Inspect Robots: Evaluating the Capabilities and Safety of Embodied AI

arXiv:2610.06306 · cs.RO · Submitted 2026-10-05 · Read on arXiv

cs.RO

Submitted: 2026-10-05

Updated: 2026-10-05

Comments: Submitted to The Science of Physical AI Safety (SPAIS) Workshop at CoRL 2026

Code: https://github.com/UKGovernmentBEIS/inspect_ai

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Embodied AI — 1× in this paper · explained in 2 episodes

Sources

• An Unexpected Robot Policy: Early Evaluations of GPT-6 Astra on RoboDojo and Beyond
• Agent as Policy for Robotic Manipulation
• RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies
• XPolicyLab: A Unified Standard and Open Ecosystem for Robot Policy Evaluation and Deployment

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