Leveraging RRT<sup>*</sup>: Probabilistically Interpreted Mechanisms Enhanced With P-HOPE and FLEX-OPT for Complex Path Planning
Path planning is a great challenge in the autonomous navigation of mobile robots. The Rapidly-exploring Random Tree<inline-formula> <tex-math notation="LaTeX">$^{\ast }$ </tex-math></inline-formula> (RRT<inline-formula> <tex-math notation="LaTeX"&...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10829612/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832583233786609664 |
|---|---|
| author | Yujie Miao Haiyang Liu Ziqiang Zhang Yanju Liang |
| author_facet | Yujie Miao Haiyang Liu Ziqiang Zhang Yanju Liang |
| author_sort | Yujie Miao |
| collection | DOAJ |
| description | Path planning is a great challenge in the autonomous navigation of mobile robots. The Rapidly-exploring Random Tree<inline-formula> <tex-math notation="LaTeX">$^{\ast }$ </tex-math></inline-formula> (RRT<inline-formula> <tex-math notation="LaTeX">$^{\ast } $ </tex-math></inline-formula>) algorithm is widely used for its probabilistic completeness. In the literature, improved RRT<inline-formula> <tex-math notation="LaTeX">$^{\ast }$ </tex-math></inline-formula>-based algorithms usually enhance search efficiency through different target bias strategies. However, these algorithms often fall into obstacle traps in complex environments with narrow passages or high obstacle densities due to the loLcal minima problem in the optimization process. In addition, the existing algorithms also exhibit inefficient sampling and slow convergence in large-scale maps. To tackle with these problems, we propose an improved algorithm, called the RRT<inline-formula> <tex-math notation="LaTeX">$^{\ast }$ </tex-math></inline-formula>-PRIME (Probabilistically Interpreted Mechanisms Enhanced RRT<inline-formula> <tex-math notation="LaTeX">$^{\ast } $ </tex-math></inline-formula>) algorithm, in this paper. First, a powerful strategy, called the P-HOPE (Probability-Driven Heuristic Optimization for Path Exploration) strategy, that integrates multidimensional influencing factors is designed in the proposed RRT<inline-formula> <tex-math notation="LaTeX">$^{\ast }$ </tex-math></inline-formula>-PRIME algorithm to optimize target sampling direction by considering angle, direction consistency, and obstacle distribution. Second, a flexible mechanism FLEX-OPT is developed to adaptively and dynamically adjust the search strategy through real-time feedback and monitoring of the cost function to tackle the above-mentioned local minima problem, which significantly improves the convergence speed and path quality of the algorithm. The experimental results suggest that the proposed RRT<inline-formula> <tex-math notation="LaTeX">$^{\ast }$ </tex-math></inline-formula>-PRIME algorithm can reduce the initial solution search time by 76.32%, reduce the number of search nodes by about 80.67%, and improve the search path quality compared with the RRT<inline-formula> <tex-math notation="LaTeX">$^{\ast }$ </tex-math></inline-formula> algorithm. In both narrow complex and large-scale map environments, the RRT<inline-formula> <tex-math notation="LaTeX">$^{\ast }$ </tex-math></inline-formula>-PRIME algorithm significantly outperforms the RRT<inline-formula> <tex-math notation="LaTeX">$^{\ast }$ </tex-math></inline-formula>, Informed-RRT<inline-formula> <tex-math notation="LaTeX">$^{\ast }$ </tex-math></inline-formula>, h-RRT<inline-formula> <tex-math notation="LaTeX">$^{\ast }$ </tex-math></inline-formula>, and PF-RRT<inline-formula> <tex-math notation="LaTeX">$^{\ast }$ </tex-math></inline-formula> algorithms in terms of reliability and efficiency. These results demonstrate the effectiveness of the RRT<inline-formula> <tex-math notation="LaTeX">$^{\ast }$ </tex-math></inline-formula>-PRIME algorithm as a robust and efficient solution for path planning in complex and large-scale environments. |
| format | Article |
| id | doaj-art-7987fc23e5dd46d481a61335c86d4e9a |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-7987fc23e5dd46d481a61335c86d4e9a2025-01-29T00:01:10ZengIEEEIEEE Access2169-35362025-01-0113159651598010.1109/ACCESS.2025.352619510829612Leveraging RRT<sup>*</sup>: Probabilistically Interpreted Mechanisms Enhanced With P-HOPE and FLEX-OPT for Complex Path PlanningYujie Miao0https://orcid.org/0009-0007-0215-8740Haiyang Liu1https://orcid.org/0000-0001-6567-8603Ziqiang Zhang2https://orcid.org/0009-0005-9806-4946Yanju Liang3https://orcid.org/0009-0006-4002-1051School of Integrated Circuits, University of Chinese Academy of Sciences, Beijing, ChinaInstitute of Microelectronics of the Chinese Academy of Sciences, Beijing, ChinaIntelligent Transportation Technology and System Research Platform, Hangzhou Innovation Research Institute of Beihang University, Hangzhou, ChinaInstitute of Microelectronics of the Chinese Academy of Sciences, Beijing, ChinaPath planning is a great challenge in the autonomous navigation of mobile robots. The Rapidly-exploring Random Tree<inline-formula> <tex-math