A dynamic path planning algorithm for UAV tracking

2009 ◽  
Author(s):  
Hongda Chen ◽  
K. C. Chang ◽  
Craig S. Agate
Keyword(s):  
Path Planning ◽  
Dynamic Path Planning ◽  
Planning Algorithm ◽  
Dynamic Path ◽  
Path Planning Algorithm

Dynamic Path Planning Algorithm Based on Chaos Genetic Vehicle Navigation

2011 ◽  
Vol 142 ◽  
pp. 12-15
Author(s):  
Ping Feng
Keyword(s):  
Path Planning ◽  
Search Algorithm ◽  
Traffic Condition ◽  
Planning Time ◽  
Dynamic Path Planning ◽  
Short Period ◽  
Planning Algorithm ◽  
Dynamic Path ◽  
Path Planning Algorithm ◽  
Chaos Genetic Algorithm

The paper puts forward the dynamic path planning algorithm based on improving chaos genetic algorithm by using genetic algorithms and chaos search algorithm. In the practice of navigation, the algorithm can compute at the best path to meet the needs of the navigation in such a short period of planning time. Furthermore,this algorithm can replan a optimum path of the rest paths after the traffic condition in the sudden.

Adaptive Dynamic Path Planning Algorithm for Interception of a Moving Target

2013 ◽  
Vol 5 (3) ◽  
pp. 19-33
Author(s):  
H. H. Triharminto ◽  
A.S. Prabuwono ◽  
T. B. Adji ◽  
N. A. Setiawan
Keyword(s):  
Path Planning ◽  
Dynamic Condition ◽  
Cylindrical Shape ◽  
Moving Target ◽  
C Language ◽  
Dynamic Path Planning ◽  
Planning Algorithm ◽  
Aerial Vehicle ◽  
Dynamic Path ◽  
Path Planning Algorithm

Most of the 3D curve path planning is used to build static path planning. For intercepting of a moving target, the path planning has to be set in a dynamic condition. L+Dumo algorithm which is based on curve is used to intercept a moving target. In the real situations, the Unmanned Aerial Vehicle (UAV) has possibility to intercept a moving target from all direction. It is assumed that environment of the UAV is in 3D Euclidean Space. It means that the UAV has to adapt for all quadrants for interception of a moving target. This research develops a path planning algorithm which enhances the previous L+Dumo algorithm to encounter the possibility quadrants. The enhancement would be simulated in C++ language to determine the accuracy of the algorithm. The simulation is conducted using one UAV and one moving target with random obstacles of cylindrical shape in between both objects. The result shows that the system accuracy is 81.0876%, a level which is able to encounter all possibility quadrants.

scholarly journals Research on Dynamic Path Planning of Wheeled Robot Based on Deep Reinforcement Learning on the Slope Ground

2020 ◽  
Vol 2020 ◽  
pp. 1-10
Author(s):  
Peng Wang ◽  
Xiaoqiang Li ◽  
Chunxiao Song ◽  
Shipeng Zhai
Keyword(s):  
Path Planning ◽  
Tree Structure ◽  
Moving Obstacles ◽  
Dynamic Path Planning ◽  
Wheeled Robot ◽  
Multiple Paths ◽  
Planning Algorithm ◽  
Simulation And Experiment ◽  
Dynamic Path ◽  
Path Planning Algorithm

The existing dynamic path planning algorithm cannot properly solve the problem of the path planning of wheeled robot on the slope ground with dynamic moving obstacles. To solve the problem of slow convergence rate in the training phase of DDQN, the dynamic path planning algorithm based on Tree-Double Deep Q Network (TDDQN) is proposed. The algorithm discards detected incomplete and over-detected paths by optimizing the tree structure, and combines the DDQN method with the tree structure method. Firstly, DDQN algorithm is used to select the best action in the current state after performing fewer actions, so as to obtain the candidate path that meets the conditions. And then, according to the obtained state, the above process is repeatedly executed to form multiple paths of the tree structure. Finally, the non-maximum suppression method is used to select the best path from the plurality of eligible candidate paths. ROS simulation and experiment verify that the wheeled robot can reach the target effectively on the slope ground with moving obstacles. The results show that compared with DDQN algorithm, TDDQN has the advantages of fast convergence and low loss function.

Sign in / Sign up

Export Citation Format

Share Document