RH20T

110K+ real-world contact-rich manipulation sequences across 147 tasks, 7 robot platforms, with vision, force, audio and human demos.

Dataset specifications
Year2023
Episodes110,000
Embodimentsfranka_panda, kuka_iiwa, multi, ur5
Modalitiesaudio, depth, ee_pose, force_torque, language, proprioception, tactile, rgb
Task categoriesmanipulation
Licensecustom
Accessopen
MaintainerShanghai Jiao Tong University (Cewu Lu Lab / MVIG)

RH20T is a large-scale real-world robotic manipulation dataset of over 110,000 contact-rich manipulation sequences spanning 147 tasks (48 from RLBench, 29 from MetaWorld, 70 self-proposed), each paired with a human demonstration video. Data was collected on 7 hardware configurations using four robot arms (Flexiv, UR5, Franka, Kuka) with 8-10 global RGBD cameras and 1-2 in-hand cameras per platform, capturing RGB, depth, binocular IR, joint angle/torque, gripper/EE pose, 6-DoF force-torque, audio, and fingertip tactile (Cfg7 only). The original data is ~40TB; the project provides a 640x360 resized version (~5TB RGB, ~10TB RGBD).