From bits to atoms: A survey of cross-layer safety in Embodied AI
cs.RO
Submitted: 2026-10-02
Updated: 2026-10-02
Project page: https://sites.google.com/view/wenguanwang
Terminology
Sources
- SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
- Concrete Problems in AI Safety
- AI Alignment: A Comprehensive Survey
- Easier Said Than Done: Unpacking Intent-Behavior Gap in Jailbreaking LLM-Based Robots
- Rolling Colors: Adversarial Laser Exploits against Traffic Light Recognition
- Towards Adversarial Control Loops in Sensor Attacks: A Case Study to Control the Kinematics and Actuation of Embedded Systems
- Safe Exploration in Continuous Action Spaces
- Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-based Decision-Making Systems
- NavThinker: Action-Conditioned World Models for Coupled Prediction and Planning in Social Navigation
- Gemini Robotics: Bringing AI into the Physical World
- A Survey on Vision-Language-Action Models for Embodied AI
- A Comprehensive Survey on Physical Risk Control in the Era of Foundation Model-enabled Robotics
- Glitch in the Sky: Exploiting Voltage Fault Injection in UAV Flight Controllers
- Attacking Motion Planners Using Adversarial Perception Errors
- Can ROS be used securely in industry? Red teaming ROS-Industrial
- Cybersecurity AI: Hacking Consumer Robots in the AI Era
- CHAI: Command Hijacking against embodied AI
- LLM-Guided Safety Agent for Edge Robotics with an ISO-Compliant Perception-Compute-Control Architecture
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies