By making transportation safer and more efficient, autonomous vehicle navigation systems are transforming the transportation industry. Autonomous cars are able to make route selections based on accurate, up-to-theminute traffic predictions, which help them avoid congestion and maximize their trip time. The use of machine learning algorithms to reliably forecast traffic conditions in real time for use in autonomous vehicle navigation is the focus of this research. Deep learning, support vector machines, and random forests are just a few examples of the machine learning models that can accurately forecast traffic conditions by mining massive datasets collected from GPS data, traffic sensors, and past trends. The suggested method incorporates these models into an autonomous vehicle navigation system that operates in real-time, enabling adaptive modifications according to the flow of traffic. We also look at how things like construction, road accidents, and weather affect the precision of traffic predictions. Based on the outcome of decreased trip time, increased safety and efficiency, results demonstrate how navigation systems supplemented with machine learning, far surpass conventional routing approaches. The study suggests that further research needs to be conducted on hybrid algorithms for better traffic prediction, and multi modal data integration to further optimize autonomous vehicle navigation and in general, machine learning presents great promise in this area.
Autonomous Vehicle Navigation Systems: Machine Learning for Real-Time Traffic Prediction
2025-02-07
501616 byte
Conference paper
Electronic Resource
English
Development of RTTI (real time traffic information) within vehicle navigation systems
IET Digital Library Archive | 2000
|Development of RTTI (real time traffic information) within vehicle navigation systems
British Library Conference Proceedings | 2000
|