Skip to main content

Project introduction


In this project, the research group decided to make a small car that could be remotely controlled, and the users could see the vision from the camera on the car through a screen. Though the vehicle is controlled by the users, the processer on the small car could detect the soundings and look for potential threats (barriers and emergency) and take emergency actions automatically. The research group is trying to rebuild the active safety system in an ordinary car.
Figure 1: The working principle of the smart car
To achieve these functions, the research group decided to use pi2go MK2 as a fundamental part of the smart car. The car contains a motional sensor, a light sensor, two motors and a platform to hold a raspberry pi.



Figure 2:Pi2go MK2

In addition to the car, another sensor has been added to the car body. In the project, the research group need a camera to record the front view of the car and have the video analysis in by the raspberry pi. In the front of the smart car, we managed to add a pixy two camera(as is shown in figure 3), which can be linked to the smart car with a mico-USB.

Figure 3: Pixy 2 motional camera
Detailed works and progress are shown in the blogs by the week.
Location: 英国利物浦

Comments

Post a Comment

Popular posts from this blog

Week 4: Change of Operating System and Problems

Change system and problems In the lab section of this week, the research group had a difficult time. In detail, it is difficult to have the video of the camera been transmitted to the computer. The data flows to the raspberry in the form of coordinate, length and height of the marked blocks. In this way, the processor of the pi could be relaxed. However, in the first place ， the basic function of the car is that the user could see what the car sees with the use of camera. If the control system is not visual, it is meaningless to have such a complex system. To make it possible to visualize the streaming video, the research group checked the driver of the camera. It turns out that it is not designed for Raspbian, and this made its function been limited to this system. To solve this problem, the research group had to change the system of the smart car and recode the programs that have been tested. In specific, the driver is designed for a pure Linux environment. Having don...
Post a Comment
Read more

Week 1: Car Assembling and Raspberry Pi Initializing

Pi2go MK2 Smart car assembling and introduction: In the first week of the project, the research group received the components that will be used in the project. The first thing to do is to assemble the smart car Pi2go MK2. In specific, Pi2go MK2 contains a chip which could control different parts of the car. The raspberry pi uses the GPIO connections to control and power the smart car. Figure 1: GPIO pins to control the car System instaling: Having assembled the car, the research group began to initialize the raspberry pi. According to the instruction, the research group had to instore an operating system into the SD card with SD card formatter and Win 32 Disk Imager. Problem-solving: However, when the raspberry is equipped with the operating system and plugged into a screen, the screen showed the following alert: kernel failure. To solve the problem, the research group tried to restart the pi for several times and it still shows a failure. Then, the researc...
Post a Comment
Read more

Week 2:Machine Learning of Pixy 2

In this lab section, the research group managed to activate the pixy 2 camera with a given driver. By using the driver, the research group could cheek whether the camera could run smoothly. Figure 1: Pixy 2 camera Then, the research had to enable the SPI and I2C service in the raspberry pi and introduce the python library module to the raspberry pi for the Pi2go MK2. In this way, all kinds of sensors and motional devices could be activated when necessary. Having activated the camera, the research group began to try the machine learning part of the program. In specific, the car needs to recognize different kinds of barriers and send alerts to the pi and have the pi to judge how to change the moving direction to avoid hitting. The machine learning part is the fatal part of the car. Firstly, the research group managed to do this from a simple task which is to recognize a sign written on paper. The detailed learning and recognition procedure are shown in the video.
Post a Comment
Read more