DexH2R: A Benchmark for Dynamic Dexterous Grasping in Human-to-Robot Handover

2025-06-29

AI Summary

Progress in human-to-robot dynamic dexterous handover is hindered by the scarcity of high-quality, real-world datasets: existing data primarily target static grasping or synthetic motions, failing to capture the kinematic and dynamic characteristics of natural dexterous hand movements. To address this, we introduce DexH2R—the first comprehensive benchmark specifically designed for real-world human-to-robot handover. DexH2R features teleoperated recordings of diverse objects, dynamic interactions, and multimodal sensing (vision + proprioception). The benchmark encompasses dynamic grasp policy learning, standardized evaluation across multiple methods, and diffusion-model-driven policy optimization. Extensive experiments validate state-of-the-art approaches on DexH2R, and we propose DynamicGrasp—a novel method that significantly improves policy robustness and reproducibility in dynamic handover tasks. DexH2R establishes foundational data and evaluation infrastructure to advance research in dexterous robotic handover.

Technology Category

• Intelligent Robots: Manipulation
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Computer Vision: Biometrics, Face, Gesture & Pose

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Handover between a human and a dexterous robotic hand is a fundamental yet challenging task in human-robot collaboration. It requires handling dynamic environments and a wide variety of objects and demands robust and adaptive grasping strategies. However, progress in developing effective dynamic dexterous grasping methods is limited by the absence of high-quality, real-world human-to-robot handover datasets. Existing datasets primarily focus on grasping static objects or rely on synthesized handover motions, which differ significantly from real-world robot motion patterns, creating a substantial gap in applicability. In this paper, we introduce DexH2R, a comprehensive real-world dataset for human-to-robot handovers, built on a dexterous robotic hand. Our dataset captures a diverse range of interactive objects, dynamic motion patterns, rich visual sensor data, and detailed annotations. Additionally, to ensure natural and human-like dexterous motions, we utilize teleoperation for data collection, enabling the robot's movements to align with human behaviors and habits, which is a crucial characteristic for intelligent humanoid robots. Furthermore, we propose an effective solution, DynamicGrasp, for human-to-robot handover and evaluate various state-of-the-art approaches, including auto-regressive models and diffusion policy methods, providing a thorough comparison and analysis. We believe our benchmark will drive advancements in human-to-robot handover research by offering a high-quality dataset, effective solutions, and comprehensive evaluation metrics.

Problem

• Lack of real-world datasets for human-robot handover tasks
• Need for robust grasping in dynamic environments
• Absence of human-like dexterous motion in robots

Innovation

• DexH2R dataset for real-world human-robot handovers
• Teleoperation ensures human-like dexterous motions
• DynamicGrasp solution for robust handover performance