physical world can harm people, damage objects, and disrupt workplaces. Although safe embodied AI has attracted substantial attention, the literature remains fragmented across planning, policy design, and runtime execution. Long-horizon robotic manipulation is a particularly revealing anchor domain for this problem because semantic misgrounding, subtask-level error propagation, execution drift, and contact-rich physical risk can accumulate within the same closed-loop system. This survey therefore provides a structured review of safety in long-horizon robotic manipulation from an embodied AI perspective. We organize the literature by intervention locus, covering planning-time, policy-time, and execution-time safety, and we analyze the strength of the evidence that each line of work provides, distinguishing formal guarantees, statistical support, and empirical safety heuristics. This framework clarifies the distinct roles of backbone capability papers, direct safety mechanisms, and benchmark or evaluation studies, while exposing where current safety claims are well supported and where they remain indirect. We identify persistent gaps, including limited evidence for policy-time safety, weak formal support for contact-rich long-horizon manipulation, immature uncertainty-triggered intervention, and a shortage of manipulation-specific safety benchmarks. We conclude by outlining research directions for cross-layer assurance, evaluation design, and safer deployment of long-horizon robotic agents in real-world settings.
Related papers
- Toward Secure AI-Powered Penetration Testing Agents: Security Threats, Guardrails, and Architectural Perspectives [0.0]
LLM-powered autonomous agents are transforming the penetration testing space with dynamic, multi-step offensive security.<n>But the ability to have persistent memory, to take actions in the real world, and to do long-horizon reasoning raises qualitatively different security concerns.<n>Existing guardrail mechanisms for conversational AI may not be sufficient to secure autonomous AI pentesting agents accordingly.
arXiv Detail & Related papers (2026-09-15T06:19:50Z) - Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms [61.29786895012393]
Vision-Language-Action (VLA) models are emerging as a unified substrate for embodied intelligence.<n>This survey provides a unified and up-to-date overview of safety in Vision-Language-Action models.
arXiv Detail & Related papers (2026-04-26T15:58:19Z) - Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses [168.50301366360344]
Embodied Artificial Intelligence (Embodied AI) integrates perception, cognition, planning, and interaction into agents that operate in safety-critical environments.<n>Unlike digital AI systems, embodied agents must act under uncertain sensing, incomplete knowledge, and dynamic human-robot interactions.<n>This survey provides a comprehensive review of safety research in embodied AI, examining attacks and defenses across the full embodied pipeline.
arXiv Detail & Related papers (2026-03-28T13:21:44Z) - What Breaks Embodied AI Security:LLM Vulnerabilities, CPS Flaws,or Something Else? [28.12412876058788]
Embodied AI systems are rapidly transitioning from controlled environments to safety critical real-world deployments.<n>Unlike disembodied AI, failures in embodied intelligence lead to irreversible physical consequences.<n>We argue that a significant class of failures arises from embodiment-induced system-level mismatches.
arXiv Detail & Related papers (2026-02-19T13:29:00Z) - RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic [56.38397499463889]
Embodied agents powered by vision-language models (VLMs) are increasingly capable of executing complex real-world tasks.<n>However, they remain vulnerable to hazardous instructions that may trigger unsafe behaviors.<n>We propose RoboSafe, a runtime safeguard for embodied agents through executable predicate-based safety logic.
arXiv Detail & Related papers (2025-12-24T15:01:26Z) - Trust in LLM-controlled Robotics: a Survey of Security Threats, Defenses and Challenges [31.289512037053246]
Large Language Models (LLMs) have revolutionized their ability to interpret complex human commands and execute sophisticated tasks.<n>Such paradigm shift introduces critical security vulnerabilities stemming from the ''embodiment gap''<n>We present a systematic survey, summarizing the emerging threat landscape and corresponding defense strategies for LLM-controlled robotics.
arXiv Detail & Related papers (2025-12-17T02:07:33Z) - ANNIE: Be Careful of Your Robots [48.89876809734855]
We present the first systematic study of adversarial safety attacks on embodied AI systems.<n>We show attack success rates exceeding 50% across all safety categories.<n>Results expose a previously underexplored but highly consequential attack surface in embodied AI systems.
arXiv Detail & Related papers (2025-09-03T15:00:28Z) - Real-Time Out-of-Distribution Failure Prevention via Multi-Modal Reasoning [18.28480383898768]
FORTRESS is a joint reasoning and planning framework for robot safety.<n>It generates semantically safe fallback strategies to prevent safety-critical, OOD failures.
arXiv Detail & Related papers (2025-05-15T17:55:28Z) - Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress? [59.96471873997733]
We propose an empirical foundation for developing more meaningful safety metrics and define AI safety in a machine learning research context.<n>We aim to provide a more rigorous framework for AI safety research, advancing the science of safety evaluations and clarifying the path towards measurable progress.
arXiv Detail & Related papers (2024-07-31T17:59:24Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.