| Autor: |
Ramón Jaramillo-Martínez, Ernesto Chavero-Navarrete, Teodoro Ibarra-Pérez |
| Jazyk: |
angličtina |
| Rok vydání: |
2024 |
| Předmět: |
|
| Zdroj: |
Applied Sciences, Vol 14, Iss 17, p 7654 (2024) |
| Druh dokumentu: |
article |
| ISSN: |
2076-3417 |
| DOI: |
10.3390/app14177654 |
| Popis: |
Path planning is a fundamental task for autonomous mobile robots (AMRs). Classic approaches provide an analytical solution by searching for the trajectory with the shortest distance; however, reinforcement learning (RL) techniques have been proven to be effective in solving these problems with the experiences gained by agents in real time. This study proposes a reward function that motivates an agent to select the shortest path with fewer turns. The solution to the RL technique is obtained via dynamic programming and Deep Q-Learning methods. In addition, a path-tracking control design is proposed based on the Lyapunov candidate function. The results indicate that RL algorithms show superior performance compared to classic A* algorithms. The number of turns is reduced by 50%, resulting in a decrease in the total distance ranging from 3.2% to 36%. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
