DeepDrive: A braking decision making approach using optimized GAN and Deep CNN for advanced driver assistance systems

Abstract

Reduction of the number of traffic accidents is a vital requirement in many countries over the world. In these circumstances, the Human–Robot Interaction (HRI) mechanisms utilization is currently exposed as a possible solution to recompense human limits. It is crucial to create a braking decision-making model in order to produce the optimal decisions possible because many braking decision-making approaches are launched with minimal performance. An effective braking decision-making system, named Optimized Deep Drive decision model is developed for making braking decisions. The video frames are extracted and the segmentation process is done using a Generative Adversarial Network (GAN). GAN is trained using the newly developed optimization technique known as the Autoregressive Anti Corona Virus Optimization (ARACVO) algorithm. ARACVO is created by combining the Conditional Autoregressive Value at Risk by Regression Quantiles (CAViaR) and Anti Corona Virus Optimization (ACVO) models. After retrieving the useful information for processing, the Deep Convolutional Neural Network (Deep CNN) is next used to decide whether to apply the brakes. The proposed approach improved performance by achieving maximum values of 0.911, 0.906, 0.924, and 0.933 for segmentation accuracy, accuracy, sensitivity, and specificity.