CN109709573A - 地面无人车乡村环境道路的检测途径 - Google Patents

地面无人车乡村环境道路的检测途径 Download PDF

Info

Publication number
CN109709573A
CN109709573A CN201711010728.2A CN201711010728A CN109709573A CN 109709573 A CN109709573 A CN 109709573A CN 201711010728 A CN201711010728 A CN 201711010728A CN 109709573 A CN109709573 A CN 109709573A
Authority
CN
China
Prior art keywords
point
ground
dimensional
segment
road
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201711010728.2A
Other languages
English (en)
Inventor
朱奕瑾
其他发明人请求不公开姓名
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Individual
Original Assignee
Individual
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Individual filed Critical Individual
Priority to CN201711010728.2A priority Critical patent/CN109709573A/zh
Publication of CN109709573A publication Critical patent/CN109709573A/zh
Pending legal-status Critical Current

Links

Landscapes

  • Traffic Control Systems (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

地面无人车乡村环境道路的检测途径,激光雷达数据在地面上投影的形态,每条扫描线的三维数据投影在理想的平面上是光滑的环形,检测这样的特征可以通过将扫描线投影分割成小段,计算小段间的圆滑程度;由于激光雷达数据本身含有的高斯噪声,以及乡村路面的不平整,所选取的小段分割方法必须要能包容一定程度的噪声;基于多尺度曲率计算的平面曲线分割方法,通过将曲线与不同方差的高斯核函数进行卷积,选择其中最佳的方差用于计算曲线的曲率,并且在曲线曲率最大处分割成小段;相邻线段用红蓝两种颜色表示,角点应该在黑圈内的中心处,而实际线段分割后端点位置在黑圈外。

Description

地面无人车乡村环境道路的检测途径
技术领域
本发明的自主行驶的地面无人车指的是车辆在没有人工干预和遥控的情况下,通过所装备的各种传感器获取环境信息,构建出环境的模型,并且指导无人车根据一定的规则实施下一步的行为;无人车所携带的传感器一般包括三种类型:二维传感器,包括各种相机,用于在图像二维空间中对环境进行感知理解;位姿姿态传感器,包括,惯导系统,用于定位和导航;三维传感器,包括激光雷达、立体视觉、声波雷达等等。
背景技术
对于乡村环境,路况复杂,路两边的树枝叶可能伸入道路需要无人车避让,而当两车在窄路交:时,又要求无人车能从非障碍区域越过,因此基于三维的道路准确理解对无人车下一时刻的行为规划至关重要;基于三维数据的乡村环境道路理解主要任务就是,在给定的三维数据之中,通过相关算法处理,对可通行的道路和不可通行的障碍物进行区分;目的是为无人车系统后续行为规划提供充足的可通行空同一个适用于基于三维数据的地面无人车道路检测算法一般需要具备一定要求。
发明内容
本发明的解决方案在乡村道路环境下地面颠簸起伏对三维传感器算法影响很大,容易出现将道路误检为障碍的情况导致无人车寸步难行;它的内涵相当于召回率一未被正确标记的可通行道路占总可通行道路的比率;一般情况下,准确性和鲁棒性是一对矛盾,算法越鲁棒说明算法对抗噪声能力越强,而区分噪声和信息的能力越弱,意味着准确性越低;要求所设计的算法能够在无人车行驶的环境中正确的区分可通行的道路和障碍物;它的内涵相当于正确率一被标记为可通行道路的正确率对于无人车来说,三维传感器几乎是其唯一可靠的障碍物检测传感器,因此为保证无人车的安全行驶正确率显得尤为重要。
具体实施方式
本发明实施如下,一些慢速智能移动机器人相比,地面无人车具有较高的行驶速度,三维道路检测系统必须在系统所要求的同步节拍下完成数据采集,数据转换,数据理解等任务;随着三维传感器的发展,三维数据量越来越大,尤其是线激光雷达高达每秒检测万的点的数据,需要算法在保证一定准确性和鲁棒性的情况下,尽量减少所需要的计算资源;乡村道路三维检测的另一个难点是颠簸的路面使得在结构化道路检测中使用的路面平坦的假设不再成立,那些利用路面平面性进行道路分割的算法鲁棒性变得很差;在保证路面检测准确性的情况下,提高算法的鲁棒性是乡村道路路面检测的一大挑战。

