dc.contributor.author
Carreras Pérez, Marc
dc.contributor.author
Batlle i Grabulosa, Joan
dc.contributor.author
Ridao Rodríguez, Pere
dc.date.accessioned
2024-05-22T09:46:06Z
dc.date.available
2024-05-22T09:46:06Z
dc.identifier
Carreras Pérez, M. , Batlle i Grabulosa, J., i Ridao Rodríguez, P. (2001). Hybrid coordination of reinforcement learning-based behaviors for AUV control. IEEE/RSJ International Conference on Intelligent Robots and Systems : 2001 : Proceedings, 3, 1410-1415. Recuperat 04 maig 2010, a http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=977178
dc.identifier
http://hdl.handle.net/10256/2162
dc.identifier.uri
https://hdl.handle.net/10256/2162
dc.description.abstract
This paper proposes a hybrid coordination method for behavior-based control architectures. The hybrid method takes advantages of the robustness and modularity in competitive approaches as well as optimized trajectories in cooperative ones. This paper shows the feasibility of applying this hybrid method with a 3D-navigation to an autonomous underwater vehicle (AUV). The behaviors are learnt online by means of reinforcement learning. A continuous Q-learning implemented with a feed-forward neural network is employed. Realistic simulations were carried out. The results obtained show the good performance of the hybrid method on behavior coordination as well as the convergence of the behaviors
dc.format
application/pdf
dc.relation
info:eu-repo/semantics/altIdentifier/doi/10.1109/IROS.2001.977178
dc.relation
info:eu-repo/semantics/altIdentifier/isbn/0-7803-6612-3
dc.rights
Tots els drets reservats
dc.rights
info:eu-repo/semantics/openAccess
dc.source
© IEEE/RSJ International Conference on Intelligent Robots and Systems : 2001 : Proceedings, vol. 3, p. 1410-1415
dc.source
Articles publicats (D-ATC)
dc.subject
Robots submarins
dc.subject
Vehicles submergibles
dc.subject
Underwater robots
dc.title
Hybrid coordination of reinforcement learning-based behaviors for AUV control
dc.type
info:eu-repo/semantics/article
