基于传感器阵列的嗅觉机器人及搜寻算法研究
|
摘要
随着传感器技术的发展,机器人技术得到了长足的进步。现在智能机器人已经应用到了生活的各个领域。机器人正在成为并终将成为人类生活不可或缺的工具。作为机器人研究领域的一个重要分支,仿生机器人的研究早已引起人们的注意。现在已经出现了能听、能说、能看的机器人。但是相对他们来讲,基于嗅觉仿生原理的嗅觉机器人的研究则处于刚刚起步阶段。
烟羽追踪是目前的嗅觉机器人研究的一个重要方面。而应用于烟羽追踪的大部分的搜寻策略都面对这样或那样的问题困扰,而不能达到理想的结果。本文通过分析对比各种搜寻策略的优缺点,提出了使用传感器阵列技术实现混合气体的定量识别以避免金属氧化物传感器的“交叉敏感”,以及集成风向传感器实现逆风搜寻以提高搜寻效率的方案。
本文通过分析生物的嗅觉机理和生物搜寻气源方式入手,对人工嗅觉系统进行了分析,总结了嗅觉机器人的工作原理和结构,介绍了基于多传感器阵列的定量识别技术,实现了BP网络对传感器阵列的标定。同时设计了一个机器人系统,完成了数据采集程序,超声避障程序和风向信息获取程序的软硬件设计工作。并在该平台上进行了浓度梯度追踪法和逆风搜寻法的实验验证工作。
通过一系列的实验,证实了本文设计的方案能够较好的达到预期目的。该机器人系统以较高的成功率实现了对清洁房间中的乙醇气味烟羽的跟踪和对气味源头的搜寻。
With the development of sensor technology, robot technology has made great progress. Intelligent robot has been applied to all areas of life. Robots are becoming and will eventually become an indispensable tool for human. As an important area of the robot research, the bio-robot research has aroused people's attention, there have been robots which can listen, say or look. In terms of their relative, the research of smelling robot based on the principles of the olfactory sense is just at the initial stage.
Plume tracking is an important part of smelling robot research. Most of the search strategies are facing sundry problems, and they can not achieve the desired results. Through analysis and comparison of the advantages and disadvantages of various search strategies, the article proposed quantitative identification using sensor array to identify mixture gas and avoid that the "cross-sensitivity" of metal oxide sensors. The article also proposed a method that use wind direction sensors to improve efficiency of searching the source.
Starting with the analysis of principle of the biology’s smell and the ways of search source, the artificial olfactory system was analyzed. The article summers up the working principle and structure of smelling robot, introduces the quantitative identification technology based on multi-sensor array, achieves a calibration of the sensor array with a BP network. At the same time, a robot system is designed. The software and hardware design of the procedures of data collection, the procedures of obstacle avoidance by ultrasound, and the procedures of getting the wind direction are completed. In the end, the verification works of concentration gradient search algorithm and up-wind search algorithm on this platform are done.
Through a series of experimental work, it proves that the design can achieve the intended purpose. The robot can track alcohol's odor plume and search the source of the odor in a clean room with a higher rate of success.
烟羽追踪是目前的嗅觉机器人研究的一个重要方面。而应用于烟羽追踪的大部分的搜寻策略都面对这样或那样的问题困扰,而不能达到理想的结果。本文通过分析对比各种搜寻策略的优缺点,提出了使用传感器阵列技术实现混合气体的定量识别以避免金属氧化物传感器的“交叉敏感”,以及集成风向传感器实现逆风搜寻以提高搜寻效率的方案。
本文通过分析生物的嗅觉机理和生物搜寻气源方式入手,对人工嗅觉系统进行了分析,总结了嗅觉机器人的工作原理和结构,介绍了基于多传感器阵列的定量识别技术,实现了BP网络对传感器阵列的标定。同时设计了一个机器人系统,完成了数据采集程序,超声避障程序和风向信息获取程序的软硬件设计工作。并在该平台上进行了浓度梯度追踪法和逆风搜寻法的实验验证工作。
通过一系列的实验,证实了本文设计的方案能够较好的达到预期目的。该机器人系统以较高的成功率实现了对清洁房间中的乙醇气味烟羽的跟踪和对气味源头的搜寻。
With the development of sensor technology, robot technology has made great progress. Intelligent robot has been applied to all areas of life. Robots are becoming and will eventually become an indispensable tool for human. As an important area of the robot research, the bio-robot research has aroused people's attention, there have been robots which can listen, say or look. In terms of their relative, the research of smelling robot based on the principles of the olfactory sense is just at the initial stage.
