摘要
移动机器人是一种集环境感知、动态决策与规划、行为控制与执行等多种功能于一体的综合系统,由于其较高的自主性、智能性和对外界环境的自适应性,使得移动机器人在各行业有一个广阔的应用前景,并成为机器人领域的一个重要分支。近几年来,移动机器人已广泛应用于星球探测、军事侦察、医疗服务、危险及恶劣环境作业、农业生产等方面,本文中重点研究移动机器人在农业中的应用。自主学习的农业机器人要求所有机器人都是全自主的,即传感器信息获取、任务规划、运动控制都是由机器人自身完成。
对于自主学习的机器人,需要一种机器学习策略的支持,进行信息获取、任务规划和运动控制。机器学习研究的一个主要问题就是针对一个学习任务,通过选取一组具有代表性的特征属性,构建一个模型。而机器学习最初的研究动机就是为了使计算机系统具有人的学习能力从而实现人工智能。之后我们又提出了自主式机器学习方法(即自主学习),摆脱了在知识获取过程中对领域专家知识依赖的约束。
20世纪90年代初期,随着统计学习理论的逐步完善,基于此理论的算法——支持向量机也随之出现。支持向量机现在已成为一种倍受关注的机器学习。由于SVM训练数据样本时,需要消耗大量的时间,而为了加快训练的速度,本文提出了一种新的自主学习策略——基于聚类分析的增量式支持向量机的学习策略。结合时间权重和数据特征分布对数据进行分析,使算法适合于处理随时间变化的大量数据。特别的,我们通过对比实验验证了这种算法的有效性和实用性。
由于加工偏差及机器人调试中后期结构的调整,势必造成质心相对几何中心的偏移。常规做法是在机器人制作完成后施加配重微调质心,但配重的加入会带来更多的能耗。为了解决该问题,本文提出了基于质心偏移时对机器人的运动控制方法,通过建立四轮机器人的控制模型,分析了质心偏移对机器人运动状态的产生的影响,并采用线性规划的方法对机器人各轮电机的出力分布进行了优化,得到质心偏移时在保证合力最大情况下电机的最省能耗。实验结果验证了该算法的有效性和正确性。
Mobile robot is a integrated system that includes several functions. Because of its high autonomy, intelligence and adaptability to the external environment, the mobile robot has a broad application prospects in various industries, and becomes an important branch in the field of robotics. In recent years, mobile robots have been widely used in planetary exploration, military reconnaissance, medical services, hazardous and harsh environment operations, agriculture, etc. This paper focuses on the mobile robot applications in agriculture.
Autonomous learning requires that all agricultural robots are fully autonomous, that is to say, sensor information acquisition, mission planning, and motion control are done by the robot itself. In recent years, a method named Learning from Demonstration used in agriculture robot has been gradually developed and become the research point in artificial intelligence and machine learning areas。In the early 90s, Support Vector Machine presents with the gradual improvement of statistical learning theory, based on this theory algorithm. Support Vector Machine now has become a closely watched classification technology.
When SVM trains data samples, it needs to consume a large amount of time. So to accelerate the training speed, we propose a new learning strategies—the learning strategy based on clustering of increamental svm. We analyze datas by combinating of time weight and data features to make the algorithm suitable for processing large amounts of datas. In particular, we prove the effectiveness and practical of this algorithm with the experiments.
Mobile Robot often has an eccentric centroid because of the limited precision in producing causes. That results in difference of robot's final position between expected one and actual one since most control approaches are based on an ideal model whose centroid is not eccentric, thus extra energy is needed for robots to adjust that difference. To solve this problem, we build a model with eccentric centroid to analyze the distribution of traction on each wheel in this condition and get an optimization solution set of this traction with linear programming algorithm. Specifically, we conduct simulation experiments to demonstrate the algorithm is of positive effect in reducing cost of extra energy.
引文
[1]陈春林.基于强化学习的移动机器人自主学习及导航控制[D].合肥:中国科技大学模式识别与智能系统,2006.
[2]易中懿,胡志超.农业机器人概况与发展[J].江苏农业科学,2010(2):390-393.
[3]沈明霞.自主行走农业机器人视觉导航信息处理技术研究[D].江苏:南京农业大学农业工程学院,2001.
[4]张学工.关于统计学习理论与支持向量机[J].自动化学报,2000(126):32-42.
[5]范明,范宏建等译.数据挖掘导论[M].北京:人民邮电出版社,2006.
[6]van Henten EJ, van Tuijl BAJ, Hemming J, et al. Field test of an autonomous cucumber picking robot [J]. Biosystems Engineering,2003,86(3):305-313.
[7]Qiao J, Sasao A, Shibusawa S, et al. Mapping yield and quality using the mobile fruit grading robot [J]. Biosystems Engineering,2005,90 (2):135-142.
[8]Reed J N, M iles S J, But ler J, et al. Automat icmush room harvester evelopment [J]. Agric. Engng. Res.2001,78(1):15-23.
[9]杨宝珍,安龙哲,李会荣.农业机器人的应用及发展[J].农机使用与维修,2008(6):103-106.
[10]王辉,程雪,李玉霞.农业机器人应用进展初探[J].安徽农业科学,2009,37(16):7674-7675.
[11]戴乃昌.农业机器人的发展和应用初探[J].农机化研究,2009(2):241-243.
[12]王珏,石纯一.机器学习研究[J].广西师范大学学报(自然科学版),2003,21(2):1-15.
