An autonomous collision avoidance and path planning method for intelligent ships based on reinforcement learning

Abstract

The invention discloses a method for autonomous collision avoidance and path planning of an intelligent ship based on reinforcement learning, which comprises the following steps: 1) acquiring environmental information around the own ship and the own ship information, and perceiving the environment state space; 2) according to the obstacles in the environment state space 3) If there is no collision risk, directly carry out path planning; if there is a collision risk, build a system that integrates LSTM and reinforcement learning principles Intelligent ship collision avoidance model, find the best collision avoidance strategy for avoidance, and obtain the corresponding speed and heading required for collision avoidance of the own ship; 4) After the collision avoidance strategy is executed, determine the critical position point where the collision risk disappears according to the set conditions as A new starting point, and then use the path planning algorithm to re-plan the path. The invention introduces the LSTM neural network, uses the Bellman equation to update the optimal strategy, and realizes the continuity of the collision avoidance action.

Description

technical field [0001] The invention relates to a path planning technology, in particular to a method for autonomous collision avoidance and path planning for intelligent ships based on reinforcement learning. Background technique [0002] With the development of artificial intelligence technology, the development of ship intelligence and automation has become a mainstream trend. At present, there are many studies on collision avoidance and path planning of intelligent ships. If the existing methods are used for collision avoidance and path planning, it will often result in a large amount of analysis, failure to comply with collision avoidance rules, and untimely and unintelligent path planning. It is difficult to achieve fast collision avoidance decision and path planning. In order to ensure the navigation safety of intelligent ships, a method that can realize autonomous collision avoidance and real-time path planning is urgently needed. SUMMARY OF THE INVENTION [0003...

AI Technical Summary

Problems solved by technology

At present, there are many studies on collision avoidance and path planning of intelligent ships. If existing methods are used for collision avoidance and path planning, it will often result in a large amount of analysis, failure to comply with collision avoidance rules, and untimely and unintelligent path planning. Difficult to achieve fast collision avoidance decision-making and path planning

Images