苹果采摘机器人视觉识别与路径规划方法研究
|
摘要
为准确有效的识别树冠苹果、实现机器人采摘前期行内可疑障碍物的检测，提供对采摘作业时的路径规划技术的理论支持，研究苹果采摘机器人的视觉识别与路径规划方法，对于提高苹果采摘机器人的采摘效率和可靠性，提升农业装备的智能化采摘水平，有十分重要的现实意义和广阔的应用前景。
本文针对当前存在的苹果采摘机器人的视觉识别和路径规划方法的关键问题，即对非结构化复杂环境下的树冠苹果识别、行间可行走区域可疑障碍物的检测，无学习机制的基于生物刺激神经网络的全局全覆盖最优路径规划、基于Q学习机制的最优安全路径规划展开了研究，利用Matlab2010a在Windows7环境下对提出的方法进行了编程验证。完成的主要工作和结果如下：
（1）针对自然环境下农业图像的非结构化特点，研究并提出了结合a*颜色模糊判决的L*a*b*检测方法。树冠苹果的检测结果表明，若苹果呈10%以上的红色，尽管有阴影，均能达到100%的有效检测；同时园区行内植草的障碍物检测结果也表明，若行内大部背景呈现绿色，尽管有树干、树枝，也能实现100%的有效检测植草背景的行内障碍物，背景的灰度级接近0，目标呈现高亮。
（2）研究并提出了基于最大熵理论分割自然环境下的灰度图像。测试结果表明，运用Renyi熵分割树冠苹果图像，运行速度快，约为16ms；结合优化遗传算法的模糊二维熵的阈值分割方法，能有效分割行内障碍物灰度图像，与图像大小、检测目标数量无关，背景和目标分割清晰、纯净，且运算速度较快（34-36ms）,可满足实时性要求。
（3）研究并提出了基于连通域质心和圆度等果形特征提取方法。测试结果表明，自然环境下拍摄的180幅树冠苹果图像，除7幅图像因曝光剧烈使其红色成分未达到10%而导致检测与识别失败外，其余173幅各类复杂环境下的苹果图像均能有效识别，识别率为96.1%，为果实的检测与识别提供了新的方法。同时针对行内障碍物检测时出现的树枝、树干粘连现象，提出了结合数学形态学滤除连通区域周长与面积之比大于0.375的粘连区域，并在98幅植草背景的行内图像中，障碍物检测成功率为96.9%。
（4）针对种植园区行间呈现行列平行的特点，研究并提出了基于生物刺激神经网络的“之”字型全覆盖作业的全局最优路径规划。静态复杂环境以及动态随机环境下的模拟测试表明，该方法的运算时间约为50ms，通过构建离散化环境拓扑地图，采用不完整约束的运动学模型，地图中未采摘位置的神经元活动性能引导机器人到达最终指定位置，整个过程无需学习、普适性高、计算量小、转向控制少，可适用于各类复杂环境下的路径规划或目标追踪。
（5）针对苹果采摘机器人的作业环境随时发生变化导致设计者无法真正理解机器人的作业环境，为确保机器人能安全作业或行走，研究并设计了基于Q学习的机器人避障策略、路径探索和学习机制。已知静态环境和未知环境的模拟测试表明，在预估静态障碍物和随机障碍物数量均小于10的园区环境，机器人经过约为10min的学习，均能找出以指导机器人从起始点到最终指定位置的最优安全路径。Q学习方法与环境模型无关，适用于不确定环境下的路径或轨迹规划以及复杂控制，提高了机器人应对突发事件的适应能力。和其它学习方法一样，唯一缺陷是学习阶段略显耗时。
To identify the apple fruits in tree canopies effectively and precisely, to detect theobstacles occurred between lines in an orchard at the walking forward direction of robotbefore being picking, and to support methodologically the path planning technology whileapple-picking-robot being operated, the study on visual identification and path planning hassignificant effect and potential practical value on improving the reliability and pickingefficiency of the apple-picking-robot, and on promoting the intelligently picking level ofagricultural equipment.
To solve the key points of visual identification and path planning for apple-picking-robot,this dissertation focused on apple in canopies recognition under a non-structured naturalenvironment, on uncertain obstacle detection at the walking forward direction between lines,on completely coverage path planning with non-learning mechanism bio-inspired neuralnetwork-based and on path planning with Q-learning mechanism. The proposed approacheswere implemented and verified using Matlab2010a in Window7. In this study, the maincontents and original results were described as follows.
(1) A novel approach to detect natural images in an unstructured canopies with fuzzycolor judgment and L*a*b*color space was proposed. The experiments on apple detection incanopies showed that if apples emerged red over10%even with some shades, they could beeffectively and totally detected; and the experiments on uncertain obstacles detection ingrass-planted orchard also revealed that if most the background appeared green even withsome branches and trunks, the obstacles could be effectively and totally detected within lines;the grey levels of the background could be close to zero, and the object could be highlightedafter completion of a*component conversion into gray image in L*a*b*.
(2) A novel thresholding method based on maximum entropy theory was proposed tosegment the apple gray-scale image after the completion of gray image conversion. Theexperiments showed that the running time of segmentation on apple gray image with Renyientropy theory was about16milliseconds, and of segmentation on obstacle image with fuzzy2D entropy with optimized genetic algorithm about34-36milliseconds, which could segmentthe object from background effectively and clearly, be regardless of the size of image andnumber of objects detected, and satisfy the real-time requirements of picking robot.
(3) A new apple shape features extraction method with the centroid and roundness ofconnected regions was proposed. The experiments verified that these proposed approachescould effectively recognize apple from173images in tree canopies under a complexenvironment, other7images failed for the reason that apples emerged red less than10%withserver light exposure, and the recognition rate was96.1%, which could provide a new trial forthe fruit detection and recognition. A new filtering method with mathematical morphologywas proposed to eliminate the sticky connected regions of branches and trunks using the ratiobetween perimeter and area of the connected regions over0.375, and the obstacle detectionratio was96.9%in the experiments of98images of grass-planted orchard.
(4) A novel global path planning of zigzag complete coverage approach based onbio-inspired neural network was proposed according to the characteristic of parallel plantinglines. The experiments under static known and dynamic unknown environments verified thatthe activity of neurons located at unpicked area could all along attract the robot until the robotreached at the appointed position after the completion of construction of discretizedtopological map using non-holonomic constraint kinematics. The running time for pathproducing was about50milliseconds. The whole planning process need not learn, and hashigh universality, lower running cost, less turn control, and could be suitable for path planningor target tracing under complex environments.
(5) A novel apple-picking-robot with Q-learning mechanism was designed to ensurerobot moving or working safely including the design of avoidance of obstacles, and pathexploring policies and learning mechanisms, while the operating environment was changed sorandomly and abruptly as that the designer could not understand the whole environmententirely. The experiments under static known and completely unknown environments verifiedthat the new robot could find the prior and safe path from the starting point to appointed point,which could guide the new robot move towards after the completion of10minutes’ learningwhile the pre-estimated obstacles number including static and random obstacles was no morethan10. The Q-learning method was regardless of environment, and suitable for path ortrajectory planning and complex control under uncertain or unknown environments, and couldpromote the adaptability of robot to process the abrupt incidents. Like other learningmethodologies, the only disadvantage was that the learning process was a littletime-consuming for the reason of high-dimension data disaster.
本文针对当前存在的苹果采摘机器人的视觉识别和路径规划方法的关键问题，即对非结构化复杂环境下的树冠苹果识别、行间可行走区域可疑障碍物的检测，无学习机制的基于生物刺激神经网络的全局全覆盖最优路径规划、基于Q学习机制的最优安全路径规划展开了研究，利用Matlab2010a在Windows7环境下对提出的方法进行了编程验证。完成的主要工作和结果如下：
（1）针对自然环境下农业图像的非结构化特点，研究并提出了结合a*颜色模糊判决的L*a*b*检测方法。树冠苹果的检测结果表明，若苹果呈10%以上的红色，尽管有阴影，均能达到100%的有效检测；同时园区行内植草的障碍物检测结果也表明，若行内大部背景呈现绿色，尽管有树干、树枝，也能实现100%的有效检测植草背景的行内障碍物，背景的灰度级接近0，目标呈现高亮。
（2）研究并提出了基于最大熵理论分割自然环境下的灰度图像。测试结果表明，运用Renyi熵分割树冠苹果图像，运行速度快，约为16ms；结合优化遗传算法的模糊二维熵的阈值分割方法，能有效分割行内障碍物灰度图像，与图像大小、检测目标数量无关，背景和目标分割清晰、纯净，且运算速度较快（34-36ms）,可满足实时性要求。
（3）研究并提出了基于连通域质心和圆度等果形特征提取方法。测试结果表明，自然环境下拍摄的180幅树冠苹果图像，除7幅图像因曝光剧烈使其红色成分未达到10%而导致检测与识别失败外，其余173幅各类复杂环境下的苹果图像均能有效识别，识别率为96.1%，为果实的检测与识别提供了新的方法。同时针对行内障碍物检测时出现的树枝、树干粘连现象，提出了结合数学形态学滤除连通区域周长与面积之比大于0.375的粘连区域，并在98幅植草背景的行内图像中，障碍物检测成功率为96.9%。
（4）针对种植园区行间呈现行列平行的特点，研究并提出了基于生物刺激神经网络的“之”字型全覆盖作业的全局最优路径规划。静态复杂环境以及动态随机环境下的模拟测试表明，该方法的运算时间约为50ms，通过构建离散化环境拓扑地图，采用不完整约束的运动学模型，地图中未采摘位置的神经元活动性能引导机器人到达最终指定位置，整个过程无需学习、普适性高、计算量小、转向控制少，可适用于各类复杂环境下的路径规划或目标追踪。
（5）针对苹果采摘机器人的作业环境随时发生变化导致设计者无法真正理解机器人的作业环境，为确保机器人能安全作业或行走，研究并设计了基于Q学习的机器人避障策略、路径探索和学习机制。已知静态环境和未知环境的模拟测试表明，在预估静态障碍物和随机障碍物数量均小于10的园区环境，机器人经过约为10min的学习，均能找出以指导机器人从起始点到最终指定位置的最优安全路径。Q学习方法与环境模型无关，适用于不确定环境下的路径或轨迹规划以及复杂控制，提高了机器人应对突发事件的适应能力。和其它学习方法一样，唯一缺陷是学习阶段略显耗时。
To identify the apple fruits in tree canopies effectively and precisely, to detect theobstacles occurred between lines in an orchard at the walking forward direction of robotbefore being picking, and to support methodologically the path planning technology whileapple-picking-robot being operated, the study on visual identification and path planning hassignificant effect and potential practical value on improving the reliability and pickingefficiency of the apple-picking-robot, and on promoting the intelligently picking level ofagricultural equipment.