[13]刘益,唐远翔.机器学习的知识结构[J].福建电脑,2010(3):76-78.
[14]许程.机器学习的主要策略与基本结构[J].科技资讯,2010(3):185.
[15]郭亚宁,冯莎莎.机器学习理论研究[J].科技教育创新,2010(14):208-210.
[16]Vapnik V. N. The Nature of Statistical Learning Theory [M]. New York:Springer-Verlag. 1995.
[17]AP Engelbrecht et al. Incremental Learning Using Sensitivity Analysis [J]. Neural Networks,1999(2):1350-1355.
[18]王静.基于DFL的自主学习子空间学习算法及应用研究[D].江苏:苏州大学计算机应用技术,2008.
[19]张莹.基于自主学习的中文文本分类算法研究[D].黑龙江:哈尔滨工业大学计算机科学与技术,2006.
[20]Dacid D. Lewis, William A. Gale. A Sequential Algorithm for Training Text Classifiers [C], Proceedings of the 17the Annual ACM-SIGIR Conference, London U.K.,1994.
[21]Dacid D. Lewis, Catlett J. Heterogeneous Uncertainty Sampling for Supervised Learning [C]. Proceedings of the Eleventh International Conference on Machine Learning, New Brunswick, NJ.1994.
[22]H. S. Seung, M. Opper, H. Somepolinsky. Workshop on Computation Learning Theory [J]. Query by Committee. Proc.5th Annu,1992:287-294.
[23]Greg Schohn, David Cohn. Less is More:Active Learning with Support Vector Machines [J], International Conference Machine Learning,2000:839-846.
[24]Simon Tong, Daphne Koller. Support Vector Machine Active Learning with Applications to Text Classification [J]. Journal Machine Learning Research.2001:999-1006.
[25]David A. Cohn, Zoubin Ghahramani, Michael I.Jordan. Active Learning with Statistical Models [J]. Artificial Intelligence Research.1996(4):129-145.
[26]Vapnik V, Levin E, Le Cun Y. Measuring the VC·dimension of a learning machine [J]. Neural Computation,1994(6):851-876.
[27]Vapnik V. N. The Nature of Statistical Learning Theory [M], New York:Springer·Verlag, 1995.
[28]Burges C.J.C. A tutorial on support vector machines for pattern recognition [J]. Data Mining and Knowledge Discovery,1998(2):24-29.
[29]罗瑜.支持向量机在机器学习中的应用研究[D].四川:西南交通大学交通信息工程与控制,2007.
[30]张浩然,汪晓东.支持向量机的学习方法综述[J].浙江师范大学学报(自然科学版),2005(28):283-288.
[31]梁俊芝.关于支持向量机方法的几点研究[D].陕西:西北大学应用数学,2009.
[32]李海,李春来,侯德艳.支持向量机下机器学习模型的分析[J].吉首大学学报(自然科学版),2010(31):39-42.
[33]梁宏霞.支持向量机模型研究及应用[D].辽宁:辽宁师范大学计算机应用,2009.
[34]林沂蒙.支持向量机的模型选择研究[D].黑龙江:哈尔滨工业大学计算机科学与技术,2006.
[35]李海生.支持向量机回归算法与应用研究[D].广东:华南理工大学自动化科学与工程学院自动化与网络工程系,2005.
[36]杜树新,吴铁军.回归型加权支持向量机方法及其应用[J].浙江大学学报(工学版),2004(38):302-306.
[37]郎宇宁,蔺娟如.基于支持向量机的多分类方法研究[J].中国西部科技,2010(17):28-29.
[38]黄勇,郑春颖,宋忠虎.多类支持向量机算法综述[J].计算技术与自动化,2005(24):61-63.
[39]孔波,郑喜英.支持向量机多类分类方法研究[J].河南教育学院学报(自然科学版),2010(19):9-12.
[40]陈树.聚类算法模型的研究及应用[D].江苏:江南大学轻工信息技术与工程,2007.
[41]行小帅,焦李成.数据挖掘的聚类方法[J].电路与系统学报,2003(8):59-67.
[42]陈建.浅析常用聚类分析算法[J].安徽电子信息职业技术学院学报,2007(28):100-102.
[43]王实,高文.数据挖掘中的聚类方法[J].计算机科学,2000(27):42-45.
[44]Honglian Li, Chunhuan Wang, Baozong Yuan, Zhanhui Zhu. A Learning Strategy of SVM Used to Large Training Set [J], Chinese Journal of Computers,2004(27):715-719.
[45]Jair Cervantes, Xiaoou Li, Wen Yu. Support Vector Classification for Large Data Sets by Reducing Training Data with Change of Classes [J], Man and Cybernetics, 2008:2609-2614
[46]Hongle Du, Shaohua Teng, Qingfang Zhu. Fast SVM incremental learning based on clustering algorithm[J], Intelligent Computing and Intelligent Systems,2009:13-17.
[47]卢慧民.机器人全向视觉系统自定位方法研究[D].湖南:国防科技大学,2005.
[48]王晓荣,张印强,陆艳.全自主移动足球机器人目标识别[J].机器人技术,2008,24(10-2):226-227.
[49]毛慧珍,陈西平,浮红霞等.中型组足球机器人全向视觉定位技术[J].信息技术,2009,1:5-9.
[50]刘玉鹏.多传感器系统设计及其在机器人定位中的应用[D].湖南:国防科技大学,2005.
[51]廖华丽,李波,赵俊.轮式移动机器人的全方位运动分析[J].机电一体化,2009,15(5):61-64.