Instructing Industrial Robots Using High-Level Task Descriptions

Abstract: With more advanced manufacturing technologies, small and medium sized enterprises can compete with low-wage labor by providing customized and high quality products. For small production series, robotic systems can provide a cost-effective solution. However, for robots to be able to perform on par with human workers in manufacturing industries, they have to become flexible and autonomous in their task execution and swift and easy to instruct. This will enable small businesses with short production series or highly customized products to use robot coworkers without consulting expert robot programmers. The objective of this thesis is to explore programming solutions that can reduce the programming effort of sensor- controlled robot tasks. The robot motions are expressed using constraints, and a number of simple constrained motions can be combined into a robot skill. The skill can be stored in a database together with a semantic description, which en- ables reuse and reasoning. The main contributions of the thesis are 1) develop- ment of ontologies for robot devices and skills, 2) a user interface that provides programming support for task descriptions in unstructured natural language and 3) an implementation where low-level code is generated from the high-level descriptions. The resulting system greatly reduces the number of parameters exposed to the user. These parameters are described on a semantic level, which means that the same skill can be used on different robot platforms. The research is presented in four peer-reviewed papers. The first covers knowledge-based instruction and the system architecture. The two following papers describe the natural language programming feature of the system as well as a description of the user interface. The fourth and last paper describes the code generation step, thus connecting the high-level language instructions to real-time executable code.