Article
A Predictive Machine Learning Approach for Autonomous Vehicle Driving Decisions
Autonomous vehicles require intelligent decision-making systems to ensure safe, efficient, and reliable driving in dynamic traffic environments. Traditional autonomous driving approaches primarily rely on external factors such as road conditions, traffic flow, and the behavior of surrounding vehicles. However, these methods often overlook the influence of internal vehicle parameters that can significantly impact driving performance and decision quality. To address this limitation, this study proposes an Intelligent Driving Decision Strategy (DDS) based on Machine Learning for autonomous vehicles. The proposed DDS framework integrates both internal and external driving factors to generate optimal driving decisions in real time. Sensor data collected from the vehicle and its environment are processed and supplied to a Genetic Algorithm (GA), which identifies optimal parameter values and enhances prediction accuracy. The optimized features are then utilized by the DDS model to support intelligent decision-making and route selection. To evaluate its effectiveness, the proposed DDS framework is compared with widely used machine learning techniques, including Random Forest (RF) and Multi-Layer Perceptron (MLP). Experimental results demonstrate that the DDS approach achieves higher prediction accuracy, improved decision quality, and faster convergence than the benchmark models. The findings indicate that the integration of genetic optimization with machine learning significantly enhances autonomous vehicle decision-making capabilities, making the proposed DDS framework a promising solution for next generation intelligent transportation systems.
Full Text Attachment
