Motion Planning for Dual-Arm Robot Based on Soft Actor-Critic

Ching-Chang Wong,Hsuan-Ming Feng,Shao-Yu Chien,Hisasuki Aoyama

doi:10.1109/access.2021.3056903

Ching-Chang Wong, Hsuan-Ming Feng + Show 2 more

Open Access

https://doi.org/10.1109/access.2021.3056903

Copy DOI

Abstract

In this paper, a motion planning method based on the Soft Actor-Critic (SAC) is designed for a dual-arm robot with two 7-Degree-of-Freedom (7-DOF) arms so that the robot can effectively avoid self-collision and at the same time can avoid the joint limits and singularities of the arm. The left-arm and right-arm of the dual-arm robot each have a neural network to control its position and orientation. Dual-agent training, distributed training structure, and progressive training environment are used to train neural networks. During the training process, the motion of one arm is regarded as the environment of the other arm, and the two agents are trained at the same time. In the input part of the neural network of the proposed method, all parameters come from the angle of each axis and kinematic calculation, no additional sensors are needed, so the method is easier to transplant to different dual-arm robots. With some appropriate neural network inputs and reward functions design, the robot can perform the expected self-collision avoidance and effectively avoid the joint limits and singularities of the arm. Finally, some experiments of the simulation tests in the Gazebo simulator and actual tests in a laboratory-made dual-arm robot are presented to illustrate the proposed SAC-based motion planning method is feasible and practicable in the avoidance of self-collision, joint limits, and singularities.

Highlights

IntroductionCompared with single-arm robots, dual-arm robots have better adaptability and flexibility
Small-volume large-variety manufacturing process has become a trend in production
Since the trajectory planning method in the joint space uses the starting angle and the target angle of each axis to plan the speed of the motor, and the output of the DMAMP method is the motion planning of each axis, the problem of joint limit and singularity does not occur in these two methods

Summary

Introduction

Compared with single-arm robots, dual-arm robots have better adaptability and flexibility. A dual-arm robot is like placing two robots close to each other, so the collision of robots needs to be considered. Zhou et al used the concept of a flag, which will be activated when one arm enters a specific area to prevent the other arm from entering the same area [1]. Lam et al used invisible sensitive skin inside the arm, but this method is mainly used to prevent the arm from colliding with the surrounding people [2]. Afaghani and Aiyama proposed a collision-map method for collision detection, which makes one arm to be an obstacle in the path of the other one [3]. There are methods of using the redundant angle characteristics of the 7-DOF robotic arm to avoid self-collision.

Objectives

Results

Conclusion