Continuous reinforcement learning to adapt multi-objective optimization online for robot motion. (23rd March 2020)

• Record Type: Journal Article
• Authors: Zhang, Kai; McLeod, Sterling; Lee, Minwoo; Xiao, Jing
• Is Part Of: International journal of advanced robotic systems. Volume 17:Number 2(2020:Mar./Apr.)
• Publication Date: 2020-03-23
• Subjects: Mobile robots -- motion planning -- reinforcement learning; Robotics -- Periodicals; Robotics; Periodicals; 629.892
• DOI: 10.1177/1729881420911491
• Languages: English
• ISSNs: 1729-8806

Abstract

This article introduces a continuous reinforcement learning framework to enable online adaptation of multi-objective optimization functions for guiding a mobile robot to move in changing dynamic environments. The robot with this framework can continuously learn from multiple or changing environments where it encounters different numbers of obstacles moving in unknown ways at different times. Using both planned trajectories from a real-time motion planner and already executed trajectories as feedback observations, our reinforcement learning agent enables the robot to adapt motion behaviors to environmental changes. The agent contains a Q network connected to a long short-term memory network. The proposed framework is tested in both simulations and real robot experiments over various, dynamically varied task environments. The results show the efficacy of online continuous reinforcement learning for quick adaption to different, unknown, and dynamic environments.