Model Predictive Trajectory Planning for Human-Robot Handovers

TL;DR

This paper introduces a model predictive trajectory planning method for human-robot handovers that adapts to human motion using Gaussian process regression, improving handover efficiency and flexibility.

Contribution

It presents a novel path-following model predictive controller that incorporates human motion prediction for more natural and effective handovers.

Findings

Effective trajectory planning for human-robot handovers

Adaptation to human motion improves handover success

Validated on a 7-DoF robotic manipulator

Abstract

This work develops a novel trajectory planner for human-robot handovers. The handover requirements can naturally be handled by a path-following-based model predictive controller, where the path progress serves as a progress measure of the handover. Moreover, the deviations from the path are used to follow human motion by adapting the path deviation bounds with a handover location prediction. A Gaussian process regression model, which is trained on known handover trajectories, is employed for this prediction. Experiments with a collaborative 7-DoF robotic manipulator show the effectiveness and versatility of the proposed approach.