智能轮椅导航与多传感器信息融合研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
智能轮椅是智能机器人技术在服务机器人领域的一个应用,目的是帮助老年人和残障人士提高行动自由度,让他们能重新融入社会。伴随着仿生学、微电子技术、模式识别等高科技的发展,轮椅功能发生了根本性的变革,具有记忆地图、避障、自动行走、与用户交互及为用户特殊需要服务等功能。本文综合分析了智能轮椅国内外研究现状,在此基础上对智能轮椅的导航及多传感器信息融合进行了研究。
     本文首先提出了基于模块化设计思想的智能轮椅硬件系统和控制体系方案。对智能轮椅运动学特性进行了分析,建立了坐标变换数学模型。设计了基于模糊神经网络的多传感器信息融合过程。对BP网络的动量梯度下降算法和L-M优化算法进行了MATLAB仿真比较,提出了一种简单、高效的分区算法用于对传感器数据进行初步融合,并将障碍物距离信息模糊化,然后采用BP神经网络对障碍物环境分类,成功地利用L-M优化算法进行了模式识别。
     在完成多传感器信息融合的基础上对智能轮椅导航进行了研究,实现了环境建模和路径规划:采用链接图法进行了全局环境信息建模,将全局路径规划转换为求带权无向图A中两点最短距离的问题,编制了基于C语言的Dijkstra算法程序实现全局路径规划,并提出了一种简单的几何方法优化全局路径:依据多传感器信息融合结果进行局部环境信息建模,实现了对环境的识别,设计了轮椅导航中跟踪全局路径、目标制导和避障行为,并给出了各种行为的算法。
     开发了基于VC6.0的轮椅导航运动动态仿真平台,给出了多种情况下的仿真结果,仿真结果表明本文提出的导航方法是切实可行的,与其它已有方法相比具有在相近的障碍物之间可以发现路径和在障碍物前并没有出现振荡的优点。
     以上的研究为智能轮椅的导航和多传感器信息融合提供了新的方法和思路,具有较好的规划能力、实时性和实用性。同时该研究方法也适用于移动机器人。
Intelligent wheelchair is an application of intelligent robot technology . Wheelchairs as mobility aids to handicapped persons and the elderly help that they can be in harmony with society. With the development of bionics, micro-electronics and pattern distinction, the skill of wheelchair changes profoundly, having the abilities of remembering map,avoiding obstacles,autonomous mobile ,communicat-ing with users and servicing users. In this paper the navigation of intelligent wheelchair and multi-sensors fusion are researched.
    The hardware and soft structure of wheelchair are designed and the kinematics character is analyzed. A multi-sensors fusion system based fuzzy logic neural network is brought forward and the momentu grads descend arithmetic and L-M advanced arithmetic are compared. Furthmore,a subarea arithmetic for fusing primarily is put forward and the obstacle environment is sorted by BP network.
    Based the result of multi-sensors fusion the sort of environment and path planning are achieved. MAKLINK Graph is used for modeling whole environment and with Dijkstra arithmetic and a geometry method the mininum value is worked out . The behaviors among navigation are designed.
    A simulation system is designed through VC6.0. Simulation results in kinds of environment are given. The results indicate that the navigation
    
