A path planning algorithm fusion of obstacle avoidance and memory functions
Abstract In this study, to address the issues of sluggish convergence and poor learning efficiency at the initial stages of training, the authors improve and optimise the Deep Deterministic Policy Gradient (DDPG) algorithm. First, inspired by the Artificial Potential Field method, the selection stra...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-12-01
|
| Series: | Cognitive Computation and Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/ccs2.12098 |
| _version_ | 1827585332664598528 |
|---|---|
| author | Qingchun Zheng Shubo Li Peihao Zhu Wenpeng Ma Yanlu Wang |
| author_facet | Qingchun Zheng Shubo Li Peihao Zhu Wenpeng Ma Yanlu Wang |
| author_sort | Qingchun Zheng |
| collection | DOAJ |
| description | Abstract In this study, to address the issues of sluggish convergence and poor learning efficiency at the initial stages of training, the authors improve and optimise the Deep Deterministic Policy Gradient (DDPG) algorithm. First, inspired by the Artificial Potential Field method, the selection strategy of DDPG has been improved to accelerate the convergence speed during the early stages of training and reduce the time it takes for the mobile robot to reach the target point. Then, optimising the neural network structure of the DDPG algorithm based on the Long Short‐Term Memory accelerates the algorithm's convergence speed in complex dynamic scenes. Static and dynamic scene simulation experiments of mobile robots are carried out in ROS. Test findings demonstrate that the Artificial Potential Field method‐Long Short Term Memory Deep Deterministic Policy Gradient (APF‐LSTM DDPG) algorithm converges significantly faster in complex dynamic scenes. The success rate is improved by 7.3% and 3.6% in contrast to the DDPG and LSTM‐DDPG algorithms. Finally, the usefulness of the method provided in this study is similarly demonstrated in real situations using real mobile robot platforms, laying the foundation for the path planning of mobile robots in complex changing conditions. |
| first_indexed | 2024-03-08T23:44:04Z |
| format | Article |
| id | doaj.art-c684205d3ae24a5bab7007289637e6ec |
| institution | Directory Open Access Journal |
| issn | 2517-7567 |
| language | English |
| last_indexed | 2024-03-08T23:44:04Z |
| publishDate | 2023-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | Cognitive Computation and Systems |
| spelling | doaj.art-c684205d3ae24a5bab7007289637e6ec2023-12-14T03:48:41ZengWileyCognitive Computation and Systems2517-75672023-12-015430031310.1049/ccs2.12098A path planning algorithm fusion of obstacle avoidance and memory functionsQingchun Zheng0Shubo Li1Peihao Zhu2Wenpeng Ma3Yanlu Wang4Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin ChinaTianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin ChinaTianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin ChinaTianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin ChinaTianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin ChinaAbstract In this study, to address the issues of sluggish convergence and poor learning efficiency at the initial stages of training, the authors improve and optimise the Deep Deterministic Policy Gradient (DDPG) algorithm. First, inspired by the Artificial Potential Field method, the selection strategy of DDPG has been improved to accelerate the convergence speed during the early stages of training and reduce the time it takes for the mobile robot to reach the target point. Then, optimising the neural network structure of the DDPG algorithm based on the Long Short‐Term Memory accelerates the algorithm's convergence speed in complex dynamic scenes. Static and dynamic scene simulation experiments of mobile robots are carried out in ROS. Test findings demonstrate that the Artificial Potential Field method‐Long Short Term Memory Deep Deterministic Policy Gradient (APF‐LSTM DDPG) algorithm converges significantly faster in complex dynamic scenes. The success rate is improved by 7.3% and 3.6% in contrast to the DDPG and LSTM‐DDPG algorithms. Finally, the usefulness of the method provided in this study is similarly demonstrated in real situations using real mobile robot platforms, laying the foundation for the path planning of mobile robots in complex changing conditions.https://doi.org/10.1049/ccs2.12098artificial intelligencedeep reinforcement learningintelligent robotsmobile robotspath planning |
| spellingShingle | Qingchun Zheng Shubo Li Peihao Zhu Wenpeng Ma Yanlu Wang A path planning algorithm fusion of obstacle avoidance and memory functions Cognitive Computation and Systems artificial intelligence deep reinforcement learning intelligent robots mobile robots path planning |
| title | A path planning algorithm fusion of obstacle avoidance and memory functions |
| title_full | A path planning algorithm fusion of obstacle avoidance and memory functions |
| title_fullStr | A path planning algorithm fusion of obstacle avoidance and memory functions |
| title_full_unstemmed | A path planning algorithm fusion of obstacle avoidance and memory functions |
| title_short | A path planning algorithm fusion of obstacle avoidance and memory functions |
| title_sort | path planning algorithm fusion of obstacle avoidance and memory functions |
| topic | artificial intelligence deep reinforcement learning intelligent robots mobile robots path planning |
| url | https://doi.org/10.1049/ccs2.12098 |
| work_keys_str_mv | AT qingchunzheng apathplanningalgorithmfusionofobstacleavoidanceandmemoryfunctions AT shuboli apathplanningalgorithmfusionofobstacleavoidanceandmemoryfunctions AT peihaozhu apathplanningalgorithmfusionofobstacleavoidanceandmemoryfunctions AT wenpengma apathplanningalgorithmfusionofobstacleavoidanceandmemoryfunctions AT yanluwang apathplanningalgorithmfusionofobstacleavoidanceandmemoryfunctions AT qingchunzheng pathplanningalgorithmfusionofobstacleavoidanceandmemoryfunctions AT shuboli pathplanningalgorithmfusionofobstacleavoidanceandmemoryfunctions AT peihaozhu pathplanningalgorithmfusionofobstacleavoidanceandmemoryfunctions AT wenpengma pathplanningalgorithmfusionofobstacleavoidanceandmemoryfunctions AT yanluwang pathplanningalgorithmfusionofobstacleavoidanceandmemoryfunctions |