AutoTuning Environment for Static Obstacle Avoidance Methods Applied to USVs

Abstract

This work is focused on reactive Static Obstacle Avoidance (SOA) methods used to increase the autonomy of Unmanned Surface Vehicles (USVs). Currently, there are multiple approaches to avoid obstacles, which can be applied to different types of USV. In order to assist in the choice of the SOA method for a particular vessel and to accelerate the pretuning process necessary for its implementation, this paper proposes a new AutoTuning Environment for Static Obstacle Avoidance (ATESOA) methods applied to USVs. In this environment, a new simplified modelling of a LIDAR (Laser Imaging Detection and Ranging) sensor is proposed based on numerical simulations. This sensor model provides a realistic environment for the tuning of SOA methods that, due to its low load computation, is used by evolutionary algorithms for the autotuning. In order to analyze the proposed ATESOA, three SOA methods were adapted and implemented to consider the measurements given by the LIDAR model. Furthermore, a mathematical model is proposed and evaluated for using as USV in the simulation enviroment. The results obtained in numerical simulations show how the new ATESOA is able to adjust the SOA methods in scenarios with different obstacle distributions.

Autonomous Water Quality Monitoring and Water Surface Cleaning for Unmanned Surface Vehicle

“…Villa et al [5] Obstacle avoidance LiDAR LOS-based GNC Algorithm Wang et al [8] Obstacle avoidance Navigation radar IACO Algorithm Kim et al [9] Obstacle detection Vision sensors Skip-ENet Algorithm Steccanella et al [10] Waterline and obstacle detection Camera U-net CNN Algorithm Guardeño et al [11] Obstacle avoidance LiDAR ATESOA algorithm Li et al [12] Obstacle avoidance Microwave radar, 4G Camera -…”

“…Steccanella et al [ 10 ] utilized a U-net convolutional neural network (CNN) based method to segment the image taken by the camera placed on the low-cost ASV for waterline and obstacle detection. Guardeño et al [ 11 ] used a LiDAR sensor mounted on the USV to detect static obstacles and developed a new autotuning environment for static obstacle avoidance (ATESOA) algorithm for reactive static obstacle avoidance.…”

A Robust Reactive Static Obstacle Avoidance System for Surface Marine Vehicles

“…First, before reading this work, we recommended that the reader consults in detail the paper [31], where a new autotuning environment is proposed for static obstacle avoidance methods applied to USVs. Specifically, to develop and evaluate the RRSOAS, the numerical simulation environment proposed in [31] was used. Moreover, several reactive methods [30,35,41,42] were autotuned in that paper, and later used in this work to make a comparison with the RRSOAS.…”

“…The organization of this paper is as follows: mathematical models used to evaluate the new RRSOAS by means of numerical simulations are described in the Section 2. As a simulation environment (USV and LIDAR sensor models), the one proposed in [31] is used. In addition, a Bayesian filter [8] is employed to generate the occupancy probability grids at each sample time of the reactive algorithm [63].…”

“…On the other hand, Section 3 presents in detail the four subsystems that form the RRSOAS. As results, the RRSOAS's performance is compared with those of other SOA methods [30,31,41] in Section 4. Furthermore, a study of the robustness of the algorithm was also carried out on nine-hundred obstacle avoidance scenarios, in which the USV navigates at different velocities and is affected by several levels of sea current.…”