{"title":"用于 UUV 全局路径规划的新型双级算法","authors":"Xin Pan, Guoli Feng, Lin Huang, Haiyan Zeng","doi":"10.1063/5.0207107","DOIUrl":null,"url":null,"abstract":"Global path planning is one of the key technologies in unmanned underwater vehicle (UUV) intelligent control. At present, research on UUV global path planning technology tends to choose long-distance and large-scale 3D space as the research environment, which leads to a sharp increase in the amount of data and search range for 3D spatial path planning. Therefore, an efficient and relatively small data volume 3D spatial path planning method is an urgent problem that needs to be solved for UUV engineering applications. To solve this problem, a new bilevel path planning algorithm for UUV is proposed. In the upper level of the algorithm, a Max Min Ant System-Elite Genetic (MMAS-EGA) algorithm is put forward, which is a hybrid ant colony optimization/genetic algorithm, in order to improve the convergence speed of the algorithm. In the lower level of the bilevel algorithm, a function optimization algorithm and the MMAS algorithm are used to minimize the number of variables to be optimized. To verify the effectiveness of the algorithm, we conducted simulation experiments in a three dimensional environment. The simulation results in the three-dimensional environment show that, compared with the existing bilevel algorithm, the time to search the global optimal solution is reduced by 9%, and the number of iterations is reduced by 4.4%. Furthermore, the new algorithm we proposed is more efficient and suitable for global path planning for different tasks.","PeriodicalId":7619,"journal":{"name":"AIP Advances","volume":null,"pages":null},"PeriodicalIF":1.4000,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A new bilevel algorithm for UUV global path planning\",\"authors\":\"Xin Pan, Guoli Feng, Lin Huang, Haiyan Zeng\",\"doi\":\"10.1063/5.0207107\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Global path planning is one of the key technologies in unmanned underwater vehicle (UUV) intelligent control. At present, research on UUV global path planning technology tends to choose long-distance and large-scale 3D space as the research environment, which leads to a sharp increase in the amount of data and search range for 3D spatial path planning. Therefore, an efficient and relatively small data volume 3D spatial path planning method is an urgent problem that needs to be solved for UUV engineering applications. To solve this problem, a new bilevel path planning algorithm for UUV is proposed. In the upper level of the algorithm, a Max Min Ant System-Elite Genetic (MMAS-EGA) algorithm is put forward, which is a hybrid ant colony optimization/genetic algorithm, in order to improve the convergence speed of the algorithm. In the lower level of the bilevel algorithm, a function optimization algorithm and the MMAS algorithm are used to minimize the number of variables to be optimized. To verify the effectiveness of the algorithm, we conducted simulation experiments in a three dimensional environment. The simulation results in the three-dimensional environment show that, compared with the existing bilevel algorithm, the time to search the global optimal solution is reduced by 9%, and the number of iterations is reduced by 4.4%. Furthermore, the new algorithm we proposed is more efficient and suitable for global path planning for different tasks.\",\"PeriodicalId\":7619,\"journal\":{\"name\":\"AIP Advances\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.4000,\"publicationDate\":\"2024-08-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"AIP Advances\",\"FirstCategoryId\":\"88\",\"ListUrlMain\":\"https://doi.org/10.1063/5.0207107\",\"RegionNum\":4,\"RegionCategory\":\"物理与天体物理\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"MATERIALS SCIENCE, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"AIP Advances","FirstCategoryId":"88","ListUrlMain":"https://doi.org/10.1063/5.0207107","RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"MATERIALS SCIENCE, MULTIDISCIPLINARY","Score":null,"Total":0}
A new bilevel algorithm for UUV global path planning
Global path planning is one of the key technologies in unmanned underwater vehicle (UUV) intelligent control. At present, research on UUV global path planning technology tends to choose long-distance and large-scale 3D space as the research environment, which leads to a sharp increase in the amount of data and search range for 3D spatial path planning. Therefore, an efficient and relatively small data volume 3D spatial path planning method is an urgent problem that needs to be solved for UUV engineering applications. To solve this problem, a new bilevel path planning algorithm for UUV is proposed. In the upper level of the algorithm, a Max Min Ant System-Elite Genetic (MMAS-EGA) algorithm is put forward, which is a hybrid ant colony optimization/genetic algorithm, in order to improve the convergence speed of the algorithm. In the lower level of the bilevel algorithm, a function optimization algorithm and the MMAS algorithm are used to minimize the number of variables to be optimized. To verify the effectiveness of the algorithm, we conducted simulation experiments in a three dimensional environment. The simulation results in the three-dimensional environment show that, compared with the existing bilevel algorithm, the time to search the global optimal solution is reduced by 9%, and the number of iterations is reduced by 4.4%. Furthermore, the new algorithm we proposed is more efficient and suitable for global path planning for different tasks.
期刊介绍:
AIP Advances is an open access journal publishing in all areas of physical sciences—applied, theoretical, and experimental. All published articles are freely available to read, download, and share. The journal prides itself on the belief that all good science is important and relevant. Our inclusive scope and publication standards make it an essential outlet for scientists in the physical sciences.
AIP Advances is a community-based journal, with a fast production cycle. The quick publication process and open-access model allows us to quickly distribute new scientific concepts. Our Editors, assisted by peer review, determine whether a manuscript is technically correct and original. After publication, the readership evaluates whether a manuscript is timely, relevant, or significant.