Coding Agents with an Obstacle-Aware Harness for Safe Robot Manipulation
A safety prompt did not stop robot coding agents from colliding with obstacles. SafeHarness instead makes route verification, replanning, and contact constraints explicit in the execution loop.
The tested coding agent recognized the obstacle and was explicitly told not to touch it, yet collided in most cases because safety never became a planning priority. SafeHarness reached **71.9% task success** and **87.5% collision avoidance**.
For safety-critical agents, encode constraints in the harness rather than relying on prompt compliance. Here that means grounding objects as boxes, generating and verifying waypoint routes, replanning blocked paths, and selecting a safe contact position.
The tested coding agent recognized the obstacle and was explicitly told not to touch it, yet collided in most cases because safety never became a planning priority. SafeHarness reached **71.9% task success** and **87.5% collision avoidance**. For safety-critical agents, encode constraints in the harness rather than relying on prompt compliance. Here that means grounding objects as boxes, generating and verifying waypoint routes, replanning blocked paths, and selecting a safe contact position. The reported gains over the previous state of the art are **6.5%** for task success and **27.0%** for collision avoidance. The abstract does not establish whether the method transfers beyond its evaluated robot-manipulation tasks and obstacle setup.
This provides task-level evidence that explicit safety instructions can fail even when the agent recognizes the hazard. It strengthens the case for moving constraints from prompts into executable planning and verification, and makes that principle concrete through grounded geometry and checked routes. Transfer beyond the tested manipulation setup remains unresolved.