A path planning method for the autonomous ship in restricted bridge area based on anisotropic fast marching algorithm

Abstract

The increasing number of bridges in inland waterways has been continuously posing the potential for ship-bridge collision accidents. To reduce the probability of accidents in the inland bridge area and facilitate the safe passage of the autonomous ship, this paper proposes a path planning method with multiple vector fields, which comprehensively considers the characteristics of inland waters, hydrological characteristics, and meteorological factors. In this method, the navigational environmental factors affecting the path generation are divided into two parts, the static vector field, and the dynamic vector field, in the modeling part of the navigation environment. The static vector field is composed of the obstacle vector field and the channel vector field, and the dynamic vector field is constructed by the simulated wind field and currents field. The resulting synthetic vector field is used as input to the Anisotropic Fast Marching (AFM) algorithm to calculate the optimal path for the autonomous ship under influence of multiple factors. The complete algorithm has been tested and validated through three different scenarios and is evaluated according to four different evaluation criteria. The contribution of this work is to develop a path planning method that could incorporate external environmental influences and navigational risk into the path planning process. The research results of this paper can provide an important reference for the research on the path planning of autonomous ships in the inland bridge area.