Autonomous navigation based on a Q-learning algorithm for a robot in a real environment

This paper explores autonomous navigation and obstacle avoidance techniques based on Q-learning for a mobile robot in a real environment. The implemented algorithm focuses on simplicity and efficiency. The learning process takes place in both simulation and real world allowing the combination of a longer learning time in the simulator with a more accurate knowledge from the real world. After learning is completed in simulation and in the real world, the robot was able to navigate without hitting obstacles and able to generate control law for complex situations such as corners and small objects.