To solve the key points of visual identification and path planning for apple-picking-robot,this dissertation focused on apple in canopies recognition under a non-structured naturalenvironment, on uncertain obstacle detection at the walking forward direction between lines,on completely coverage path planning with non-learning mechanism bio-inspired neuralnetwork-based and on path planning with Q-learning mechanism. The proposed approacheswere implemented and verified using Matlab2010a in Window7. In this study, the maincontents and original results were described as follows.
(1) A novel approach to detect natural images in an unstructured canopies with fuzzycolor judgment and L*a*b*color space was proposed. The experiments on apple detection incanopies showed that if apples emerged red over10%even with some shades, they could beeffectively and totally detected; and the experiments on uncertain obstacles detection ingrass-planted orchard also revealed that if most the background appeared green even withsome branches and trunks, the obstacles could be effectively and totally detected within lines;the grey levels of the background could be close to zero, and the object could be highlightedafter completion of a*component conversion into gray image in L*a*b*.
(2) A novel thresholding method based on maximum entropy theory was proposed tosegment the apple gray-scale image after the completion of gray image conversion. Theexperiments showed that the running time of segmentation on apple gray image with Renyientropy theory was about16milliseconds, and of segmentation on obstacle image with fuzzy2D entropy with optimized genetic algorithm about34-36milliseconds, which could segmentthe object from background effectively and clearly, be regardless of the size of image andnumber of objects detected, and satisfy the real-time requirements of picking robot.
(3) A new apple shape features extraction method with the centroid and roundness ofconnected regions was proposed. The experiments verified that these proposed approachescould effectively recognize apple from173images in tree canopies under a complexenvironment, other7images failed for the reason that apples emerged red less than10%withserver light exposure, and the recognition rate was96.1%, which could provide a new trial forthe fruit detection and recognition. A new filtering method with mathematical morphologywas proposed to eliminate the sticky connected regions of branches and trunks using the ratiobetween perimeter and area of the connected regions over0.375, and the obstacle detectionratio was96.9%in the experiments of98images of grass-planted orchard.
(4) A novel global path planning of zigzag complete coverage approach based onbio-inspired neural network was proposed according to the characteristic of parallel plantinglines. The experiments under static known and dynamic unknown environments verified thatthe activity of neurons located at unpicked area could all along attract the robot until the robotreached at the appointed position after the completion of construction of discretizedtopological map using non-holonomic constraint kinematics. The running time for pathproducing was about50milliseconds. The whole planning process need not learn, and hashigh universality, lower running cost, less turn control, and could be suitable for path planningor target tracing under complex environments.
(5) A novel apple-picking-robot with Q-learning mechanism was designed to ensurerobot moving or working safely including the design of avoidance of obstacles, and pathexploring policies and learning mechanisms, while the operating environment was changed sorandomly and abruptly as that the designer could not understand the whole environmententirely. The experiments under static known and completely unknown environments verifiedthat the new robot could find the prior and safe path from the starting point to appointed point,which could guide the new robot move towards after the completion of10minutes’ learningwhile the pre-estimated obstacles number including static and random obstacles was no morethan10. The Q-learning method was regardless of environment, and suitable for path ortrajectory planning and complex control under uncertain or unknown environments, and couldpromote the adaptability of robot to process the abrupt incidents. Like other learningmethodologies, the only disadvantage was that the learning process was a littletime-consuming for the reason of high-dimension data disaster.
引文
曾岑.2008.室内清洁机器人的全区域路径规划及避障研究.[硕士学位论文].无锡:江南大学
陈春林.2006.基于强化学习的移动机器人自主学习及导航控制.[博士学位论文].合肥:中国科学技术大学
陈军,蒋浩然,刘沛,张勤.2012.果园移动机器人曲线路径导航控制.农业机械学报.43(4):179-182,187
陈卫东,席裕庚,顾冬雷.2001.自主机器人的强化学习研究进展.机器人.23(4):379-384
陈学松.2011.强化学习及其在机器人系统中的应用研究.[博士学位论文].广州:广东工业大学
陈玉,赵德安.2010.基于LBM的苹果采摘机器人视觉图像自动修复算法.农业机械学报.41(11):153-157,162
陈自立,徐娅萍,顾立彬.2012.基于模糊Q学习算法的AGV路径规划研究.制造业自动化.34(6):4-6,16
褚建华.2009. Q-learning强化学习算法改进及其应用研究.[硕士学位论文].北京:北京化工大学
崔建军,魏娟,刘坤.2009.基于遗传算法移动机器人的路径规划研究.煤矿机械.30(9):58-60
崔淑娟.2012.自然场景下成熟苹果目标的识别及其定位技术研究.[硕士学位论文].咸阳:陕西科技大学
崔淑娟,李健.2011.基于色差信息的成熟苹果识别.西北大学学报(自然科学版).41(6):993-997
丁幼春,王书茂,陈红.2009.农用车辆作业环境障碍物检测方法.农业机械学报.40(S1):23-27,17
范莉丽,王奇志,孙富春.2006.生物激励神经网络路径规划仿真研究与改进.北京交通大学学报.30(2):84-88
高国琴,孙玉坤.开关磁阻电动机的受生物启发滑模控制研究.中小型电机.31(4):53-56
高国琴,张际先,黄卫忠.2004.受生物启发的离散滑模变结构液位控制研究.农业工程学报.20(4):26-29
高国琴,朱湘临.2003.一种受生物启发的变结构模型跟踪控制算法.系统工程与电子技术.25(12):1508-1510
高云峰,黄海.2004.复杂环境下基于势场原理的路径规划方法.机器人.(02):114-118
耿楠.2012.田间及作物信息远程获取关键技术研究.[博士学位论文].杨凌:西北农林科技大学
何东健,何勇,李明赞,洪添胜,王成红,宋苏,刘允刚.2011.精准农业中信息相关科学问题研究进展.中国科学基金.1:10-16
何东健,杨青,薛少平,耿楠.1998.果实表面颜色计算机视觉分级技术研究.农业工程学报.14(3):207-210
何祖恩,吴海彬,李文锦.2009.基于双目视觉的移动机器人障碍物检测研究.机械设计与制造.No.226(12):171-173
侯大军,朱伟兴,董国贵,彭彦松,朱晓芳.2009.基于图像处理的苹果形状特征的提取研究.信息化纵横.(14):54-57
胡彩石,吴功平,曹珩,蒋国伟.2008.高压输电线路巡线机器人障碍物视觉检测识别研究.传感技术学报. v.21(12):2092-2096
胡华梅.2007.未知环境中基于视觉的移动机器人障碍物检测研究.[硕士学位论文].长沙:中南大学
黄金杰,郭鲁强,逯仁虎,丁艳军.2010.改进的二维Renyi熵图像阈值分割.计算机科学.37(10):251-253
黄星奕,林建荣,赵杰文.2004.苹果果梗和缺陷的识别技术研究.江苏大学学报(自然科学版).25(3):193-195
金立左,袁晓辉,赵一凡,夏良正.2002.二维模糊划分最大熵图像分割算法.电子与信息学报.24(8):1040-1048
井利民,何东建,张建锋.2009.基于ARM的苹果果实图像识别与定位技术研究.微计算机信息.25(20):87-89
雷博,范九伦.2010.二维Renyi熵阈值分割方法中参数的自适应选取.计算机工程与应用.46(22):16-19
李庆中.2000.苹果自动分级中计算机视觉信息快速获取与处理技术的研究.[博士学位论文].北京:中国农业大学
刘健庄,栗文青.1993.灰度图象的二维Otsu自动阈值分割法.自动化学报.19(1):101-105
刘军弟,王静,刘天军,韩明玉,霍学喜.2012.中国苹果加工产业发展趋势分析.林业经济问题.32(02):185-188
刘晴蕊,何东健,张宏鸣,朱珊娜,郭云忠.2011.苹果病害智能诊断方法研究与设计.农机化研究.33(4):76-78
刘淑华,夏菁,孙学敏,张友.2011.已知环境下一种高效全覆盖路径规划算法.东北师大学报(自然科学版).43(4):39-43
刘松,李志蜀,李奇.2009.机器人全覆盖最优路径规划的改进遗传算法.计算机工程与应用.45(662):245-248
刘锁兰,杨静宇.2009.基于模糊理论的2维隶属划分Renyi熵分割算法.中国图象图形学报A.14(2):323-327
刘锁兰,杨静宇,郭克华.2007.基于最大模糊指数熵的模糊目标分割算法.计算机科学.34(9):240-241,272
刘媛媛.2008.智能算法在图像分割中的应用研究.[硕士学位论文].南京:南京航空航天大学
柳平增,毕树生,付冬菊,苗良.2010.室外农业机器人导航研究综述.农业网络信息.(3):5-10
龙建武,申铉京,魏巍,何月,陈海鹏.2011.一种结合纹理信息的三维Renyi熵阈值分割算法.小型微型计算机系统.32(5):947-952
龙满生,何东健.2007.玉米苗期杂草的计算机识别技术研究.农业工程学报.23(7):139-143
罗荣贵,屠大维.2011.栅格法视觉传感集成及机器人实时避障.计算机工程与应用.47(24):233-235
吕继东,赵德安,姬伟,陈玉,沈惠良,张颖.2012a.苹果采摘机器人对振荡果实的快速定位采摘方法.农业工程学报.28(13):48-53
吕继东,赵德安,姬伟,郭金亮,李占坤.2010.苹果采摘机器人无线数据传输系统.农业工程学报.26(12):225-230
吕继东,赵德安,姬伟,郭金亮,李占坤.2012b.开放分布式苹果采摘机器人控制系统研究及实现.小型微型计算机系统.33(02):289-292
马正华,李敏,章明,储建华.2012.智能吸尘器全覆盖遍历路径规划及仿真实现.测控技术.31(240):99-102
孟伟,洪炳熔,韩学东.2002.强化学习在机器人足球比赛中的应用.计算机应用研究.(6):79-81
邱丽君,侯德文,王依才.2010.改进的二维Otsu图像分割方法的研究.计算机工程与应用.46(33):195-197
邱雪娜,刘士荣,俞金寿, Yang Simon X.2006.移动机器人的完全遍历路径规划:生物激励与启发式模板方法.模式识别与人工智能.19(1):122-128
任永新,李伟,陈晓,李吉,杨会华,谭豫之,杨庆华.2008.非结构环境下基于机器视觉的机器人路径跟踪方法.北京工业大学学报.34(10):1021-1025
沈明霞,姬长英,张瑞合.2001.基于小波变换的农田景物边缘检测.农业机械学报.32(02):27-29,41
司永胜,乔军,刘刚,高瑞,何蓓.2010.苹果采摘机器人果实识别与定位方法.农业机械学报.41(9):148-153
司永胜,乔军,刘刚,刘兆祥,高瑞.2009.基于机器视觉的苹果识别和形状特征提取.农业机械学报.40(8):161-165,73
汤修映,张铁中.2005.果蔬收获机器人研究综述.机器人.27(1):90-96
唐晶磊.2010.喷药机器人杂草识别与导航参数获取方法研究.杨凌:西北农林科技大学
汪景彦.2012.2012年我国苹果生产与售价预测.果树实用技术与信息.(8):4
王俭,赵鹤鸣,陈卫东.2006a.移动机器人全覆盖路径规划研究.微计算机信息.(8):194-197
