Global path planning of mobile robot based on improved A* algorithm
Konferenz: ICMLCA 2021 - 2nd International Conference on Machine Learning and Computer Application
17.12.2021 - 19.12.2021 in Shenyang, China
Tagungsband: ICMLCA 2021
Seiten: 4Sprache: EnglischTyp: PDF
Persönliche VDE-Mitglieder erhalten auf diesen Artikel 10% Rabatt
Autoren:
Yuan, Jiannan; Tang, Zhuang; Zhang, Zhian; Wang, Hailong (Nanjing University of Science And Technology, NJUST, Nanjing, China)
Inhalt:
As a widely used global path search algorithm, A* algorithm has various deficiencies such as low search efficiency and relatively tortuous paths. In response to these problems, the following improvements have been made: optimize the search space, address the shortcomings of the A* algorithm heuristic function cannot be equivalent to the shortest path, search for obstacles in the grid map, eliminate invalid search areas, and improve the algorithm's performance Search efficiency: After the path is generated, by eliminating invalid nodes and introducing the concept of dynamic programming, the path is further optimized to reduce the path distance and the number of turns. Finally, the simulation is performed under the grid map through MATLAB, and the search time of the path and the distance and smoothness of the generated path are compared with the original algorithm. Simulation shows that the improved algorithm has better capabilities in terms of search time, path distance and smoothness.