Learning Navigational Behaviors using a Predictive Sparse Distributed Memory

We describe a general framework for the acquisition of perception-based navigational behaviors in autonomous mobile robots. A self-organizing sparse distributed memory equivalent to a three-layered neural network is used to learn the desired transfer function mapping sensory input into motor commands. The memory is initially trained by teleoperating the robot on a small number of paths within a given domain of interest. During training, the vectors in the sensory space as well as the motor space are continually adapted using a form of competitive learning to yield basis vectors aimed at efficiently spanning the sensorimotor space. After training, the robot navigates from arbitrary locations to a desired goal location using motor output vectors computed by a saliency-based weighted averaging scheme. The pervasive problem of perceptual aliasing in non-Markov environments is handled by allowing both current as well as the set of immediately preceding perceptual inputs to predict the motor output vector for the current time instant. Simulation results obtained for a mobile robot, equipped with simple photoreceptors and infrared receivers, navigating within an enclosed obstacle-ridden arena indicate that the method performs successfully in a variety of navigational tasks, some of which exhibit substantial perceptual aliasing.