王俭,赵鹤鸣,陈卫东.2006b.移动机器人全覆盖任务的研究进展.工矿自动化.(3):26-30
王俭,赵鹤鸣,肖金球.2006c.基于区域优化分割的机器人全覆盖路径规划.计算机工程与应用.(22):59-62
王荣本,李琳辉,金立生,郭烈,赵一兵.2007.基于双目视觉的智能车辆障碍物探测技术研究.中国图象图形学报.12(138):2158-2163
王文玺,肖世德,孟祥印,陈应松,张卫华.2010.基于Agent的递阶强化学习模型与体系结构.机械工程学报.46(2):76-82
王文玺,肖世德,孟祥印,张卫华.2009.模糊神经网络下基于强化学习的自主式地面车辆路径规划研究.中国机械工程.20(21):2536-2541
吴洪岩.2009.基于强化学习的自主移动机器人导航研究.[硕士学位论文].沈阳:东北师范大学
武奕晶,张海洪.2007.基于BP神经网络的清扫机器人的环境建模.机床与液压.9(231):93-96
谢民,高利新.2008.蚁群算法在最优路径规划中的应用.计算机工程与应用.44(8):245-248
邢方山,何东健.2011.植物叶子枯萎变形虚拟方法研究.计算机工程.37(5):238-240
邢军,王杰.2005.神经网络在移动机器人路径规划中的应用研究.微计算机信息.21(11-2):110-111,153
徐光祐,朱志刚,林学誾,石定机.1997.用于室外道路环境综合理解的多种新型视觉传感技术和系统.高技术通讯.(8):9-13
徐明亮.2009.强化学习及其应用研究.[博士学位论文].无锡:江南大学
徐昕.2002.增强学习及其在移动机器人导航与控制中的应用研究.[博士学位论文].长沙:国防科学技术大学
荀一,陈晓,李伟,刘刚,许晨光.2007.基于轮廓曲率的树上苹果自动识别.江苏大学学报(自然科学版).6(28):461-464
杨传华,杨萍,周美艳,刘金利.2006.自学习移动机器人在未知环境中的路径规划.机械设计.(02):16-19
杨福增,刘珊,陈丽萍,宋怀波,王元杰,兰玉彬.2012.基于立体视觉技术的多种农田障碍物检测方法.农业机械学报.43(5):168-172,202
杨沛,何东健.2010a.基于参数L-系统的黄瓜苗期生长可视化研究.农机化研究.32(8):181-185
杨沛,何东健.2010b.黄瓜叶片三维重建方法研究与实现.农机化研究.32(7):65-67
杨蕊蕊,朱大奇.2011.基于生物启发模型的自治水下机器人平面轨迹跟踪控制.上海海事大学学报.32(3):58-63
杨志华.2008.基于不确定知识的强化学习及其应用研究.[硕士学位论文].合肥:中国科学技术大学
杨转.2011.基于HSI颜色模型的杂草与土壤背景分割方法研究.河北农业大学学报.34(4):124-127
尹秀珍.2011.低分辨率苹果果实病害图像识别方法研究.[硕士学位论文].杨凌:西北农林科技大学
尹秀珍,何东健,霍迎秋.2012.自然场景下低分辨率苹果果实病害智能识别方法.农机化研究.(10):29-32
余洪山.2007.移动机器人地图创建和自主探索方法研究.[博士学位论文].长沙:湖南大学
苑严伟,张小超,胡小安.2009.苹果采摘路径规划最优化算法与仿真实现.农业工程学报.25(4):141-144
张建锋.2012.苹果采摘机器人移动控制系统关键技术研究.[博士学位论文].杨凌:西北农林科技大学
张洁,李艳文.2010.果蔬采摘机器人的研究现状、问题及对策.机械设计.27(6):1-5
张磊,王书茂,陈兵旗,刘志刚.2007.基于双目视觉的农田障碍物检测.中国农业大学学报.12(4):70-74
张奇,顾伟康.1998.基于多传感器数据融合的环境理解及障碍物检测算法.机器人.(2):25-31
张倩.2010.智能割草机路径规划和障碍物探测技术的研究.[硕士学位论文].武汉:武汉理工大学
张汝波,顾国昌,刘照德,王醒策.1999b.强化学习理论、算法及应用.控制理论与应用.17(5):637-642
张汝波,杨广铭,顾国昌,张国印.1999a. Q-学习及其在智能机器人局部路径规划中的应用研究.计算机研究与发展.36(12):1430-1436
张汝波,周宁,顾国昌,张国印.1999c.基于强化学习的智能机器人避碰方法研究.机器人.3(21):204-209
张亚静,李民赞,刘刚,乔军.2009.基于机器视觉和信息融合的邻接苹果分割算法.农业机械学报.40(11):180-183
张志勇.2012.苹果采摘机器人手臂稳定性控制技术研究.[博士学位论文].杨凌:西北农林科技大学
张志勇,何东健,张建锋,黄铝文,姬红卫.2008.苹果采摘机器人手臂控制研究.中国农业大学学报.13(2):78-82
赵金星.2007.割草机器人总体设计与关键技术研究.[硕士学位论文].南京:南京理工大学
赵静,何东健.2001.果实形状的计算机识别方法研究.农业工程学报.17(2):165-167
周俊,程嘉煜.2011.基于机器视觉的农业机器人运动障碍目标检测.农业机械学报.42(8):154-158
朱安民,明仲.2009.基于神经动力学的目标跟踪算法.深圳大学学报理工版.3(26):83-88
朱大奇,颜明重.2010.移动机器人路径规划技术综述.控制与决策.25(7):961-967
朱庆保.2005.动态复杂环境下的机器人路径规划蚂蚁预测算法.计算机学报.28(11):1898-1906
朱志刚,徐光佑,林学言,石定机.1997.视觉导航的多尺度全方位时空图象综合理解方法.清华大学学报(自然科学版).(3):13-16
Abbeel P., Coates A., Quigley M., Ng A. Y.2007. An application of reinforcement learning toaerobatic helicopter flight.20th Annual Conference on Neural Information Processing Systems, NIPS2006.Vancouver, British Columbia, Canada:1-8
Baeten J., Donne K., Boedrij S., Beckers W., Claesen E.2008. Autonomous fruit picking machine: Arobotic apple harvester. Field and Service Robotics: Results of the6th International Conference.Heidelberg, Germany:531-539
Batavia P. H., Singh S.2001. Obstacle Detection using Adaptive Color Segmentation and ColorStereo Homography.2001IEEE International Conference on Robotics and Automation (ICRA).DOI:10.1109/ROBOT.2001.932633:705-710
Baxter J., Bartlett P. L.2001. Infinite-horizon policy-gradient estimation. Journal of ArtificialIntelligence Research.15(1):319-350
Benavidez P., Jamshidi M., Chair L. B. E.2011. Mobile Robot Navigation and Target TrackingSystem. Proceedings of the20116th International Conference on System of Systems Engineering.Albuquerque, New Mexico, USA:1-6
Bulanon D. M., Kataoka T., Okamoto H., Hata S.2004. Development of a Real-time Machine VisionSystem for the Apple Harvesting Robot. SICE Annual Conference in Sapporo. Hokkaido Institute ofTechnology, Japan:595-598
Bulanon D. M., Kataoka T., Ota Y., Hiroma T.2002. A Segmentation Algorithm for the AutomaticRecognition of Fuji Apples at Harvest. Biosystems Engineering.83(4):405-412
Cannon J.2010. Robot Motion Planning using Real-time Heuristic Search.[Master Thesis]. Durham,New Hampshire, USA: University of New Hampshire
Chatila R., Laumond J.1985. Position referencing and consistent world modeling for mobile robots.IEEE International Conference on Robotics and Automation. St. Louis, Missouri, USA:138-145
Chen G. Y., Tsai W. H.2000. Vision-based Obstacle Detection and Avoidance for Autonomous LandVehicle Navigation in Outdoors Roads. Automation in Construction.10:1-25
Cheng H. D., Chen Y. H., Jiang X. H.2000. Thresholding Using Two-Dimensional Histogram andFuzzy Entropy Principle. IEEE Transactions on Image Processing.9(4):732-735
Cheng H., Chen Y. H., Sun Y.1999. A novel fuzzy entropy approach to image enhancement andthresholding. Signal Processing.75(3):277-301
Chopra A.2009. An Empirical approach to path planning in unstructured outdoor environments.[Master Thesis]. Toronto, Ontario, Canada: York University
Christopher J. C. H. W.1989. Learning from Delayed Rewards.[PH. D Dissertation]. Cambridge,London, United Kingdom: King's College
Coates A., Abbeel P., Ng A. Y.2008. Learning for control from multiple demonstrations. Proceedingsof the25th International Conference on Machine Learning. Helsinki, Finland:144-151
Coggan M.2008. Reinforcement learning in commercial computer games.[Master Thesis]. Montreal,Quebec, Canada: MCgill University
de Carvalho R. N., Vidal H. A., Vieira P., Ribeiro M. I.1997. Complete Coverage Path Planning andGuidance for Cleaning Robots. IEEE International Symposium on Industrial Electronics. Guimaraes,Portugal:1-6
D'Esnon A. G., Rabatel G., Pellenc R.1987. Magali: A self-propelled robot to pick apples. ASAEPaper87-1037.: St. Joseph, Missouri,49085
Dijkstra E.1959. A note on two problems in connection with graphs. Numerische Mathematik.1:269-270
Dima C., Hebert M.2005. Active Learning For Outdoor Obstacle Detection. Proceedings of Scienceand Systems.:3-15
Dollé L., Sheynikhovich D., Girard B., Chavarriaga R., Guillot A.2010. Path planning versus cueresponding: a bio-inspired model of switching between navigation strategies. Biologicial Cybernetics.103:299-317
Doya K.2000. Reinforcement learning in continuous time and space. Neural Computation.12(1):219-245
Driscoll T. M.2011. Complete coverage path planning in an agricultural environment.[Master Thesis].Ames, Iowa, USA: Iowa State University
Duguleana M., Barbuceanu F. G., Teirelbar A., Mogan G.2012. Obstacle avoidance of redundantmanipulators using neural networks based reinforcement learning. Robotics and Computer-IntegratedManufacturing.28:132–146
Ernst D., Glavic M., Capitanescu F., Wehenkel L.2009. Reinforcement learning versus modelpredictive control: a comparison on a power system problem. IEEE Transactions on Systems, Man andCybernetics Part B.39(2):517-529
Esmaili M., Naghdy F.1992. Further progress in robotics fruit harvesting and grading. Proceedings ofthe International Conference on Manufacturing Automation,10-12Aug.1992. Hong Kong, HongKong:812-17
Ferdaus S. N.2008. A topological approach to online autonomous map building for mobile robotnavigation.[Master Thesis]. Newfoundland, Canada: Memorial University of Newfoundland
Fernandez-Maloigne C., Laugier D., Boscolo C.1993. Detection of apples in natural images withtexture analysis. Proceedings of the International Conference on Intelligent Autonomous Systems IAS-3,15-18Feb.1993. Amsterdam, Netherlands:664-674
Gmen H.., Gagné S.1990. Neural network architectures for motion perception and elementarymotion detection in the fly visual system. Neural Networks.3(5):487-505
Grossberg S.1983. Absolute stability of global pattern formation and parallel memory storage bycompetitive neural networks. IEEE Transactions on Systems Man and Cybernetics.13(5):815-926
Grossberg S.1988. Nonlinear neural networks: Principles, mechanisms, and architecture. NeuralNetworks.1:17-61
Guo F., Cao Q. X.2004. Study on Color Image Processing based Intelligent Fruit Sorting System.Proceedings of the5" World Congress on Intelligent Control and Automation. Hangzhou, P.R.China:4802-4805
