The following repository contains the code for the path planning reinforcement learning algorithm through a randomly generated environment. Which can help in reducing the computational load on a CPU for path planning.
As the world moves towards autonomy, one field that is at the forefront is that of self-driving vehicles. These vehicles take information regarding their environment from various sensors and use it to navigate through complex situations.
In this git repository, complex environments are generated in the form of random tracks, and we use a Feed-Forward Neural-Network to train a model car that can successfully navigate these tracks without collisions.
- OS version: Windows 10/11 or Ubuntu or Mac OS
- Coding Environment: VS Code or PyCharm or any other suitable coding platform to run python
- Python Version 3.8.10
- Pygame Version 2.1.0
- Neat Version 0.92
For more necessary packages please refer to packages.txt in the repository
pip install -r packages.txt
- Download all the files in one folder.
- Before running, install all the necessary dependencies in your coding environment using the terminal.
- Simply run the program using compile and run.
- A screen will appear where the A.I. will start to train the model to trace the track.
- On the terminal, you can see the scores, rewards, fitness of the model in each generation.
Contributors' names and contact info
Anagha Ramaswamy GitHub
Himanshu Gautam GitHub
Harin Vashi