A New Algorithm of the Best Path Selection Based on Machine Learning

Abstract

This paper proposes and designs a best path selection algorithm, which can solve the problem of path planning for intelligent driving vehicles in the case of restricted driving, traffic congestions and accidents. We tried to solve the problem under these emergency situations in path planing process for there's no driver in intelligent driving vehicle. We designed a new method of the best path selection with length priority based on the prior knowledge applied reinforcement learning strategy, and improved the search direction setting of A* shortest path algorithm in the program. This best path planing algorithm can effectively help different types of intelligent driving vehicles to select the best path in the traffic network with limited height, width and weight, accidents and traffic jams. Through simulation experiments and practical test, it is proved that the proposed algorithm has good stability, high efficiency and practicability.

Keywords

• Reinforcement learning
• intelligent driving
• path planning
• shortest path algorithm