Multi-sensor Dataset of Multiple Sequential Human-to-Human Object Handovers in Shelving and Un-shelving Tasks

We provide a multi-sensor dataset containing RGB-D and motion tracking data from sequential human-to-human object handovers. We recorded 12 pairs of participants executing shelving and un-shelving tasks involving 30 object handovers, resulting in 1440 handovers. Each recording consists of the position and orientation trajectories of 13 upper-body bones of the giver and the receiver and position trajectories of the 27 markers placed on their upper bodies, all recorded at 120Hz. The recordings also include two RGB-D data streams at 30Hz. We also provide four anthropometric measurements of the participants: height, waistline height, arm span, and weight. The dataset is valuable for investigating the body movements, grasps, and coordination strategies utilized by humans while performing tasks such as shelving which involve multiple sequential object handovers. Additionally, the dataset can be used to teach robots perform tasks involving object handovers with people, as well as self-handovers to correct grasps.

The details about the dataset collection procedure are available in the article:
Kshirsagar, A., Fortuna, R., Xie, Z., & Hoffman, G. (2025). Descriptor: Multi-sensor Dataset of Multiple Sequential Human-to-Human Object Handovers in Shelving and Un-shelving Tasks (MH2HO). IEEE Data Descriptions. (http://dx.doi.org/10.1109/IEEEDATA.2025.3580058)