AutoDex is an automated system designed to close the loop of real-world dexterous grasping data collection by handling perception, execution, labeling, and reset without human intervention. It addresses the scalability issues of teleoperation and the lack of physical certification in simulation by generating candidate grasps and verifying them on real hardware.
- The system uses dense 20-camera perception to localize objects under severe occlusion and executes collision-monitored robot motions.
- AutoDex actively resets objects between trials to expose additional candidates across stable poses, labeling lift-and-hold success or failure.
- Researchers collected 3,593 grasp trials across Allegro and Inspire hands on 100 diverse objects using the system.
- For a matched 500-trajectory collection, AutoDex required 10.3 hours compared to 49.4 hours for teleoperation, achieving a 4.8x throughput improvement.
- Grasps retrieved from the AutoDex-validated database succeeded 76% of the time, versus 34% for simulation-only validation.
The system enables the creation of reusable databases of physically labeled grasp trials that downstream systems can query by retrieval and feasibility filtering, with code and data to be publicly released.