Autonomous Driving

The aim of this project is to predict the trajectory from a series of frames to emulate the autonomous drive in a radio controlled machine. For more details read the report and watch the video in this link.

Table of Contents

• Preprocessing
• Create csv files
• Training and Testing
• Video creation

All the settings, path and configurations are in config/config.py file. Please read all sections to make sure all work correctly.

Dependacies

• PyTorch
• numpy
• opencv
• mathplotlib
• pil

For detailed steps to install PyTorch, follow the PyTorch installation instruction. A typical user can install PyTorch using the following commands:

# Create virtual environment
conda create -n pytorch python=3.7

# Activate virtual environment
conda activate pytorch

# Install PyTorch
conda install pytorch torchvision cudatoolkit=10.1 -c pytorch

The other packet can be installed using pip:

conda activate pytorch
pip install numpy
pip install mathplotlib
pip install Pillow==2.2.2
pip install opencv-python
pip install tqtm