This project is focused on creating a self-driving car using the PiCar platform applying a machine-learning neural network model to sustain autonomous driving capabilities on a mapped track.
- Autonomous driving: The car is capable of following a track autonomously using a trained neural network model.
- Real-time image processing: The car processes images from its camera in real-time to make decisions about steering and speed.
- Customizable: The project can be customized to use different machine learning frameworks and models, and can be adapted to work with other robotic platforms.
- Raspberry Pi and PiCar
- Python 3.x
- TensorFlow or PyTorch
- OpenCV
git clone https://github.com/kputhanangadi/autopilot-project.git
- Clone the repository
- Install the necessary dependencies
You can install all the dependencies for this class by typing
pip install -r requirements.txt - Train the neural network model using your own data
python train_model.py --data_path /path/to/training/data - Integrate the model with the PiCar's software
- Run the program on the PiCar
- Place the car on a track and watch it drive autonomously
- Adjust the model's parameters as needed to improve performance
If you'd like to contribute to the development of this application, please follow these steps:
- Fork the repository
- Create a new branch for your feature or bug fix
- Make your changes and commit them
- Push your changes to your fork
- Create a pull request
This project is licensed under the MIT License. See the LICENSE file for details.