Plume tracking is an important part of smelling robot research. Most of the search strategies are facing sundry problems, and they can not achieve the desired results. Through analysis and comparison of the advantages and disadvantages of various search strategies, the article proposed quantitative identification using sensor array to identify mixture gas and avoid that the "cross-sensitivity" of metal oxide sensors. The article also proposed a method that use wind direction sensors to improve efficiency of searching the source.
Starting with the analysis of principle of the biology’s smell and the ways of search source, the artificial olfactory system was analyzed. The article summers up the working principle and structure of smelling robot, introduces the quantitative identification technology based on multi-sensor array, achieves a calibration of the sensor array with a BP network. At the same time, a robot system is designed. The software and hardware design of the procedures of data collection, the procedures of obstacle avoidance by ultrasound, and the procedures of getting the wind direction are completed. In the end, the verification works of concentration gradient search algorithm and up-wind search algorithm on this platform are done.
Through a series of experimental work, it proves that the design can achieve the intended purpose. The robot can track alcohol's odor plume and search the source of the odor in a clean room with a higher rate of success.
引文
1孟庆春,齐勇等.智能机器人及其发展.中国海洋大学学报. 2004, 34(5):831~838
2王树国,战强,陈在礼.智能机器人的现状及未来.机器人技术与应用, 1998, 01:4~7
3 L. Marques, U. Nunes etc. Olfaction-Based Mobile Robot Navigation. Thin Solid Films 2002, 418:51~58
4 H. Ishida, Y. Kagawa, T. Nakamoto, T. Moriizumi. Odor-source Localization in the Clean Room by an Autonomous Mobile Sensing System. Sensors and Actuators.1996, B(33):115~121
5 W. Frank, Grasso, J. Atema. Integration of Flow and Chemical Sensing for Guidance of Autonomous Marine Robots in Turbulent Flows. Environmental Fluid Mechanics. 2002, 2:95~114
6 T. Nakamoto, H. Ishida, T. Moriizumi. An Odor Compass for Localizing an Odor Source. Sensors and Actuators.1996, B(35):32~36
7郭晓强.解读2004年诺贝尔生理学或医学奖.生物学教学2005, 30(3): 69~70
8谭文长.嗅觉模型研究的进展国外医学生物医学工程分册. 1996, 19(5):256~263
9郝博.机器人嗅觉系统的研究.哈尔滨工业大学硕士论文.2005
10徐保港.基于传感器阵列的嗅觉机器人的研究.哈尔滨工业大学硕士论文. 2006
11焦晓国等.鳞翅目蛾类雄性昆虫的信息素.昆虫知识. 2004, 41(4):398~403
12 H. Ishida. Robotic Systems for Gas/Odor Source Localization: Gap Between Experiments and Real-Life Situations. IEEE.
13曲建岭,王磊,杨建华等.基于自组织特征映射网络的气体识别方法研究.测控技术. 2000, 19(3):6~8
14张哲,佟金.电子鼻和电子舌在食品检测中的研究和应用.华中农业大学学报. 2005, 10:25~30
15 H. K. Hong, H. W. Shin, D. H. Yun, S. R. Kim, C. H. Kwow, K. Lee, T. Moriizumi. Electronic Nose System with Micro Gas Sensor Array.Sensors and Actuators 1996, B(35-36) 338~341
16 H. Ishida, T. Tokuhiro, T. Nakamoto and T. Moriizumi. Improvement of Olfactory Video Camera: Gas/Odor Flow Visualization System. Sensors and Actuators 2002, B83(1-3):256~261
17 M. Wandel1, A. Lilienthal, T. Duckett, U. Weimar, A. Zell. Gas Distribution in Unventilated Indoor Environments Inspected by a Mobile Robot. Proceedings of the IEEE International Conference on Advanced Robotics(ICAR 2003). 2003:507-512
