H2O: A Benchmark for Visual Human-human Object Handover Analysis
Authors:
- 1 October 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 15742-15751
Abstract
Object handover is a common human collaboration behavior that attracts attention from researchers in Robotics and Cognitive Science. Though visual perception plays an important role in the object handover task, the whole handover process has not been specifically explored. In this work, we propose a novel rich-annotated dataset, H2O, for visual analysis of human-human object handovers. The H2O, which contains 18K video clips involving 15 people who hand over 30 objects to each other, is a multi-purpose benchmark. It can support several vision-based tasks, from which, we specifically provide a baseline method, RGPNet, for a less-explored task named Receiver Grasp Prediction. Extensive experiments show that the RGPNet can produce plausible grasps based on the giver’s hand-object states in the pre-handover phase. Besides, we also report the hand and object pose errors with existing baselines and show that the dataset can serve as the video demonstrations for robot imitation learning on the handover task.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China
This publication has 21 references indexed in Scilit:
- Embodied handsACM Transactions on Graphics, 2017
- Human Detection and Tracking for Video Surveillance: A Cognitive Science Approach2017
- Mask R-CNN2017
- Learning Dynamic Robot-to-Human Object Handover from Human Feedback2017
- Deep Residual Learning for Image Recognition2016
- The GRASP Taxonomy of Human Grasp TypesIEEE Transactions on Human-Machine Systems, 2015
- A position generation algorithm utilizing a biomechanical model for robot-human object handover2015
- Towards Seamless Human-Robot HandoversJournal of Human-Robot Interaction, 2013
- Human preferences for robot-human hand-over configurations2011
- Planning optimal grasps1992