    
    method is good and feasible. Compared with other arithmetic the strongpoints of this method are it can find out safe path between near obstacles without surge.
    In the support of above achievement,a flexible and good method of navigation and multi-sensors fusion is found.The result in this paper can be used in mobile robot and high performance can also be gained.
引文
[1] G.Bourhis,O.Hom,O.Habert,A.Pruski.An autonomous vehicle for people with motor disabilities.IEEE Robotics and Automation.2001.vol.8.pp20~28
    [2] Axel lankenau,Thomas rofer. A versatile and safe mobility assistant. IEEE Robotics and Automation. 2001.vol.8.pp29~37
    [3] Erwin Prassler, Jens Scholz,Paolo Fiorini.A robotic wheelchair for crowded public environments. IEEE Robotics and Automation. 2001 vol.8.pp38~45
    [4] Manuel mazo, the research group of the SIAMO project.An integral system for assisted mobility. IEEE Robotics and Automation.2001 vol.8.pp46~56
    [5] Christian martens,Nils ruchel, Oliver lang, Oleg ivlev, Axel graser. A friend for assisting handicapped people.IEEE Robotics and Automation. 2001 vol.8.pp57~65
    [6] H.A.Yanco.Integrating robotic research:A survey of robotic wheelchair development, in Proc. AAAI Spring Symposium on Integrating Robotic Research, Stanford University.CA. 1998
    [7] E.Prassler, J.Scholz,M.Strobel.Maid: Mobility assistance for elderly and disabled people.inProc.24th Int.Conf.IEEE.Industrial.ElectronicsSoc.IECON'98,Aachen,Germa ny. 1998
    [8] MIT Artificial Intelligence Laboratory.Preliminary Investigation of a Semi-Autonomous Robotic Wheelchair Directed Through Electrodes.June 1997 published in Proceedings of the Rehabilitation Engineering and Assistive Technology Society of North America annual Conference.RESNA Press. 1997.pp.414~416
    [9] Klaus Schilling, Hubert Roth, Robert Lieb, Hubert Stützle .Sensors to Improve the Safety for Wheelchair Users. TIDE 1998 Conference
    [10] Th.Rofer, A.Lankenau. Architecture and application of the Bremen Autonomous Wheelchair Information Sciences.2000.1~20
    [11] L.Boquete,P.Martin,M.Mazo.Hardware implentation of a new neurocontrol wheerchair-guidance system.neurocomputing 47(2002) 145~160
    [12] Vijay Kumer, Tariq Rahman,Venkat Krovi, Assistive Devices For People With
    
    Motor Disabilities.wiley Encyclopaedia of Electrics Engineering, 1997
    [13] M.Mazo,J.C.Garcia,F.J.Rodriguez.Integral system for assisted mobility, Information Sciences.2000(129).pp1~20
    [14] 新华网.日本发明一种声控轮椅.www.chinese.com.2001年11月26日
    [15] 李学恩.智能轮椅导航与定位:[硕士学位论文].北京:中科院,2002
    [16] 李贻斌,李彩虹,刘明,周风余,苏学成.移动机器人导航技术.山东科技大学学报(自然科学版)1999,3:67~71
    [17] 王宏,张钹.基于地图的室外移动机器人路径规划与导航系统.机器人.1994,16(1):24~29
    [18] 孟凯,孙茂相,孙金根.基于主动路标的全方位移动机器人定位系统.沈阳工业大学学报.2000,22(2):148~151
    [19] 刘伟军,董再励,郝颖明,朱枫.基于立体视觉的移动机器人自导航定位系统.高技术通讯.2001,10:91~94
    [20] 柳明,冯建农.一种基于多信息融合的环境探测方法.华南理工大学学报(自然科学版).1998,26(9):112~116
    [21] 冯建农,柳明,吴捷.自主移动机器人智能导航研究进展.机器人.1997,19(6):468~473
    [22] 李磊,叶涛,谭民.移动机器人技术研究现状与未来.机器人.2002,24(5):475~480
    [23] 徐国华,谭民.移动机器人的发展现状及其趋势.机器人技术与应用.2001,3:7~14
    [24] 王祁,聂伟,张兆礼.数据融合与智能传感系统.传感器技术.1998,17(6):51~53
    [25] 王耀南,李树涛.多传感器信息融合及其应用综述.控制与决策.2001.16(5):518~522
    [26] Gavey T D,et al. An Inference Technique for Integrating Knowledge from Disparate Sources.Proc.7th Joint Conf.Artifieial Intelligent. 1981
    [27] Durrant-Whyte.Sensor Models and Multisensor Integration.Int Journ.of Robotics Research, 1988(7)
    [28] Durrant-Whyte,et al. Toward a Fully Decentralized Architecture for Multi Sensor Data Fusion.Proc of IEEE Int.Conf.on Robotics and Automations,1990
    
