Developing a stereo vision system for control of an AGV

Abstract

In the course of recent work on the ESPRIT VOILA Vision Research Pilot Project, the GEC-Marconi Hirst Research Centre and the AI Vision Research Unit at the University of Sheffield have established a platform for the development of a machine stereo vision system for the control of a robot vehicle. This platform at the Hirst Research Centre is based on a laboratory scale autonomous guided vehicle, a multitransputer vision architecture known as MARVIN and, TINA, a mature stereo vision system. The laser guidance system enables the vehicle's position and orientation to be monitored and controlled very accurately whilst the passive vision provides capabilities for recognizing, locating and tracking objects of interest, such as simple boxes and pallets, and for determining the free space where it is safe to drive the vehicle. The capabilities provided by passive vision thus complement the performance of the laser guidance system and should enable the flexibility and autonomy of robot vehicle systems to be improved so that they can operate in incompletely controlled or unknown environments and can interface more easily to the imperfect human world.