主办:陕西省汽车工程学会
ISSN 1671-7988  CN 61-1394/TH
创刊:1976年

汽车实用技术 ›› 2023, Vol. 48 ›› Issue (15): 82-86.DOI: 10.16638/j.cnki.1671-7988.2023.015.014

• 智能网联汽车 • 上一篇    

模糊逻辑在自动驾驶换道中的应用

冯虢靓雯,何亚楠*,徐马长啸,郑 好,周 莉   

  1. 陕西法士特汽车传动集团有限责任公司 智能传动研究院
  • 出版日期:2023-08-15 发布日期:2023-08-15
  • 通讯作者: 何亚楠
  • 作者简介:冯虢靓雯(1996-),女,硕士,助理工程师,研究方向为智能网联汽车决策与测试,E-mail:836741735@qq.com。 通信作者:何亚楠(1992-),女,硕士,工程师,研究方向为智能网联汽车规划,E-mail:heyanan@fastgroup.cn。

Application of Fuzzy Logic in Automatic Driving Lane Change

FENG Guoliangwen, HE Yanan* , XU Machangxiao, ZHENG Hao, ZHOU Li   

  1. Intelligent Transmission Research Institute, Shaanxi Fast Auto Drive Refco Group Company Limited
  • Online:2023-08-15 Published:2023-08-15
  • Contact: HE Yanan

摘要: 在自动驾驶过程中,自动驾驶决策系统能够根据环境物体目标提取出对本车有用的目 标车辆信息,并预测交通场景中周围车辆的运动趋势,从而为规避危险场景作出最佳决策, 保证决策换道系统的准确性和细致性。文章将模糊逻辑应用于商用车自动驾驶换道功能,作 为决策系统的输入系统,环境感知系统首先利用雷达、视觉相机、导航定位为决策系统提供 车辆以及环境的信息,随后决策系统从得到的信号中提取出对本车有用的信息,最后对目标 车辆的运动趋势进行合理预测,并将目标车辆与本车间的预测距离作为模糊逻辑系统的输入 变量,将换道概率作为输出变量,制定模糊规则,建立基于模糊逻辑的车辆换道模型。决策 后的信号和动作指令传输给主规控系统控制车辆进行换道,且这些过程无需驾驶员操作,提 高了车辆的安全性和用户的舒适性以及智能化水平。

关键词: 自动驾驶车辆;模糊逻辑;决策系统;换道模型

Abstract: In the process of autonomous driving, the autonomous driving decision-making system can extract useful information about the target vehicle according to the environmental object target and predict the movement trend of the surrounding vehicles in the traffic scene, so as to avoid the dangerous scene and make the best decision to ensure the accuracy and detail of the decision-making lane changing system. This paper applies fuzzy logic to the automatic driving lane change function in commercial vehicles. The environment perception system, as the input system of the decisionmaking system, uses radar, visual camera, navigation and positioning to provide the information of the vehicle and the environment for the decision-making system. The decision-making system extracts useful information for the vehicle from the obtained signals, makes reasonable prediction of the movement trend of the target vehicle, and takes the predicted distance between the target vehicle and this vehicle as the input variable of the fuzzy logic system. Lane change probability is taken as output variable. The fuzzy rules are formulated, and a vehicle lane change model based on fuzzy logic is established. After the decision, the signal and action instruction are transmitted to the main control system to control the vehicle for lane change, and these processes do not require the operation of the driver, improve the safety of the vehicle and the comfort of the user and the level of intelligence.

Key words: Self-driving vehicles; Fuzzy logic; Decision-making system; Lane change model