The application of the Kohonen self-organizing topology preserving neural network for learning and developing a minimal representation for the open environment for mobile robot navigation is presented. The input to the algorithm is the coordinates of randomly selected points in the open environment. No specific knowledge of the size, number, and shape of the obstacles is needed by the network. The parameter selection for the network is discussed and two illustrative examples are presented
Date of Conference: 13-16 Oct 1991