A Hybrid Visual–Haptic Framework for Motion Synchronization in Human–Robot Cotransporting: A Human Motion Prediction Method

Abstract

In this article, we propose a hybrid visual–haptic framework enabling a robot to achieve motion synchronization in human–robot cotransporting. Visual sensing is employed in capturing human motion in real time. To deal with the inherent delays between the human’s initiative motion and the robot’s responsive motion in cotransporting, a human motion prediction method is developed to make the robot follow human motion proactively. Motion synchronization is achieved when the robot accurately tracks the filtered and predicted human motion. Force sensing is utilized to regulate interaction forces to ensure compliance when motion error between the human and robot is generated. A neural network (NN)-based control is proposed to achieve precise trajectory tracking. Comparative experimental results show that our proposed framework is effective in such cotransporting tasks.