多层增强的蜣螂优化器用于多机器人系统在线路径规划

doi:10.3778/j.issn.1002-8331.2501-0213

摘要/Abstract

摘要： 为提升多机器人系统效率和安全性以促进工业5.0时代制造业的生产效率和质量，针对蜣螂优化器在多机器人路径规划中精度低、收敛性差和稳定性弱等问题，提出了一种多层增强的蜣螂优化器（MEDBO）。基于正弦函数构建正弦定向模型，为蜣螂选向提供全方位动态引导，同时，构建突变增殖模型，扩大蜣螂产卵区域，增加种群多样性和搜索能力。采用群体指导个体机制设计均值引导策略，增强算法的开发能力。引入对立学习，为对偶性估计提供理想候选解，防止次优收敛。通过CEC-2005、CEC-2017和CEC-2022测试套件中的28个优化问题，从定性分析、定量分析和统计检验维度对MEDBO进行实验，验证了该方法的有效性和可行性。此外，将MEDBO应用于多机器人系统在线路径规划的两个场景，通过平均适应度、平均时间消耗和平均最优-实际路径偏差指标验证了该方法的适用性。结果表明，随着机器人和动态、静态障碍物数量的增加，总路径长度减少了10.45%至43.48%，平均时间消耗相近且逐步缩小，平均最优-实际路径偏差降低了至少35.95%。

关键词: 工业5.0, 蜣螂优化器, 多机器人系统, 路径规划

Abstract: To enhance the efficiency and safety of multi-robot systems and promote the production efficiency and quality of manufacturing in the era of industry 5.0, addressing the issues of low precision, poor convergence, and weak stability of the dung beetle optimizer in multi-robot path planning, a multi-level enhanced dung beetle optimizer (MEDBO) is proposed. Firstly, a sinusoidal orientation is constructed based on the sine function to provide comprehensive dynamic guidance for the orientation selection of dung beetles. Meanwhile, a mutation proliferation model is built to expand the oviposition area of dung beetles, thereby increasing population diversity and search capability. Secondly, a mean-guided strategy is designed based on the population-guiding-individual mechanism to enhance the exploitation ability of the algorithm. Finally, opposition-based learning is introduced to provide ideal candidate solutions for dual estimation, thus preventing suboptimal convergence. The effectiveness and feasibility of MEDBO are verified through experiments on 28 optimization problems from the CEC-2005, CEC-2017, and CEC-2022 test suites, using three dimensions：qualitative analysis, quantitative analysis, and statistical testing. Additionally, MEDBO is applied to two scenarios of online path planning for multi-robot systems, and its applicability is validated by three metrics：average fitness, average time consumption, and average optimal-actual path deviation. The results show that as the number of robots and the number of dynamic and static obstacles increase, the total path length is reduced by 10.45% to 43.48%, the average time consumption remains stable and gradually decreases, and the average optimal-actual path deviation is reduced by at least 35.95%.

Key words: industry 5.0, dung beetle optimizer, multi-robot systems, path planning

蒋兴和, 冯毅雄, 金柯兵, 李志武, 吴潇, 洪兆溪, 谭建荣. 多层增强的蜣螂优化器用于多机器人系统在线路径规划[J]. 计算机工程与应用, 2026, 62(8): 340-354.

JIANG Xinghe, FENG Yixiong, JIN Kebing, LI Zhiwu, WU Xiao, HONG Zhaoxi, TAN Jianrong. Multi-Level Enhanced Dung Beetle Optimizer for Online Path Planning in Multi-Robot Systems[J]. Computer Engineering and Applications, 2026, 62(8): 340-354.

