《Local Path Planning Method of the Selfpropelled Model Based on Reinforcement Learning in Complex Conditions》.pdfVIP

J. Marine Sci. Appl. (2014) 13: 333-339 DOI: 10.1007/s11804-014-1265-7 Local Path Planning Method of the Self-propelled Model Based on Reinforcement Learning in Complex Conditions 1* 1 1 2 Yi Yang , Yongjie Pang , Hongwei Li and Rubo Zhang 1. Science and Technology on Underwater Vehicle Laboratory, Harbin Engineering University, Harbin 150001, China 2. College of Electromechanical Information Engineering, Dalian Nationalities University, Dalian 116600, China Abstract: Conducting hydrodynamic and physical motion Since the local path planning is the basis for safety simulation tests using a large-scale self-propelled model under navigation and all kinds of complex tests of the SPM, many actual wave conditions is an important means for researching methods and algorithms have been researched. The Morphin environmental adaptability of ships. During the navigation test of algorithm is a typical one (Simmons et al., 1996. Larson et the self-propelled model, the complex environment including al., 2006.), and it is based on a grid model of the various port facilities, navigation facilities, and the ships nearby must be considered carefully, because in this dense environment environment. The algorithm first shoots a series of arcs the impact of sea waves and winds on the model is particularly along both sides of the boat to cover the entire front grid significant. In order to improve the security of the self-propelled and then by voting the o