基于信息融合技术的煤矿井下探测机器人检测系统研究
|
摘要
多传感器信息融合技术是一门产生不久但却得到迅速发展的新兴技术,涉及了控制理论、信号处理、模糊逻辑、神经网络以及人工智能等众多学科,得到了广泛的应用,它为机器人在复杂未知的环境中工作提供了一种良好的解决途径。课题来自山西省科技攻关项目“煤矿井下搜救探测机器人技术与系统研究”,要求机器人在井下具备环境感知和自主工作能力。本文研究了煤矿井下探测机器人的检测系统,并采用信息融合技术,对机器人在井下未知复杂环境中的导航做了研究,重点针对机器人的自主避障问题,利用基于Takagi-Sugeno模型的模糊神经网络信息融合方法来实现探测机器人的避障问题。
本文对多传感器信息融合技术做了重点研究,结合它在煤矿井下探测机器人导航中的应用进行了理论与实践上的探讨,主要研究工作如下:
1、阐述了国内外煤矿探测机器人和信息融合技术的发展历程、现状和研究趋势。从总体上对信息融合技术做了介绍,分析了多传感器信息融合的基本原理、拓扑结构以及融合层次等重要问题,对机器人传感器数量以及种类的选择等问题进行了探讨。分析研究了机器人配备的各种传感器的基本原理及性能特点,在此基础上确定了传感器型号。
2、分析了模糊逻辑和神经网络的基本原理和它们的几种常见结合方式,在此基础上,对模糊神经网络在信息融合技术中的应用进行了研究,并把基于T-S模型的模糊神经网络信息融合方法应用在煤矿井下探测机器人的自主避障中。
3、根据煤矿井下探测机器人的特殊性及其要求,对本文机器人的结构以及硬件配置进行了总体设计。分析了机器人的几种控制体系,并提出了本文采用的机器人混合式控制体系。
4、研究了煤矿井下探测机器人的检测系统,并对其进行了软硬件的设计。另外简单介绍了本文采用的路径规划方法以及对煤矿井下探测机器人的运动控制。
5、对机器人的导航问题进行了分析,把基于T-S模型的模糊神经网络信息融合技术应用到煤矿井下探测机器人的自主避障中。建立了基于超声与红外传感器的信息融合系统,设计了机器人的避障模式和物理模型。在此基础上对机器人的避障进行了计算机仿真研究,以验证所用方法的可行性。
Multi-sensor information fusion technology is an emerging technology, which appeared not long ago but got a rapid development and has been widely used in recent years. It involved in control theory, signal processing, fuzzy logic, neural network, artificial intelligence and many other subjects. It provides a good solution for the robot working in a complex and unknown environment. The topics "research on technology and system for coal mine rescue detection robot" is a scientific and technological project in Shanxi Province, which requires the robot has the ability to perceive mine environment and work independently. The information collection was researched and the robot navigation in complex and unknown mine environment was researched in this paper. Focusing on the autonomous obstacle avoidance of robot, the information fusion technology of fuzzy neural network based on Takagi-Sugeno model was used to solve the obstacle avoidance problem of detection robot.
Multi-sensor information fusion technology was made a key research, and its application in navigation of coal mine detection robot was explored in theory and practice. The main research works are as follows:
1、The development process, current situation and research trends on mine detection robot and information fusion technology at home and abroad were elaborated. Information fusion technology was introduced systematically and its important issues such as basic principle, topology, and the level were analyzed. In addition, the choice of number and kind for robot sensor was explored. The basic principles and performance characteristics of various sensors equipped by robot were analyzed and the sensor models were chosen.
2、The basic principles and several common binding mode of fuzzy logic and neural network were analyzed. The application of fuzzy neural networks in information fusion technology was researched and the information fusion method of fuzzy neural network based on T-S model was used in autonomous obstacle avoidance for coal mine detection robot.
