Mobile robots capable of moving autonomously in more or less structured environments are being increasingly employed in the automation of certain industrial processes. Along these lines, the authors constructed a platform, on the base of a commercial industrial truck, provided with sufficient autonomy to carry out tasks within an industrial environment (VIA: Autonomous Industrial Vehicle).
One of the sensor systems used in the truck is a system of artificial vision which enables it to move on asphalted surfaces both in open environments (roads) and closed ones, seeking the markings which most easily allow it to determine the path marked in the images. The system for following roads is capable of following painted lines, determining the sides of the road by texture analysis or determining the minimum width of the road for the robot to pass, according to the circumstances. A model of the road predicts its situation and enables a decision to be made on whether the information provided by the algorithm is reliable or not. At the same time, a neural network is trained with the results obtained by any of the previous algorithms, in such a way that when the training process converges the network takes over the steering of the truck.
The vision system, composed of a CCD colour camera and a “frame grabber” installed in a PCI slot of a Pentium 120 PC, provides a path every 100 ms, which allows the industrial truck to be steered at its maximum speed of 10 m/s.