ROS2 Prius Self Driving Car using AI/Deeplearning and Computer Vision

Table of Contents

1. About This Repository
2. Using this Repository
3. Course Workflow
4. Features
5. Pre-Course Requirments
6. Link to the Course
7. Instructors
8. License

About this Repository

A tesla Like Car in ROS2 will follow lane , Use AI to classify Sign Boards and perform Object tracking to act on the sign boards and set speed respectively

Using this Repository

• Clone the repository in you Home folder

git clone https://github.com/noshluk2/ROS2-Self-Driving-Car-AI-using-OpenCV.git

• Get into the downloaded repository

cd path/to/ROS2-Self-Driving-Car-AI-using-OpenCV/
##e.g cd ~/ROS2-Self-Driving-Car-AI-using-OpenCV/

• Bring all models into your .gazebo/models ( requires gazebo to be installed )

cp /models/* ~/.gazebo/models 

or manually copy->paste them into ~/.gazebo/models/ ( if not avaible press ctrl + H , a hidden foler )

• Perform Colcon Build ( if not installed refer to Repo_resources/How_to_run_the_project.txt )

colcon build

• Source your Workspace in any terminal you open to Run files from this workspace ( Basic thing of ROS )

source /path/to/ROS2-Self-Driving-Car-AI-using-OpenCV/install/setup.bash

• (Optional for Power USERs ) Add source to this workspace into bash file

 echo "source /opt/ros/noetic/setup.bash" >> ~/.bashrc

NOTE: This upper command is going to add the source file path into your ~/.bashrc file ( Only perform it once and you know what you are doing).This will save your time when running things from the Workspace

• If the repository is not working for you. Watch the free preview video on our course page Where full explaination is given on setting up this repository.
  • [How to Run the Project]

---

Course Workflow

Ros Package

• World Models Creation
• Prius OSRF gazebo Model Editing
• Nodes , Launch Files
• SDF through Gazebo
• Textures and Plugins in SDF

Computer Vision

• Perception Pipeline setup
• Lane Detection with Computer Vision Techniques
• Traffic Light Detection Using Haar Cascades
• Sign and Traffic Light Tracking using Optical Flow
• Rule-Based Control Algorithms

DeepLearning

• Sign Classification using (custom-built) CNN

---

Features

• Prius Hybrid Car

  • 

• Lane Following

  • 

• Sign Board Detection

  • 

• Traffic Signal Recognition

  • 

• T-Junction Navigation

  • 

• The World

  • 

• Custom Models

  • 

---

Pre-Course Requirments

Software Based

• Ubuntu 20.04 (LTS)
• ROS2 - Foxy Fitzroy
• Python 3.6
• Opencv 4.2
• Tensorflow 2.14

Skill Based

• Basic ROS2 Nodes Communication
• Launch Files
• Gazebo Model Creation
• Basic OpenCV Usage
• Motivated mind :)

---

Link to the Course

[Discounted Link]

---

Instructors

Haider Najeeb (Computer Vision) - Profile Link
Muhammad Luqman (ROS Simulation and Control Systems) - Profile Link

---

License

Distributed under the GNU-GPL License. See LICENSE for more information.