PhysClaw-0: A Symbiotic Agentic System for Robot Autonomy via Language Corrections
For robot learning from real-world data, PhysClaw-0 reduces human oversight cost per distinct failure mode rather than per episode, making large-scale autonomous data collection more practical.
PhysClaw-0 is a human-robot symbiotic system that retains and reuses language corrections across data collection rounds, reducing human working time to 16% of teleoperation while matching success rates and raising single-attempt success from 12.5% to 47.5%.
Autonomous data collection governs the volume and quality of real-world trajectories for manipulation policy learning. Existing pipelines reduce human effort via self-resetting, VLM verification, or language-guided correction, yet episode-scoped fixes must be reissued whenever the same failure recurs, so oversight cost grows with session length rather than with the number of distinct problems. We present PhysClaw-0, a human-robot symbiotic agentic system in which corrections are retained and reused across rounds. The collection loop collects, verifies, and resets autonomously, pausing for a remote operator only when a phase exhausts an explicit retry budget. An LLM parser maps each natural-language utterance to a structured adjustment stored in Corrective Memory, so addressed failure modes typically need not be corrected again under the same conditions. On a real-robot desktop-clearing testbed, PhysClaw-0 matches teleoperation episode success while reducing human working time to 16%. Language corrections improve verifier-human agreement in all four evaluated settings and raise average single-attempt success from 12.5% to 47.5% (arm-selection: 20.0% to 50.0%). Policies fine-tuned on PhysClaw-0 data match teleoperation-trained policy success at a fraction of collection human cost.