Han K. M.2007. Collision Free Path Planning Algorithms for Robot Navigation Problem.[MasterThesis]. Columbia, Missouri, USA: University of Missouri-Columbia
Hart S. W.2009. The development of hierarchical knowledge in robot systems.[PH. D Dissertation].Amherst, Massachusetts, USA: University of Massachusetts Amherst
Horn B. K., Schunck B. G.1981. Determining optical flow. Artificial Intelligence.17(1):185-203
Hosseinzadeh A., Izadkhah H.2010. Evolutionary Approach for Mobile Robot Path Planning inComplex environment. IJCSI International Journal of Computer Science Issues.4(7):1-9
Huang L., He D.2012. Ripe Fuji Apple Detection Model Analysis in Natural Tree Canopy.TELKOMNIKA.10(7):1537-1542
Huang L., Yang S. X., He D.2012. Abscission Point Extraction for Ripe Tomato Harvesting Robots.Intelligent Automation and Soft Computing.18(6):751-763
Ji W., Zhao D., Cheng F., Xua B., Zhang Y., Wang J.2011. Automatic recognition vision systemguided for apple harvesting robot. Computers and Electrical Engineering.5(38):1186-1195
Jiménez A. R., Ceres R., Pons J. L.2002. A Survey of Computer Vision Methods for Locating Fruiton Trees. Transactions of the ASAE.43(6):1911-1920
Jimenez A., Jain A. K., Ceres R., Pons J. L.1999. Automatic fruit recognition: a survey and newresults using range/attenuation images. Pattern Recognition.32(10):1719-1736
Jin D., Lin S.2012. Improved Genetic Algorithm Based2-D Maximum Entropy Image SegmentationAlgorithm. Advances in CSIE.2:529-534
Kaelbling L. P., Littman M. L., Cassandra A. R.1998. Planning and acting in partially observablestochastic domains. Artificial Intelligence.101(1-2):99-134
Kapur J. N., Sahoo P. K., Wong A. K. C.1985. A new method for gray level picture thresholdingusing the entropy of the histogram. Vision Graphics Image Process.29:273–285
Kortenkamp D., Wermouth T.1994. Topological mapping for mobile robots using a combination ofsonar and vision sensing. Proceedings of the national conferenceon artificial intelligence:979-984
Kuipers B.1978. Modeling spatial knowledge. Cognitive Science.2(2):129-153
Kuipers B.2000. The Spatial Semantic Hierarchy. Artificial Intelligence.(119):191-233
Kuipers B., Byun Y. T.1991. A robot exploration and mapping strategy based on a semantic hierarchyof spatial representations. Journal of Robotics and Autonomous Systems.(8):47-63
Kuter U.2006. Planning under uncertainty: Moving forward.[PH. D Dissertation]. College Park,Maryland, USA: University of Maryland at College Park
Laemmer E., Deruyver A., Sowinska M.2002. Watershed and adaptive pyramid for determining theapple's maturity state. Proceedings of ICIP2002International Conference on Image Processing. Rochester,New York, USA:I/789-I/792
Lei Z.2011. A Robotic Approach to the Analysis of Obstacle Avoidance in Crane Lift Path Planning.[Master Thesis]. Edmonton, Alberta, Canada: University of Alberta
Li X., Wang J., Ning X.2011. A*algorithm based robot path planning method. Applied Mechanicsand Materials.63-64:686-689
Littman M. L.1996. Algorithms for Sequential Decision Making.[PH. D Dissertation]. Providence,Rhode Island, USA: Brown University
Liu S. R., Qiu X. N., Yang S. X.2005. Heuristic template approach to complete coverage pathplanning of mobile robot.4th International Conference on Engineering Applications and ComputationalAlgorithms. University of Guelph, Guelph, Canada:358-363
Lu J.2009. Learning Multi-Agent Pursuit of a Moving Target.[Master Thesis]. Edmonton, Alberta,Canada: University of Alberta
Luo C.2002. Neural dynamics and computation for complete coverage path planning of mobilecleaning robots.[Master Thesis]. Guelph, Ontario, Canada: University of Guelph
Luo C., Yang S. X., Meng M. Q. H.2005. Real-time Map Building and Area Coverage in UnknownEnvironments. Proceedings of the2005IEEE International Conference on Robotics and Automation.Barcelona, Spain:1736-1741
March P. S.2008. Geometric-based Spatial Path Planning.[PH. D Dissertation]. Austin, Texas, USA:University of Texas at Austin
Marvel J. A.2010. Autonomous learning for robotic assembly applications.[PH. D Dissertation].Cleveland, Ohio, USA: Case Western Reserve University
Men H.2012. Robotic exploration for mapping: Systems and algorithms.[PH. D Dissertation].Hoboken, New Jersey, USA: Stevens Institute of Technology
Minsky M. L.1954. Theory of Neural-analog Reinforcement Systems and its Application to theBrain-model Problem.[PH. D Dissertation]. Princeton, New Jersey, USA: Princeton University
Minsky M. L.1961. Steps toward Artificial Intelligence. Proceedings of the Institute of RadioEngineers:49(3):8-30
Nash A.2012. Any-angle path planning.[PH. D Dissertation]. Los Angeles, California, USA:University of Southern California
Nicolás N., Cornelius W., Pascal S., Stefan W.2012. Real-world reinforcement learning forautonomous humanoid robot docking. Robotics and Autonomous Systems.60:1400-1407
Norwood J. D.1989. Robotic path planning and obstacle avoidance: A neural network approach.[Master Thesis]. Houston, Texas, USA: Rice University
Oh J. S., Choi Y. H., Park J. B., Zheng Y. F.2004. Complete coverage navigation of cleaning robotsusing triangular-cell-based map. IEEE Transactions on Industrial Electron.51(3):718-726
Ollis M., Stentz A.1997. Vision-based perception for an antomated harvester. Proceedings of the1997IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS'97:1838-1844
Pal S. K., King R. A., Hashim A. A.1983. Automatic Gray Level Thresholding through Index ofFuzziness and Entropy. Pattern Recognition Letters.1:141-146
Parker L. E.1999. Cooperative Robotics for Multi-target Observation. Intelligent Automation and SoftComputing, Special issue on Robotics Research at Oak Ridge National Laboratory.5(1):5-19
Parrish E., Goksel A. K.1977. Pictorial pattern recognition applied to fruit harvesting. Transactions ofthe ASAE.20(5):822-827
Penman D. W.2001. Determination of stem and calyx location on apples using automatic visualinspection. Computers and Electronics in Agriculture.33(1):7-18
Peterson D. L., Bennedsen B. S., Anger W. C., Wolford S. D.1999. A Systems Approach to RoboticBulk Harvesting of Apples. Transactions of the ASAE.42(4):871-876
Peterson D. L., Kornecki T. S.1987. Mechanical apple harvester for T-trellis canopies. Transactionsof the American Society of Agricultural Engineers.30(3):597-600
Peterson D. L., Miller S. S., Kornecki T. S.1985. Over-the-row harvester for apples. Transactions ofthe American Society of Agricultural Engineers.28(5):1393-1397
Pun T.1980. A new method for gray-level picture thresholding using the entropy of the histogram.Signal Processing.2:223-237
Pun T.1981. Entropy thresholding, a new approach. Compute Graphics and Image Processing.16:210-239
Rakun J., Stajnko D., Zazula D.2011. Detecting fruits in natural scenes by using spatial-frequencybased texture analysis and multiview geometry. Computers and Electronics in Agriculture.76(1):80-88
Rao N. S. V.1988. An algorithmic framework for robot navigation in unknown terrains.[PH. DDissertation]. Baton Rouge, Louisiana, USA: Louisiana State University and Agricultural and MechanicalCollege
Reynolds S.1993. Building a map for robot path planning by fusing video images and laserrangefinder data.[PH. D Dissertation]. Houston, Texas, USA: Rice University
Safren O., Alchanatis V., Ostrovsky V., Levi O.2007. Detection of green apples in hyperspectralimages of apple-tree foliage using machine vision. Transactions of the ASABE.50(6):2303-2313
Sahoo P. K., Arora G.2004. A thresholding method based on two-dimensional Renyi's entropy.Pattern Recognition.37(6):1149-1161
Sahoo P., Wilkins C., Yeager J.1997. Threshold selection using Renyi's entropy. Pattern Recognition.30(1):71-84
