Case‐based automatic programming in robotic assembly production

The purpose of this paper is to present a case‐based system for offline automatic programming in robotic assembly production. This system can reuse past learned robot programs to generate programs for new assembly tasks.

The approach used in this paper is case‐based reasoning. The assembly knowledge acquired from the robot program for an assembly task is retained in a case, which is composed of the primitive task description and the corresponding robot program schema. The retained cases are retrieved by matching features of their primitive task descriptions, and are reused to automatically program for new tasks by instantiating their robot program schemata.

A case not only can be reused as a whole, but also can be reused partly by synthesizing different parts of several cases to generate a program for a new task in a variant environment.

The teaching time of robots can be greatly reduced. This helps to introduce robots into small and medium enterprises.

This paper proposes a novel system that can automatically program for assembly tasks in various environments by flexibly reusing past robot programs.