arXiv:2608. 13438v1 Announce Type: cross Abstract: Contact-rich manipulation failures are often detected only after the robot has committed to contact.
By Gehan Zheng, Matthew Johnson-Roberson, Weiming Zhi
arXiv:2606. 05660v1 Announce Type: cross Abstract: Embodied AI systems are increasingly expected to reason and act over extended horizons in physical environments.
By Dabin Kim, Daemin Park, Sangyub Lee, Jinsik Kim, Yeongtak Oh, Jongho Shin, Sungroh Yoon
The paper introduces FailureSpot, a label‑efficient method for detecting failures at the timestamp level in vision‑language‑action (VLA) policies. It first generates weak supervision from unlabeled VLA action chunks by identifying abnormal patterns, then employs active learning to annotate only the most uncertain trajectories. Experiments on multiple VLA policies demonstrate improved performance for both timestamp‑level and trajectory‑level failure detection.
By Jie Ma, Zongxi Liu, Yi Zhu
arXiv:2607. 01111v1 Announce Type: cross Abstract: Robot policies inevitably encounter failures when deployed in real environments.
By Haoran Hao, Shahram Najam Syed, Jeffrey Ichnowski, Jeff Schneider
arXiv:2606. 08881v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have demonstrated strong generalization in robotic manipulation, yet existing evaluations are primarily conducted in simulation or on expensive robotic platforms, leaving their robustness on affordable real-world robots largely unexplored.
By Yi Yu, Xinchuan Qiu
arXiv:2606. 08414v1 Announce Type: cross Abstract: Diffusion policies have achieved remarkable success in robotic manipulation, yet they often fail to satisfy strict physical constraints required for safe deployment.
By Lingxuan Wu, Zijian Zhu, Lizhong Wang, Chengyang Ying, Huayu Chen, Xiao Yang, Fangming Liu, Jun Zhu