LIBERO-RIG: A Hardware-Setup Robustness Benchmark for Vision-Language-Action Models
Robot policies are expected to generalize across deployment environments, including variations in the robot itself: cameras are bumped and remounted, calibrations drift, controllers run at different rates, and end-effector pads wear down. We present LIBERO-RIG, a benchmark that perturbs only the robot's hardware and se...
Andrea Yaoyun Cui, Han-Yu Wang, Xin-Yi Wang et al.
· 1 citation