Autonomous Car Simulation using Soft-Computing

In the modern era, vehicles are focused to be automated to give human driver relaxed driving. In the field of automobile various aspects have been considered which makes a vehicle automated. Nvidia, the leading gaming industry has started working on the self-driving cars since 2016 and still making and adding some new feature according to the environment. In this paper we have mainly focused on Lane detection, Speed control and steering angle. Our system automatically learns internal representations of the necessary processing steps such as detecting useful road with only the human steering angle as the training signal with help of keyboard (WASD). Here we are collecting/creating our data using the Udacity Car Simulator and then using it to train the model with the help of TensorFlow. For now, we plan to create a virtual environment where the the car will be running autonomously with all the objects in environment taken into consideration like pedestrians and traffic lights, etc.