Learning-based Dynamic Robot-to-Human Handover

2025-02-18

AI Summary

This work addresses inefficient and uncomfortable human–robot object handovers caused by uncertainty in the receiver’s motion during dynamic interactions. We propose a nonparametric motion generation framework that integrates human demonstration data (1,000 samples), preference learning, and adaptive dynamic impedance control to enable real-time perception of the receiver’s motion state and online synthesis of continuous handover trajectories. To our knowledge, this is the first method validated in real-world human–robot handover scenarios. Compared to conventional static-assumption strategies, our dynamic approach significantly reduces handover time (23.6% reduction in physical experiments) and markedly improves user comfort (p < 0.01 in user studies). Consistent results from both simulation and physical experiments confirm the method’s effectiveness and robustness. The framework establishes a scalable, generative motion planning paradigm for robots operating in dynamic interactive environments.

Technology Category

• Intelligent Robots: Manipulation
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

This paper presents a novel learning-based approach to dynamic robot-to-human handover, addressing the challenges of delivering objects to a moving receiver. We hypothesize that dynamic handover, where the robot adjusts to the receiver's movements, results in more efficient and comfortable interaction compared to static handover, where the receiver is assumed to be stationary. To validate this, we developed a nonparametric method for generating continuous handover motion, conditioned on the receiver's movements, and trained the model using a dataset of 1,000 human-to-human handover demonstrations. We integrated preference learning for improved handover effectiveness and applied impedance control to ensure user safety and adaptiveness. The approach was evaluated in both simulation and real-world settings, with user studies demonstrating that dynamic handover significantly reduces handover time and improves user comfort compared to static methods. Videos and demonstrations of our approach are available at https://zerotohero7886.github.io/dyn-r2h-handover .

Problem

• Dynamic robot-to-human handover
• Adapting to receiver's movements
• Improving handover efficiency and comfort

Innovation

• Learning-based dynamic handover
• Nonparametric motion generation
• Impedance control for safety