基于无模型自适应控制的无人驾驶汽车横向控制方法-ACSL.PDFVIP

基于无模型自适应控制的无人驾驶汽车横向控制方法 1 1 1 2 XXX XXX* XXX XXX 摘 要 本文提出了一种基于无模型自适应控制的无人驾驶汽车横向控制方案. 首先，将无人驾驶汽车循迹跟踪 控制问题转化成预瞄偏差角跟踪问题，然后基于无人驾驶汽车横向控制系统的动态线性化数据模型，设计出无模 型自适应控制算法、伪梯度估计算法和伪梯度重置算法，进而实现了自主车辆的无人驾驶. 该方法的实现仅用到 无人驾驶汽车运行时的输入输出数据，避免了对无人驾驶汽车进行复杂机理建模的难题，对于复杂的无人驾驶汽 车运行过程具有很好的自适应性，对不同的无人驾驶车辆具有较强的可移植性. 该方案已实际应用于清华大学无 人驾驶汽车实验平台，在北京市丰台区的实地测试实验、在江苏省常熟市高速路的测试以及2015 年 “中国智能 车未来挑战赛”的现场应用验证了所提方案的有效性. 关键词 无模型自适应控制，无人驾驶汽车，横向控制，预瞄偏差角 Model Free Adaptive Control Based Lateral Control of Self-driving Car 1 1 1 2 XXX XXX* XXX XXX Abstract In this paper, a control scheme based on model free adaptive control is proposed for the lateral control problem of self-driving car. First, a trajectory tracking problem for self-driving car is converted into stabilization problem concerning a proposed preview-deviation-yaw. Then, the lateral control system of self-driving car is converted into a virtual dynamical linearization data model via a novel dynamic linearization technique. After that, the model free adaptive control algorithm, and the corresponding pseudo gradient estimating algorithm, pseudo gradient resetting algorithm are designed, such that the automatic drive of the self-driving car can be realized. The implementation of the proposed method only utilizes the input and output data of our self-driving car, avoiding the complex modeling problem for self-driving car. Thus, it has good adaptability for complex operation processes of self-driving car and is also applicable to other self-driving cars. Furthermore, the proposed scheme is employed in the experiment