SLP-Improved DDPG Path-Planning Algorithm for Mobile Robot in Large-Scale Dynamic Environment
Navigating robots through large-scale environments while avoiding dynamic obstacles is a crucial challenge in robotics. This study proposes an improved deep deterministic policy gradient (DDPG) path planning algorithm incorporating sequential linear path planning (SLP) to address this challenge. Thi...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/7/3521 |
| _version_ | 1797607053343064064 |
|---|---|
| author | Yinliang Chen Liang Liang |
| author_facet | Yinliang Chen Liang Liang |
| author_sort | Yinliang Chen |
| collection | DOAJ |
| description | Navigating robots through large-scale environments while avoiding dynamic obstacles is a crucial challenge in robotics. This study proposes an improved deep deterministic policy gradient (DDPG) path planning algorithm incorporating sequential linear path planning (SLP) to address this challenge. This research aims to enhance the stability and efficiency of traditional DDPG algorithms by utilizing the strengths of SLP and achieving a better balance between stability and real-time performance. Our algorithm generates a series of sub-goals using SLP, based on a quick calculation of the robot’s driving path, and then uses DDPG to follow these sub-goals for path planning. The experimental results demonstrate that the proposed SLP-enhanced DDPG path planning algorithm outperforms traditional DDPG algorithms by effectively navigating the robot through large-scale dynamic environments while avoiding obstacles. Specifically, the proposed algorithm improves the success rate by 12.33% compared to the traditional DDPG algorithm and 29.67% compared to the A*+DDPG algorithm in navigating the robot to the goal while avoiding obstacles. |
| first_indexed | 2024-03-11T05:24:52Z |
| format | Article |
| id | doaj.art-7f6e79541c9c4342b29e0129e0361303 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T05:24:52Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-7f6e79541c9c4342b29e0129e03613032023-11-17T17:33:46ZengMDPI AGSensors1424-82202023-03-01237352110.3390/s23073521SLP-Improved DDPG Path-Planning Algorithm for Mobile Robot in Large-Scale Dynamic EnvironmentYinliang Chen0Liang Liang1School of Computer Science, Wuhan University, Wuhan 430072, ChinaSchool of Power and Mechanical Engineering, Wuhan University, Wuhan 430072, ChinaNavigating robots through large-scale environments while avoiding dynamic obstacles is a crucial challenge in robotics. This study proposes an improved deep deterministic policy gradient (DDPG) path planning algorithm incorporating sequential linear path planning (SLP) to address this challenge. This research aims to enhance the stability and efficiency of traditional DDPG algorithms by utilizing the strengths of SLP and achieving a better balance between stability and real-time performance. Our algorithm generates a series of sub-goals using SLP, based on a quick calculation of the robot’s driving path, and then uses DDPG to follow these sub-goals for path planning. The experimental results demonstrate that the proposed SLP-enhanced DDPG path planning algorithm outperforms traditional DDPG algorithms by effectively navigating the robot through large-scale dynamic environments while avoiding obstacles. Specifically, the proposed algorithm improves the success rate by 12.33% compared to the traditional DDPG algorithm and 29.67% compared to the A*+DDPG algorithm in navigating the robot to the goal while avoiding obstacles.https://www.mdpi.com/1424-8220/23/7/3521deep reinforcement learningpath planningmobile robotdeep neural network |
| spellingShingle | Yinliang Chen Liang Liang SLP-Improved DDPG Path-Planning Algorithm for Mobile Robot in Large-Scale Dynamic Environment Sensors deep reinforcement learning path planning mobile robot deep neural network |
| title | SLP-Improved DDPG Path-Planning Algorithm for Mobile Robot in Large-Scale Dynamic Environment |
| title_full | SLP-Improved DDPG Path-Planning Algorithm for Mobile Robot in Large-Scale Dynamic Environment |
| title_fullStr | SLP-Improved DDPG Path-Planning Algorithm for Mobile Robot in Large-Scale Dynamic Environment |
| title_full_unstemmed | SLP-Improved DDPG Path-Planning Algorithm for Mobile Robot in Large-Scale Dynamic Environment |
| title_short | SLP-Improved DDPG Path-Planning Algorithm for Mobile Robot in Large-Scale Dynamic Environment |
| title_sort | slp improved ddpg path planning algorithm for mobile robot in large scale dynamic environment |
| topic | deep reinforcement learning path planning mobile robot deep neural network |
| url | https://www.mdpi.com/1424-8220/23/7/3521 |
| work_keys_str_mv | AT yinliangchen slpimprovedddpgpathplanningalgorithmformobilerobotinlargescaledynamicenvironment AT liangliang slpimprovedddpgpathplanningalgorithmformobilerobotinlargescaledynamicenvironment |