Program robots manufacturing tasks by natural language instructions

Abstract

Robotic systems are traditionally programmed through off-line coding interfaces for manufacturing tasks. These programming methods are usually time-consuming and cost a lot of human efforts. They cannot meet the emerging requirements of robotic systems in many areas such as intelligent manufacturing and customized production. To address this issue, this paper develops a human-friendly approach to on-site program robots manufacturing tasks through human-robot interaction by natural language without need of off-line training data. The new programming approach consists of three processes: human teaching, robot learning and robot execution. Through them, the humans are able to use natural language to on-site program robot manufacturing tasks which can involve operations of both single and groups of objects. The effectiveness of the proposed approach is illustrated through experimental results.