Dynamic Handover: Throw and Catch with Bimanual Hands
Abstract
Humans throw and catch objects all the time. However, such a seemingly common skill introduces a lot of challenges for robots to achieve: The robots need to operate such dynamic actions at high-speed, collaborate precisely, and interact with diverse objects. In this paper, we design a system with two multi-finger hands attached to robot arms to solve this problem. We train our system using Multi-Agent Reinforcement Learning in simulation and perform Sim2Real transfer to deploy on the real robots. To overcome the Sim2Real gap, we provide multiple novel algorithm designs including learning a trajectory prediction model for the object. Such a model can help the robot catcher has a real-time estimation of where the object will be heading, and then react accordingly. We conduct our experiments with multiple objects in the real-world system, and show significant improvements over multiple baselines. Our project page is available at \url{https://binghao-huang.github.io/dynamic_handover/}.
Cite
@article{arxiv.2309.05655,
title = {Dynamic Handover: Throw and Catch with Bimanual Hands},
author = {Binghao Huang and Yuanpei Chen and Tianyu Wang and Yuzhe Qin and Yaodong Yang and Nikolay Atanasov and Xiaolong Wang},
journal= {arXiv preprint arXiv:2309.05655},
year = {2023}
}
Comments
Accepted at CoRL 2023. https://binghao-huang.github.io/dynamic_handover/