Pushing Dexterity and Safety for In-Hand Object Pose Reaching That Works Remarka
Overview
Source roundup from published reports. Claims below are attributed to their publishers, not independently verified. arXiv Robotics — research abstracts: Pushing Dexterity and Safety for In-Hand Object Pose Reaching That Works Remarkably Well. This research introduces a method for training dexterous manipulation policies for a LEAP hand in simulation, without human data. The approach combines diverse resets, generated grasp datasets, and an adaptive friction c…
Generated from attributed reports · Updated 29 minutes ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · real-robot evaluation hours: 13.3 hours · Basis not reported
“culum. With careful system identification, the policies transfer zero-shot to the real hand, using either motion capture or a single wrist-mounted depth camera, and prove remarkably capable and robust. On top of the task policy, we add a learned residual safety filter with adjustable conservativeness, letting us tune the balance between performance and safety and greatly reduce object drops. In 13.3 hours of real-rob”
Exact source · revision 1Source owner not reported
Reported quantity · unseen goals: 4800 other · Basis not reported
“ot evaluation over 4,800 unseen goals across 4 objects and diverse wrist orientations, the state-based policy reaches 95.2% of goals within 2 cm and 0.4 rad, and the filter cuts its drops by 75% while still reaching 91.5% of goals. The policies can also spin a lightbulb held in an arbitrary pose, reach out-of-distribution goals, withstand fast arm motion and perturbations, and, needing only a wrist camera, serve as p”
Exact source · revision 1Source owner not reported
Reported quantity · objects used in evaluation: 4 other · Basis not reported
“ot evaluation over 4,800 unseen goals across 4 objects and diverse wrist orientations, the state-based policy reaches 95.2% of goals within 2 cm and 0.4 rad, and the filter cuts its drops by 75% while still reaching 91.5% of goals. The policies can also spin a lightbulb held in an arbitrary pose, reach out-of-distribution goals, withstand fast arm motion and perturbations, and, needing only a wrist camera, serve as p”
Exact source · revision 1Source owner not reported
Reported quantity · wrist orientations tested: 4 other · Basis not reported
“ot evaluation over 4,800 unseen goals across 4 objects and diverse wrist orientations, the state-based policy reaches 95.2% of goals within 2 cm and 0.4 rad, and the filter cuts its drops by 75% while still reaching 91.5% of goals. The policies can also spin a lightbulb held in an arbitrary pose, reach out-of-distribution goals, withstand fast arm motion and perturbations, and, needing only a wrist camera, serve as p”
Exact source · revision 1Source owner not reported
Reported quantity · tasks performed by robot: 2 other · Basis not reported
“ot evaluation over 4,800 unseen goals across 4 objects and diverse wrist orientations, the state-based policy reaches 95.2% of goals within 2 cm and 0.4 rad, and the filter cuts its drops by 75% while still reaching 91.5% of goals. The policies can also spin a lightbulb held in an arbitrary pose, reach out-of-distribution goals, withstand fast arm motion and perturbations, and, needing only a wrist camera, serve as p”
Exact source · revision 1Source owner not reported
Evidence dependency changes (1)
- 2026-10-30T17:34:26.676Z · evidence updated · source revision 1. Evidence extraction was updated; current source attributions are shown above.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalPushing Dexterity and Safety for In-Hand Object Pose Reaching That Works Remarkably Well
This research introduces a method for training dexterous manipulation policies for a LEAP hand in simulation, without human data. The approach combines diverse resets, generated grasp datasets, and an adaptive friction curriculum. Policies transfer zero-shot to the real hand using motion capture or a wrist-mounted depth camera, achieving 95.2% success in reaching goals within 2 cm and 0.4 rad. A learned safety filter reduces object drops by 75% while maintaining 91.5% success. The work also demonstrates the ability to spin a lightbulb, reach out-of-distribution goals, and withstand perturbations, with the full recipe released as a platform for studying high-dimensional dexterous systems.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).