Particle swarm optimization algorithms with selective differential evolution for AUV path planning

Abstract

<span lang="EN-US">Particle swarm optimization (PSO)-based algorithms are suitable for path planning of the Autonomous Underwater Vehicle (AUV) due to their high computational efficiency. However, such algorithms may produce sub-optimal paths or require higher computational load to produce an optimal path. This paper proposed a new approach that improves the ability of PSO-based algorithms to search for the optimal path while maintaining a low computational requirement. By hybridizing with differential evolution (DE), the proposed algorithms carry out the DE operator selectively to improve the search ability. The algorithms were applied in an offline AUV path planner to generate a near-optimal path that safely guides the AUV through an environment with a priori known obstacles and time-invariant non-uniform currents. The algorithm performances were benchmarked against other algorithms in an offline path planner because if the proposed algorithms can provide better computational efficiency to demonstrate the minimum capability of a path planner, then they will outperform the tested algorithms in a realistic scenario. Through Monte Carlo simulations and Kruskal-Wallis test, SDEAPSO (selective DE-hybridized PSO with adaptive factor) and SDEQPSO (selective DE-hybridized Quantum-behaved PSO) were found to be capable of generating feasible AUV path with higher efficiency than other algorithms tested, as indicated by their lower computational requirement and excellent path quality.</span>

An Improved Quantum-Behaved Particle Swarm Optimization Algorithm Combined with Reinforcement Learning for AUV Path Planning

“…Its path points are generated according to the curve function as the control points of the b-sample curve. P(t) generates a smooth path with continuous curvature as a discrete series of path points, defned as equation (15), where B i,k (t) is defned by Cox and DeBoor, defned as equation (16).…”

“…Te particle swarm algorithm (PSO) is a well-known evolutionary algorithm due to its robustness and easy parameter tuning advantages. Considering the complex and variable characteristics of the underwater environment, the PSO algorithm and its variants have been widely used in AUV path planning obstacle avoidance experiments [15][16][17][18][19]. Wu et al [17] proposed a method to optimize parameters which afect performance of the PSO algorithm by using Rauch-Tung-Striebel (RTS) smoother.…”

Time-Optimal Path Planning of a Hybrid Autonomous Underwater Vehicle Based on Ocean Current Neural Point Grid

“…Considering the shortcomings of the PSO algorithm, the PSO algorithm is hybridized with differential evolution (DE) to improve its path searching ability. The generated path can make the AUV safely pass through a marine environment with obstacles [41]. A swarm hyper-heuristic algorithm (SHH) with online learning capability is proposed to solve the path planning problem of AUVs [42].…”

Optimized formation control of multi-agent system using PSO algorithm

“…In this work, the Consensus Algorithm (CA) has been accelerated using a powerful optimization method called Particle Swarm Optimization (PSO) that can be reviewed in [20][21][22] and then used to configure the Formation control with Graph Theory (GT) for Multi-Agent System. The rest of the paper is organized as follows: the basic concepts on Graph Theory (GT) and a definition on the problem formulation is presented in section 2, the stability of the networked MAS is discussed in section 3, while the simulation results and the improvement of the optimized performance is presented in section 4 and 5, respectively.…”