AutoDex: An Automated Real-World System for Dexterous Grasping Data Collection
Overview
This paper introduces AutoDex, a system that automates the collection of real-world dexterous grasping data. By combining generated grasp candidates with multi-view object tracking and residual-torque collision monitoring, AutoDex plans, executes, labels, and resets grasps without continuous human supervision. The authors report collecting over 3,500 trials across 100 objects using Allegro and Inspire hands, reducing human effort from an estimated 9.3 hours to 0.2 hours for 500 trajectories compared to teleoperation. Retrieval from the collected library achieves a 76% success rate in new configurations, outperforming simulation-only screening at 34%. Code and data are available publicly.
Generated from attributed reports · Updated 3 days ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Data origin: robot trajectories
“500 grasp trials across 100 objects with Allegro and Inspire hands, recording both successes and failures together with synchronized visual observations and robot states. AutoDex reduces human effort by more than an order of magnitude, requiring an estimated 0.2 human-hours to collect 500 trajectories compared with 9.3 for teleoperation. As AutoDex collects trials, it builds a library of physically validated grasps f”
Exact source · revision 1Source owner not reported
Reported quantity · grasp trials: 500 other · reported trials
“500 grasp trials across 100 objects with Allegro and Inspire hands, recording both successes and failures together with synchronized visual observations and robot states. AutoDex reduces human effort by more than an order of magnitude, requiring an estimated 0.2 human-hours to collect 500 trajectories compared with 9.3 for teleoperation. As AutoDex collects trials, it builds a library of physically validated grasps f”
Exact source · revision 1Source owner not reported
Reported quantity · objects: 100 other · Basis not reported
“500 grasp trials across 100 objects with Allegro and Inspire hands, recording both successes and failures together with synchronized visual observations and robot states. AutoDex reduces human effort by more than an order of magnitude, requiring an estimated 0.2 human-hours to collect 500 trajectories compared with 9.3 for teleoperation. As AutoDex collects trials, it builds a library of physically validated grasps f”
Exact source · revision 1Source owner not reported
Artifact availability · code: available
“or subsequent execution. In new object placements and obstacle configurations, retrieval from this library achieves 76% success, compared with 34% for candidates screened only in simulation. Code and data are available at https://snuvclab.github.io/AutoDex/.”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalAutoDex: An Automated Real-World System for Dexterous Grasping Data Collection
This paper introduces AutoDex, a system that automates the collection of real-world dexterous grasping data. By combining generated grasp candidates with multi-view object tracking and residual-torque collision monitoring, AutoDex plans, executes, labels, and resets grasps without continuous human supervision. The authors report collecting over 3,500 trials across 100 objects using Allegro and Inspire hands, reducing human effort from an estimated 9.3 hours to 0.2 hours for 500 trajectories compared to teleoperation. Retrieval from the collected library achieves a 76% success rate in new configurations, outperforming simulation-only screening at 34%. Code and data are available publicly.
Event coverage history
Current attention 3·Peak within the comparable range 3（2026-11-07 02:00 UTC）·Change within the comparable range over 24 hours –
The trend compares participants observed continuously; its scope may be narrower than current attention totals. Hover or click to explore hourly observations, or use the left and right arrow keys.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).