← Back to all news
arXiv AI By Bingxin Xu, Yuzhang Shang, Zhen Dong, Emilio Ferrara

Coding Agents with an Obstacle-Aware Harness for Safe Robot Manipulation

Read the original on arXiv AI →

The paper introduces SafeHarness, an obstacle‑aware framework that improves the safety of coding agents for robot manipulation. By decomposing tasks into route planning and contact execution, the harness enables the agent to prioritize collision avoidance, achieving 71.9% task success and 87.5% collision avoidance—significantly better than prior methods. The study demonstrates that safety constraints can be effectively integrated into language‑model‑driven robot controllers.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Aug 25

Physical Agentic AI: An Architecture for Orchestrating a Robot Crew with LLMs

Physical Agentic AI proposes an architecture that links semantic planning with physical execution for robot crews. Each robot exposes a typed skill library, while a foundation model planner decomposes tasks into phases and assigns robot‑skill pairs. A Robot Orchestrator validates and authorizes one skill at a time, ensuring actions are grounded in robot capabilities, system state, and workflow constraints before actuation.

By Xinyuan Liu, Eren Sadikoglu, Riana Chatterjee, Ransalu Senanayake
llmsagentsroboticsbenchmarks
More like this →
arXiv AI
Sep 25

CrossSafe: Towards Cross-Embodiment Latent Safety Filters

CrossSafe proposes embodiment-conditioned safety filtering that uses a Hamilton‑Jacobi reachability value function shared across robots while conditioning on each robot’s morphology and kinematics via a morphology‑aware latent representation. The method performs reachability analysis directly in latent space, enabling a single policy trained on multiple bimanual robot embodiments and manipulation tasks to generalize zero‑shot to a held‑out embodiment and reduce collision rates. Experiments on five embodiments and five tasks demonstrate that training with more embodiments improves generalization.

By Ihab Tabbara, Yuxuan Yang, Hussein Sibai
diffusionroboticsmultimodalsafety
More like this →