参考文献

[1] AKUNDI A，EURESTI D，LUNA S，et al.State of industry 5.0：analysis and identification of current research trends[J].Applied System Innovation，2022，5（1）：27.
[2] DOYLE KENT M，KOPACEK P.Do we need synchronization of the human and robotics to make industry 5.0 a success story?[C]//Proceedings of the International Symposium for Production Research.Cham：Springer，2021：302-311.
[3] 王湉，范峻铭，郑湃.基于大语言模型的人机交互移动检测机器人导航方法[J].计算机集成制造系统，2024，30（5）：1587-1594.
WANG T，FAN J M，ZHENG P.Large language model-based approach for human-mobile inspection robot interactive navigation[J].Computer Integrated Manufacturing Systems，2024，30（5）：1587-1594.
[4] TANG J T，MA H.Mixed integer programming for time-optimal multi-robot coverage path planning with efficient heuristics[J].IEEE Robotics and Automation Letters，2023，8（10）：6491-6498.
[5] ZHONG H G，CONG M，WANG M H，et al.HB-RRT：a path planning algorithm for mobile robots using Halton sequence-based rapidly-exploring random tree[J].Engineering Applications of Artificial Intelligence，2024，133：108362.
[6] CHEN L，WANG Y N，MIAO Z Q，et al.Transformer-based imitative reinforcement learning for multirobot path planning[J].IEEE Transactions on Industrial Informatics，2023，19（10）：10233-10243.
[7] 袁瑞萍，傅之家，李俊韬，等.面向智能制造零件拣选的多机器人无冲突路径规划方法[J].计算机集成制造系统，2025，31（11）：4071-4084.
YUAN R P，FU Z J，LI J T，et al.Multi-robot conflict-free path planning method for intelligent manufacturing-oriented part-picking[J].Computer Integrated Manufacturing Systems，2025，31（11）：4071-4084.
[8] ZHOU W，ZHANG C，CHEN S Y.Dual deep Q-learning network guiding a multiagent path planning approach for virtual fire emergency scenarios[J].Applied Intelligence，2023，53（19）：21858-21874.
[9] OU J L，HONG S H，SONG G，et al.Hybrid path planning based on adaptive visibility graph initialization and edge computing for mobile robots[J].Engineering Applications of Artificial Intelligence，2023，126：107110.
[10] LEI T J，CHINTAM P，LUO C M，et al.A convex optimization approach to multi-robot task allocation and path planning[J].Sensors，2023，23（11）：5103.
[11] SUNG I，CHOI B，NIELSEN P.On the training of a neural network for online path planning with offline path planning algorithms[J].International Journal of Information Management，2021，57：102142.
[12] LIU Y，ZHU X M，ZHANG X Y，et al.RGG-PSO+：random geometric graphs based particle swarm optimization method for UAV path planning[J].International Journal of Computational Intelligence Systems，2024，17（1）：127.
[13] ZHANG Z，HE R，YANG K.A bioinspired path planning approach for mobile robots based on improved sparrow search algorithm[J].Advances in Manufacturing，2022，10（1）：114-130.
[14] CUI Y B，HU W，RAHMANI A.Multi-robot path planning using learning-based artificial bee colony algorithm[J].Engineering Applications of Artificial Intelligence，2024，129：107579.
[15] XUE J K，SHEN B.Dung beetle optimizer：a new meta-heuristic algorithm for global optimization[J].The Journal of Supercomputing，2023，79（7）：7305-7336.
[16] HU W，ZHANG Q，YE S.An enhanced dung beetle optimizer with multiple strategies for robot path planning[J].Scientific Reports，2025，15：4655.
[17] 万怡华，张雪梅.混合多策略改进蜣螂算法的避障路径规划[J].电子测量技术，2024，47（2）：69-78.
WAN Y H，ZHANG X M.Obstacle avoidance path planning of hybrid multi-strategy improved dung beetle optimizer[J].Electronic Measurement Technology，2024，47（2）：69-78.
[18] 赵子贺，马继东，张毅然.基于改进粒子群蜣螂算法的机器人路径规划研究[J].中国新技术新产品，2024（20）：1-4.
ZHAO Z H，MA J D，ZHANG Y R.Research on robot path planning based on improved particle swarm dung beetle algorithm[J].New Technology & New Products of China，2024（20）：1-4.
