基于激光雷达的托盘位姿识别算法及验证
|
摘要
托盘拾取是自动化仓储的重要环节之一,为提高叉车的托盘拾取能力,提出一种基于2-D激光雷达的托盘探测算法,实现托盘位置和姿态的识别。建立了托盘探测模型,确立了算法有效探测范围与激光点数量(分布于托盘支架正面)、托盘支架宽度和激光雷达分辨率的函数关系;通过改进的增量式直线提取算法,获取托盘姿态;根据托盘姿态,建立动态模板,以滑动窗口模式进行匹配,获取托盘位置。结果表明,有效探测范围,随激光点数量减小扩大,随托盘宽度增加而扩大,随分辨率增加而扩大;当激光扫描仪分辨率为0.33°,托盘支架宽度为90 mm时,实际探测范围符合托盘探测模型计算,x轴方向定位误差为±60 mm,y轴方向定位误差为±59 mm,托盘角度探测误差为±6°。本算法实现托盘位姿可靠识别,明确探测范围,为提高智能仓储装备拾取作业能力提供理论基础。
Pallet picking is one of the important links of automated warehousing. An algorithm was proposed for estimating the localization and angle of pallet with lake information,based on 2-D Lidar. It aims at improving the recognition pallet ability of forklift and the flexibility in automated warehousing. A detection model was built to define the geometry relationship between detection region the number of lidar point( detecting the pallet foot),the width of pallet foot and the resolution of Lidar. The algorithm extracted the lines as candidate pallet foot with the improved incremental algorithm and calculate the angle of pallet. Then the dynamic template was created and matched with sliding window,to calculated the position of the pallet. The result shows that the detect region was expend with smaller the threshold number of laser,longer the width of pallet foot and higher resolution of Lidar; the detect region met the result calculated based on the pallet detect model; error on x axis and y axis were ± 60 mm mm and ± 59 mm respectively; pallet angle error was. With the flexible pallet detecting algorithm,the requirement of localization of warehouse equipment and human was reduced and effect would be enhanced.
Pallet picking is one of the important links of automated warehousing. An algorithm was proposed for estimating the localization and angle of pallet with lake information,based on 2-D Lidar. It aims at improving the recognition pallet ability of forklift and the flexibility in automated warehousing. A detection model was built to define the geometry relationship between detection region the number of lidar point( detecting the pallet foot),the width of pallet foot and the resolution of Lidar. The algorithm extracted the lines as candidate pallet foot with the improved incremental algorithm and calculate the angle of pallet. Then the dynamic template was created and matched with sliding window,to calculated the position of the pallet. The result shows that the detect region was expend with smaller the threshold number of laser,longer the width of pallet foot and higher resolution of Lidar; the detect region met the result calculated based on the pallet detect model; error on x axis and y axis were ± 60 mm mm and ± 59 mm respectively; pallet angle error was. With the flexible pallet detecting algorithm,the requirement of localization of warehouse equipment and human was reduced and effect would be enhanced.
引文
[1]TAMBA T A,HONG B,HONG K S.A path following control of an unmanned autonomous forklift[J].International Journal of Control,Automation and Systems,2009,7(1):113-122.
[2]NYGARDS J,HOGSTROM T,WERNERSSON A.Docking to pallets with feedback from a sheet-of-light range camera[C].IEEE/RSJ International Conference on Intelligent Robots and Systems,2000:1853-1859.
[3]BELLOMO N,MARCUZZI E,BAGLIVO L,et al.Pallet pose estimation with LIDAR and vision for autonomous forklifts[J].IFAC Proceedings Volumes,2009,42(4):612-617.
[4]WALTER M R,FRIEDMAN Y,ANTONE M,ET Al.Appearance-based object reacquisition for mobile manipulation[C].IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops(CVPRW),2010:1-8.
[5]WALTER M R,ANTONE M,EKAPOL C,et al.A situationally aware voice-commandable robotic forklift working alongside people in unstructured outdoor environments[J].Journal of Field Robotics,2015,32(4):590-628.
[6]LECKING D,WULF O,VIERECK V.The RTS-STILL robotic fork-lift:Variable pallet pick-up and 3D localization in industrial environments[J].European Robotic Network(EURON),2006.
[7]AREF M M,GHABCHELOO R,KOLU A,et al.A multistage controller with smooth switching for autonomous pallet picking[C].IEEE International Conference on Robotics and Automation(ICRA),2016:2535-2542.
[8]SEELINGER M,YODER J.Automatic visual guidance of a forklift engaging a pallet[J].Robotics and Autonomous Systems,2006,54(12):1026-1038.
[9]BYUN S,KIM M.Real-time positioning and orienting of pallets based on monocular vision[C].20th IEEE International Conference on Tools with Artificial Intelligence,2008:505-508.
