WE DESCRIBE AN AUTONOMOUS MOBILE ROBOT THAT EMPLOYS A SIMPLE SENSORIMOTOR LEARNING ALGORITHM AT THREE DIFFERENT BEHAVIORS TO ACHIEVE COHERENT GOAL - DIRECTED BEHAVIOR. THE ROBOT AUTONOMOUSLY NAVIGATES TO A GOAL DESTINATION WHITIN A OBSTACLE - RIDDEN ENVIRONMENT BY USING THE LEARNED BEHAVIORS OF OBSTACLE DETECTION, OBSTACLE AVOIDANCE, AND BEACON FOLLOWING. THESE REACTIVE BEHAVIORS ARE LEARNED IN A HIERACHICAL MANNER BY USING A SIMPLE HILLCLIMBING ROUTINE THAT ATTEMPTS TO FIND THE OPTIMAL TRANSFER FUNCTION FROM PERCEPTIONS TO ACTIONS FOR EACH BEHAVIOR. WE PRESENT EXPERIMENTAL RESULTS WICH SHOW THAT EACH BEHAVIOR WAS SUCCESSFULLY LAERNED BY THE ROBOT WITHIN A REASONABLY SHORT PERIOD OF TIME. WE CONCLUDE BY DISCUSSING SALIENT FEATURES OF OUR APPROACH AND POSSIBLE DIRECTIONS FOR FUTURE RESEARCH.WE DESCRIBE AN AUTONOMOUS MOBILE ROBOT THAT EMPLOYS A SIMPLE SENSORIMOTOR LEARNING ALGORITHM AT THREE DIFFERENT BEHAVIORS TO ACHIEVE COHERENT GOAL - DIRECTED BEHAVIOR. THE ROBOT AUTONOMOUSLY NAVIGATES TO A GOAL DESTINATION WHITIN A OBSTACLE - RIDDEN ENVIRONMENT BY USING THE LEARNED BEHAVIORS OF OBSTACLE DETECTION, OBSTACLE AVOIDANCE, AND BEACON FOLLOWING. THESE REACTIVE BEHAVIORS ARE LEARNED IN A HIERACHICAL MANNER BY USING A SIMPLE HILLCLIMBING ROUTINE THAT ATTEMPTS TO FIND THE OPTIMAL TRANSFER FUNCTION FROM PERCEPTIONS TO ACTIONS FOR EACH BEHAVIOR. WE PRESENT EXPERIMENTAL RESULTS WICH SHOW THAT EACH BEHAVIOR WAS SUCCESSFULLY LAERNED BY THE ROBOT WITHIN A REASONABLY SHORT PERIOD OF TIME. WE CONCLUDE BY DISCUSSING SALIENT FEATURES OF OUR APPROACH AND POSSIBLE DIRECTIONS FOR FUTURE RESEARCH.