Path Planning and Energy Efficiency of Heterogeneous Mobile Robots Using Cuckoo–Beetle Swarm Search Algorithms with Applications in UGV Obstacle Avoidance

• Published in: Sustainability Vol. 14; no. 22; p. 15137
• Main Authors: Chen, Dechao, Wang, Zhixiong, Zhou, Guanchen, Li, Shuai
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.11.2022
• Subjects: Algorithms; Artificial intelligence; Control systems; Deep learning; Electric vehicles; Equipment and supplies; Heuristic; Kinematics; Mobile robots; Network management systems; Neural networks; Optimization; R&D; Research & development; Robots; Sustainability; Teaching methods; China
• ISSN: 2071-1050; 2071-1050
• DOI: 10.3390/su142215137

In this paper, a new meta-heuristic path planning algorithm, the cuckoo–beetle swarm search (CBSS) algorithm, is introduced to solve the path planning problems of heterogeneous mobile robots. Traditional meta-heuristic algorithms, e.g., genetic algorithms (GA), particle swarm search (PSO), beetle swarm optimization (BSO), and cuckoo search (CS), have problems such as the tenancy to become trapped in local minima because of premature convergence and a weakness in global search capability in path planning. Note that the CBSS algorithm imitates the biological habits of cuckoo and beetle herds and thus has good robustness and global optimization ability. In addition, computer simulations verify the accuracy, search speed, energy efficiency and stability of the CBSS algorithm. The results of the real-world experiment prove that the proposed CBSS algorithm is much better than its counterparts. Finally, the CBSS algorithm is applied to 2D path planning and 3D path planning in heterogeneous mobile robots. In contrast to its counterparts, the CBSS algorithm is guaranteed to find the shortest global optimal path in different sizes and types of maps.