Hierarchical Reinforcement Learning for Sensor-Based Navigation
share
Robotic systems are nowadays capable of solving complex navigation tasks under real-world conditions. However, their capabilities are intrinsically limited to the imagination of the designer and consequently lack generalizability to initially unconsidered situations. This makes deep reinforcement learning especially interesting, as these algorithms promise a self-learning system only relying on feedback from the environment. Having the system itself search for an optimal solution brings the benefit of great generalization or even constant improvement when life-long learning is addressed. In this paper, we address robot navigation in continuous action space using deep hierarchical reinforcement learning without including the target location in the state representation. Our agent self-assigns internal goals and learns to extract reasonable waypoints to reach the desired target position only based on local sensor data. In our experiments we demonstrate that our hierarchical structure improves the performance of the navigation agent in terms of collected reward and success rate in comparison to a flat structure, while not requiring any global or target information.
READ FULL TEXT