LiHRA: A LiDAR-Based HRI Dataset for Automated Risk Monitoring Methods

Dataset related to IROS 2025 Paper. Please cite the paper if you use the dataset. Cite as: F. Plahl, G. Katranis, I. Mamaev and A. Morozov, "LiHRA: A LiDAR-Based HRI Dataset for Automated Risk Monitoring Methods," 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Hangzhou, China, 2025, pp. 6351-6357, doi: 10.1109/IROS60139.2025.11245888. LiHRA is a novel LiDAR-based dataset designed for automated Risk Monitoring (RM) in Human-Robot Interaction (HRI). It provides 3D LiDAR point clouds, human keypoints, and robot joint states, capturing real-world HRI dynamics. The dataset includes safety-critical scenarios, such as object handovers and shared workspace interactions, featuring both intentional contacts and unintentional collisions to support risk monitoring and mitigation research. Please note that the dataset is provided for research purposes only and should not be used for commercial purposes.