notation="LaTeX">$^{\ast }$ </tex-math></inline-formula> (RRT<inline-formula> <tex-math notation="LaTeX">$^{\ast } $ </tex-math></inline-formula>) algorithm is widely used for its probabilistic completeness. In the literature, improved RRT<inline-formula> <tex-math notation="LaTeX">$^{\ast }$ </tex-math></inline-formula>-based algorithms usually enhance search efficiency through different target bias strategies. However, these algorithms often fall into obstacle traps in complex environments with narrow passages or high obstacle densities due to the loLcal minima problem in the optimization process. In addition, the existing algorithms also exhibit inefficient sampling and slow convergence in large-scale maps. To tackle with these problems, we propose an improved algorithm, called the RRT<inline-formula> <tex-math notation="LaTeX">$^{\ast }$ </tex-math></inline-formula>-PRIME (Probabilistically Interpreted Mechanisms Enhanced RRT<inline-formula> <tex-math notation="LaTeX">$^{\ast } $ </tex-math></inline-formula>) algorithm, in this paper. First, a powerful strategy, called the P-HOPE (Probability-Driven Heuristic Optimization for Path Exploration) strategy, that integrates multidimensional influencing factors is designed in the proposed RRT<inline-formula> <tex-math notation="LaTeX">$^{\ast }$ </tex-math></inline-formula>-PRIME algorithm to optimize target sampling direction by considering angle, direction consistency, and obstacle distribution. Second, a flexible mechanism FLEX-OPT is developed to adaptively and dynamically adjust the search strategy through real-time feedback and monitoring of the cost function to tackle the above-mentioned local minima problem, which significantly improves the convergence speed and path quality of the algorithm. The experimental results suggest that the proposed RRT<inline-formula> <tex-math notation="LaTeX">$^{\ast }$ </tex-math></inline-formula>-PRIME algorithm can reduce the initial solution search time by 76.32%, reduce the number of search nodes by about 80.67%, and improve the search path quality compared with the RRT<inline-formula> <tex-math notation="LaTeX">$^{\ast }$ </tex-math></inline-formula> algorithm. In both narrow complex and large-scale map environments, the RRT<inline-formula> <tex-math notation="LaTeX">$^{\ast }$ </tex-math></inline-formula>-PRIME algorithm significantly outperforms the RRT<inline-formula> <tex-math notation="LaTeX">$^{\ast }$ </tex-math></inline-formula>, Informed-RRT<inline-formula> <tex-math notation="LaTeX">$^{\ast }$ </tex-math></inline-formula>, h-RRT<inline-formula> <tex-math notation="LaTeX">$^{\ast }$ </tex-math></inline-formula>, and PF-RRT<inline-formula> <tex-math notation="LaTeX">$^{\ast }$ </tex-math></inline-formula> algorithms in terms of reliability and efficiency. These results demonstrate the effectiveness of the RRT<inline-formula> <tex-math notation="LaTeX">$^{\ast }$ </tex-math></inline-formula>-PRIME algorithm as a robust and efficient solution for path planning in complex and large-scale environments.https://ieeexplore.ieee.org/document/10829612/Path planningRRT*objective biasdynamic feedback optimizationlocal minima problem |
| spellingShingle | Yujie Miao Haiyang Liu Ziqiang Zhang Yanju Liang Leveraging RRT<sup>*</sup>: Probabilistically Interpreted Mechanisms Enhanced With P-HOPE and FLEX-OPT for Complex Path Planning IEEE Access Path planning RRT* objective bias dynamic feedback optimization local minima problem |
| title | Leveraging RRT<sup>*</sup>: Probabilistically Interpreted Mechanisms Enhanced With P-HOPE and FLEX-OPT for Complex Path Planning |
| title_full | Leveraging RRT<sup>*</sup>: Probabilistically Interpreted Mechanisms Enhanced With P-HOPE and FLEX-OPT for Complex Path Planning |
| title_fullStr | Leveraging RRT<sup>*</sup>: Probabilistically Interpreted Mechanisms Enhanced With P-HOPE and FLEX-OPT for Complex Path Planning |
| title_full_unstemmed | Leveraging RRT<sup>*</sup>: Probabilistically Interpreted Mechanisms Enhanced With P-HOPE and FLEX-OPT for Complex Path Planning |
| title_short | Leveraging RRT<sup>*</sup>: Probabilistically Interpreted Mechanisms Enhanced With P-HOPE and FLEX-OPT for Complex Path Planning |
| title_sort | leveraging rrt sup sup probabilistically interpreted mechanisms enhanced with p hope and flex opt for complex path planning |
| topic | Path planning RRT* objective bias dynamic feedback optimization local minima problem |
| url | https://ieeexplore.ieee.org/document/10829612/ |
| work_keys_str_mv | AT yujiemiao leveragingrrtsupsupprobabilisticallyinterpretedmechanismsenhancedwithphopeandflexoptforcomplexpathplanning AT haiyangliu leveragingrrtsupsupprobabilisticallyinterpretedmechanismsenhancedwithphopeandflexoptforcomplexpathplanning AT ziqiangzhang leveragingrrtsupsupprobabilisticallyinterpretedmechanismsenhancedwithphopeandflexoptforcomplexpathplanning AT yanjuliang leveragingrrtsupsupprobabilisticallyinterpretedmechanismsenhancedwithphopeandflexoptforcomplexpathplanning |