Knowledge-based instruction of manipulation tasks for industrial robotics

•We present a system for knowledge-based task specification in assembly.•Robotic skills are described in ontologies and used as building blocks for task specification and synthesis.•Robotic skills are declarative, compositional, and reusable.•An architecture to maintain and use industrial robotics knowledge is provided.

When robots are working in dynamic environments, close to humans lacking extensive knowledge of robotics, there is a strong need to simplify the user interaction and make the system execute as autonomously as possible, as long as it is feasible. For industrial robots working side-by-side with humans in manufacturing industry, AI systems are necessary to lower the demand on programming time and system integration expertise. Only by building a system with appropriate knowledge and reasoning services can one simplify the robot programming sufficiently to meet those demands while still getting a robust and efficient task execution.In this paper, we present a system we have realized that aims at fulfilling the above demands. The paper focuses on the knowledge put into ontologies created for robotic devices and manufacturing tasks, and presents examples of AI-related services that use the semantic descriptions of skills to help users instruct the robot adequately.