[1]李盛辉,夏春华,姬长英,等.自主导航农业车辆的全景视觉同时定位与地图创建[J].江苏农业学报,2017,(03):598-609.[doi:doi:10.3969/j.issn.1000-4440.2017.03.017]
 LI Sheng-hui,XIA Chun-hua,JI Chang-ying,et al.Simutaneous localization and mapping for autonomously-navigating agricultural vehicle based on panoramic vision[J].,2017,(03):598-609.[doi:doi:10.3969/j.issn.1000-4440.2017.03.017]
点击复制

自主导航农业车辆的全景视觉同时定位与地图创建()
分享到:

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2017年03期
页码:
598-609
栏目:
耕作栽培·资源环境
出版日期:
2017-06-30

文章信息/Info

Title:
Simutaneous localization and mapping for autonomously-navigating agricultural vehicle based on panoramic vision
作者:
李盛辉1夏春华2;3姬长英3周俊3田光兆3
(1.南京理工大学紫金学院,江苏南京210023;2.农业部南京农业机械化研究所,江苏南京210014;3.南京农业大学工学院,江苏南京210031)
Author(s):
LI Sheng-hui1XIA Chun-hua2;3JI Chang-ying3ZHOU Jun3TIAN Guang-zhao3
(1.Zijin College, Nanjing University of Science and Technology, Nanjing 210023, China;2.Nanjing Research Institute for Agricultural Mechanization, Ministry of Agriculture, Nanjing 210014, China;3.College of Engineering, Nanjing Agricultural University, Nanjing 210031, China)
关键词:
全景视觉同时定位与地图创建农业车辆惯性测量单元自主导航
Keywords:
panoramic visionSLAMagricultural vehicleinertial measurement unitautonomous navigation
分类号:
TP23
DOI:
doi:10.3969/j.issn.1000-4440.2017.03.017
文献标志码:
A
摘要:
为更好地实现在实际农业作业环境下智能农业车辆的自主导航,提出了基于全景视觉的同时定位与地图创建方法(PV-SLAM)。首先对惯性测量单元(IMU)的姿态进行了解算分析,并设计实现了惯性测量单元的硬件电路模块。其次研究建立了农业车辆运动模型和全景视觉系统观测模型。然后将多目全景视觉(PV)和惯性测量单元(IMU)结合,采用扩展卡尔曼滤波(EKF),实现了自主导航农业车辆的PV-SLAM过程,并具体分析阐释了算法实现流程和步骤。试验结果表明,相较传统视觉SLAM算法,本研究提出的PV-SLAM方法,在较少或无固定路标情况下,获取的环境路标数平均增加802%,成功率平均提高158个百分点,在x和y方向的平均精度分别提高353%和378%,定位平均精度提高362%。PV-SLAM能较准确完整地提取环境路标信息,且对环境固定路标的依赖较小,因此在实际农业路径作业中运行效果较好。
Abstract:
Simutaneous localization and mapping based on panoramic vision(PV-SLAM) was developed for the autonomous navigation of agricultural vehicles. Firstly, the principle of inertial navigation system (INS) was analyzed to design the hardware circuit module of inertial measurement unit (IMU). Secondly, the motion model of agricultural vehicle and the observation model of panoramic vision system were established. Thirdly, the panoramic vision (PV) was combined with IMU and Extended Kalman Filtering (EKF) to realize the PV-SLAM process for autonomously navigating agricultural vehicles. Compared with traditional visual SLAM (vSLAM), the number of landmarks was averagely increased by 80.2%, and the success rate was increased by 15.8% using PV-SLAM, under the condition of little or no fixed landmarks. The average accuracies on x and y directions were enhanced by 35.3% and 37.8% respectively using PV-SLAM method. To conclude, PV-SLAM could perform better in agricultural work owing to its more accurate extraction of enviromental landmarks and less dependence on fixed landmarks.

