JiaoyangLcc-by-4.0

OpenRIF: Open Robot Interaction Force Dataset

An open-source dataset containing approximately 15 hours of real-world and simulated robot interactions (8.6 million time steps) designed to support large-scale learning for sensorless robot interaction force estimation and robotic haptics research.

Downloads0
Hours15
Likes1

Why This Matters for Physical AI

OpenRIF enables robots to learn sensorless force estimation through large-scale interaction data, advancing tactile perception and haptic feedback capabilities critical for physical human-robot interaction and manipulation tasks.

Technical Profile

Modalities
proprioceptionforce_torque
Action Space
joint_positions
Environment
labsimulation
Task Types
manipulationinteraction
Total Hours
15
Data Format
HDF5
Annotation Types
action_labels
License
cc-by-4.0
Part of the OpenRIF family

Access

Need custom proprioception data?

Claru builds purpose-built datasets for lab applications with dense human annotations and quality assurance.

Request a Sample Pack

Related Datasets