Greedy Mechanism Based Particle Swarm Optimization for Path Planning Problem of an Unmanned Surface Vehicle

Abstract

Recently, issues of climate change, environment abnormality, individual requirements, and national defense have caused extensive attention to the commercial, scientific, and military development of unmanned surface vehicles (USVs). In order to design high-quality routes for a multi-sensor integrated USV, this work improves the conventional particle swarm optimization algorithm by introducing the greedy mechanism and the 2-opt operation, based on a combination strategy. First, a greedy black box is established for particle initialization, overcoming the randomness of the conventional method and excluding a great number of infeasible solutions. Then the greedy selection strategy and 2-opt operation are adopted together for local searches, to maintain population diversity and eliminate path crossovers. In addition, Monte-Carlo simulations of eight instances are conducted to compare the improved algorithm with other existing algorithms. The computation results indicate that the improved algorithm has the superior performance, with the shortest route and satisfactory robustness, although a fraction of computing efficiency becomes sacrificed. Moreover, the effectiveness and reliability of the improved method is also verified by its multi-sensor-based application to a USV model in real marine environments.

Multi-Subdomain Grouping-Based Particle Swarm Optimization for the Traveling Salesman Problem

“…First, three of our PSO or GA-based algorithms are selected for comparison with the MSGPSO: a multi-domain inversionbased GA (MDIGA) [42], an improved PSO with adaptively adjusted acceleration coefficients and inertia weight (AWIPSO) [41], and a greedy strategy-based PSO (GSPSO) (abbreviated as IPSO in [32]). It is worth noting that this study has certain connections and essential differences with the three recently published works.…”

“…This is also a criterion to identify the global best-known solution of the entire swarm (Pgs) and the personal best-known solution of each particle (Pjs). Subsequently, the velocity and position of each particle are updated using (2) and (3) [32,33,34].…”

Iterative Learning-Based Path and Speed Profile Optimization for an Unmanned Surface Vehicle

“…The calculation of an adaptive step length will be further explained later. Based on the test results, the cost function values can be obtained, and the unit gradient vector e k is numerically estimated from the previous two iterations by using Equations (6) and 7.…”

“…A reliable autonomous navigation system with the capabilities of path-planning, obstacle avoidance, and auto-guidance is essential for an USV to deal with various and dynamic marine situations [3]. The most widely used obstacle avoidance and path-planning algorithms include artificial potential fields (APF) [4], rapidly exploring random trees (RRTs) [5], greedy mechanism-based particle swarm optimization (PSO) [6], and grid map-based path-planning algorithms (e.g., A* algorithm [7], Field D* [8], and Theta* [9]). These algorithms focus on path-planning for obstacle avoidance considering the kinematics of the vehicle and the obstacles.…”

Whale Optimization Algorithm for Ship Path Optimization in Large-Scale Complex Marine Environment

“…Therefore, it is extremely important to find a novel large-scale optimization method to solve these real-world large-scale and complex problems. In recent years, meta-heuristic algorithms have received widespread attention from scholars [5]. The main purpose of the development of meta-heuristic algorithms is to quickly solve path planning problem and get satisfactory solutions.…”