Self Driving Car

Self Driving Car Using Covolutinal Neural Networks Via Using NVIDIA Model Architecture for End To End Self Driving Car And For Simulation Using Udacity Open Source Unity Self Driving Car Simulator

Demo

Dependencies

• Keras
• Pandas
• Matplotlib
• Numpy
• OpenCV
• SKlearn

Usage

Clone this repository

Type the following commands in your terminal:

cd path/to/directory/
git clone https://github.com/Aman-py/Self_Driving_Car
cd Self_Driving_Car/

Run the pretrained model

Start up the Udacity self-driving simulator, choose a scene and press the Autonomous Mode button. Then, run the model as follows:

python Drive.py

Dataset

I have created my own dataset using udacity simulator self driving car training mode and after that i have trained my model on that dataset for convenience you can use my data to train ur model here For more good datasets u can check these

• Udacity: https://medium.com/udacity/open-sourcing-223gb-of-mountain-view-driving-data-f6b5593fbfa5
  70 minutes of data ~ 223GB
  Format: Image, latitude, longitude, gear, brake, throttle, steering angles and speed
  
• Udacity Dataset: https://github.com/udacity/self-driving-car/tree/master/datasets [Datsets ranging from 40 to 183 GB in different conditions]
  
• Comma.ai Dataset [80 GB Uncompressed] https://github.com/commaai/research
  
• Apollo Dataset with different environment data of road: http://data.apollo.auto/?locale=en-us&lang=en
  

Vote of Thanks

Rayan Slim

NVIDIA's paper: End to End Learning for Self-Driving Cars for the inspiration and model structure.

Siraj Raval

Andrew Ng for the knowledge.