A smooth path planning method for mobile robot using a BES-incorporated modified QPSO algorithm

被引：4

作者：

Dian S. ^{[1
]}

Zhong J. ^{[1
]}

Guo B. ^{[1
]}

Liu J. ^{[2
]}

Guo R. ^{[3
]}

机构：

[1] College of Electrical Engineering, Sichuan University, Chengdu

[2] State Grid Liaoning Electric Power Research Institute, Shenyang

[3] State Grid Intelligence Technology Co., Ltd., Jinan

来源：

Expert Systems with Applications | 2022年 / 208卷

关键词：

BES-MQPSO; Bezier curve; Metaheuristic; Mobile robot; Smooth path planning;

D O I：

10.1016/j.eswa.2022.118256

中图分类号：

学科分类号：

摘要：

The design of path planning algorithms to obtain a smooth path that satisfies constraints such as obstacle avoidance, minimized cost, and dynamic feasibility for mobile robots in the workspace is a hot issue in the field of intelligent robotics. The metaheuristic optimization algorithm, which aims to solve path planning problems, is more efficient compared to traditional algorithms. In the current metaheuristic approaches, avoiding local minimum traps is the core goal of the scheme. In this paper, with the benefit of a high-order continuous Bezier curve, we construct an optimization problem of smooth path planning based on the length and the requirement of collision-free safety as constraints of the robot's expected path. Then, the smooth path planning problem is transformed into an optimization problem that searches the locations of control nodes of the Bezier curve. We solve the constructed path planning problem with our modified quantum particle swarm optimization algorithm (QPSO). Specifically, to overcome the shortcomings of the current PSO and QPSO-based particle swarm algorithms like prematurity, unbalanced global search, local exploitation, and local minima, we implement an improved QPSO algorithm denoted as BES-MQPSO that incorporates the search and swoop mechanisms from bald eagle search (BES) strategies. The method consists of four improved modifications: an improved local attractor, improved feature length, BES-enhanced intensive exploitation Strategy, and random variation mechanism. Our proposed BES-MQPSO with these four modifications is tested with benchmark functions and then applied to the smooth path planning problem. Finally, the superiority of BES-MQPSO is confirmed, and the ideal smooth path of the mobile robot is successfully planned. The planned path length is reduced by 4.45% and 2.82% compared to e-QPSO and SDEQPSO respectively, while the standard deviation is reduced by 67.46% and 69.82%, respectively. © 2022 Elsevier Ltd

引用

共 38 条

[1]

Agrawal R.K., Kaur B., Agarwal P., Quantum inspired Particle Swarm Optimization with guided exploration for function optimization, Applied Soft Computing, 102, (2021)

[2]

Ahmadianfar I., Heidari A.A., Gandomi A.H., Chu X., Chen H., RUN beyond the metaphor: An efficient optimization algorithm based on Runge Kutta method, Expert Systems with Applications, 181, (2021)

[3]

Alsattar H.A., Zaidan A.A., Zaidan B.B., Novel meta-heuristic bald eagle search optimisation algorithm, Artificial Intelligence Review, 53, 3, pp. 2237-2264, (2020)

[4]

Askari Q., Saeed M., Younas I., Heap-based optimizer inspired by corporate rank hierarchy for global optimization, Expert Systems with Applications, 161, (2020)

[5]

Berglund T., Brodnik A., Jonsson H., Staffanson M., Soderkvist I., Planning Smooth and Obstacle-Avoiding B-Spline Paths for Autonomous Mining Vehicles, IEEE Transactions on Automation Science and Engineering, 7, 1, pp. 167-172, (2010)

[6]

Chagas C., Zacarias E., de Lima Silva L.A., Pignaton De Freitas E., Hierarchical and smoothed topographic path planning for large-scale virtual simulation environments, Expert Systems with Applications, 189, (2022)

[7]

Chen M., Zhu D., Optimal Time-Consuming Path Planning for Autonomous Underwater Vehicles Based on a Dynamic Neural Network Model in Ocean Current Environments, IEEE Transactions on Vehicular Technology, 69, 12, pp. 14401-14412, (2020)

[8]

Chen Y., Pi D., Xu Y., Neighborhood global learning based flower pollination algorithm and its application to unmanned aerial vehicle path planning, Expert Systems with Applications, 170, (2021)

[9]

Chou J., Truong D., A novel metaheuristic optimizer inspired by behavior of jellyfish in ocean, Applied Mathematics and Computation, 389, (2021)

[10]

Deng X., Li R., Zhao L., Wang K., Gui X., Multi-obstacle path planning and optimization for mobile robot, Expert Systems with Applications, 183, (2021)

← 1 2 3 4 →