MobileH2R: Learning Generalizable Human to Mobile Robot Handover Exclusively from Scalable and Diverse Synthetic Data

TL;DR

This paper presents MobileH2R, a scalable framework that uses synthetic data to teach mobile robots to perform human-to-robot handovers reliably in large workspaces, eliminating the need for real-world training data.

Contribution

It introduces a novel pipeline for generating diverse synthetic human motion data and an imitation learning method for mobile robot handover skills, enabling generalization without real-world demonstrations.

Findings

At least 15% success rate improvement over baselines

Synthetic data significantly enhances robot learning

Framework effective in both simulation and real-world tests

Abstract

This paper introduces MobileH2R, a framework for learning generalizable vision-based human-to-mobile-robot (H2MR) handover skills. Unlike traditional fixed-base handovers, this task requires a mobile robot to reliably receive objects in a large workspace enabled by its mobility. Our key insight is that generalizable handover skills can be developed in simulators using high-quality synthetic data, without the need for real-world demonstrations. To achieve this, we propose a scalable pipeline for generating diverse synthetic full-body human motion data, an automated method for creating safe and imitation-friendly demonstrations, and an efficient 4D imitation learning method for distilling large-scale demonstrations into closed-loop policies with base-arm coordination. Experimental evaluations in both simulators and the real world show significant improvements (at least +15% success rate) over baseline methods in all cases. Experiments also validate that large-scale and diverse synthetic data greatly enhances robot learning, highlighting our scalable framework.