WBAG: A Whole-Body and Attached-Geometry Safety Framework for Vision-Language-Action Manipulation

This paper presents WBAG, a safety framework for vision-language-action (VLA) policies that models the robot's whole-body and grasp-dependent attached geometry. WBAG constructs a grasp-conditioned safe set and converts it into differentiable CBF constraints for collision avoidance. On the SafeLIBERO benchmark, WBAG achieves 97.38% aggregate Scene Safety and 59.38% Safe Success, outperforming other methods.