Implemention of Reinforcement Learning Environment for Mobile Manipulator Using Robo-gym

Abstract

Many studies utilize reinforcement learning in simulation environments to control robots. Since simulation environments do not provide reinforcement learning environments for all robots, it is important for researchers to choose a simulation environment with the robots they use. This paper adds and expands a new robot-platform to the robot-gym environment, a reinforcement learning framework used in the Gazebo simulation environment. The added robot-platform is Husky-ur3, a mobile manipulator robot, and it can recognize the coordinates of the target point by itself through the camera. It was confirmed that the mobile manipulator learning environment was well established through experiments of recognizing and following target.