AUTHOR=hu wen , kang longyun , yu zongguang 

TITLE=A Possibilistic Risk Assessment Framework for Unmanned Electric Vehicles With Predict of Uncertainty Traffic

JOURNAL=Frontiers in Energy Research

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2022.888298

DOI=10.3389/fenrg.2022.888298

ISSN=2296-598X

ABSTRACT=At present, electric vehicles have entered a stage of rapid development. With the rapid development of artificial intelligence technology and the combination of electric vehicles, almost most electric vehicles sold in China are equipped with automatic driving technology to achieve safer and more energy-saving driving. In order to solve the problem of anti-collision of self-driving Smart EV(Electric Vehicles) under complex Traffic, especially at intersections, most of the existing methods make sequential prediction for the driving level of vehicles, and it is difficult to deal with the sudden change of intention of other vehicles. Therefore, a collision risk assessment framework based on other vehicles' trajectory prediction is proposed. The framework integrates the solutions of other vehicles' expected path planning, uncertainty description of driving process, trajectory change caused by obstacle intrusion, etc., and adopts Gaussian mixture model to evaluate the risk according to the probability of collision between other vehicles and unmanned self-owned vehicles. It realizes the real-time evaluation of the object, position and probability of collision in the future and corrects the decision-making and trajectory planning of the vehicle. After verification, it can effectively solve the decision-making planning problem of autonomous vehicles under complex traffic flow conditions in complex scenes.