Client-server control architecture for a vision-based pick-and-place robot

Abstract

This article presents the software development for a vision-based pick-and-place robot to provide the computational intelligence required for its operation. It follows a client-server control architecture and aims to expand the applications of simply PC-based mechatronics systems to achieve distributed and flexible control through the introduction of a multi-featured and application-suited control unit in the form of a microcontroller as a client to the PC-based server. The system includes a five degree-of-freedom pick-and-place robot whereby a vision system is incorporated in its workspace to identify workpieces with respect to their shape and color. On user specification of the class of workpiece to be manipulated through a graphical user interface, the robot performs the manipulation. A personal computer, operating under the Windows platform, carries out all vision related processing and motion planning for the robot. On request, relevant motion information is communicated through the parallel port of the computer to peripheral interface controller (PIC) microcontroller, which interfaces with the sensing and actuation devices for robot control. The development of the system sees the integration of a number of technologies to achieve a customized control unit including: a vision system, actuation and sensing devices for precise motions, personal computer, microcontroller, and enhanced parallel port. In addition, a layered approach towards software development enables reusability, maintainability, and testability of the system through data abstraction.