Schaal S., Atkeson C. G.1993. Open loop stable control strategies for robot juggling. IEEEInternational Conference on Robotics and Automation. Atlanta, Georgia, USA:913-918
Schertz C. E., Brown G. K.1968. Basic considerations in mechanizing citrus harvest. Transactions ofthe ASAE.11(2):343-346
Setiawan A. I., Furukawa T., Preston A.2004. A low-cost gripper for an apple picking robot.2004IEEE International Conference on Robotics and Automation. New Orleans, Louisiana, USA:4448-4453
Shatkay H., Kaelbling L. P.2002. Learning geometrically constrained hidden Markov models forrobot navigation: Bridging the topological-geometrical gap. Journal of Artificial Intelligence Research.16:167-207
Silver D.2009. Reinforcement Learning and Simulation-Based Search in Computer Go.[PH. DDissertation]. Edmonton, Alberta, Canada: University of Alberta
Simmons R., Koenig S.1995. Probabilistic robot navigation in partially observable environments.Proceeding of IJCAl. Montreal, Canada:1080-1087
Sorg J. D.2011. The Optimal Reward Problem: Designing Effective Reward for Bounded Agents.[PH. D Dissertation]. Ann Arbor, Michigan, USA: University of Michigan
Stajnko D., Lakota M., Hocevar M.2004. Estimation of number and diameter of apple fruits in anorchard during the growing season by thermal imaging. Computers and Electronics in Agriculture.(42):31-42
Sutton R. S.1988. Learning to predict by the method of temporal differences. Machine Learning.3(1):9-44
Sutton R. S.1990. Integrated architectures for learning, planning, and reacting based onapproximating dynamic programming. Proceedings of the7th International Conference on MachineLearning. Austin, Texas, USA:216-224
Sutton R. S., Mcallester D., Singh S., Mansour Y.2000. Policy gradient methods for reinforcementlearning with function approximation. Advances in Neural Information Processing Systems12:1057-1063
Tabb A. L., Peterson D. L., Park J.2006. Segmentation of apple fruit from video via backgroundmodeling.2006ASABE Annual International Meeting. Portland, Oregon, USA:No.063060
Theodorou E. A.2011. Iterative Path Integral Stochastic Optimal Control: Theory and Applications toMotor Control.[PH. D Dissertation]. Los Angeles, California, USA: University of Southern California
Thrun S.1998. Learning metric-topological maps for indoor mobile robot navigation.99(1):21-71
Thrun S., Bucken A.1996. Integrating grid-based and topological maps for mobile robot navigation.Proceedings of the AAAI13th National Conference on Artificial Intelligence. Portland, Oregon,USA:944-950
Unay D., Gosselin B.2005. Thresholding-based segmentation and apple grading by machine vision.13th European Signal Processing Conference, EUSIPCO2005, September4,2005-September8,2005.Antalya, Turkey:926-929
Unay D., Gosselin B., Debeir O.2006. Apple stem and calyx recognition by decision trees.Proceedings of the6th IASTED International Conference on Visualization, Imaging, and Image Processing.Palma de Mallorca, Spain:549-552
Wachs J. P., Stern H. I., Burks T., Alchanatis V.2010. Low and high-level visual feature-based appledetection from multi-modal images. Precision Agriculture.11(6):717-735
Walsh T. J., Nouri A., Li L., Littman M. L.2009. Learning and planning in environments with delayedfeedback. Autonomous Agents and Multi-Agent Systems.18(1):83-105
Wang X.2007. A vision-based perceptual learning system for autonomous mobile robot.[PH. DDissertation]. Nashville, Tennessee, USA: Vanderbilt University
Watkins C. J. C. H., Dayan P.1992. Q-Learning. Machine Learning.8:279-292
Whiteson S. A.2007. Adaptive representations for reinforcement learning.[PH. D Dissertation].Austin, Texas, USA: University of Texas at Austin
Xu B.2009. Fast Path Planning in Uncertain Environments: Theory and Experiments.[PH. DDissertation]. Blacksburg, Virginia, USA: Virginia Polytechnic Institute and State University
Xu H., Yang S. X.2002. Real-time Collision-free Motion Planning of Nonholonomic Robots using aNeural Dynamics based Approach. Proceedings of the2002IEEE International Conference on Robotics&Automation. Washington DC, USA:3087-3092
Yang S. X.2003. Neural dynamics and computation for real-time map building and path planning ofmobile robots. Dynamics of Continuous Discrete and Impulsive Systems-Series B-Applications&Algorithms.10(1-3):1-17
Yang S. X., Meng M.2001. Neural network approaches to dynamic collision-free trajectorygeneration. IEEE Transactions on Systems Man and Cybernetics Part B-Cybernetics.31(3):302-318
Yang S. X., Yuan G., Meng M.2001. Real-time Collision-free Path Planning and Tracking Control ofa Nonholonomic Mobile Robot using a Biologically Inspired Approach. Proceeding of2001IEEEIntentional Symposium on Computational Intelligence in Robotics and Automation. Banff, Alberta,Canada:113-118
Yang S. X., Zhu A., Yuan G., Meng M. Q. H.2012. A Bioinspired Neurodynamics-Based Approachto Tracking Control of Mobile Robots. IEEE Transactions on Industrial Electronics.59(8):3211-3220
Yang X.1999. Neural network approaches to real-time motion planning and control of roboticsystems.[PH. D Dissertation]. Edmonton, Alberta, Canada: University of Alberta
Yen G. G., Hickey T. W.2004. Reinforcement learning algorithms for robotic navigation in dynamicenvironments. ISA Transactions.43:217-230
Yin H., Chai Y., Yang S. X., Mittal G. S.2009. Ripe Tomato Extraction For A Harvesting RoboticSystem. Proceedings of the2009IEEE International Conference on Systems, Man and Cybernetics. SanAntonio, TX, USA:2984-2989
Zamstein L. M.2009. Koolio: Path-Planning using Reinforcement Learning on a Real Robot in a RealEnvironment.[PH. D Dissertation]. Gainesville, Florida, USA: University of Florida
Zhang G., Lu W., Ferrari S.2012. An Information Potential Approach to Integrated Sensor PathPlanning and Control. IEEE Transactions on Robotics.7:1-17
Zhang J., He D., Huang L.2012. Recognition and segmentation of Fuji apples in orchards based on2D entropy. International Journal of Digital Content Technology and its Applications.6(18):572-578
Zhao D. A., Lv J. D., Ji W.2011. Design and control of an apple harvesting robot. BiosystemsEngineering.110(2):112-122
陈春林.2006.基于强化学习的移动机器人自主学习及导航控制.[博士学位论文].合肥:中国科学技术大学
陈军,蒋浩然,刘沛,张勤.2012.果园移动机器人曲线路径导航控制.农业机械学报.43(4):179-182,187
陈卫东,席裕庚,顾冬雷.2001.自主机器人的强化学习研究进展.机器人.23(4):379-384
陈学松.2011.强化学习及其在机器人系统中的应用研究.[博士学位论文].广州:广东工业大学
陈玉,赵德安.2010.基于LBM的苹果采摘机器人视觉图像自动修复算法.农业机械学报.41(11):153-157,162
陈自立,徐娅萍,顾立彬.2012.基于模糊Q学习算法的AGV路径规划研究.制造业自动化.34(6):4-6,16
褚建华.2009. Q-learning强化学习算法改进及其应用研究.[硕士学位论文].北京:北京化工大学
崔建军,魏娟,刘坤.2009.基于遗传算法移动机器人的路径规划研究.煤矿机械.30(9):58-60
崔淑娟.2012.自然场景下成熟苹果目标的识别及其定位技术研究.[硕士学位论文].咸阳:陕西科技大学
崔淑娟,李健.2011.基于色差信息的成熟苹果识别.西北大学学报(自然科学版).41(6):993-997
丁幼春,王书茂,陈红.2009.农用车辆作业环境障碍物检测方法.农业机械学报.40(S1):23-27,17
范莉丽,王奇志,孙富春.2006.生物激励神经网络路径规划仿真研究与改进.北京交通大学学报.30(2):84-88
高国琴,孙玉坤.开关磁阻电动机的受生物启发滑模控制研究.中小型电机.31(4):53-56
高国琴,张际先,黄卫忠.2004.受生物启发的离散滑模变结构液位控制研究.农业工程学报.20(4):26-29
高国琴,朱湘临.2003.一种受生物启发的变结构模型跟踪控制算法.系统工程与电子技术.25(12):1508-1510
高云峰,黄海.2004.复杂环境下基于势场原理的路径规划方法.机器人.(02):114-118
耿楠.2012.田间及作物信息远程获取关键技术研究.[博士学位论文].杨凌:西北农林科技大学
何东健,何勇,李明赞,洪添胜,王成红,宋苏,刘允刚.2011.精准农业中信息相关科学问题研究进展.中国科学基金.1:10-16
何东健,杨青,薛少平,耿楠.1998.果实表面颜色计算机视觉分级技术研究.农业工程学报.14(3):207-210
何祖恩,吴海彬,李文锦.2009.基于双目视觉的移动机器人障碍物检测研究.机械设计与制造.No.226(12):171-173
侯大军,朱伟兴,董国贵,彭彦松,朱晓芳.2009.基于图像处理的苹果形状特征的提取研究.信息化纵横.(14):54-57
胡彩石,吴功平,曹珩,蒋国伟.2008.高压输电线路巡线机器人障碍物视觉检测识别研究.传感技术学报. v.21(12):2092-2096
胡华梅.2007.未知环境中基于视觉的移动机器人障碍物检测研究.[硕士学位论文].长沙:中南大学
黄金杰,郭鲁强,逯仁虎,丁艳军.2010.改进的二维Renyi熵图像阈值分割.计算机科学.37(10):251-253
黄星奕,林建荣,赵杰文.2004.苹果果梗和缺陷的识别技术研究.江苏大学学报(自然科学版).25(3):193-195
金立左,袁晓辉,赵一凡,夏良正.2002.二维模糊划分最大熵图像分割算法.电子与信息学报.24(8):1040-1048
井利民,何东建,张建锋.2009.基于ARM的苹果果实图像识别与定位技术研究.微计算机信息.25(20):87-89
雷博,范九伦.2010.二维Renyi熵阈值分割方法中参数的自适应选取.计算机工程与应用.46(22):16-19
李庆中.2000.苹果自动分级中计算机视觉信息快速获取与处理技术的研究.[博士学位论文].北京:中国农业大学