参考文献/References:

[1]SMITH R C,CHEESEMAN P.On the representation and estimation of spatial uncertainty[J].The International Journal of Robotics Research,1986,5(4):56-68.
[2]SE S,LOWE D,LITTLE J.Mobile robot localization and mapping with uncertainty using scale-invariant visual landmarks[J].The International Journal of Robotics Research,2002,21(8):735-758.
[3]DAVISON A J,REID I D,MOLTON N D,et al.MonoSLAM: real-time single camera SLAM[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(6):1052-1067.
[4]DAVISON A J,MURRAY D W.Simultaneous localization and map-building using active vision[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(7):865-880.
[5]CIVERA J,DAVISON A J,MONTIEL J M M.Inverse depth parametrization for monocular SLAM[J].IEEE Transactions on Robotics,2008,24(5):932-945.
[6]CIVERA J,GRASA O G,DAVISON A J,et al.1-Point RANSAC for extended Kalman filtering: Application to real-time structure from motion and visual odometry[J].Journal of Field Robotics,2010,27(5):609-631.
[7]STRASDAT H,MONTIEL J M M,DAVISON A J.Visual SLAM:why filter?[J].Image and Vision Computing,2012,30(2):65-77.
[8]MARKS T K,HOWARD A,BAJRACHARYA M,et al.Gamma-SLAM: visual SLAM in unstructured environments using variance grid maps[J].Journal of Field Robotics,2009,26(1):26-51.
[9]GUIVANT J E,NEBOT E M.Optimization of the simultaneous localization and map-building algorithm for real-time implementation[J].IEEE Transactions on Robotics and Automation,2001,17(3):242-257.
[10]KONOLIGE K,AGRAWAL M.Frame SLAM:From bundle adjustment to real-time visual mapping[J].IEEE Transactions on Robotics,2008,24(5):1066-1077.
[11]庄严,王伟,王珂,等.移动机器人基于激光测距和单目视觉的室内同时定位和地图构建[J].自动化学报,2005,31(6):925-933.
[12]梁明杰,闵华清,罗荣华.基于图优化的同时定位与地图创建综述[J].机器人,2013,35(4):500-512.
[13]季秀才,郑志强,张辉.SLAM 问题中机器人定位误差分析与控制[J].自动化学报,2008,34(3):323-330.
[14]祝继华,郑南宁,袁泽剑,等.基于 ICP 算法和粒子滤波的未知环境地图创建[J].自动化学报,2009,35(8):1107-1113.
[15]LI M,IMOU K,WAKABAYASHI K,et al.Review of research on agricultural vehicle autonomous guidance[J].International Journal of Agricultural and Biological Engineering,2009,2(3):1-16.
[16]MIZUSHIMA A,ISHII K,NOGUCHI N,et al.Development of a low-cost attitude sensor for agricultural vehicles [J].Computers and Electronics in Agriculture,2011,76(2):198-204.
[17]姬长英,周俊.农业机械导航技术发展分析[J].农业机械学报,2014,45(9):44 -54.
[18]刘沛,陈军,张明颖.基于激光导航的果园拖拉机自动控制系统[J].农业工程学报,2011,27(3):196-199.
[19]李明,李旭,孙松林,等.基于全方位视觉传感器的农业机械定位系统[J].农业工程学报,2010,26(2):170-174.
[20]张闻宇,丁幼春,王雪玲,等.基于SVR逆向模型的拖拉机导航纯追踪控制方法[J].农业机械学报,2016,47(1):29-36.
[21]孟庆宽,仇瑞承,张漫,等.基于改进粒子群优化模糊控制的农业车辆导航系统 [J].农业机械学报,2015,46(3):29-36.
[22] DURRAN-WHYTE H,BAILEY T.Simultaneous localization and mapping:part 1[J].IEEE Robotics and Automation Magazine,2006,13(2):99-108.
[23] DURRAN-WHYTE H,BAILEY T.Simultaneous localization and mapping:Part 2[J].IEEE Robotics and Automation Magazine,2006,13(2):108-117.
[24]DISSANAYAKE M,NEWMAN P,CLARK S,et al.A solution to the simultaneous localization and map building (SLAM) problem[J].IEEE Transactions on Robotics and Automation,2001,17(3):229-241.
[25]KALMAN R E.A new approach to linear filtering and prediction problems[J].Journal of Basic Engineering,1960,82(1):35-45.

备注/Memo

备注/Memo:
收稿日期:2016-12-03 基金项目:江苏高校“青蓝工程”项目;江苏省高校自然科学研究项目(15KJD210002) 作者简介:李盛辉(1984-),男,浙江舟山人,博士,讲师,主要从事农业机器人视觉和导航技术研究。(E-mail)lshhui2006@163.com
更新日期/Last Update: 2017-06-29