An autonomous vehicle's current driving strategy is determined solely by factors external to the vehicle (pedestrians, road conditions, etc.). This paper proposes "A Driving Decision Strategy(DDS) Based on Machine Learning for an Autonomous Vehicle," which determines the optimal strategy of an autonomous vehicle by analysing both external and internal factors of the vehicle. It is a solution to this problem (consumable conditions, RPM levels etc.). Autonomous vehicles can learn a genetic algorithm from sensor data stored in the cloud and use it to find the best driving strategy. Using MLP and RF neural network models, this paper tested the validity of the DDS.

Genetic Algorithm, DDS, MLP