VR-DAgger: Immersive VR for Dexterous Data Collection and Uncertainty-Guided On-Policy Correction

arXiv:2605.27114v1 Announce Type: new Abstract: Learning from demonstrations is effective for robotic manipulation, but collecting sufficient task-specific data remains a major bottleneck. Under distribution shift, small errors compound, performance degrades, and expert time is often spent on redundant, low-value corrections instead of the few critical failure cases.

Source: arXiv cs.RO | 2026-05-27