    
    [29] Wan W, Fraser D.Multisource data fusion with multiple self-organizing maps.IEEE Trans on GeosciRemote Sensing,1999,37(3): 1344~1349
    [30] 王耀南.计算智能数据处理技术及其应用.长沙:湖南大学出版社,1999.18~21
    [31] 蔡自兴.机器人学.清华大学出版社.2000.230~231
    [32] 张伟.美国马里兰大学自动化研究中心机器人教研工作一瞥.机器人技术与应用2001,3:37~39
    [33] Thorsten Belker, Michael Beetz, Armin B. Cremers. Learning action models for the improved execution of navigation plans. Robotics and Autonomous Systems, Volume 38, Issues 3-4, 31 March 2002, PP137~148
    [34] 谭民.先进机器人控制技术研究与发展.迈向新世纪的中国机器人.辽宁科学技术出版社.2000.46~48
    [35] 欧青立,何克忠.室外智能移动机器人的发展及关键技术研究.机器人.2000,22(6):519~526
    [36] 陈方,高升.语音识别技术及发展.电信科学1996,10:54~57
    [37] 陈永.MIS界面设计的工效学原则.湖北汽车工业学院学报2001,2:41~43
    [38] 刘锋.服务机器人实用化关键技术研究:[硕士学位论文].武汉.华中理工大学.2001
    [39] 蔡希饶,康耀红,卢科学.多传感器数据融合的研究现状.西安电子科技大学学报.1994,21(增刊)
    [40] 张福学.传感器应用及其电路精选.电子工业出版社.1993.274
    [41] 李圣怡.多传感器信息融合理论及在智能制造系统中的应用.长沙:国防科技大学出版社.1998.119~190
    [42] 诸静.模糊控制原理与应用.机械工业出版社.2001
    [43] 许东.基于MATLAB6.X的系统分析与设计——神经网络.西安电子科技大学出版社.2002.1~3
    [44] 程卫国,冯峰.MATLAB5.3应用指南.人民邮电出版社.2000
    [45] Habit M K,Asama H. Efficient Method to Generate Collision Free Paths for Autonomous Mobile Robot Based on New Free Space Structuring Approach. IEEE/RSJ IROS'91.1991.PP563~567
    
    
    [46] 周明.使用遗传算法规划移动机器人路径.西北工业大学学报.1998(3):219~223
    [47] Canny J F, et al.Simplified voronoi diagrams.Discrete and Computational Geometry. 1988(3):219
    [48] 邹小兵,蔡自兴.基于传感器信息的环境非光滑建模与路径规划.自然科学进展.2002(11):1188~1192
    [49] 陆新华,张桂林.室内服务机器人导航方法研究.机器人2003(1):80~87
    [50] Y Koren,J Borenstein.Potential Field Methods and Their Inherent Limitation for Mobile Robot Navigation.Proceedings of the IEEEConference on Robotics and Automation,Sacramento,Califoria,April 7-12,1991; 1398~1404
    [51] 李强,林良明,颜国正.一种新的移动机器人环境模型.机器人.1999,21(5)
    [52] 严蔚敏,吴伟民.数据结构.清华大学出版社.2001
    [53] 楼顺天,胡昌华,张伟.基于MATLAB的系统分析与设计——模糊系统.西安电子科技大学出版社.2001
    [54] 张朋飞,何克忠,欧阳正柱.多功能室外智能移动机器人实验平台.机器人.2002,24(2):97-101
    [55] 肖海荣,富文军,张小军.基于多传感器数据融合的移动机器人导航.系统工程与电子技术.2001,23(7):456~460
    [56] 张纯刚,席裕庚.动态未知环境中移动机器人的滚动路径规划.机器人.2002,24(1):71~75
    [57] 郭琦,洪炳熔.基于人工神经网络实现智能机器人的避障轨迹控制.机器人.2002,24(6):508~512
    [58] 邱仲藩.Visual C++从入门到精通.电子工业出版社.1999年第一版
    [59] 钱能.C++程序设计教程.清华大学出版社.1999年4月第1版
    [60] 候俊杰.深入浅出MFC第2版.华中科技大学出版社.2001年1月

© 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