Real-time collision avoidance planning for unmanned surface vessels based on field theory

Abstract

With the development of commercial application of unmanned surface vessels, the real-time collision avoidance is the research focus on the multi-vessels situation, the structure complexity and time consumption problem limit its efficiency. To simplify the complex model and enhance the collision avoidance performance, the field theory is used to describe the navigation of ships abstractly, from which a more simplified optimization model of collision avoidance is derived, so the synthetic field regarding the virtual spatial electric field and velocity field is presented to exhibit the situation of ship motion. On the basis of the field environment, the more simplified collision avoidance model is designed, combining with the improved Electromagnetism-like mechanism algorithm, to generate the optimal collision avoidance strategy, for considering the energy and other loss. The complete algorithm has been compared and validated under the different layout, it is worth mentioning that the algorithm can potentially be developed to advance collision-free navigation in multi-vessels situation.