Flexible Handover with Real-Time Robust Dynamic Grasp Trajectory Generation

TL;DR

This paper presents a real-time, robust approach for flexible human-to-robot handovers involving moving objects, utilizing dynamic grasp trajectory generation and future prediction to improve success rates in complex scenarios.

Contribution

The work introduces a novel real-time grasp trajectory generation method and a future grasp prediction algorithm for flexible, dynamic handover tasks.

Findings

78.15% success rate on a diverse household object benchmark

Effective grasping of moving objects with flexible trajectories

Robust system performance in dynamic handover scenarios

Abstract

In recent years, there has been a significant effort dedicated to developing efficient, robust, and general human-to-robot handover systems. However, the area of flexible handover in the context of complex and continuous objects' motion remains relatively unexplored. In this work, we propose an approach for effective and robust flexible handover, which enables the robot to grasp moving objects with flexible motion trajectories with a high success rate. The key innovation of our approach is the generation of real-time robust grasp trajectories. We also design a future grasp prediction algorithm to enhance the system's adaptability to dynamic handover scenes. We conduct one-motion handover experiments and motion-continuous handover experiments on our novel benchmark that includes 31 diverse household objects. The system we have developed allows users to move and rotate objects in their hands within a relatively large range. The success rate of the robot grasping such moving objects is 78.15% over the entire household object benchmark.