Route-Guided CBF-QP Repair for Safe Vision-Language-Action Models

1. 05:00
   arXiv Robotics — research abstractsSignal

   Route-Guided CBF-QP Repair for Safe Vision-Language-Action Models

   This paper introduces Route-Guided CBF-QP Repair, a post-hoc repair module designed to enhance the safety and reliability of vision-language-action (VLA) models in obstacle-rich manipulation scenarios. By incorporating short-horizon action chunks predicted by the VLA into a route-guidance term within a Control Barrier Function Quadratic Programming (CBF-QP) framework, the method ensures that unsafe actions are corrected without deviating excessively from the learned task trajectory. The approach maintains hard CBF safety constraints while using soft guidance to navigate around obstacles, improving collision avoidance, task success, and SafeSuccess metrics compared to the AEGIS baseline on the SafeLIBERO benchmark. The project page is available on GitHub.

Current attention 3·Peak within the comparable range 4（2026-11-04 16:00 UTC）·Change within the comparable range over 24 hours –

The trend compares participants observed continuously; its scope may be narrower than current attention totals. Hover or click to explore hourly observations, or use the left and right arrow keys.