18 G. Ferri, M.V. Jakuba, E. Caselli, V. Mattoli etc. Localizing Multiple Gas/Odor Sources in an Indoor Environment using Bayesian Occupancy Grid Mapping. Intelligent Robots and Systems, 2007. IROS 2007. IEEE/RSJ International Conference on. 2007:566~571
19孟庆浩,李飞.主动嗅觉研究现状.机器人. 2006, 28(1): 89~96
20 T. Moriizumi, H. Ishida. Robotic Systems to Track Chemical Plumes. Optoelectronic and Microelectronic Materials and Devices, 2002 537- 540
21 L. Marques, A. T. de Almeida. Electronic Nose-Based Odour Source Localization. IEEE.2000:36~40
22 V. Braitenberg, Vehicles. Experiments in Synthetic Psychology. MIT Press/Bradford Books, 1984
23 H. Ishida, T. Nakamoto, T. Moriizumi. Fundamental Study of Mobile System for Smelling-Object Localization Using Plural Gas Sensor. IEEE Industrial Electrics Society 1993:767~768
24 H. Ishida, K. Suetsugu etc. Study of Autonomous Mobile Sensing System for Localization of Odor Source Using Gas Sensors and Anemometric Sensors Sensors and actuators. A.1994, 45(2) 153~157
25 H. Ishida, G. Nakayama, T. Nakamoto, and T. Moriizumi. Controlling a Gas Plume-Tracking Robot Based on Transient Responses of Gas Sensors.IEEE.2002:1665~1670
26 H. Ishida, H. Tanaka, H. Taniguchi and T. Moriizumi. Mobile Robot Navigation Using Vision and Olfaction to Search for a Gas/Odor Source. Autonomous Robots. 2006, 20(3):231~238
27 R. Russell, D. Thiel, A. Mackay-Sim. Sensing Odour Trails for Mobile Robot Navigation. IEEE International Conference on Robotics and Automation,1994:2672~2677
28 R. Russell, D. Thiel, R. Deveza, A. Mackay-Sim. A Robotic System to Locate Hazardous Chemical Leaks. IEEE International Conference on Robotics and Automation.1995: 556~561
29 Y. Kuwana, I. Shimoyama, H. Miura. Steering Control of a Mobile Robot Using Insect Antennae. Intelligent Robots and Systems 1995, 2: 530~535
30 Y. Kuwana, I. Shimoyama, Y. Sayama, H. Miura. Synthesis of Pheromone-Oriented Emergent Behavior of a Silkworm Moth. Intelligent Robots and Systems. 1996, 3:1722~1729
31 A. Loutfi, S. Coradeschi. Odor Recognition for Intelligent Systems. Intelligent Systems, IEEE. 2008, 23(1). :41-48
32 M. Iida, D. Kang, M. Taniwaki, M. Tanaka and M. Umeda. Localization of CO2 Source by a Hexapod Robot Equipped with an Anemoscope and a Gas Sensor. Computers and Electronics in Agriculture 2008, 63:73~80
33李俊彩,孟庆浩,梁琼.基于进化梯度搜索的机器人主动嗅觉仿真研究.机器人, 2007, 29(3): 234~238
34张志,单越康,项荣,于洋,张健.融合视觉和嗅觉的管道探测机器人的设计与实现.机器人. 2006, 28(5) :499~503
35 H. Ishida, T. Nakamoto and T. Moriizumi. Remote Sensing and Localization of Gas Source and Distribution Using Mobile Sensing System. IEEE.1997:559~562
36李磊.移动机器人系统设计与视觉导航控制研究.中国科学院研究生院博士学位论文. 2003:2~27
37吴玉峰等.气体传感器研究进展和发展方向.计算机测量与控制. 2003, 11(10):731~734
38江福椿等.气体浓度检测技术的现状和应用.河海大学常州分校学报. 2003,18(1):16~19
39马丽杰.日本气体传感器产业化发展现状.云南大学学报(自然科学版). 1997, 19(2):211~216
40吴春生,王丽江,刘清君,赵鲁杭,王平.嗅觉传导机理及仿生嗅觉传感器的研究.科学通报. 2007, 52(12):1362~1371
41黄素平,何清华.一种移动机器人路径规划方法.机床与液压. 2004, 5:45-46
42杨建华,候宏,王磊等.基于集成气敏传感器阵列的电子鼻系统环境响应特性分析.传感器技术学报. 2002, 3:197~203