刘健庄,栗文青.1993.灰度图象的二维Otsu自动阈值分割法.自动化学报.19(1):101-105
刘军弟,王静,刘天军,韩明玉,霍学喜.2012.中国苹果加工产业发展趋势分析.林业经济问题.32(02):185-188
刘晴蕊,何东健,张宏鸣,朱珊娜,郭云忠.2011.苹果病害智能诊断方法研究与设计.农机化研究.33(4):76-78
刘淑华,夏菁,孙学敏,张友.2011.已知环境下一种高效全覆盖路径规划算法.东北师大学报(自然科学版).43(4):39-43
刘松,李志蜀,李奇.2009.机器人全覆盖最优路径规划的改进遗传算法.计算机工程与应用.45(662):245-248
刘锁兰,杨静宇.2009.基于模糊理论的2维隶属划分Renyi熵分割算法.中国图象图形学报A.14(2):323-327
刘锁兰,杨静宇,郭克华.2007.基于最大模糊指数熵的模糊目标分割算法.计算机科学.34(9):240-241,272
刘媛媛.2008.智能算法在图像分割中的应用研究.[硕士学位论文].南京:南京航空航天大学
柳平增,毕树生,付冬菊,苗良.2010.室外农业机器人导航研究综述.农业网络信息.(3):5-10
龙建武,申铉京,魏巍,何月,陈海鹏.2011.一种结合纹理信息的三维Renyi熵阈值分割算法.小型微型计算机系统.32(5):947-952
龙满生,何东健.2007.玉米苗期杂草的计算机识别技术研究.农业工程学报.23(7):139-143
罗荣贵,屠大维.2011.栅格法视觉传感集成及机器人实时避障.计算机工程与应用.47(24):233-235
吕继东,赵德安,姬伟,陈玉,沈惠良,张颖.2012a.苹果采摘机器人对振荡果实的快速定位采摘方法.农业工程学报.28(13):48-53
吕继东,赵德安,姬伟,郭金亮,李占坤.2010.苹果采摘机器人无线数据传输系统.农业工程学报.26(12):225-230
吕继东,赵德安,姬伟,郭金亮,李占坤.2012b.开放分布式苹果采摘机器人控制系统研究及实现.小型微型计算机系统.33(02):289-292
马正华,李敏,章明,储建华.2012.智能吸尘器全覆盖遍历路径规划及仿真实现.测控技术.31(240):99-102
孟伟,洪炳熔,韩学东.2002.强化学习在机器人足球比赛中的应用.计算机应用研究.(6):79-81
邱丽君,侯德文,王依才.2010.改进的二维Otsu图像分割方法的研究.计算机工程与应用.46(33):195-197
邱雪娜,刘士荣,俞金寿, Yang Simon X.2006.移动机器人的完全遍历路径规划:生物激励与启发式模板方法.模式识别与人工智能.19(1):122-128
任永新,李伟,陈晓,李吉,杨会华,谭豫之,杨庆华.2008.非结构环境下基于机器视觉的机器人路径跟踪方法.北京工业大学学报.34(10):1021-1025
沈明霞,姬长英,张瑞合.2001.基于小波变换的农田景物边缘检测.农业机械学报.32(02):27-29,41
司永胜,乔军,刘刚,高瑞,何蓓.2010.苹果采摘机器人果实识别与定位方法.农业机械学报.41(9):148-153
司永胜,乔军,刘刚,刘兆祥,高瑞.2009.基于机器视觉的苹果识别和形状特征提取.农业机械学报.40(8):161-165,73
汤修映,张铁中.2005.果蔬收获机器人研究综述.机器人.27(1):90-96
唐晶磊.2010.喷药机器人杂草识别与导航参数获取方法研究.杨凌:西北农林科技大学
汪景彦.2012.2012年我国苹果生产与售价预测.果树实用技术与信息.(8):4
王俭,赵鹤鸣,陈卫东.2006a.移动机器人全覆盖路径规划研究.微计算机信息.(8):194-197
王俭,赵鹤鸣,陈卫东.2006b.移动机器人全覆盖任务的研究进展.工矿自动化.(3):26-30
王俭,赵鹤鸣,肖金球.2006c.基于区域优化分割的机器人全覆盖路径规划.计算机工程与应用.(22):59-62
王荣本,李琳辉,金立生,郭烈,赵一兵.2007.基于双目视觉的智能车辆障碍物探测技术研究.中国图象图形学报.12(138):2158-2163
王文玺,肖世德,孟祥印,陈应松,张卫华.2010.基于Agent的递阶强化学习模型与体系结构.机械工程学报.46(2):76-82
王文玺,肖世德,孟祥印,张卫华.2009.模糊神经网络下基于强化学习的自主式地面车辆路径规划研究.中国机械工程.20(21):2536-2541
吴洪岩.2009.基于强化学习的自主移动机器人导航研究.[硕士学位论文].沈阳:东北师范大学
武奕晶,张海洪.2007.基于BP神经网络的清扫机器人的环境建模.机床与液压.9(231):93-96
谢民,高利新.2008.蚁群算法在最优路径规划中的应用.计算机工程与应用.44(8):245-248
邢方山,何东健.2011.植物叶子枯萎变形虚拟方法研究.计算机工程.37(5):238-240
邢军,王杰.2005.神经网络在移动机器人路径规划中的应用研究.微计算机信息.21(11-2):110-111,153
徐光祐,朱志刚,林学誾,石定机.1997.用于室外道路环境综合理解的多种新型视觉传感技术和系统.高技术通讯.(8):9-13
徐明亮.2009.强化学习及其应用研究.[博士学位论文].无锡:江南大学
徐昕.2002.增强学习及其在移动机器人导航与控制中的应用研究.[博士学位论文].长沙:国防科学技术大学
荀一,陈晓,李伟,刘刚,许晨光.2007.基于轮廓曲率的树上苹果自动识别.江苏大学学报(自然科学版).6(28):461-464
杨传华,杨萍,周美艳,刘金利.2006.自学习移动机器人在未知环境中的路径规划.机械设计.(02):16-19
杨福增,刘珊,陈丽萍,宋怀波,王元杰,兰玉彬.2012.基于立体视觉技术的多种农田障碍物检测方法.农业机械学报.43(5):168-172,202
杨沛,何东健.2010a.基于参数L-系统的黄瓜苗期生长可视化研究.农机化研究.32(8):181-185
杨沛,何东健.2010b.黄瓜叶片三维重建方法研究与实现.农机化研究.32(7):65-67
杨蕊蕊,朱大奇.2011.基于生物启发模型的自治水下机器人平面轨迹跟踪控制.上海海事大学学报.32(3):58-63
杨志华.2008.基于不确定知识的强化学习及其应用研究.[硕士学位论文].合肥:中国科学技术大学
杨转.2011.基于HSI颜色模型的杂草与土壤背景分割方法研究.河北农业大学学报.34(4):124-127
尹秀珍.2011.低分辨率苹果果实病害图像识别方法研究.[硕士学位论文].杨凌:西北农林科技大学
尹秀珍,何东健,霍迎秋.2012.自然场景下低分辨率苹果果实病害智能识别方法.农机化研究.(10):29-32
余洪山.2007.移动机器人地图创建和自主探索方法研究.[博士学位论文].长沙:湖南大学
苑严伟,张小超,胡小安.2009.苹果采摘路径规划最优化算法与仿真实现.农业工程学报.25(4):141-144
张建锋.2012.苹果采摘机器人移动控制系统关键技术研究.[博士学位论文].杨凌:西北农林科技大学
张洁,李艳文.2010.果蔬采摘机器人的研究现状、问题及对策.机械设计.27(6):1-5
张磊,王书茂,陈兵旗,刘志刚.2007.基于双目视觉的农田障碍物检测.中国农业大学学报.12(4):70-74
张奇,顾伟康.1998.基于多传感器数据融合的环境理解及障碍物检测算法.机器人.(2):25-31
张倩.2010.智能割草机路径规划和障碍物探测技术的研究.[硕士学位论文].武汉:武汉理工大学
张汝波,顾国昌,刘照德,王醒策.1999b.强化学习理论、算法及应用.控制理论与应用.17(5):637-642
张汝波,杨广铭,顾国昌,张国印.1999a. Q-学习及其在智能机器人局部路径规划中的应用研究.计算机研究与发展.36(12):1430-1436
张汝波,周宁,顾国昌,张国印.1999c.基于强化学习的智能机器人避碰方法研究.机器人.3(21):204-209
张亚静,李民赞,刘刚,乔军.2009.基于机器视觉和信息融合的邻接苹果分割算法.农业机械学报.40(11):180-183
张志勇.2012.苹果采摘机器人手臂稳定性控制技术研究.[博士学位论文].杨凌:西北农林科技大学
张志勇,何东健,张建锋,黄铝文,姬红卫.2008.苹果采摘机器人手臂控制研究.中国农业大学学报.13(2):78-82
赵金星.2007.割草机器人总体设计与关键技术研究.[硕士学位论文].南京:南京理工大学
赵静,何东健.2001.果实形状的计算机识别方法研究.农业工程学报.17(2):165-167
周俊,程嘉煜.2011.基于机器视觉的农业机器人运动障碍目标检测.农业机械学报.42(8):154-158
朱安民,明仲.2009.基于神经动力学的目标跟踪算法.深圳大学学报理工版.3(26):83-88
朱大奇,颜明重.2010.移动机器人路径规划技术综述.控制与决策.25(7):961-967
朱庆保.2005.动态复杂环境下的机器人路径规划蚂蚁预测算法.计算机学报.28(11):1898-1906
朱志刚,徐光佑,林学言,石定机.1997.视觉导航的多尺度全方位时空图象综合理解方法.清华大学学报(自然科学版).(3):13-16
Abbeel P., Coates A., Quigley M., Ng A. Y.2007. An application of reinforcement learning toaerobatic helicopter flight.20th Annual Conference on Neural Information Processing Systems, NIPS2006.Vancouver, British Columbia, Canada:1-8
Baeten J., Donne K., Boedrij S., Beckers W., Claesen E.2008. Autonomous fruit picking machine: Arobotic apple harvester. Field and Service Robotics: Results of the6th International Conference.Heidelberg, Germany:531-539
Batavia P. H., Singh S.2001. Obstacle Detection using Adaptive Color Segmentation and ColorStereo Homography.2001IEEE International Conference on Robotics and Automation (ICRA).DOI:10.1109/ROBOT.2001.932633:705-710
Baxter J., Bartlett P. L.2001. Infinite-horizon policy-gradient estimation. Journal of ArtificialIntelligence Research.15(1):319-350
Benavidez P., Jamshidi M., Chair L. B. E.2011. Mobile Robot Navigation and Target TrackingSystem. Proceedings of the20116th International Conference on System of Systems Engineering.Albuquerque, New Mexico, USA:1-6
Bulanon D. M., Kataoka T., Okamoto H., Hata S.2004. Development of a Real-time Machine VisionSystem for the Apple Harvesting Robot. SICE Annual Conference in Sapporo. Hokkaido Institute ofTechnology, Japan:595-598
Bulanon D. M., Kataoka T., Ota Y., Hiroma T.2002. A Segmentation Algorithm for the AutomaticRecognition of Fuji Apples at Harvest. Biosystems Engineering.83(4):405-412
Cannon J.2010. Robot Motion Planning using Real-time Heuristic Search.[Master Thesis]. Durham,New Hampshire, USA: University of New Hampshire
Chatila R., Laumond J.1985. Position referencing and consistent world modeling for mobile robots.IEEE International Conference on Robotics and Automation. St. Louis, Missouri, USA:138-145
Chen G. Y., Tsai W. H.2000. Vision-based Obstacle Detection and Avoidance for Autonomous LandVehicle Navigation in Outdoors Roads. Automation in Construction.10:1-25
Cheng H. D., Chen Y. H., Jiang X. H.2000. Thresholding Using Two-Dimensional Histogram andFuzzy Entropy Principle. IEEE Transactions on Image Processing.9(4):732-735
Cheng H., Chen Y. H., Sun Y.1999. A novel fuzzy entropy approach to image enhancement andthresholding. Signal Processing.75(3):277-301
Chopra A.2009. An Empirical approach to path planning in unstructured outdoor environments.[Master Thesis]. Toronto, Ontario, Canada: York University
Christopher J. C. H. W.1989. Learning from Delayed Rewards.[PH. D Dissertation]. Cambridge,London, United Kingdom: King's College
Coates A., Abbeel P., Ng A. Y.2008. Learning for control from multiple demonstrations. Proceedingsof the25th International Conference on Machine Learning. Helsinki, Finland:144-151
Coggan M.2008. Reinforcement learning in commercial computer games.[Master Thesis]. Montreal,Quebec, Canada: MCgill University
de Carvalho R. N., Vidal H. A., Vieira P., Ribeiro M. I.1997. Complete Coverage Path Planning andGuidance for Cleaning Robots. IEEE International Symposium on Industrial Electronics. Guimaraes,Portugal:1-6
D'Esnon A. G., Rabatel G., Pellenc R.1987. Magali: A self-propelled robot to pick apples. ASAEPaper87-1037.: St. Joseph, Missouri,49085
Dijkstra E.1959. A note on two problems in connection with graphs. Numerische Mathematik.1:269-270
Dima C., Hebert M.2005. Active Learning For Outdoor Obstacle Detection. Proceedings of Scienceand Systems.:3-15
Dollé L., Sheynikhovich D., Girard B., Chavarriaga R., Guillot A.2010. Path planning versus cueresponding: a bio-inspired model of switching between navigation strategies. Biologicial Cybernetics.103:299-317
Doya K.2000. Reinforcement learning in continuous time and space. Neural Computation.12(1):219-245
Driscoll T. M.2011. Complete coverage path planning in an agricultural environment.[Master Thesis].Ames, Iowa, USA: Iowa State University