Claims (1)

1.本发明是利用三维激光雷达数据结构的特点:任意三维点与其在同一扫描线上相邻角度的点以及前后扫描线相同角度的点组成四邻域系统,可以将三维点云以无向图的方式组织起来;使用三维数据环之间的距离来确定单个三维点是否属于地面区域(三维激光雷达地面反射点在二维平面上呈现出环的样式,障碍物点的环间距要远小于地面点的间距),在遇到颠簸地面时,根据车体的姿态修正环间距的阈值;使用局部凸性分割不同物体:对于三维点用它相邻的四个点进行平面拟合,得出该点处估计平面的法向量;若相邻两个平面符合凸性质,则两个平面被归为一类;通过种子点生长的方式,找出三维场景内所有凸性质的区域,选择其中面积最大的区域作为地面。
CN201711010728.2A 2017-10-25 2017-10-25 地面无人车乡村环境道路的检测途径 Pending CN109709573A (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711010728.2A CN109709573A (zh) 2017-10-25 2017-10-25 地面无人车乡村环境道路的检测途径

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711010728.2A CN109709573A (zh) 2017-10-25 2017-10-25 地面无人车乡村环境道路的检测途径

Publications (1)

Publication Number Publication Date
CN109709573A true CN109709573A (zh) 2019-05-03

Family

ID=66252518

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711010728.2A Pending CN109709573A (zh) 2017-10-25 2017-10-25 地面无人车乡村环境道路的检测途径

Country Status (1)

Country Link
CN (1) CN109709573A (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113009453A (zh) * 2020-03-20 2021-06-22 青岛慧拓智能机器有限公司 矿山路沿检测及建图方法及装置

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113009453A (zh) * 2020-03-20 2021-06-22 青岛慧拓智能机器有限公司 矿山路沿检测及建图方法及装置

Similar Documents

Publication Publication Date Title
CA3168740C (en) Method for object avoidance during autonomous navigation
US11270457B2 (en) Device and method for detection and localization of vehicles
US10677907B2 (en) Method to determine the orientation of a target vehicle
US11530924B2 (en) Apparatus and method for updating high definition map for autonomous driving
Choi et al. Multi-target tracking using a 3d-lidar sensor for autonomous vehicles
Wijesoma et al. Road-boundary detection and tracking using ladar sensing
CN108007452B (zh) 根据障碍物更新环境地图的方法、装置及机器人
Jeong et al. Road-SLAM: Road marking based SLAM with lane-level accuracy
US8564657B2 (en) Object motion detection system based on combining 3D warping techniques and a proper object motion detection
Shim et al. An autonomous driving system for unknown environments using a unified map
CN108983781A (zh) 一种无人车目标搜索系统中的环境探测方法
Han et al. Road boundary detection and tracking for structured and unstructured roads using a 2D lidar sensor
Dickmann et al. Radar contribution to highly automated driving
CN112034479A (zh) 一种应用于煤矿井下智能巡检无人机的定位方法及系统
Li et al. A new 3D LIDAR-based lane markings recognition approach
TWI680898B (zh) 近距離障礙物之光達偵測裝置及其方法
Bernardi et al. High integrity lane-level occupancy estimation of road obstacles through LiDAR and HD map data fusion
WO2021245515A1 (en) Detection of traffic safety mirrors and navigational response
CN109709573A (zh) 地面无人车乡村环境道路的检测途径
Bayerl et al. Detection and tracking of rural crossroads combining vision and LiDAR measurements
Eraqi et al. Static free space detection with laser scanner using occupancy grid maps
Yun et al. Dynamic path planning for underwater vehicles based on modified artificial potential field method
Noaman et al. Landmarks exploration algorithm for mobile robot indoor localization using VISION sensor
Kolu et al. A mapping method tolerant to calibration and localization errors based on tilting 2D laser scanner
Raaijmakers et al. Circle detection in single-layer laser scans for roundabout perception

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
DD01 Delivery of document by public notice

Addressee: Zhu Yijin

Document name: Notification of Publication of the Application for Invention

DD01 Delivery of document by public notice
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20190503

WD01 Invention patent application deemed withdrawn after publication