Real-time robot learning

This paper presents the design, implementation and testing of a real-time system using computer vision and machine learning techniques to demonstrate learning behavior in a miniature mobile robot. The miniature robot, through environmental sensing, learns to navigate a maze choosing the optimum route. Several reinforcement learning based algorithms, such as the Q-learning, Q(λ)-learning, fast online Q(λ)-learning and DYNA structure, are considered. Experimental results based on simulation and an integrated real-time system are presented for varying density of obstacles in a 15×15 maze.