基于信息融合的汽车防撞决策系统研究

研究并提出了基于多传感器信息融合的动态目标跟踪算法来实现防撞系统的信息获取，并引入预测残留误差来修正跟踪残留误差不能完全反映不可预测的信息所带来的误差；研究了驾驶过程状态信息的表达方法，建立了汽车一环境状态特征模型，描述了汽车在行驶过程中时变动态的驾驶状态。在此基础之上，利用模糊积分方法融合多种相关信息，确定汽车应采用的安全运行模式，实现主动安全防撞决策。

A Study on the System of Decision-making for Vehicle Collision Avoidance Based on Information Fusion

An algorithm for knowledge acquirement of the collision avoidance system based on dynamic target tracking with the method of multisensor information fusion is presented in this paper, and predicted residual error is introduced to modify the error caused by the unpredicted information that is not represented completely by residual track error. This paper also studies the representation approaches of state information during driving and establishes vehicle-surroundings state feature model to illustrate the variable and dynamic state of running vehicles. Then, a pertinent information fusion method based on fuzzy integral is presented, and it can make a decision for traveling model and realize active safety.