Path Planning Method of Mobile Robot Using Improved Deep Reinforcement Learning
A mobile robot path planning method based on improved deep reinforcement learning is proposed. First, in order to conform to the actual kinematics model of the robot, the continuous environmental state space and discrete action state space are designed. In addition, an improved deep Q-network (DQN)...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-01-01
|
| Series: | Journal of Electrical and Computer Engineering |
| Online Access: | http://dx.doi.org/10.1155/2022/5433988 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849401244240576512 |
|---|---|
| author | Wei Wang Zhenkui Wu Huafu Luo Bin Zhang |
| author_facet | Wei Wang Zhenkui Wu Huafu Luo Bin Zhang |
| author_sort | Wei Wang |
| collection | DOAJ |
| description | A mobile robot path planning method based on improved deep reinforcement learning is proposed. First, in order to conform to the actual kinematics model of the robot, the continuous environmental state space and discrete action state space are designed. In addition, an improved deep Q-network (DQN) method is proposed, which takes the directly collected information as the training samples and combines the environmental state characteristics of the robot and the target point to be reached as the input of the network. DQN method takes the Q value at the current position as the output of the network model and uses ε-greedy strategy for action selection. Finally, the reward function combined with the artificial potential field method is designed to optimize the state-action space. The reward function solves the problem of sparse reward in the environmental state space and makes the action selection of the robot more accurate. Experiments show that compared with the classical DQN method, the average loss function value is reduced by 36.87% and the average reward value is increased by 12.96%, which can effectively improve the working efficiency of mobile robot. |
| format | Article |
| id | doaj-art-85f82d176b1f4eb9b55f7c1f2ecd85fe |
| institution | Kabale University |
| issn | 2090-0155 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Electrical and Computer Engineering |
| spelling | doaj-art-85f82d176b1f4eb9b55f7c1f2ecd85fe2025-08-20T03:37:49ZengWileyJournal of Electrical and Computer Engineering2090-01552022-01-01202210.1155/2022/5433988Path Planning Method of Mobile Robot Using Improved Deep Reinforcement LearningWei Wang0Zhenkui Wu1Huafu Luo2Bin Zhang3Department of Electrical EngineeringSchool of Information EngineeringDepartment of Electrical Information EngineeringInner Mongolia Kingdomway Pharmaceutical LimitedA mobile robot path planning method based on improved deep reinforcement learning is proposed. First, in order to conform to the actual kinematics model of the robot, the continuous environmental state space and discrete action state space are designed. In addition, an improved deep Q-network (DQN) method is proposed, which takes the directly collected information as the training samples and combines the environmental state characteristics of the robot and the target point to be reached as the input of the network. DQN method takes the Q value at the current position as the output of the network model and uses ε-greedy strategy for action selection. Finally, the reward function combined with the artificial potential field method is designed to optimize the state-action space. The reward function solves the problem of sparse reward in the environmental state space and makes the action selection of the robot more accurate. Experiments show that compared with the classical DQN method, the average loss function value is reduced by 36.87% and the average reward value is increased by 12.96%, which can effectively improve the working efficiency of mobile robot.http://dx.doi.org/10.1155/2022/5433988 |
| spellingShingle | Wei Wang Zhenkui Wu Huafu Luo Bin Zhang Path Planning Method of Mobile Robot Using Improved Deep Reinforcement Learning Journal of Electrical and Computer Engineering |
| title | Path Planning Method of Mobile Robot Using Improved Deep Reinforcement Learning |
| title_full | Path Planning Method of Mobile Robot Using Improved Deep Reinforcement Learning |
| title_fullStr | Path Planning Method of Mobile Robot Using Improved Deep Reinforcement Learning |
| title_full_unstemmed | Path Planning Method of Mobile Robot Using Improved Deep Reinforcement Learning |
| title_short | Path Planning Method of Mobile Robot Using Improved Deep Reinforcement Learning |
| title_sort | path planning method of mobile robot using improved deep reinforcement learning |
| url | http://dx.doi.org/10.1155/2022/5433988 |
| work_keys_str_mv | AT weiwang pathplanningmethodofmobilerobotusingimproveddeepreinforcementlearning AT zhenkuiwu pathplanningmethodofmobilerobotusingimproveddeepreinforcementlearning AT huafuluo pathplanningmethodofmobilerobotusingimproveddeepreinforcementlearning AT binzhang pathplanningmethodofmobilerobotusingimproveddeepreinforcementlearning |