The achievement of a mission with an autonomous robot in an unknown and unstructured environment is still a non-solved problem. This presentation proposes the use of a behavior-based control architecture and a reinforcement learning algorithm to accomplish the sub-goals of a mission. The behavior-based approach provides real-time capabilities and reactivity to the perceived environment. Reinforcement learning is used to learn the state-action mappings that each behavior must contain. The biggest problem of a reinforcement learning algorithm when applied in a real system is the generalization problem. In the presented approach, this is solved by combining the Q_learning algorithm with a neural network. Real experiments show the effectiveness of the approach with an autonomous underwater robot. Also, the generalization capability of the reinforcement learning algorithm is tested with the mountain-car benchmark.
Reinforcement Learning, Behavior-based Robotics
Marc Carreras. (2003)
A Proposal of a Behavior-based Control Architecture with Reinforcement Learning for an Autonomous Underwater Robot. Ph.D. Thesis. University of Girona, Universitat de Girona, Edifici Politecnica 4, Campus Montilivi, 17071 Girona, Spain.