基于最优路径的智能车设计与实现  

Design and Implementation of Smart Car Based on Optimal Path

作　　者：刘博[1] 张盛兵[1] 马志强[2] 

机构地区：[1]西北工业大学计算机学院,西安710072 [2]西北工业大学自动化学院,西安710072

出　　处：《计算机测量与控制》2012年第8期2264-2266,2269,共4页Computer Measurement &Control

摘　　要：针对城市交通中车辆的智能行驶,以MC9S12XS128单片机为核心控制器,设计并实现了一种基于单目视觉的智能车最优路径控制系统;在简单模拟路况环境下,使用CCD摄像头采集道路信息,先提取二值化图像中的路径信息,再对道路中的不同路况进行分类与识别;构造特殊的路网带权有向图,使用Dijkstra算法计算两顶点间的最优路径;通过分析路径上顶点间的关系得到最优路径控制策略,进行速度和特殊转向控制;实验表明:单片机在48MHz下能够稳定地处理数据,实现了智能车点到点的最优路径自主行驶。For the intelligent driving of vehicles in city traffic, design and implement an optimal path control system based on monocular vision using MC9S12XS128 microcontroller as the core controller. In a simple simulation of road environment, collect road information using the CCD camera, first extract the path information in the binary image and then classify and identify the different intersection on the road. Construct special weighted directed graph of the road network, calculate the optimal path between points using the Dijkstra algorithm. Get the optimal path control strategy by analysing the relationship between the vertices on the path and carry out speed and special direction con- trol. The experimental results show that the mierocontroller can process data steadily and implement the optimal path autonomous driving be- tween points for smart ear in the 48MHz.

关 键 词：单目视觉 智能车 带权有向图 最优路径 

分 类 号：TP273.5[自动化与计算机技术—检测技术与自动化装置]