3、According to the particularity and requirements of coal mine detecting robot , the structure and hardware configuration were made a overall design. Several control systems of robot were analyzed and the mixed control system applied by coal mine detection robot was presented.
4、The detection system of coal mine detection robot was researched, and its conduct of the hardware and software was designed. The path planning method and motion control of coal mine detection robot was analyzed briefly.
5、The robot navigation was analyzed, and the information fusion technology of fuzzy neural network based on T-S model was applied to autonomous obstacle avoidance for coal mine detection robot. The information fusion system based on ultrasonic and infrared sensors was established, obstacle avoidance pattern and physical model of robot were designed. The obstacle avoidance of robot was simulated by computer to verify the feasibility of the method used.
本文对多传感器信息融合技术做了重点研究,结合它在煤矿井下探测机器人导航中的应用进行了理论与实践上的探讨,主要研究工作如下:
1、阐述了国内外煤矿探测机器人和信息融合技术的发展历程、现状和研究趋势。从总体上对信息融合技术做了介绍,分析了多传感器信息融合的基本原理、拓扑结构以及融合层次等重要问题,对机器人传感器数量以及种类的选择等问题进行了探讨。分析研究了机器人配备的各种传感器的基本原理及性能特点,在此基础上确定了传感器型号。
2、分析了模糊逻辑和神经网络的基本原理和它们的几种常见结合方式,在此基础上,对模糊神经网络在信息融合技术中的应用进行了研究,并把基于T-S模型的模糊神经网络信息融合方法应用在煤矿井下探测机器人的自主避障中。
3、根据煤矿井下探测机器人的特殊性及其要求,对本文机器人的结构以及硬件配置进行了总体设计。分析了机器人的几种控制体系,并提出了本文采用的机器人混合式控制体系。
4、研究了煤矿井下探测机器人的检测系统,并对其进行了软硬件的设计。另外简单介绍了本文采用的路径规划方法以及对煤矿井下探测机器人的运动控制。
5、对机器人的导航问题进行了分析,把基于T-S模型的模糊神经网络信息融合技术应用到煤矿井下探测机器人的自主避障中。建立了基于超声与红外传感器的信息融合系统,设计了机器人的避障模式和物理模型。在此基础上对机器人的避障进行了计算机仿真研究,以验证所用方法的可行性。
Multi-sensor information fusion technology is an emerging technology, which appeared not long ago but got a rapid development and has been widely used in recent years. It involved in control theory, signal processing, fuzzy logic, neural network, artificial intelligence and many other subjects. It provides a good solution for the robot working in a complex and unknown environment. The topics "research on technology and system for coal mine rescue detection robot" is a scientific and technological project in Shanxi Province, which requires the robot has the ability to perceive mine environment and work independently. The information collection was researched and the robot navigation in complex and unknown mine environment was researched in this paper. Focusing on the autonomous obstacle avoidance of robot, the information fusion technology of fuzzy neural network based on Takagi-Sugeno model was used to solve the obstacle avoidance problem of detection robot.
Multi-sensor information fusion technology was made a key research, and its application in navigation of coal mine detection robot was explored in theory and practice. The main research works are as follows:
1、The development process, current situation and research trends on mine detection robot and information fusion technology at home and abroad were elaborated. Information fusion technology was introduced systematically and its important issues such as basic principle, topology, and the level were analyzed. In addition, the choice of number and kind for robot sensor was explored. The basic principles and performance characteristics of various sensors equipped by robot were analyzed and the sensor models were chosen.
2、The basic principles and several common binding mode of fuzzy logic and neural network were analyzed. The application of fuzzy neural networks in information fusion technology was researched and the information fusion method of fuzzy neural network based on T-S model was used in autonomous obstacle avoidance for coal mine detection robot.
3、According to the particularity and requirements of coal mine detecting robot , the structure and hardware configuration were made a overall design. Several control systems of robot were analyzed and the mixed control system applied by coal mine detection robot was presented.
