A Survey of Robot Learning Strategies for Human-Robot Collaboration in Industrial Settings

Abstract Increased global competition has placed a premium on customer satisfaction, and there is a greater demand for manufacturers to be flexible with their products and services. This challenge is usually addressed with the introduction of human operators for precise tasks that require dexterity, flexibility and cognitive decision making. On the other hand, robots, through automation, are very effective in carrying out repetitive, non-ergonomic tasks. Owing to the complementary nature of robots’ and humans’ capabilities, there is an increased interest towards a shared workspace for humans and robots to work together collaboratively, forming the motivation behind the field of human-robot collaboration (HRC). Research in HRC in industry is concerned with the safety of the humans and robots, extent, and modes of collaboration among them, and the level of autonomy and adaptability of robots that can be trained for different tasks. This paper introduces a novel taxonomy of levels of interaction between humans and robots along the lines of SAEs guidelines for autonomous vehicles in response to a need for standard definitions and evolving nature of the field. Research into modes of communication for HRC driven by machine learning are reviewed followed by broad definitions of the types of machine learning. The authors also present a comprehensive review of the machine learning (ML) methodologies and industrial applications of the same in the context of adaptable collaborative robots.