| In recent years,with the rapid development of the global economy,the number of vehicles has increased rapidly.At the same time,the incidence of traffic accidents is increasing.According to the traffic accident statistics,the human factors play an important role in the cause of traffic accidents.When the driver is making drive decision,if he can perceive the real-time information of the surrounding vehicles accurately,such as vehicle position,speed,direction of travel,he will make the correct judgment and operation in the first time and avoid the occurrence of traffic accidents.However,when the driver is driving,his information processing capability is limited,and he is unable to get multi-source data such as people,car,road and environment,which result that sometimes the driver cannot accurately and quickly determine the vehicle environment and even result traffic accidents.Therefore,it is critical to ensure the accurate and fast driving decision and the traffic safety,that intelligently perceive vehicle environment information and process the information and help the driver to determine the optimal driving behavior,which gives drivers driving assistant decision-making.Recently there are many studies on vehicle environment perception and driving decision-making behavior,but it is still a challenging research direction that how to ensure the access to vehicle information accurately and comprehensively and how to reduce the time of the driving decision-making behavior.For the error and time delay problem when the past algorithm of driving behavior decision obtain data,Having realized the vehicle network multicast communication based on the WAVE protocol in our prior research,we realized the fast data exchanged at application level among the vehicles to ensure the comprehensiveness and accuracy of data.After realizing the fast and reliable data exchange based on WAVE protocol,we design the the intelligent decision system,which include early multi-vehicle warning and Q learning algorithm with neural network,to process the information of data exchanged.The intelligent decision system is tested in Repast J simulation environment,the results show that it can realize communication among vehicles fast and reliably;and the data acquisition time and the decision time is short,which only have 0.5s total delay time,and it can provide a real-time optimal decision for the driver in order to assist the drivers to drive safely. |
