Spatial Problems for a Simulated Robot

Abstract

This paper is ex>ncerned with spatial aspects of perceptien aril actien in a simple robot. To this end, the problem of designing a robot-controller for a robot in a simulated environment is considered. The environment is a two-dimensional tabletop with I!OITable polygcnal shapes en it. The robot has an eye which 'sees' an area of the tabletop centred en itself, with a resolutien which decreases fran the centre to the periphery. Algorithms are oresented for simulating the motien and oollision of t1o0 dimensional shapes in this environment. These algorithms use representations of shape both as a sequence of boundary points aril as a regien in a digital image. A method is outlined for constructing aril updating the world model of the robot as new visual inpJt is received fran the eye. It is proposed that, in the 1o0rld model, the spatial problems of path-finding and object-I!OITing be based on algorithms that find the skeleton of the shape of empty space and of the shape of the moved object.