dc.contributor.author | Martinsen, Andreas Bell | |
dc.contributor.author | Lekkas, Anastasios M. | |
dc.date.accessioned | 2019-05-07T10:20:47Z | |
dc.date.available | 2019-05-07T10:20:47Z | |
dc.date.created | 2019-01-14T08:37:53Z | |
dc.date.issued | 2018 | |
dc.identifier.isbn | 978-1-5386-4814-8 | |
dc.identifier.uri | http://hdl.handle.net/11250/2596760 | |
dc.description.abstract | This paper proposes a methodology for solving the curved path following problem for underactuated vehicles under unknown ocean current influence using deep reinforcement learning. Three dynamic models of high complexity are employed to simulate the motions of a mariner vessel, a container vessel and a tanker. The policy search algorithm is tasked to find suitable steering policies, without any prior info about the vessels or their environment. First, we train the algorithm to find a policy for tackling the straight line following problem for each of the simulated vessels and then perform transfer learning to extend the policies to the curved-path case. This turns out to be a much faster process compared to training directly for curved paths, while achieving indistinguishable performance. | nb_NO |
dc.language.iso | eng | nb_NO |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE) | nb_NO |
dc.relation.ispartof | OCEANS 2018 MTS/IEEE Charleston | |
dc.title | Curved Path Following with Deep Reinforcement Learning: Results from Three Vessel Models | nb_NO |
dc.type | Chapter | nb_NO |
dc.description.version | acceptedVersion | nb_NO |
dc.identifier.doi | 10.1109/OCEANS.2018.8604829 | |
dc.identifier.cristin | 1655779 | |
dc.description.localcode | © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | nb_NO |
cristin.unitcode | 194,63,25,0 | |
cristin.unitname | Institutt for teknisk kybernetikk | |
cristin.ispublished | true | |
cristin.fulltext | original | |
cristin.qualitycode | 1 | |