InFeR retrains imitation learning policies with a VIB loss for OOD failure detection and applies Grad-CAM to localize failure sources, enabling heuristic recovery in visual navigation without additional demonstrations.
Real-time anomaly detection and reactive planning with large language models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.RO 2years
2025 2verdicts
UNVERDICTED 2representative citing papers
A passively compliant soft wrist structures insertion as sequential contact formations and uses a VLM to recover from failures, reaching 83% success in simulation across randomized grasp, pose, friction, and shape variations with real-robot validation.
citing papers explorer
-
InFeR: Informed Failure Resilience in Learned Visual Navigation Control
InFeR retrains imitation learning policies with a VIB loss for OOD failure detection and applies Grad-CAM to localize failure sources, enabling heuristic recovery in visual navigation without additional demonstrations.
-
Robust and Resilient Soft Robotic Object Insertion with Compliance-Enabled Contact Formation and Failure Recovery
A passively compliant soft wrist structures insertion as sequential contact formations and uses a VLM to recover from failures, reaching 83% success in simulation across randomized grasp, pose, friction, and shape variations with real-robot validation.