[19] ZHANG W Y，ZHANG H J，ZHANG X T.An enhanced dung beetle optimizer with adaptive node selection and dynamic step search for mobile robots path planning[J].Measurement Science and Technology，2025，36（3）：036301.
[20] 王海群，郭庆通，葛超.基于改进蜣螂优化算法的搬运机器人路径规划[J].现代制造工程，2024（11）：87-95.
WANG H Q，GUO Q T，GE C.Path planning of handling robot based on improved dung beetle optimization algorithm[J].Modern Manufacturing Engineering，2024（11）：87-95.
[21] LI L H，LIU L L，SHAO Y X，et al.Enhancing swarm intelligence for obstacle avoidance with multi-strategy and improved dung beetle optimization algorithm in mobile robot navigation[J].Electronics，2023，12（21）：4462.
[22] JIN H W，JI H T，YAN F Z.An effective obstacle avoidance and motion planning design for underwater telescopic arm robots based on a tent chaotic dung beetle algorithm[J].Electronics，2023，12（19）：4128.
[23] ZHANG C，LIU M，ZHONG P S，et al.An adaptive balance optimization algorithm and its engineering application[J].Advanced Engineering Informatics，2023，55：101908.
[24] TIZHOOSH H R.Opposition-based learning：a new scheme for machine intelligence[C]//Proceedings of the International Conference on Computational Intelligence for Modelling，Control and Automation and International Conference on Intelligent Agents，Web Technologies and Internet Commerce.Piscataway：IEEE，2006：695-701.
[25] WU G H，MALLIPEDDI R，SUGANTHAN P N.Problem definitions and evaluation criteria for the CEC 2017 competition on constrained real-parameter optimization[EB/OL].[2024?12?20].https：//www.researchgate.net/publication/317228117.
[26] AHRARI A，ELSAYED S M，SARKER R，et al.Problem definition and evaluation criteria for the CEC’2022 competition on dynamic multimodal optimization：2022001[R].Canberra：University of New South Wales.School of Engineering and Information Technology，2022.
[27] WANG Z L，SHAO P.A multi-strategy dung beetle optimization algorithm for optimizing constrained engineering problems[J].IEEE Access，2023，11：98805-98817.
[28] ZHU F，LI G S，TANG H，et al.Dung beetle optimization algorithm based on quantum computing and multi-strategy fusion for solving engineering problems[J].Expert Systems with Applications，2024，236：121219.
[29] SHEN Q W，ZHANG D M，XIE M S，et al.Multi-strategy enhanced dung beetle optimizer and its application in three-dimensional UAV path planning[J].Symmetry，2023，15（7）：1432.
[30] MORALES-CASTA?EDA B，ZALDíVAR D，CUEVAS E，et al.A better balance in metaheuristic algorithms：does it exist?[J].Swarm and Evolutionary Computation，2020，54：100671.
[31] GIVI H，HUBALOVSKA M.Skill optimization algorithm：a new human-based metaheuristic technique[J].Computers，Materials & Continua，2023，74（1）：179-202.
[32] LIAN J B，HUI G H，MA L，et al.Parrot optimizer：algorithm and applications to medical problems[J].Computers in Biology and Medicine，2024，172：108064.
[33] SOWMYA R，PREMKUMAR M，JANGIR P.Newton-Raphson-based optimizer：a new population-based metaheuristic algorithm for continuous optimization problems[J].Engineering Applications of Artificial Intelligence，2024，128：107532.
[34] WU L，WU J W，MENG Z Z.Enhancing grey wolf optimizer with levy flight for engineering applications[J].IEEE Access，2023，11：74865-74897.
[35] ELSEIFY M A，HASHIM F A，HUSSIEN A G，et al.Boosting prairie dog optimizer for optimal planning of multiple wind turbine and photovoltaic distributed generators in distribution networks considering different dynamic load models[J].Scientific Reports，2024，14：14173.
基金项目：国家自然科学基金（52130501，52105281）；浙江省重点研发计划项目（2023C01214，2024C01029）。