From bits to atoms: A survey of cross-layer safety in Embodied AI
arXiv:2610.14038 · doi:10.59717/ipj.aiplus.2026.100013
Abstract
Embodied Artificial Intelligence (AI) introduces cyber-physical risks because digital failures and attacks can cause physical harm. This survey organizes embodied AI safety through a four-layer reference architecture -- comprising the physical interaction, system and middleware, algorithm and decision, and cloud-edge and data layers -- and uses it to connect vulnerabilities, propagation paths, and safeguards across the system stack. It traces the evolution of safety paradigms and examines how faults and attacks cross architectural boundaries to produce physical consequences. Furthermore, the survey systematizes composite attack chains, outlines multi-layered defense strategies, and reviews representative embodied safety benchmarks. Ultimately, we advocate for unifying software alignment with rigorous hardware constraints to build trustworthy systems capable of operating safely within human-centric environments.
arXiv commentReview article published in AI Plus. 25 pages, 6 figures. URL: https://www.the-innovation.org/ai-plus/article/doi/10.59717/ipj.aiplus.2026.100013
References in corpus (15)
- Catastrophic cascade of failures in interdependent networks
- Control Barrier Function Based Quadratic Programs for Safety Critical Systems
- Lidar for Autonomous Driving: The principles, challenges, and trends for automotive lidar and perception systems
- Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Driving
- Electromagnetic fault injection: towards a fault model on a 32-bit microcontroller
- AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways
- Software Architectures for Robotics Systems: A Systematic Mapping Study
- Run Time Assurance for Safety-Critical Systems: An Introduction to Safety Filtering Approaches for Complex Control Systems
- ROSpace: Intrusion Detection Dataset for a ROS2-Based Cyber-Physical System
- The Black-Box Simplex Architecture for Runtime Assurance of Autonomous CPS
- DaDu-Corki: Algorithm-Architecture Co-Design for Embodied AI-powered Robotic Manipulation
- The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies
- Safety on the Fly: Constructing Robust Safety Filters via Policy Control Barrier Functions at Runtime
- CHAI: Command Hijacking against embodied AI
- CREATE: Cross-Layer Resilience Characterization and Optimization for Efficient yet Reliable Embodied AI Systems