车辆感知与定位研究——第29届国际智能车大会综述  

A Study of Vehicle Perception and Localization: An Overview of the 29^(th) IEEE Intelligent Vehicles Symposium

作　　者：陶倩文 胡钊政[1,2] 蔡浩 黄刚[1,2] 王相龙[1,2] TAO Qianwen;HU Zhaozheng;CAI Hao;HUANG Gang;WANG Xianglong(Intelligent Transportation Systems Research Center,Wuhan University of Technology,Wuhan 430063,China;School of Energy and Power Engineer,Wuhan University of Technology,Wuhan 430063,China;School of Computer Science and Technology,Wuhan University of Technology,Wuhan 430063,China)

机构地区：[1]武汉理工大学智能交通系统研究中心,武汉430063 [2]武汉理工大学能动学院,武汉430063 [3]武汉理工大学计算机学院,武汉430063

出　　处：《交通信息与安全》2019年第2期1-9,共9页Journal of Transport Information and Safety

基　　金：国家自然科学基金项目(51679181);湖北省技术创新项目重大专项(2016AAA007);湖北省留学人员科技活动项目择优资助经费(2016-12);中央高校基本科研业务费专项资金(2018III062GX)资助

摘　　要：近年来,由于摄像头、激光雷达等传感器的更新换代和大数据、人工智能等高科技在汽车领域的广泛应用,汽车智能化的程度越来越高,智能汽车的整体制造近在眼前。第29届国际智能车大会(The 29^(th) IEEE Intelligent Vehicles Symposium, Ⅳ 2018)旨在促进全球智能汽车技术发展和国际汽车领域的交流合作。会议整体分为智能车的感知、决策、路径规划和控制等主题,探讨了当前智能车领域的最新技术动态以及未来发展前景。综述了会议报告的热点,从传感器数据融合、智能车定位与导航、激光雷达感知与定位和目标检测与识别等方面对车辆感知与定位技术的发展状态进行了分析,展望了未来车辆感知与定位研究的发展趋势,提出了深度学习方法与基于激光雷达的定位方法是未来车辆感知与定位可能的研究热点。In recent years,sensors such as cameras and LiDAR are gradually upgrading and updating,high technologies such as big data and artificial intelligence have been widely used in automotive field,and level of vehicle intelligence is much high.As a result,the overall manufacturing of intelligent vehicle is close at hand.The 29 th IEEE Intelligent Vehicles Symposium(Ⅳ2018)is aimed to promote exchanges and cooperation in the development of global intelligent vehicle technology and international automotive sector.The whole conference is divided into several major topics,such as perception,decision making,path planning,and control of intelligent vehicles.It also discusses the latest technological trends and future development prospects of intelligent vehicles.This paper summarizes hot issues of conference reports,analyzes development status and trends of perception and localization technology for vehicles from the aspects of sensor data fusion,intelligent vehicle localization and navigation,LiDAR perception and localization,and target detection and recognition.It forecasts trends of vehicle perception and localization studies in the future,and proposes that deep learning methods and LiDAR based localization methods are potential hotspots for vehicle perception and localization studies in the future.

关 键 词：交通信息 智能车 车辆定位 车辆感知 Ⅳ2018 

分 类 号：U471.15[机械工程—车辆工程]