We are the champions of digital race.
Our paper published at ICSCA 2021, you can see details at https://doi.org/10.1145/3457784.3457827.
Welcome! This is an open-source self-driving car aimed for rapid prototyping, deep learning, and robotics research. The system currently runs on a jetson tx2 module. Here are our goals:
Research and develop a deep learning-driven self-driving car. The vehicle should be able to finish the race.
To know the role, please read documentation.
- Semantic Segmentation
- Object Detection
For the full documentation of the development process, please visit my website: datvuthanh.github.io
Digital Race is a contest that is sponsored by FPT Corp. The task of the teams completing the race in the shortest time.
To compile the project:
- Make sure that you have ROS installed on your computer. (I am using ROS Melodic)
- Make sure you have all the dependencies installed.
- Clone the repository.
$ git clone https://github.com/datvuthanh/Digital-Race.git $ cd Digital-Race$ cp -r src/. ~/catkin_ws/src/.$ cd ~/catkin_ws/$ catkin_make$ source devel/setup.bash
This project uses ROS. For more information on ROS, nodes, topics and others please refer to the ROS README.
The cart understands its surrounding through semantic segmentation, which is a technique in computer that classifies each pixel in an image into different categories. The vehicle can also make decisions based on the segmentic segmentation results. The cart can change its speed based on the proximity to nearby obstacles.
We deployed the PSPNet architecture for segmentation. PSPNet is design to work well in realtime applications. For more information, please visit the paper. We collect dataset for training and the python code for training and inferencing are located in the segmentation directory.
If you are interested in the detailed development process of this project, you can contact me at email address: [email protected] or [email protected]
Contributors:
Dat Vu (Leader) | Email | Github | Website
Tra Dinh | Email
Huy Phan | Email
