An intelligent method for real-time ship collision risk assessment and visualization

Ship collision attracts prevalent attention due to its high occurrence frequency and severe potential conse-quence. It is therefore of pressing importance to prevent ship collision at sea for safe maritime transporta-tion. Non-linear Velocity Obstacle (NL-VO) algorithm has received increasing attention in maritime colli-sion avoidance by taking the dynamics of ship action during the encounter process into consideration. How-ever, one precondition of NL-VO algorithm is that the trajectory of target ship needs to be known in ad-vance, which makes the application of this algorithm limited in the historical ship collision risk analysis ra-ther than the in real-time collision avoidance. Although the generalized velocity obstacle algorithm over-comes this limitation using the trajectory prediction module, the trajectory uncertainty of the target ship is not discussed leading to the possible inaccurate collision risk assessment. Therefore, this paper presents a real-time collision risk assessment method based on an improved NL-VO algorithm by including the uncer-tainty analysis of the target ship’s predicted trajectory. The proposed method consists of two main modules: trajectory uncertainty module assumes that the increase in the radius of the circular restricted area is con-sistent with the Wiener process; collision risk assessment module utilizes the non-linear velocity obstacle algorithm combined with the dynamic circular restricted area to evaluate the potential collisions. Several encounter scenarios in a specific port channel are designed to demonstrate the feasibility of using this pro-posed method to assess ship collision risk in real-time. The result shows that this improved NL-VO algo-rithm can timely identify a ship that is in danger of colliding with the own ship and know when the collision will occur, which contributes to reducing ship collision occurrence probability.