[10]VARGA R,NEDEVSCHI S.Vision-based autonomous load handling for automated guided vehicles[C].IEEE International Conference on Intelligent Computer Communication and Processing(ICCP),2014:239-244.
[11]CINTAS R,MANSO L J,PINERO L,et al.Robust behavior and perception using hierarchical state machines:A pallet manipulation experiment[J].Journal of Physical Agents,2011,5(1):35-44.
[12]SPAMPINATO G,LIDHOLM J,ASPLUND L,et al.Stereo vision based navigation for automated vehicles in industry[C].IEEE Conference on Emerging Technologies&Factory Automation,2009:1-4.
[13]郑芳,李赣华,蔡宣平.基于激光传感器的统计特征提取和误差分析[J].红外与激光工程,2006,35(6):705-708.ZHENG F,LI G H,CAI X P.Statistical characteristics detection and error analysis of LMS[J].Infrared and Laser Engineering,2006,35(6):705-708.
[14]晓东,刘文耀,金月寒,等.嵌入式DSP激光雷达距离图像处理系统[J].仪器仪表学报,2005,26(10):1044-1046.WANG X,LIU W Y,JIN Y H,et al.An embedded DSP system of laser radar range image processing[J].Chinese Journal of Scientific Instrument,2005,26(10):1044-1046.
[15]钱晓明,张浩,王晓勇,等.基于激光扫描匹配的移动机器人相对定位技术研究[J].农业机械学报,2016,47(3):14-21.QIAN X M,ZHANG H,WANG X Y,et al.Relative localization technology for mobile robot based on laser scan matching[J].Transactions of Chinese Society for Agricultural Machinery,2016,47(3):14-21.
[16]NGUYEN V,MARTINELLI A,TOMATIS N,et al.A comparison of line extraction algorithms using 2D rangedata for indoor mobile robotics[J].Autonomous Robots,2007,23(2):97-111.
[17]王亚雄,康峰,李文彬,等.基于2D激光探测的立木胸径几何算法优化[J].农业机械学报,2016,47(6):290-296.WANG Y X,KANG F,LI W B,et al.Optimization of geometry algorithm for DBH of standing tree on 2D laser detection[J].Transactions of the Chinese Society for Agricultural Machinery,2016,47(6):290-296.
[18]刘洞波,刘国荣,胡慧,等.基于激光测距的温室移动机器人全局定位方法[J].农业机械学报,2010,41(5):158-163.LIU D B,LIU G R,HU H,et al.Method of mobile robot global localization based on laser range finder in greenhouse[J].Transactions of the Chinese Society for Agricultural Machinery,2010,41(5):158-163.
[19]侯维岩,张利伟,党蟒,等.一种基于图像处理的棒材计数测量系统的设计与实现[J].仪器仪表学报,2013,34(5):1100-1106.HOU W Y,ZHANG L W,DANG M,et al.Design and implementation of bar count measurement system based on image processintang[J].Chinese Journal of Scientific Instrument,2013,34(5):1100-1106.
[20]吴晓军,邹广华.基于边缘几何特征的高性能模板匹配算法[J].仪器仪表学报,2013,34(7):1462-1469.WU X J,ZOU G H.High performance template matching algorithm based on edge geometric features[J].Chinese Journal of Scientific Instrument,2013,34(7):1462-1469.
[21]陈硕,骆腾斌,刘丰,等.应用于水表检定的机器视觉技术研究[J].电子测量与仪器学报,2017,31(1):144-149.CH EN SH,LUO T B,LIU F,et al.Research on m achine vision technology applied in water m eter verification[J].Journal of Electronic Measurement and Instrumentation,2017,31(1):144-149.
[22]霍迎秋,秦仁波,邢彩燕,等.基于CUDA的并行Kmeans聚类分割算法优化[J].农业机械学报,2014,45(11):47-74.HUO Y Q,QIN R B,HE C Y,et al.CUDA-based parallel k-means clustering algorithm[J].Transactions of the Chinese Society for Agricultural Machinery,2014,45(11):47-74.
[2]NYGARDS J,HOGSTROM T,WERNERSSON A.Docking to pallets with feedback from a sheet-of-light range camera[C].IEEE/RSJ International Conference on Intelligent Robots and Systems,2000:1853-1859.
[3]BELLOMO N,MARCUZZI E,BAGLIVO L,et al.Pallet pose estimation with LIDAR and vision for autonomous forklifts[J].IFAC Proceedings Volumes,2009,42(4):612-617.
[4]WALTER M R,FRIEDMAN Y,ANTONE M,ET Al.Appearance-based object reacquisition for mobile manipulation[C].IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops(CVPRW),2010:1-8.
[5]WALTER M R,ANTONE M,EKAPOL C,et al.A situationally aware voice-commandable robotic forklift working alongside people in unstructured outdoor environments[J].Journal of Field Robotics,2015,32(4):590-628.
