A Construction Method of a Sequential Decision Chain for Unmanned-Ship Autonomous Collision Avoidance Based on Human-Like Thinking

Abstract

As one of the key technologies restricting the development of intelligent ships, autonomous collision avoidance has attracted the attention of many scholars all over the world. Existing research on collision-avoidance behavior focuses more on collision risk assessment and local path-planning methods for studies on the human-like sequential logic of the whole collision-avoidance process, as well as the decision-making process of various stages. Further in-depth thinking is needed urgently. Based on this, a construction method of a human-like sequential decision chain for the autonomous collision avoidance of unmanned ships is proposed through the construction of a collision-avoidance rule base and strategy set, efficient data access based on the Knowledge Graph concept, global collision risk assessment considering sequential decision process, and the construction of a complete collision-avoidance logic process to simulate the decision-making process of humans in complex multi-ship encounters in open waters. For multi-ship encounter scenarios, considering the sequential decision-making process of collision avoidance, a method was proposed to divide the collision risk of the target ship into direct collision risk and potential collision risk. The validity and reliability of the constructed sequential decision chain are verified by simulation experimental results. The results show that the method is effective for collision avoidance (especially multi-ship collision avoidance) in open waters and can provide a theoretical basis and technical support with good interpretability for the decision-making process of an unmanned ship’s autonomous collision avoidance.

Local Path Planning Method for Unmanned Ship Based on Encounter Situation Inference and COLREGS Constraints

“…The experimental result data included the relevant parameters of all ships (including target ships and interfering ships). Part of the data is extracted and calculated [39] to obtain the data required for the result analysis, which mainly includes the following: Time series of the distance percentage between the TS and its local target point to its original distance (DPTMSFTS), which can present the navigation efficiency to a certain extent.…”

The Analysis of Intelligent Functions Required for Inland Ships

“…This method ensures autonomous collision avoidance in complex environments while complying with COLREG regulations. Wang et al [70] proposed an autonomous collision avoidance sequential decision-making chain construction method based on humanoid thinking. The construction process involves situational awareness, collision risk identification, collision avoidance rule library and strategy set construction, humanoid thinking sequence collision avoidance strategy generation, collision avoidance process monitoring and strategy adjustment, and restoration of navigational conditions, thereby enhancing the collision avoidance decision-making capability of unmanned ships in multi-ship encounter scenarios.…”

A Method for Coastal Global Route Planning of Unmanned Ships Based on Human-like Thinking

“…"ZHIFEI" (shown in Figure 9) is a container ship with autonomous navigation capabilities. The ship has three navigation modes of manual driving, remote control driving and unmanned autonomous navigation, and can realize the functions of intelligent perception and cognition of navigation situations [44], intelligent collision avoidance [45], automatic berthing and unberthing and remote-control driving. The specific parameters of the ship are shown in Table 1.…”