中文摘要：

通过基于视觉的车道标志线识别系统建立智能车的期望跟踪轨迹，并将智能车运动学模型转换为链式系统模型，同时利用后推方法设计控制律，克服了采用动态反馈线性化方法设计的控制器维数较高以及滑模变结构控制器易出现高频抖振的缺点．仿真结果表明：该方法具有较好的轨迹跟踪控制效果和全局稳定性．

英文摘要：

In this paper, a vision-based lane marking detection system is adopted to establish the anticipant tracking trajectory of an intelligent vehicle and to transform the kinematic model of the intelligent vehicle into a chained one. Moreover, the backstepping method is employed to design the control rule, thus overcoming not only the defect of high dimension arising from the dynamic feedback linearization controller but also the problem of high-frequency shake existing in the sliding-mode controller. Simulated results indicate that the proposed method is of good trajectory tracking control ability and global stability.