摘要
基于简单视觉的缩微智能车自主驾驶行为,提出一种完全基于视觉的超车换道策略及超车开关模糊控制算法.根据检测车道线拟合出的行驶轨迹,获得车辆中心轴与行驶轨迹之间的偏移距离E及其变化率Ec,针对直道行驶和超车换道行驶采用不同的模糊转向控制算法.此外,本文通过实验研究像素点距与实际距离关系、安全超车距离与速度的关系;并通过实验验证视觉换道策略的有效性及车辆切换模糊控制算法的高效性和稳定性.
Based on the simple vision-based autonomous driving behavior of intelligent micro-vehicles, a vision-based overtaking lane-changing strategy and an overtaking switch fuzzy control algorithm are proposed. According to the wheel path fitted through the lane detection, the lateral error E representing the error between the central axis of micro-vehicle and the wheel path, and its changing rate Ec are derived. Different fuzzy steering control strategies are then proposed for straight driving and lane-changing driving, respectively. In addition, the relationship between the pixel distance and the actual distance, and the relationship between the velocity and the safe-overtaking distance are investigated through experiments. Experimental results illustrate the effectiveness of the vision-based lane-changing strategy and the efficiency and stability of the vehicle switch-fuzzy control algorithm.
出处
《信息与控制》
CSCD
北大核心
2013年第3期351-357,共7页
Information and Control
基金
清华大学校自主基金资助项目(20111081071)
关键词
视觉导航
视觉测距
超车换道
安全超车距离
模糊控制
visual navigation
visual ranging
overtaking lane-change
safe-overtaking distance
fuzzy control
