Human-robot collaborative object transfer using human motion prediction based on Cartesian pose Dynamic Movement Primitives

TL;DR

This paper presents a method for human-robot collaborative object transfer that predicts human motion using Dynamic Movement Primitives and an Extended Kalman Filter, enabling effective transfer to unknown targets with reduced human effort.

Contribution

It introduces a novel approach combining DMPs and EKF for predicting human motion in collaborative object transfer tasks to unknown targets.

Findings

The proposed method reduces human effort compared to admittance control.

Experimental validation with a Kuka robot demonstrates effectiveness.

Stability of the control scheme is theoretically analyzed.

Abstract

In this work, the problem of human-robot collaborative object transfer to unknown target poses is addressed. The desired pattern of the end-effector pose trajectory to a known target pose is encoded using DMPs (Dynamic Movement Primitives). During transportation of the object to new unknown targets, a DMP-based reference model and an EKF (Extended Kalman Filter) for estimating the target pose and time duration of the human's intended motion is proposed. A stability analysis of the overall scheme is provided. Experiments using a Kuka LWR4+ robot equipped with an ATI sensor at its end-effector validate its efficacy with respect to the required human effort and compare it with an admittance control scheme.