The invention relates to a traffic event prediction method and device for an autonomous vehicle. The method comprises the following steps: classifying a current scene according to scene information and determining all scene events and propositions in the classified scene; obtaining historical data of the scene event, determining a prior probability of the scene event and determining a calculation result of each proposition; according to the historical data and the calculation result of each proposition, obtaining a first conditional probability that each proposition is true before each scene event occurs and a second conditional probability that each proposition is true when the scene event does not occur; calculating an event occurrence probability according to the prior probability, the first conditional probability and the second conditional probability; and generating avoidance measures according to the event occurrence probability. According to the invention, the probability of occurrence of an event within a preset time period or a preset distance can be calculated according to information such as the vehicle state (vehicle speed, vehicle position, fault or not) and the environment (congestion or red light or not), and a method for avoiding an accident can be obtained, so that danger is avoided.
本发明涉及一种自动驾驶车辆交通事件预测方法及装置,包括根据场景信息对当前所处场景进行分类并确定分类后的场景下的所有场景事件和命题;获取场景事件的历史数据,确定场景事件的先验概率以及确定每个命题的计算结果;根据历史数据和每个命题的计算结果获取每个场景事件发生前的每个命题为真的第一条件概率以及场景事件未发生时每个命题为真的第二条件概率;根据先验概率、第一条件概率以及第二条件概率计算得到事件发生概率;根据事件发生概率生成规避措施。本发明可以根据自车状态(车速、车辆位置、是否故障等)和环境(是否拥堵、是否红灯)等信息计算出预设时间段或预设距离内发生事件的概率,可以获取规避事故的方法,从而避免危险。
Traffic incident prediction method and device for autonomous vehicle
一种自动驾驶车辆交通事件预测方法及装置
2021-10-22
Patent
Electronic Resource
Chinese