4、The detection system of coal mine detection robot was researched, and its conduct of the hardware and software was designed. The path planning method and motion control of coal mine detection robot was analyzed briefly.
5、The robot navigation was analyzed, and the information fusion technology of fuzzy neural network based on T-S model was applied to autonomous obstacle avoidance for coal mine detection robot. The information fusion system based on ultrasonic and infrared sensors was established, obstacle avoidance pattern and physical model of robot were designed. The obstacle avoidance of robot was simulated by computer to verify the feasibility of the method used.
引文
[1]何友,王国宏.多传感器信息融合及应用[M].北京:电子工业出版社,2000:1-11.
[2]方建军,何广平.智能机器人[M].北京:化学工业出版社,2004:1.
[3]燕奎臣,李一平,袁学庆.远程自治水下机器人研究[J].机器人,2002,24(4):299-303.
[4]甘小明,徐滨士,董世运等.管道机器人的发展现状[J].机器人技术与应用,2003,(6):5-10.
[5] Kawaguchi Y,Yoshida I,Kumatani H,etc.Development of an in pipe inspection robot for iron pipes[J].Journal of Robotics Society of Japan,1996,14(1):137-143.
[6] Roman H T,Pellegrino B A,Sigrist Wr.Pipe crawling inspection robots:an overview[J].IEEE Transaction on Energy Conversion,1993,8:576-583.
[7] Georgios A.Demetriou,Kimon P.Valavanis.A hybrid control architecture for an autonomous underwater vehicle[D].Lafayette:University of Louisiana,1998.
[8] Fearing R S,Chiang K H,Dickinson M H,etc.Wing transmission for a micro-mechanical flying insect[C] . USA : San Francisco , IEEE International Conference on Robotics and Automation,2000:509-516.
[9]蔡自兴.中国的智能机器人研究[J].莆田学院学报,2002,9(3):36-39.
[10] Dusko Katic,Miomir Vukobratovic.Survey of intelligent control techniques for humanoid robots[J].Journal of Intelligent and Robotic Systems,2003,(6):117-141.
[11] Carl DiSalvo,Francine Gemperle.From seduction to fulfillment:the use of anthropomorphic form in design[C]. Proceedings of International Conference :Proceedings of the 2003 International Conference on Designing Pleasurable Products and Interfaces,New York USA:ACM Press,2003:67-72.
[12]谢涛,徐建峰,张永学等.仿人机器人的研究历史、现状及展望[J].机器人,2002,24(4):367-374.
[13] Tanmio TANIKAWA,Tatuo ARAI.Two-finger micro hand[C]. Proceedings of the 1995 IEEE International Conference on Robotics and Automation,1995:1674-1679.
[14]王守杰.微操作机器人级显微视觉的研究[D].北京:北京航空航天大学,1998.
[15]王勇,朱华,王永胜等.煤矿就在机器人研究现状及需要重点解决的技术问题[J].煤机械,2007,28(4):107-108.
[16]臧大进,严宏凤,王跃才.多传感器信息融合技术综述[J].工矿自动化,2005,6:30-31.
[17] David L . Hall , Hames Llinas . An introduction to multi-sensor data fusion[J].Proceedings of the IEEE,1997,85(1):6-23.
[18] Toshio Fukuda,Koji Shimojima,Fumihito Arai.Multi-sensor integration system based on fuzzy inference and neural network[J].Information Sciences,1993,(71):27-41.
[19] Ramanarayanan Viswanathan,Pramod K.Varshney.Distributed detection with multiple sensors:part I-fundamentals[J].Proceedings of the IEEE,1997,85(1):54-63.
[20] Thamova.Evidence reasoning theory with application to the identity estimation and data association systems[J].Mathematics and Computers in Simulation,1997,(43):139-142.
[21] Gao J B,Harris C J.Some remarks on kalman filters for the multi-sensor fusion[J].Information Fusion ,2002(3):191-20.
[22]黄鵾,陈森发,周振国等.基于粗集理论和证据理论的多源信息融合方法[J].信息与控制,2004,33(4):422 -433.
