Skill transfer learning for autonomous robots and human-robot cooperation: A survey

Designing a robot system with reasoning and learning ability has gradually become a research focus in robotics research field. Recently, Skill Transfer Learning (STL), i.e., the ability of transferring human skills to robots, has become a research thrust for autonomous robots and human-robot cooperation. It provides the following benefits: (i) the skill transfer learning system with independent decision-making and learning ability enables the robot to learn and acquire manipulation skills in a complex and dynamic environment, which can overcome the shortages of conventional methods such as traditional programming, and greatly improve the adaptability of the robot to complex environments and (ii) human physiological signals allow us to extract motion control characteristics from physiological levels which create a rich sensory signal. In this survey, we provide an overview of the most important applications of STL by analyzing and categorizing existing works in autonomous robots and human-robot cooperation area. We close this survey by discussing remaining open challenges and promising research topics in future. (C) 2020 Elsevier B.V. All rights reserved.