Skip to content

Commit

Permalink
Update README.md
Browse files Browse the repository at this point in the history
  • Loading branch information
Timthony authored Nov 15, 2018
1 parent c355beb commit 5e94011
Showing 1 changed file with 22 additions and 13 deletions.
35 changes: 22 additions & 13 deletions README.md
Original file line number Diff line number Diff line change
@@ -1,31 +1,40 @@
# self_drive
基于树莓派的人工智能自动驾驶小车
Artificial intelligence automatic driving car based on raspberry pie
github传送门:https://github.com/Timthony/self_drive
# 整体流程
电机控制
摄像头调试
道路数据采集
搭建深度学习模型,参数调试
自动驾驶真实道路模拟
参数最终调试
# 整体流程(Technological process)
电机控制(Motor control)
摄像头调试(Camera debugging)
道路数据采集(Road data acquisition)
搭建深度学习模型,参数调试(Build deep learning model, parameter debug)
自动驾驶真实道路模拟(Real road simulation of automatic driving)
参数最终调试(Final debugging of parameters)

使用方法:
1. 先将树莓派小车硬件组装好
使用方法(Usage method)
1. 先将树莓派小车硬件组装好(assemble the raspberry cart hardware.)
2. 使用zth_car_control.py来控制小车的前后左右移动,配合zth_collect_data.py来人工操作,使小车在自己制作的跑道进行数据采集。(该过程在树莓派进行)
(Use zth_car_control.py to control the front and rear movement of the car, and cooperate with zth_collect_data.py to operate manually, so that the car can collect data on its own runway. (the process is carried out in raspberry pie).)
3. 数据采集完成以后使用zth_process_img.py来对采集的数据进行处理,之前当前先完成一些数据清洗的工作。(电脑上执行)
(After data acquisition is completed, zth_process_img.py is used to process the collected data, and some data cleaning work is completed before. (computer execution))
4. 使用神经网络模型对数据进行训练zth_train.py,得到训练好的模型。(电脑上执行)
( using neural network model to train data, zth_train.py, get a trained model. (computer execution))
5. 在树莓派小车上使用zth_drive和训练好的模型,载入模型,即可实现在原先跑道的自动驾驶。(树莓派上执行)
注意:只需要使用上述提到的代码即可,别的都是一些初始版本或者正在增加的一些新模块。
(Auto-driving on the original runway can be realized by using zth_drive and trained model in the raspberry dispatch car and loading the model. (raspberry pie execution))
注意:只需要使用上述提到的代码即可,别的都是一些初始版本或者正在增加的一些新模块。
(Note: All you need to do is use the code mentioned above. Others are original versions or new modules that are being added.)
![](https://ws3.sinaimg.cn/large/006tNbRwly1fw2xwxarf2j30u0140tbg.jpg)
![](https://ws4.sinaimg.cn/large/006tNbRwly1fx7tmmq5jjj30u00hgq6z.jpg)

# 注意事项
# 注意事项(Matters needing attention):
1. 赛道需要自己制作,很重要,决定了数据质量。(我是在地板上,贴的有色胶带,然后贴成了跑道的形状)。
(the track needs to be produced by itself, which is very important and determines the quality of data. (I was on the floor, taped with colored tape, and then pasted into the shape of the runway).)
2. 赛道的宽度大约是车身的两倍。
(the width of the track is about two times that of the body.)
3. 大约采集了五六万张图像,然后筛选出三四万张。
(about fifty thousand or sixty thousand images were collected and thirty thousand or forty thousand were screened out.)
4. 摄像头角度问题

# 具体制作流程:
(camera angle problem)
# 具体制作流程(Specific production process)
1. 小车原始模型,某宝购买玩具车即可,比如:有电机,有自带电池盒(给电机供电)
2. 树莓派,摄像头,蓄电电池组(用于树莓派供电)
3. 使用一些螺栓,螺柱,亚克力板将树莓派,蓄电电池固定在小车上(具体方法,看手头的工具吧)
Expand Down

0 comments on commit 5e94011

Please sign in to comment.