HRDexDB: A Large-Scale Dataset of Dexterous Human and Robotic Hand Grasps
For researchers in dexterous manipulation, this dataset fills a gap by providing aligned human and robotic grasping data with multiple modalities, enabling cross-domain learning and benchmarking.
HRDexDB is a large-scale multi-modal dataset of dexterous grasping sequences for human and robotic hands, covering 100 objects with 1.4K trials including successes and failures. It provides high-precision 3D motion, tactile signals, and multi-view video to serve as a benchmark for policy learning and cross-domain manipulation.
We present HRDexDB, a large-scale, multi-modal dataset of high-fidelity dexterous grasping sequences featuring both human and diverse robotic hands. Unlike existing datasets, HRDexDB provides a comprehensive collection of grasping trajectories across human hands and multiple robot hand embodiments, spanning 100 diverse objects. Leveraging state-of-the-art vision methods and a new dedicated multi-camera system, our HRDexDB offers high-precision spatiotemporal 3D ground-truth motion for both the agent and the manipulated object. To facilitate the study of physical interaction, HRDexDB includes high-resolution tactile signals, synchronized multi-view video, and egocentric video streams. The dataset comprises 1.4K grasping trials, encompassing both successes and failures, each enriched with visual, kinematic, and tactile modalities. By providing closely aligned captures of human dexterity and robotic execution on the same target objects under comparable grasping motions, HRDexDB serves as a foundational benchmark for multi-modal policy learning and cross-domain dexterous manipulation.