Search papers, labs, and topics across Lattice.
2
0
4
1
RAFAIL is introduced, a framework for detecting execution failures during robotic manipulation that requires no failure data and achieves 73.4% balanced accuracy across three real-world robotic manipulation tasks, outperforming the strongest evaluated OOD- and uncertainty-based baselines.
Decomposing pose estimation into error attribution and targeted mitigation allows simple algorithms like ICP to rival the robustness of complex foundation models, but with significantly less computation.
