Chinese Journal of Intelligent Science and Technology ›› 2022, Vol. 4 ›› Issue (2): 255-263.doi: 10.11959/j.issn.2096-6652.202228

• Papers and Reports • Previous Articles    

Automatic path planning program generation system based on swarm intelligence results

Yuqian WANG1, Rong DING2   

  1. 1 School of Computer Science and Engineering, Beihang University, Beijing 100191, China
    2 Institute of Artificial Intelligence, Beihang University, Beijing 100191, China
  • Online:2022-06-01 Published:2022-06-01
  • Supported by:
    The National Key Research and Development Program of China(2017YFB1001802)

Abstract:

Path planning algorithms are widely used in various motion planning tasks, such as robot motion and autonomous driving.So far, many excellent path planning algorithms have been proposed for applications in different fields.For a specific task environment, choosing the appropriate path planning algorithm can plan a better path that satisfies the constraints more efficiently.Based on the results of swarm intelligence, the adaptability and path planning efficiency of rapidly-exploring random tree (RRT) path planning algorithm and its variants RRT-Star path planning algorithm and RRT-Star-Smart path planning algorithm under different task environments were studied.Using genetic programming algorithm as a framework to design a system, which could automatically analyze the map features of the current environment and combine the characteristics of RRT path planning algorithm and its variants to generate new path planning algorithms that were more suitable for the current environment.The generated path planning algorithm can efficiently plan a feasible path from the starting point to the target point.

Key words: swarm intelligence, path planning algorithm, genetic programming, rapidly-exploring random tree, RRT-Star, RRT-Star-Smart

CLC Number: 

No Suggested Reading articles found!