Dynamic Handover: Throw and Catch with Bimanual Hands

TL;DR

This paper presents a robotic system capable of dynamic object handover using bimanual hands, trained with multi-agent reinforcement learning and a novel trajectory prediction model to improve real-time catching accuracy.

Contribution

The paper introduces a novel system combining multi-agent reinforcement learning with trajectory prediction for dynamic handover tasks, enabling robots to catch objects more accurately in real-world settings.

Findings

Significant improvement over baselines in real-world object catching.

Effective Sim2Real transfer with novel algorithms.

Robust handling of multiple objects during handover.

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/}.