[6]LECKING D,WULF O,VIERECK V.The RTS-STILL robotic fork-lift:Variable pallet pick-up and 3D localization in industrial environments[J].European Robotic Network(EURON),2006.
[7]AREF M M,GHABCHELOO R,KOLU A,et al.A multistage controller with smooth switching for autonomous pallet picking[C].IEEE International Conference on Robotics and Automation(ICRA),2016:2535-2542.
[8]SEELINGER M,YODER J.Automatic visual guidance of a forklift engaging a pallet[J].Robotics and Autonomous Systems,2006,54(12):1026-1038.
[9]BYUN S,KIM M.Real-time positioning and orienting of pallets based on monocular vision[C].20th IEEE International Conference on Tools with Artificial Intelligence,2008:505-508.
[10]VARGA R,NEDEVSCHI S.Vision-based autonomous load handling for automated guided vehicles[C].IEEE International Conference on Intelligent Computer Communication and Processing(ICCP),2014:239-244.
[11]CINTAS R,MANSO L J,PINERO L,et al.Robust behavior and perception using hierarchical state machines:A pallet manipulation experiment[J].Journal of Physical Agents,2011,5(1):35-44.
[12]SPAMPINATO G,LIDHOLM J,ASPLUND L,et al.Stereo vision based navigation for automated vehicles in industry[C].IEEE Conference on Emerging Technologies&Factory Automation,2009:1-4.
[13]郑芳,李赣华,蔡宣平.基于激光传感器的统计特征提取和误差分析[J].红外与激光工程,2006,35(6):705-708.ZHENG F,LI G H,CAI X P.Statistical characteristics detection and error analysis of LMS[J].Infrared and Laser Engineering,2006,35(6):705-708.
[14]晓东,刘文耀,金月寒,等.嵌入式DSP激光雷达距离图像处理系统[J].仪器仪表学报,2005,26(10):1044-1046.WANG X,LIU W Y,JIN Y H,et al.An embedded DSP system of laser radar range image processing[J].Chinese Journal of Scientific Instrument,2005,26(10):1044-1046.
[15]钱晓明,张浩,王晓勇,等.基于激光扫描匹配的移动机器人相对定位技术研究[J].农业机械学报,2016,47(3):14-21.QIAN X M,ZHANG H,WANG X Y,et al.Relative localization technology for mobile robot based on laser scan matching[J].Transactions of Chinese Society for Agricultural Machinery,2016,47(3):14-21.
[16]NGUYEN V,MARTINELLI A,TOMATIS N,et al.A comparison of line extraction algorithms using 2D rangedata for indoor mobile robotics[J].Autonomous Robots,2007,23(2):97-111.
[17]王亚雄,康峰,李文彬,等.基于2D激光探测的立木胸径几何算法优化[J].农业机械学报,2016,47(6):290-296.WANG Y X,KANG F,LI W B,et al.Optimization of geometry algorithm for DBH of standing tree on 2D laser detection[J].Transactions of the Chinese Society for Agricultural Machinery,2016,47(6):290-296.
[18]刘洞波,刘国荣,胡慧,等.基于激光测距的温室移动机器人全局定位方法[J].农业机械学报,2010,41(5):158-163.LIU D B,LIU G R,HU H,et al.Method of mobile robot global localization based on laser range finder in greenhouse[J].Transactions of the Chinese Society for Agricultural Machinery,2010,41(5):158-163.
[19]侯维岩,张利伟,党蟒,等.一种基于图像处理的棒材计数测量系统的设计与实现[J].仪器仪表学报,2013,34(5):1100-1106.HOU W Y,ZHANG L W,DANG M,et al.Design and implementation of bar count measurement system based on image processintang[J].Chinese Journal of Scientific Instrument,2013,34(5):1100-1106.
[20]吴晓军,邹广华.基于边缘几何特征的高性能模板匹配算法[J].仪器仪表学报,2013,34(7):1462-1469.WU X J,ZOU G H.High performance template matching algorithm based on edge geometric features[J].Chinese Journal of Scientific Instrument,2013,34(7):1462-1469.
[21]陈硕,骆腾斌,刘丰,等.应用于水表检定的机器视觉技术研究[J].电子测量与仪器学报,2017,31(1):144-149.CH EN SH,LUO T B,LIU F,et al.Research on m achine vision technology applied in water m eter verification[J].Journal of Electronic Measurement and Instrumentation,2017,31(1):144-149.
[22]霍迎秋,秦仁波,邢彩燕,等.基于CUDA的并行Kmeans聚类分割算法优化[J].农业机械学报,2014,45(11):47-74.HUO Y Q,QIN R B,HE C Y,et al.CUDA-based parallel k-means clustering algorithm[J].Transactions of the Chinese Society for Agricultural Machinery,2014,45(11):47-74.