Unmanned Vessel Collision Avoidance Algorithm by Dynamic Window Approach Based on COLREGs Considering the Effects of the Wind and Wave

Abstract

In recent years, the rapid development of artificial intelligence algorithms has promoted the intelligent transformation of the ship industry; unmanned surface vessels (USVs) have become a widely used representative product. The dynamic window approach (DWA) is an effective robotic collision avoidance algorithm; however, there are deficiencies in its application to the ship field. First, the DWA algorithm does not consider International Regulations for Preventing Collisions at Sea (COLREGs), which must be met for ship collision avoidance to ensure the navigational safety of the USV and other ships. Second, the DWA algorithm does not consider the influence of wind and waves on the collision avoidance of USVs in actual navigational environments. Reasonable use of windy and wavy environments not only improves navigational safety but also saves navigational time and fuel consumption, thereby improving the economy. Therefore, this paper proposes an improvement algorithm by DWA referred to as utility DWA (UDWA) based on COLREGs considering the sailing environment. The velocity sampling area was improved by dividing the priority, and the velocity function in the objective function was enhanced to convert the effect of wind and waves on the USVs into a change in velocity. The simulation results showed that the UDWA algorithm optimized the distance to the obstacle ship by 43.25%, 31.36%, and 67.81% in a head-on situation, crossing situation, and overtaking situation, respectively, compared to the COLREGs-compliant DWA algorithm, which considers the COLREGs. The improved algorithm not only follows the COLREGs but also has better flexibility in emergency collision avoidance and can safely and economically navigate and complete collision avoidance in windy and wavy environments.

Path Planning of Self-driving Vehicles Combining Ant Colony and DWA Algorithms in Complex Dense Obstacles

“…The implementation process of the classical DWA algorithm is to convert the position control of the selfdriving car into the speed control, and describe the obstacle avoidance problem as an optimization problem with constraints in the speed space of the car [11], including the speed of the car, the driving direction and the position constraints of obstacles in the surrounding environment [12].…”

“…On the basis of CVM, a more perfect DWA algorithm is proposed in reference [7]. The objective function comprehensively considers three factors: heading angle, speed and obstacle distance, and the trajectory obtained is relatively smooth, which effectively solves the problem of circling around obstacles [8]- [11].…”

An Optimal-Path-Planning Method for Unmanned Surface Vehicles Based on a Novel Group Intelligence Algorithm

“…To eliminate the impact of ocean currents on optimal path planning for UUVs, an intelligent algorithm with an adjusted function was proposed [23], but the actual scenario maneuverability was not considered. As winds and waves had a great impact on obstacle avoidance for unmanned aerial vehicles (UAVs) in actual flight environments, a UAV path-planning method based on COLREGS (Convention on the International Regulations for Preventing Collisions at Sea) and an improved DWA algorithm (UDWA) was proposed [24]. By prioritizing speed sampling areas and enhancing speed functions in the target function, the impact of winds and waves on UAVs was transformed into speed changes.…”

Model Predictive Control Based on State Space and Risk Augmentation for Unmanned Surface Vessel Trajectory Tracking

“…In comparison with conventional ships, USVs present reduced costs, increased efficiency, and superior security. It is imperative to develop a robust and risk-free steering system that meets the different operational prerequisites [3].…”