Fuzzy Inference-Based Adaptive Sonar Control for Collision Avoidance in Autonomous Underwater Vehicles

Abstract This article discusses the use of adaptive control in the sonar scanning sector within an obstacle detection system, to improve the effectiveness of collision avoidance for autonomous underwater vehicles (AUVs). An adaptive network-based fuzzy inference system (ANFIS) was used for dynamic calculations of the sonar scanning sector. Based on 100 simulation scenarios containing various trajectories created by the mission planner, with various shapes, dimensions and arrangements of static obstacles, and various arrangements and displacement vectors of dynamic obstacles, the effectiveness of the proposed system was tested in comparison with other classical approaches such as a single echosounder and sonar with a fixed scanning sector width. The above sensor configurations were evaluated in terms of the percentage of collision-free trials, the average percentage of trajectory completion, and the average number of activations of the collision avoidance system. Simulations conducted based on the mathematical model of the AUV confirmed that the proposed approach increased the effectiveness of collision avoidance systems for AUVs compared to classical echosounder and sonar-based systems.