Deep Learning Model for Simulating Self Driving Car

• Published in: 2023 International Conference on Communication System, Computing and IT Applications (CSCITA) pp. 26 - 31
• Main Authors: Bhujbal, Kunal, Pawar, Dr. Mahendra
• Format: Conference Proceeding
• Language: English
• Published: IEEE 31.03.2023
• Subjects: Autonomous Cars; Behavioral sciences; Behavioural Cloning; CNN (Convolutional Neural Network); Computational modeling; Computer Vision; Data models; Deep learning; Image Augmentation; Image pre-processing; Machine Learning; Real-time systems; Recurrent neural networks; Self-Driving cars; Training
• DOI: 10.1109/CSCITA55725.2023.10104750

Self-driving cars have become a trending subject with a significant improvement in the technologies in the last decade. The project purpose is to train a convolutional neural network to drive an autonomous car agent on the tracks of Udacity's Car Simulator environment. Udacity has released the simulator as an open source software. Driving a car in an autonomous manner requires learning to control steering angle, throttle and brakes. Behavioral cloning technique is used to mimic human driving behavior in the training mode on the track. That means a dataset is generated in the simulator by a user driven car in training mode, and the NVIDIA's convolutional neural network model then drives the car in autonomous mode. Augmentation and image pre-processing are used to increase the accuracy of CNN model.