Navigation in Restricted Channels Under Environmental Conditions: Fast-Time Simulation by Asynchronous Deep Reinforcement Learning

Autor(es)

Amendola, Jose ^[1] ; Miura, Lucas S. ^[1] ; Costa, Anna H. Reali ^[2] ; Cozman, Fabio G. ^[3] ; Tannuri, Eduardo Aoun ^[3]

Afiliação do(s) autor(es)

^[1] Univ Sao Paulo, Numer Offshore Tank Lab, BR-05508900 Sao Paulo - Brazil

^[2] Univ Sao Paulo, Intelligent Tech Lab, BR-05508900 Sao Paulo - Brazil

^[3] Univ Sao Paulo, Dept Mech Engn & Mech Syst, BR-05508900 Sao Paulo - Brazil

• Tipo de documento: Artigo Científico
• Fonte: IEEE ACCESS; v. 8, p. 149199-149213, 2020.
• Citações Web of Science: 0

Resumo

This paper proposes an efficient method, based on reinforcement learning, to be used as ship controller in fast-time simulators within restricted channels. The controller must operate the rudder in a realistic manner in both time and angle variation so as to approximate human piloting. The method is well suited to scenarios where no previous navigation data is available; it takes into account, during training, both the effect of environmental conditions and also curves in channels. We resort to an asynchronous distributed version of the reinforcement learning algorithm Deep Q Network (DQN), handling channel segments as separate episodes and including curvature information as context variables (thus moving away from most work in the literature). We tested our proposal in the channel of Porto Sudeste, in the southern Brazilian coast, with realistic environment scenarios where wind and current incidence varies along the channel. The method keeps a simple representation and can be applied to any port channel configuration that respects local technical regulations. (AU)

• Processo FAPESP: 19/07665-4 - Centro de Inteligência Artificial
• Beneficiário: Fabio Gagliardi Cozman
• Modalidade de apoio: Auxílio à Pesquisa - Programa eScience e Data Science - Centros de Pesquisa em Engenharia