Event
LEAP Dexterous Hand In-Hand Object Pose Reaching and Safety Filtering
1 reports · 1 sources
The research team proposes a training recipe for in-hand object pose reaching with the LEAP dexterous hand: trained in simulation without human data, it transfers zero-shot to the real robot after system identification, and can use motion capture or a wrist-mounted monocular depth camera. In real-robot evaluations across 4 objects and 4,800 unseen targets over 13.3 hours, the state-based policy reached 95.2% of targets within 2 cm and 0.4 rad; adding a learned residual safety filter with adjustable conservativeness reduced drops by 75% while still reaching 91.5% of targets. The team states that the full recipe has been released as a platform for studying the performance, reliability, and safety of high-dimensional dexterous systems.
Report timeline
- In-hand object pose reaching strategy and safety filter for the LEAP dexterous hand
The research team proposed a training recipe for in-hand object pose reaching with the LEAP dexterous hand. It trains in simulation without human data and, after system identification, transfers zero-shot to the real robot, using either motion capture or a single wrist-mounted monocular depth camera. In a real-robot evaluation with 4 objects and 4,800 unseen targets over 13.3 hours, the state-based policy reached 95.2% of targets within 2 cm and 0.4 rad; adding a learned residual safety filter with adjustable conservativeness reduced drops by 75% while still reaching 91.5% of targets.
arXiv cs.RO ·