# Qlearning_AGVpath
Demonstrate the Q-Learning approach for AGV path planning
Execute "run.py" to open the demonstrate UI.
The UI shows how AGV agent learn how to avoid the new obstacle in the path by reinforcement learning skill.
The UI not only demonstrate the effect of Q-Learning but the A-star and Dijkstra path algorithm as well.
Set the position (x, y) of the starting and goal point for AGV and the position of the obstacles then press "start".
## State-Action Setting
![image](https://github.com/arrtvv852/Qlearning_AGVpath/blob/master/state-action.PNG)
## Reward Function Setting
![image](https://github.com/arrtvv852/Qlearning_AGVpath/blob/master/reward.PNG)
## Illustration:
![image](https://github.com/arrtvv852/Qlearning_AGVpath/blob/master/ezgif.com-video-to-gif.gif)
演示AGV路径规划的Q学习方法
需积分: 0 69 浏览量
2023-10-08
21:10:49
上传
评论
收藏 1.42MB ZIP 举报
Older司机渣渣威
- 粉丝: 5
- 资源: 202
最新资源
- 第12章spring-mvc自定义类型转换器
- 基于PHP图书管理系统实验报告.docx
- Python爬取淘宝热卖商品并可视化分析
- 5152单片机proteus仿真和源码将按键次数写入AT24C02再读出并用1602LCD显示
- SE-SSD复现过程(Det3D的安装教程)
- 基于Python的在线学习与推荐系统设计与实现(论文+源码)-kaic
- 串口通过 YMODEM 协议进行文件传输
- 蓝桥杯2024年第十五届省赛真题-前缀总分
- com.qihoo.appstore_300101305-1.apk
- tensorflow-gpu-2.7.1-cp37-cp37m-manylinux2010-x86-64.whl
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