Duguleana M., Barbuceanu F. G., Teirelbar A., Mogan G.2012. Obstacle avoidance of redundantmanipulators using neural networks based reinforcement learning. Robotics and Computer-IntegratedManufacturing.28:132–146
Ernst D., Glavic M., Capitanescu F., Wehenkel L.2009. Reinforcement learning versus modelpredictive control: a comparison on a power system problem. IEEE Transactions on Systems, Man andCybernetics Part B.39(2):517-529
Esmaili M., Naghdy F.1992. Further progress in robotics fruit harvesting and grading. Proceedings ofthe International Conference on Manufacturing Automation,10-12Aug.1992. Hong Kong, HongKong:812-17
Ferdaus S. N.2008. A topological approach to online autonomous map building for mobile robotnavigation.[Master Thesis]. Newfoundland, Canada: Memorial University of Newfoundland
Fernandez-Maloigne C., Laugier D., Boscolo C.1993. Detection of apples in natural images withtexture analysis. Proceedings of the International Conference on Intelligent Autonomous Systems IAS-3,15-18Feb.1993. Amsterdam, Netherlands:664-674
Gmen H.., Gagné S.1990. Neural network architectures for motion perception and elementarymotion detection in the fly visual system. Neural Networks.3(5):487-505
Grossberg S.1983. Absolute stability of global pattern formation and parallel memory storage bycompetitive neural networks. IEEE Transactions on Systems Man and Cybernetics.13(5):815-926
Grossberg S.1988. Nonlinear neural networks: Principles, mechanisms, and architecture. NeuralNetworks.1:17-61
Guo F., Cao Q. X.2004. Study on Color Image Processing based Intelligent Fruit Sorting System.Proceedings of the5" World Congress on Intelligent Control and Automation. Hangzhou, P.R.China:4802-4805
Han K. M.2007. Collision Free Path Planning Algorithms for Robot Navigation Problem.[MasterThesis]. Columbia, Missouri, USA: University of Missouri-Columbia
Hart S. W.2009. The development of hierarchical knowledge in robot systems.[PH. D Dissertation].Amherst, Massachusetts, USA: University of Massachusetts Amherst
Horn B. K., Schunck B. G.1981. Determining optical flow. Artificial Intelligence.17(1):185-203
Hosseinzadeh A., Izadkhah H.2010. Evolutionary Approach for Mobile Robot Path Planning inComplex environment. IJCSI International Journal of Computer Science Issues.4(7):1-9
Huang L., He D.2012. Ripe Fuji Apple Detection Model Analysis in Natural Tree Canopy.TELKOMNIKA.10(7):1537-1542
Huang L., Yang S. X., He D.2012. Abscission Point Extraction for Ripe Tomato Harvesting Robots.Intelligent Automation and Soft Computing.18(6):751-763
Ji W., Zhao D., Cheng F., Xua B., Zhang Y., Wang J.2011. Automatic recognition vision systemguided for apple harvesting robot. Computers and Electrical Engineering.5(38):1186-1195
Jiménez A. R., Ceres R., Pons J. L.2002. A Survey of Computer Vision Methods for Locating Fruiton Trees. Transactions of the ASAE.43(6):1911-1920
Jimenez A., Jain A. K., Ceres R., Pons J. L.1999. Automatic fruit recognition: a survey and newresults using range/attenuation images. Pattern Recognition.32(10):1719-1736
Jin D., Lin S.2012. Improved Genetic Algorithm Based2-D Maximum Entropy Image SegmentationAlgorithm. Advances in CSIE.2:529-534
Kaelbling L. P., Littman M. L., Cassandra A. R.1998. Planning and acting in partially observablestochastic domains. Artificial Intelligence.101(1-2):99-134
Kapur J. N., Sahoo P. K., Wong A. K. C.1985. A new method for gray level picture thresholdingusing the entropy of the histogram. Vision Graphics Image Process.29:273–285
Kortenkamp D., Wermouth T.1994. Topological mapping for mobile robots using a combination ofsonar and vision sensing. Proceedings of the national conferenceon artificial intelligence:979-984
Kuipers B.1978. Modeling spatial knowledge. Cognitive Science.2(2):129-153
Kuipers B.2000. The Spatial Semantic Hierarchy. Artificial Intelligence.(119):191-233
Kuipers B., Byun Y. T.1991. A robot exploration and mapping strategy based on a semantic hierarchyof spatial representations. Journal of Robotics and Autonomous Systems.(8):47-63
Kuter U.2006. Planning under uncertainty: Moving forward.[PH. D Dissertation]. College Park,Maryland, USA: University of Maryland at College Park
Laemmer E., Deruyver A., Sowinska M.2002. Watershed and adaptive pyramid for determining theapple's maturity state. Proceedings of ICIP2002International Conference on Image Processing. Rochester,New York, USA:I/789-I/792
Lei Z.2011. A Robotic Approach to the Analysis of Obstacle Avoidance in Crane Lift Path Planning.[Master Thesis]. Edmonton, Alberta, Canada: University of Alberta
Li X., Wang J., Ning X.2011. A*algorithm based robot path planning method. Applied Mechanicsand Materials.63-64:686-689
Littman M. L.1996. Algorithms for Sequential Decision Making.[PH. D Dissertation]. Providence,Rhode Island, USA: Brown University
Liu S. R., Qiu X. N., Yang S. X.2005. Heuristic template approach to complete coverage pathplanning of mobile robot.4th International Conference on Engineering Applications and ComputationalAlgorithms. University of Guelph, Guelph, Canada:358-363
Lu J.2009. Learning Multi-Agent Pursuit of a Moving Target.[Master Thesis]. Edmonton, Alberta,Canada: University of Alberta
Luo C.2002. Neural dynamics and computation for complete coverage path planning of mobilecleaning robots.[Master Thesis]. Guelph, Ontario, Canada: University of Guelph
Luo C., Yang S. X., Meng M. Q. H.2005. Real-time Map Building and Area Coverage in UnknownEnvironments. Proceedings of the2005IEEE International Conference on Robotics and Automation.Barcelona, Spain:1736-1741
March P. S.2008. Geometric-based Spatial Path Planning.[PH. D Dissertation]. Austin, Texas, USA:University of Texas at Austin
Marvel J. A.2010. Autonomous learning for robotic assembly applications.[PH. D Dissertation].Cleveland, Ohio, USA: Case Western Reserve University
Men H.2012. Robotic exploration for mapping: Systems and algorithms.[PH. D Dissertation].Hoboken, New Jersey, USA: Stevens Institute of Technology
Minsky M. L.1954. Theory of Neural-analog Reinforcement Systems and its Application to theBrain-model Problem.[PH. D Dissertation]. Princeton, New Jersey, USA: Princeton University
Minsky M. L.1961. Steps toward Artificial Intelligence. Proceedings of the Institute of RadioEngineers:49(3):8-30
Nash A.2012. Any-angle path planning.[PH. D Dissertation]. Los Angeles, California, USA:University of Southern California
Nicolás N., Cornelius W., Pascal S., Stefan W.2012. Real-world reinforcement learning forautonomous humanoid robot docking. Robotics and Autonomous Systems.60:1400-1407
Norwood J. D.1989. Robotic path planning and obstacle avoidance: A neural network approach.[Master Thesis]. Houston, Texas, USA: Rice University
Oh J. S., Choi Y. H., Park J. B., Zheng Y. F.2004. Complete coverage navigation of cleaning robotsusing triangular-cell-based map. IEEE Transactions on Industrial Electron.51(3):718-726
Ollis M., Stentz A.1997. Vision-based perception for an antomated harvester. Proceedings of the1997IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS'97:1838-1844
Pal S. K., King R. A., Hashim A. A.1983. Automatic Gray Level Thresholding through Index ofFuzziness and Entropy. Pattern Recognition Letters.1:141-146
Parker L. E.1999. Cooperative Robotics for Multi-target Observation. Intelligent Automation and SoftComputing, Special issue on Robotics Research at Oak Ridge National Laboratory.5(1):5-19
Parrish E., Goksel A. K.1977. Pictorial pattern recognition applied to fruit harvesting. Transactions ofthe ASAE.20(5):822-827
Penman D. W.2001. Determination of stem and calyx location on apples using automatic visualinspection. Computers and Electronics in Agriculture.33(1):7-18
Peterson D. L., Bennedsen B. S., Anger W. C., Wolford S. D.1999. A Systems Approach to RoboticBulk Harvesting of Apples. Transactions of the ASAE.42(4):871-876
