<abstract xmlns="http://www.w3.org/1999/xhtml"><p><italic>This paper presents the application of the reinforcement learning algorithms</italic><italic>to the task of autonomous determination of the ship trajectory during the</italic><italic>in-harbour and harbour approaching manoeuvres. Authors used Markov</italic><italic>decision processes formalism to build up the background of algorithm</italic><italic>presentation. Two versions of RL algorithms were tested in the simulations:</italic><italic>discrete (Q-learning) and continuous form (Least-Squares Policy Iteration).</italic><italic>The results show that in both cases ship trajectory can be found. However</italic><italic>discrete Q-learning algorithm suffered from many limitations (mainly curse</italic><italic>of dimensionality) and practically is not applicable to the examined task. On the other hand, LSPI gave</italic><italic>promising results. To be fully operational, proposed solution should be extended by taking into account</italic><italic>ship heading and velocity and coupling with advanced multi-variable controller.</italic></p></abstract>

This paper presents the application of the reinforcement learning algorithmsto the task of autonomous determination of the ship trajectory during thein-harbour and harbour approaching manoeuvres. Authors used Markovdecision processes formalism to build up the background of algorithmpresentation. Two versions of RL algorithms were tested in the simulations:discrete (Q-learning) and continuous form (Least-Squares Policy Iteration).The results show that in both cases ship trajectory can be found. Howeverdiscrete Q-learning algorithm suffered from many limitations (mainly curseof dimensionality) and practically is not applicable to the examined task. On the other hand, LSPI gavepromising results. To be fully operational, proposed solution should be extended by taking into accountship heading and velocity and coupling with advanced multi-variable controller.

Reinforcement learning in discrete and continuous domains applied to ship trajectory generation

Polish Maritime Research

This paper presents the application of the reinforcement learning algorithmsto the task of autonomous determination of the ship trajectory during thein-harbour...

Reinforcement learning in discrete and continuous domains applied to ship trajectory generation

Publié en ligne: 31 oct. 2012

Pages: 31 - 36

DOI: https://doi.org/10.2478/v10012-012-0020-8

Mots clés
ship motion control, trajectory generation, autonomous navigation, reinforcement learning, least-squares policy iteration

This content is open access.

Reinforcement learning in discrete and continuous domains applied to ship trajectory generation

Publié en ligne: 31 oct. 2012

Pages: 31 - 36

DOI: https://doi.org/10.2478/v10012-012-0020-8

Mots clésship motion control, trajectory generation, autonomous navigation, reinforcement learning, least-squares policy iteration

This content is open access.

Mots clés
ship motion control, trajectory generation, autonomous navigation, reinforcement learning, least-squares policy iteration