[23]王海晖,彭嘉雄.基于多小波变换的图像融合研究[J].中国图像图形学报,2004,9(8):1002-1007.
[24]徐从富,耿卫东,潘云鹤.面向数据融合的DS方法综述[J].电子学报,2001,29(3):393-396.
[25] Gonzalo Pajares,Jesus Menuelde,La Cruz.A wavelet-based image fusion tutorial[J].Pattern Recognition ,2004,37:1855-1872.
[26] Tuan D Pham.An image restoration by fusion[J].Pattern Recognition,2001,34:2403-2411.
[27] Jinshan Tang . A Contrast based image fusion technique in the DCTdomain[J].Digital Signal Processing,2004,14:218-226.
[28] J.L1inas,E.Waltz.Multi-sensor data fusion[M].Massachusetts:Artech House,1990:118-123.
[29]罗志增,蒋静坪.机器人感觉与多信息融合[M].北京:机械工业出版社,2002:91-101.
[30]王耀南,李树涛.多传感器信息融合及其应用综述[J].控制与决策,2001,16(9):518-521.
[31]马平,吕锋,杜海莲.多传感器信息融合基本原理及应用[J].控制工程,2006,13(1):48-51.
[32]刘庆龙.基于Agent的自主机器人路径规划[D].合肥:中国科学技术大学,2001.
[33]谭民,王硕,曹志强.多机器人系统[M].北京:清华大学出版社,2005,115-150.
[34]王军,苏剑波,席裕庚.多传感器集成与融合概述[J].机器人,2001,23(2):183-186.
[35]叶涛.基于传感器信息的移动机器人导航与控制研究[D].北京:中国科学院自动化研究所,2003.
[36] REN C.LUO,MICHAEL G.KAY.Multi-sensor integration and fusion in intelligent systems[J].IEEE trans On SMC,1989,19(5):901-931.
[37] H F.Durrant-Whyte.Sensor models and multi-sensor integration[J].Robot.Res.,1988,7(6):97-113.
[38] Robin R . Dempster-shafer theory for sensor fusion in autonomous mobile robots[J].IEEE Trans On Robotics and Automation,1998,14(2):278-288.
[39] NOEL E.SHARKEY.Learning from innate behaviors:a quantitative evaluation of neural network controllers[J].Autonomous Robots,1998,5:317-334.
[40]杨万海.多传感器数据融合及其应用.西安:西安电子科技大学出版社,2004:8-20.
[41] Dampster.A.P.Upper and lover predictive control approach to the high-speed cross-country autonomous navigation problem[D].Ph.D.Thesis:CMU,1995.
[42] Shafter.G.h.Mathematical theory of evidence[D].Princetion:Princetion U.P,1976.
[43] Ivo Duntsch , Gunther Gediga . Uncertainty measures of rough setprediction[J].Artificial Intelligence,1998,106:109—137.
[44]郭巧.现代机器入学:仿生系统的运动感知与控制[M].北京:北京理工大学出版社,1999.150—167.
[45]方建军,何广平.智能机器人[M].北京:化学工业出版社,2003.49-52.
[46]朱长宏.轮式可移动机器人的研究[D].南京:南京航空航天大学,2000.
[47]张传才,贺利乐,匡伟春.轮式移动教育机器人避障方法的研究[J].现代电子技术,2007(13):116-117,120.
[48]高富国,谢少荣,罗均.机器人传感器机器应用[M].北京:化学工业出版社,2005:56.
[49]童敏明,陆生华,杨礼现.矿井救灾机器人的传感与避障系统[J].煤炭科学技术,2006,34(8):11-14.
[50]李士勇.模糊控制·神经控制和智能控制论[M].哈尔滨:哈尔滨工业大学出版社,1998:23-71,254-275.
[51]冯冬青,谢宋和.模糊智能控制[M].北京:化学工业出版社,1998:18-22.