Peterson D. L., Kornecki T. S.1987. Mechanical apple harvester for T-trellis canopies. Transactionsof the American Society of Agricultural Engineers.30(3):597-600
Peterson D. L., Miller S. S., Kornecki T. S.1985. Over-the-row harvester for apples. Transactions ofthe American Society of Agricultural Engineers.28(5):1393-1397
Pun T.1980. A new method for gray-level picture thresholding using the entropy of the histogram.Signal Processing.2:223-237
Pun T.1981. Entropy thresholding, a new approach. Compute Graphics and Image Processing.16:210-239
Rakun J., Stajnko D., Zazula D.2011. Detecting fruits in natural scenes by using spatial-frequencybased texture analysis and multiview geometry. Computers and Electronics in Agriculture.76(1):80-88
Rao N. S. V.1988. An algorithmic framework for robot navigation in unknown terrains.[PH. DDissertation]. Baton Rouge, Louisiana, USA: Louisiana State University and Agricultural and MechanicalCollege
Reynolds S.1993. Building a map for robot path planning by fusing video images and laserrangefinder data.[PH. D Dissertation]. Houston, Texas, USA: Rice University
Safren O., Alchanatis V., Ostrovsky V., Levi O.2007. Detection of green apples in hyperspectralimages of apple-tree foliage using machine vision. Transactions of the ASABE.50(6):2303-2313
Sahoo P. K., Arora G.2004. A thresholding method based on two-dimensional Renyi's entropy.Pattern Recognition.37(6):1149-1161
Sahoo P., Wilkins C., Yeager J.1997. Threshold selection using Renyi's entropy. Pattern Recognition.30(1):71-84
Schaal S., Atkeson C. G.1993. Open loop stable control strategies for robot juggling. IEEEInternational Conference on Robotics and Automation. Atlanta, Georgia, USA:913-918
Schertz C. E., Brown G. K.1968. Basic considerations in mechanizing citrus harvest. Transactions ofthe ASAE.11(2):343-346
Setiawan A. I., Furukawa T., Preston A.2004. A low-cost gripper for an apple picking robot.2004IEEE International Conference on Robotics and Automation. New Orleans, Louisiana, USA:4448-4453
Shatkay H., Kaelbling L. P.2002. Learning geometrically constrained hidden Markov models forrobot navigation: Bridging the topological-geometrical gap. Journal of Artificial Intelligence Research.16:167-207
Silver D.2009. Reinforcement Learning and Simulation-Based Search in Computer Go.[PH. DDissertation]. Edmonton, Alberta, Canada: University of Alberta
Simmons R., Koenig S.1995. Probabilistic robot navigation in partially observable environments.Proceeding of IJCAl. Montreal, Canada:1080-1087
Sorg J. D.2011. The Optimal Reward Problem: Designing Effective Reward for Bounded Agents.[PH. D Dissertation]. Ann Arbor, Michigan, USA: University of Michigan
Stajnko D., Lakota M., Hocevar M.2004. Estimation of number and diameter of apple fruits in anorchard during the growing season by thermal imaging. Computers and Electronics in Agriculture.(42):31-42
Sutton R. S.1988. Learning to predict by the method of temporal differences. Machine Learning.3(1):9-44
Sutton R. S.1990. Integrated architectures for learning, planning, and reacting based onapproximating dynamic programming. Proceedings of the7th International Conference on MachineLearning. Austin, Texas, USA:216-224
Sutton R. S., Mcallester D., Singh S., Mansour Y.2000. Policy gradient methods for reinforcementlearning with function approximation. Advances in Neural Information Processing Systems12:1057-1063
Tabb A. L., Peterson D. L., Park J.2006. Segmentation of apple fruit from video via backgroundmodeling.2006ASABE Annual International Meeting. Portland, Oregon, USA:No.063060
Theodorou E. A.2011. Iterative Path Integral Stochastic Optimal Control: Theory and Applications toMotor Control.[PH. D Dissertation]. Los Angeles, California, USA: University of Southern California
Thrun S.1998. Learning metric-topological maps for indoor mobile robot navigation.99(1):21-71
Thrun S., Bucken A.1996. Integrating grid-based and topological maps for mobile robot navigation.Proceedings of the AAAI13th National Conference on Artificial Intelligence. Portland, Oregon,USA:944-950
Unay D., Gosselin B.2005. Thresholding-based segmentation and apple grading by machine vision.13th European Signal Processing Conference, EUSIPCO2005, September4,2005-September8,2005.Antalya, Turkey:926-929
Unay D., Gosselin B., Debeir O.2006. Apple stem and calyx recognition by decision trees.Proceedings of the6th IASTED International Conference on Visualization, Imaging, and Image Processing.Palma de Mallorca, Spain:549-552
Wachs J. P., Stern H. I., Burks T., Alchanatis V.2010. Low and high-level visual feature-based appledetection from multi-modal images. Precision Agriculture.11(6):717-735
Walsh T. J., Nouri A., Li L., Littman M. L.2009. Learning and planning in environments with delayedfeedback. Autonomous Agents and Multi-Agent Systems.18(1):83-105
Wang X.2007. A vision-based perceptual learning system for autonomous mobile robot.[PH. DDissertation]. Nashville, Tennessee, USA: Vanderbilt University
Watkins C. J. C. H., Dayan P.1992. Q-Learning. Machine Learning.8:279-292
Whiteson S. A.2007. Adaptive representations for reinforcement learning.[PH. D Dissertation].Austin, Texas, USA: University of Texas at Austin
Xu B.2009. Fast Path Planning in Uncertain Environments: Theory and Experiments.[PH. DDissertation]. Blacksburg, Virginia, USA: Virginia Polytechnic Institute and State University
Xu H., Yang S. X.2002. Real-time Collision-free Motion Planning of Nonholonomic Robots using aNeural Dynamics based Approach. Proceedings of the2002IEEE International Conference on Robotics&Automation. Washington DC, USA:3087-3092
Yang S. X.2003. Neural dynamics and computation for real-time map building and path planning ofmobile robots. Dynamics of Continuous Discrete and Impulsive Systems-Series B-Applications&Algorithms.10(1-3):1-17
Yang S. X., Meng M.2001. Neural network approaches to dynamic collision-free trajectorygeneration. IEEE Transactions on Systems Man and Cybernetics Part B-Cybernetics.31(3):302-318
Yang S. X., Yuan G., Meng M.2001. Real-time Collision-free Path Planning and Tracking Control ofa Nonholonomic Mobile Robot using a Biologically Inspired Approach. Proceeding of2001IEEEIntentional Symposium on Computational Intelligence in Robotics and Automation. Banff, Alberta,Canada:113-118
Yang S. X., Zhu A., Yuan G., Meng M. Q. H.2012. A Bioinspired Neurodynamics-Based Approachto Tracking Control of Mobile Robots. IEEE Transactions on Industrial Electronics.59(8):3211-3220
Yang X.1999. Neural network approaches to real-time motion planning and control of roboticsystems.[PH. D Dissertation]. Edmonton, Alberta, Canada: University of Alberta
Yen G. G., Hickey T. W.2004. Reinforcement learning algorithms for robotic navigation in dynamicenvironments. ISA Transactions.43:217-230
Yin H., Chai Y., Yang S. X., Mittal G. S.2009. Ripe Tomato Extraction For A Harvesting RoboticSystem. Proceedings of the2009IEEE International Conference on Systems, Man and Cybernetics. SanAntonio, TX, USA:2984-2989
Zamstein L. M.2009. Koolio: Path-Planning using Reinforcement Learning on a Real Robot in a RealEnvironment.[PH. D Dissertation]. Gainesville, Florida, USA: University of Florida
Zhang G., Lu W., Ferrari S.2012. An Information Potential Approach to Integrated Sensor PathPlanning and Control. IEEE Transactions on Robotics.7:1-17
Zhang J., He D., Huang L.2012. Recognition and segmentation of Fuji apples in orchards based on2D entropy. International Journal of Digital Content Technology and its Applications.6(18):572-578
Zhao D. A., Lv J. D., Ji W.2011. Design and control of an apple harvesting robot. BiosystemsEngineering.110(2):112-122
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |