Multi-step motion learning by combining learning-from-demonstration and policy-search. (3rd May 2023)

• Record Type: Journal Article
• Authors: Mo, Yaqiang; Sasaki, Hikaru; Matsubara, Takamitsu; Yamazaki, Kimitoshi
• Is Part Of: Advanced robotics. Volume 37:Number 9(2023)
• Page Start: 560
• Page End: 575
• Publication Date: 2023-05-03
• Subjects: Multi-step task -- motion learning -- learning from demonstration -- reinforcement learning; Robotics -- Periodicals; Robotics -- Japan -- Periodicals; Robotics; Japan; Periodicals; 629.89205
• DOI: 10.1080/01691864.2022.2163187
• Languages: English
• ISSNs: 0169-1864

Abstract

ABSTRACT: In this paper, we focus on tasks that require multi-step motions to achieve the goal (defined as a 'multi-step task'), and we describe a method for a robot to automatically achieve the final goal of a multi-step task. We proposed a method based on reinforcement learning and 'Teaching by Showing' for multi-step tasks. A robot can learn how to complete a task automatically by referring to the motions of a human operator, even if the task consists of multi-step motions. Because a human operator is not required to operate the robot during the learning process, we believe that our proposed method can reduce the burden on the human operator. Finally, we conducted experiments to validate the effectiveness of the proposed method and compared it to a conventional reinforcement learning method. GRAPHICAL ABSTRACT: UF0001