[52]阎平凡,张长水.人工神经网络与模拟进化计算(第二版)[M].北京:清华大学出版社,2005:132-156.
[53]王旭,王宏,王文辉.人工神经元网络原理与应用[M].沈阳:东北大学出版社,2000:128-139.
[54] B.Kosko.Neural networks and fuzzy systems:a dynamical approach to intelligence[N].Prentice-Hall,1992.
[55] A.Blanco,M.I.Requena.Improved fuzzy neural networks for solving relational equations[J].Fuzzy sets and Systems, 1995,72:311-322.
[56] H.Ishibuchi,H.Tanaka.A learning algorithm of fuzzy neural networks with triangular fuzzy weights[J].Fuzzy sets and Systems,1995,71:277-293.
[57] J.J.Buckley,Y.Hayashi.Fuzzy neural networks:a survey[J].Fuzzy sets and Systems,1994,66:1-13.
[58]王勇,朱华,王勇胜.煤矿救灾机器人研究现状及需要重点解决的技术问题[J].煤矿机械,2007,28(4):108-109.
[59]苏学成,李贻斌,樊炳辉等.煤矿井下机器人结构与控制的若干问题[J].煤炭学报,1995,20(5):514-515.
[60]张颖,吴成东,原宝龙.机器人路径规划方法综述[J].控制工程,2003,10(5):152-153.
[61]李磊,叶涛,谭民等.移动机器人技术研究现状与未来[J].机器人,2002,24(5):475-477.
[62] W.S.Newman,M.SBranicky.Real-time configuration space transforms for obstacle avoidance[J].Robotics Research,1991,10(6):650-667.
[63] A.A.Maciejewsky,J.J.Fox.Path planning and the topology of space[J].IEEE Trans on Robotics and Automation.1993,9(4):444-456.
[64] Shoo.J,Suzuki,M.K.Habib,etc.How to describe the mobile robot’s sensor-based behavior[J].Robotics and Autonomous Systems,1991:227-237.
[65] H . Noborio . Robot path-planning in connection with sensing control corporation[J].Advanced Robotics,1993,7(5):409-412.
[66]马兆青,袁曾任.基于栅格方法的移动机器人实时导航与避障[J].机器人,1996,18(6):344-348.
[2]方建军,何广平.智能机器人[M].北京:化学工业出版社,2004:1.
[3]燕奎臣,李一平,袁学庆.远程自治水下机器人研究[J].机器人,2002,24(4):299-303.
[4]甘小明,徐滨士,董世运等.管道机器人的发展现状[J].机器人技术与应用,2003,(6):5-10.
[5] Kawaguchi Y,Yoshida I,Kumatani H,etc.Development of an in pipe inspection robot for iron pipes[J].Journal of Robotics Society of Japan,1996,14(1):137-143.
[6] Roman H T,Pellegrino B A,Sigrist Wr.Pipe crawling inspection robots:an overview[J].IEEE Transaction on Energy Conversion,1993,8:576-583.
[7] Georgios A.Demetriou,Kimon P.Valavanis.A hybrid control architecture for an autonomous underwater vehicle[D].Lafayette:University of Louisiana,1998.
[8] Fearing R S,Chiang K H,Dickinson M H,etc.Wing transmission for a micro-mechanical flying insect[C] . USA : San Francisco , IEEE International Conference on Robotics and Automation,2000:509-516.
[9]蔡自兴.中国的智能机器人研究[J].莆田学院学报,2002,9(3):36-39.
[10] Dusko Katic,Miomir Vukobratovic.Survey of intelligent control techniques for humanoid robots[J].Journal of Intelligent and Robotic Systems,2003,(6):117-141.
[11] Carl DiSalvo,Francine Gemperle.From seduction to fulfillment:the use of anthropomorphic form in design[C]. Proceedings of International Conference :Proceedings of the 2003 International Conference on Designing Pleasurable Products and Interfaces,New York USA:ACM Press,2003:67-72.
