| LIU Andong(刘安东)*,ZHANG Baixin*,CUI Qi,ZHANG Dan*,NI Hongjie*.[J].高技术通讯(英文),2023,29(4):365~376 |
|
| A dynamic fusion path planning algorithm for mobile robotsincorporating improved IB-RRT∗ and deep reinforcement learning |
| |
| DOI： |
| 中文关键词: |
| 英文关键词: mobile robot,improved IB-RRT∗ algorithm,deep reinforcement learning(DRL),
real-time dynamic obstacle avoidance |
| 基金项目: |
| Author Name | Affiliation | | LIU Andong(刘安东)* | (College of Information Engineering,Zhejiang University of Technology,Hangzhou 310023,P. R. China) | | ZHANG Baixin* | | | CUI Qi | | | ZHANG Dan* | | | NI Hongjie* | |
|
| Hits: 600 |
| Download times: 532 |
| 中文摘要: |
| |
| 英文摘要: |
| Dynamic path planning is crucial for mobile robots to navigate successfully in unstructured environments.
To achieve globally optimal path and real-time dynamic obstacle avoidance during the
movement,a dynamic path planning algorithm incorporating improved IB-RRT? and deep reinforcement
learning (DRL) is proposed. Firstly,an improved IB-RRT? algorithm is proposed for global
path planning by combining double elliptic subset sampling and probabilistic central circle target bias.
Then,to tackle the slow response to dynamic obstacles and inadequate obstacle avoidance of traditional
local path planning algorithms,deep reinforcement learning is utilized to predict the movement
trend of dynamic obstacles,leading to a dynamic fusion path planning. Finally,the simulation
and experiment results demonstrate that the proposed improved IB-RRT? algorithm has higher convergence
speed and search efficiency compared with traditional Bi-RRT?,Informed-RRT?,and IBRRT?
algorithms. Furthermore,the proposed fusion algorithm can effectively perform real-time obstacle
avoidance and navigation tasks for mobile robots in unstructured environments. |
|
View Full Text
View/Add Comment Download reader |
| Close |
|
|
|
