HOH: Markerless Multimodal Human-Object-Human Handover Dataset with Large Object Count
This dataset addresses the need for markerless, high-resolution data to advance research in human-robot handovers and AI parameter estimation, though it is incremental as it builds on existing handover datasets by increasing scale and removing markers.
The authors tackled the lack of comprehensive datasets for studying human-human handovers by creating the HOH dataset, which includes 2,720 interactions across 136 objects and 40 participants, and demonstrated its utility by training neural networks for grasp, orientation, and trajectory prediction.
We present the HOH (Human-Object-Human) Handover Dataset, a large object count dataset with 136 objects, to accelerate data-driven research on handover studies, human-robot handover implementation, and artificial intelligence (AI) on handover parameter estimation from 2D and 3D data of person interactions. HOH contains multi-view RGB and depth data, skeletons, fused point clouds, grasp type and handedness labels, object, giver hand, and receiver hand 2D and 3D segmentations, giver and receiver comfort ratings, and paired object metadata and aligned 3D models for 2,720 handover interactions spanning 136 objects and 20 giver-receiver pairs-40 with role-reversal-organized from 40 participants. We also show experimental results of neural networks trained using HOH to perform grasp, orientation, and trajectory prediction. As the only fully markerless handover capture dataset, HOH represents natural human-human handover interactions, overcoming challenges with markered datasets that require specific suiting for body tracking, and lack high-resolution hand tracking. To date, HOH is the largest handover dataset in number of objects, participants, pairs with role reversal accounted for, and total interactions captured.