Machine Learning Based Decision-Making Framework for Autonomous Driving

Autonomous vehicles represent a significant technological advancement poised to revolutionize transportation systems worldwide. A critical aspect of Autonomous vehicles lies in their decision-making capabilities, wherein they must navigate complex environments while ensuring passenger safety and adhering to legal and ethical guidelines. The driving style of a moving, autonomous vehicle that is not totally determined by external factors (such as pedestrian traffic, road conditions, etc.) ignoring the state of the interior of the car. In order to determine the optimal approach for an autonomous car, this paper suggests “A Driving Decision Strategy (DDS) In light of ML for an Autonomous Vehicle,” which takes into account both external and internal vehicle components. The advent of autonomous vehicles has brought about a paradigm shift in transportation, promising safer and more efficient journeys. Central to the effectiveness of these vehicles is the decision-making process that governs their actions in real-world scenarios. In this research, we investigate and compare three prominent machine learning approaches Multilayer Perceptron (MLP), Genetic Algorithm (GA), and Random Forest Classifier (RFC) to determine the optimal decision-driving strategy for autonomous vehicles.