[12]谢涛,徐建峰,张永学等.仿人机器人的研究历史、现状及展望[J].机器人,2002,24(4):367-374.
[13] Tanmio TANIKAWA,Tatuo ARAI.Two-finger micro hand[C]. Proceedings of the 1995 IEEE International Conference on Robotics and Automation,1995:1674-1679.
[14]王守杰.微操作机器人级显微视觉的研究[D].北京:北京航空航天大学,1998.
[15]王勇,朱华,王永胜等.煤矿就在机器人研究现状及需要重点解决的技术问题[J].煤机械,2007,28(4):107-108.
[16]臧大进,严宏凤,王跃才.多传感器信息融合技术综述[J].工矿自动化,2005,6:30-31.
[17] David L . Hall , Hames Llinas . An introduction to multi-sensor data fusion[J].Proceedings of the IEEE,1997,85(1):6-23.
[18] Toshio Fukuda,Koji Shimojima,Fumihito Arai.Multi-sensor integration system based on fuzzy inference and neural network[J].Information Sciences,1993,(71):27-41.
[19] Ramanarayanan Viswanathan,Pramod K.Varshney.Distributed detection with multiple sensors:part I-fundamentals[J].Proceedings of the IEEE,1997,85(1):54-63.
[20] Thamova.Evidence reasoning theory with application to the identity estimation and data association systems[J].Mathematics and Computers in Simulation,1997,(43):139-142.
[21] Gao J B,Harris C J.Some remarks on kalman filters for the multi-sensor fusion[J].Information Fusion ,2002(3):191-20.
[22]黄鵾,陈森发,周振国等.基于粗集理论和证据理论的多源信息融合方法[J].信息与控制,2004,33(4):422 -433.
[23]王海晖,彭嘉雄.基于多小波变换的图像融合研究[J].中国图像图形学报,2004,9(8):1002-1007.
[24]徐从富,耿卫东,潘云鹤.面向数据融合的DS方法综述[J].电子学报,2001,29(3):393-396.
[25] Gonzalo Pajares,Jesus Menuelde,La Cruz.A wavelet-based image fusion tutorial[J].Pattern Recognition ,2004,37:1855-1872.
[26] Tuan D Pham.An image restoration by fusion[J].Pattern Recognition,2001,34:2403-2411.
[27] Jinshan Tang . A Contrast based image fusion technique in the DCTdomain[J].Digital Signal Processing,2004,14:218-226.
[28] J.L1inas,E.Waltz.Multi-sensor data fusion[M].Massachusetts:Artech House,1990:118-123.
[29]罗志增,蒋静坪.机器人感觉与多信息融合[M].北京:机械工业出版社,2002:91-101.
[30]王耀南,李树涛.多传感器信息融合及其应用综述[J].控制与决策,2001,16(9):518-521.
[31]马平,吕锋,杜海莲.多传感器信息融合基本原理及应用[J].控制工程,2006,13(1):48-51.
[32]刘庆龙.基于Agent的自主机器人路径规划[D].合肥:中国科学技术大学,2001.
[33]谭民,王硕,曹志强.多机器人系统[M].北京:清华大学出版社,2005,115-150.
[34]王军,苏剑波,席裕庚.多传感器集成与融合概述[J].机器人,2001,23(2):183-186.
[35]叶涛.基于传感器信息的移动机器人导航与控制研究[D].北京:中国科学院自动化研究所,2003.
[36] REN C.LUO,MICHAEL G.KAY.Multi-sensor integration and fusion in intelligent systems[J].IEEE trans On SMC,1989,19(5):901-931.
[37] H F.Durrant-Whyte.Sensor models and multi-sensor integration[J].Robot.Res.,1988,7(6):97-113.
[38] Robin R . Dempster-shafer theory for sensor fusion in autonomous mobile robots[J].IEEE Trans On Robotics and Automation,1998,14(2):278-288.
[39] NOEL E.SHARKEY.Learning from innate behaviors:a quantitative evaluation of neural network controllers[J].Autonomous Robots,1998,5:317-334.
[40]杨万海.多传感器数据融合及其应用.西安:西安电子科技大学出版社,2004:8-20.
[41] Dampster.A.P.Upper and lover predictive control approach to the high-speed cross-country autonomous navigation problem[D].Ph.D.Thesis:CMU,1995.
[42] Shafter.G.h.Mathematical theory of evidence[D].Princetion:Princetion U.P,1976.
[43] Ivo Duntsch , Gunther Gediga . Uncertainty measures of rough setprediction[J].Artificial Intelligence,1998,106:109—137.
[44]郭巧.现代机器入学:仿生系统的运动感知与控制[M].北京:北京理工大学出版社,1999.150—167.
[45]方建军,何广平.智能机器人[M].北京:化学工业出版社,2003.49-52.
[46]朱长宏.轮式可移动机器人的研究[D].南京:南京航空航天大学,2000.
[47]张传才,贺利乐,匡伟春.轮式移动教育机器人避障方法的研究[J].现代电子技术,2007(13):116-117,120.
[48]高富国,谢少荣,罗均.机器人传感器机器应用[M].北京:化学工业出版社,2005:56.
[49]童敏明,陆生华,杨礼现.矿井救灾机器人的传感与避障系统[J].煤炭科学技术,2006,34(8):11-14.
[50]李士勇.模糊控制·神经控制和智能控制论[M].哈尔滨:哈尔滨工业大学出版社,1998:23-71,254-275.
[51]冯冬青,谢宋和.模糊智能控制[M].北京:化学工业出版社,1998:18-22.
[52]阎平凡,张长水.人工神经网络与模拟进化计算(第二版)[M].北京:清华大学出版社,2005:132-156.
[53]王旭,王宏,王文辉.人工神经元网络原理与应用[M].沈阳:东北大学出版社,2000:128-139.
[54] B.Kosko.Neural networks and fuzzy systems:a dynamical approach to intelligence[N].Prentice-Hall,1992.
[55] A.Blanco,M.I.Requena.Improved fuzzy neural networks for solving relational equations[J].Fuzzy sets and Systems, 1995,72:311-322.
[56] H.Ishibuchi,H.Tanaka.A learning algorithm of fuzzy neural networks with triangular fuzzy weights[J].Fuzzy sets and Systems,1995,71:277-293.
[57] J.J.Buckley,Y.Hayashi.Fuzzy neural networks:a survey[J].Fuzzy sets and Systems,1994,66:1-13.
[58]王勇,朱华,王勇胜.煤矿救灾机器人研究现状及需要重点解决的技术问题[J].煤矿机械,2007,28(4):108-109.
[59]苏学成,李贻斌,樊炳辉等.煤矿井下机器人结构与控制的若干问题[J].煤炭学报,1995,20(5):514-515.
[60]张颖,吴成东,原宝龙.机器人路径规划方法综述[J].控制工程,2003,10(5):152-153.
[61]李磊,叶涛,谭民等.移动机器人技术研究现状与未来[J].机器人,2002,24(5):475-477.
[62] W.S.Newman,M.SBranicky.Real-time configuration space transforms for obstacle avoidance[J].Robotics Research,1991,10(6):650-667.
[63] A.A.Maciejewsky,J.J.Fox.Path planning and the topology of space[J].IEEE Trans on Robotics and Automation.1993,9(4):444-456.
[64] Shoo.J,Suzuki,M.K.Habib,etc.How to describe the mobile robot’s sensor-based behavior[J].Robotics and Autonomous Systems,1991:227-237.
[65] H . Noborio . Robot path-planning in connection with sensing control corporation[J].Advanced Robotics,1993,7(5):409-412.
[66]马兆青,袁曾任.基于栅格方法的移动机器人实时导航与避障[J].机器人,1996,18(6):344-348.