43李广义等.基于MSP430单片机和神经网络的气体浓度检测仪.仪表技术与传感器. 2006, 2:19~20
44何勇,宋海燕.基于神经网络的作物营养诊断专家系统.农业工程学报. 2005, 21(1):110-113
2王树国,战强,陈在礼.智能机器人的现状及未来.机器人技术与应用, 1998, 01:4~7
3 L. Marques, U. Nunes etc. Olfaction-Based Mobile Robot Navigation. Thin Solid Films 2002, 418:51~58
4 H. Ishida, Y. Kagawa, T. Nakamoto, T. Moriizumi. Odor-source Localization in the Clean Room by an Autonomous Mobile Sensing System. Sensors and Actuators.1996, B(33):115~121
5 W. Frank, Grasso, J. Atema. Integration of Flow and Chemical Sensing for Guidance of Autonomous Marine Robots in Turbulent Flows. Environmental Fluid Mechanics. 2002, 2:95~114
6 T. Nakamoto, H. Ishida, T. Moriizumi. An Odor Compass for Localizing an Odor Source. Sensors and Actuators.1996, B(35):32~36
7郭晓强.解读2004年诺贝尔生理学或医学奖.生物学教学2005, 30(3): 69~70
8谭文长.嗅觉模型研究的进展国外医学生物医学工程分册. 1996, 19(5):256~263
9郝博.机器人嗅觉系统的研究.哈尔滨工业大学硕士论文.2005
10徐保港.基于传感器阵列的嗅觉机器人的研究.哈尔滨工业大学硕士论文. 2006
11焦晓国等.鳞翅目蛾类雄性昆虫的信息素.昆虫知识. 2004, 41(4):398~403
12 H. Ishida. Robotic Systems for Gas/Odor Source Localization: Gap Between Experiments and Real-Life Situations. IEEE.
13曲建岭,王磊,杨建华等.基于自组织特征映射网络的气体识别方法研究.测控技术. 2000, 19(3):6~8
14张哲,佟金.电子鼻和电子舌在食品检测中的研究和应用.华中农业大学学报. 2005, 10:25~30
15 H. K. Hong, H. W. Shin, D. H. Yun, S. R. Kim, C. H. Kwow, K. Lee, T. Moriizumi. Electronic Nose System with Micro Gas Sensor Array.Sensors and Actuators 1996, B(35-36) 338~341
16 H. Ishida, T. Tokuhiro, T. Nakamoto and T. Moriizumi. Improvement of Olfactory Video Camera: Gas/Odor Flow Visualization System. Sensors and Actuators 2002, B83(1-3):256~261
17 M. Wandel1, A. Lilienthal, T. Duckett, U. Weimar, A. Zell. Gas Distribution in Unventilated Indoor Environments Inspected by a Mobile Robot. Proceedings of the IEEE International Conference on Advanced Robotics(ICAR 2003). 2003:507-512
18 G. Ferri, M.V. Jakuba, E. Caselli, V. Mattoli etc. Localizing Multiple Gas/Odor Sources in an Indoor Environment using Bayesian Occupancy Grid Mapping. Intelligent Robots and Systems, 2007. IROS 2007. IEEE/RSJ International Conference on. 2007:566~571
19孟庆浩,李飞.主动嗅觉研究现状.机器人. 2006, 28(1): 89~96
20 T. Moriizumi, H. Ishida. Robotic Systems to Track Chemical Plumes. Optoelectronic and Microelectronic Materials and Devices, 2002 537- 540
21 L. Marques, A. T. de Almeida. Electronic Nose-Based Odour Source Localization. IEEE.2000:36~40
22 V. Braitenberg, Vehicles. Experiments in Synthetic Psychology. MIT Press/Bradford Books, 1984
23 H. Ishida, T. Nakamoto, T. Moriizumi. Fundamental Study of Mobile System for Smelling-Object Localization Using Plural Gas Sensor. IEEE Industrial Electrics Society 1993:767~768
24 H. Ishida, K. Suetsugu etc. Study of Autonomous Mobile Sensing System for Localization of Odor Source Using Gas Sensors and Anemometric Sensors Sensors and actuators. A.1994, 45(2) 153~157
25 H. Ishida, G. Nakayama, T. Nakamoto, and T. Moriizumi. Controlling a Gas Plume-Tracking Robot Based on Transient Responses of Gas Sensors.IEEE.2002:1665~1670
26 H. Ishida, H. Tanaka, H. Taniguchi and T. Moriizumi. Mobile Robot Navigation Using Vision and Olfaction to Search for a Gas/Odor Source. Autonomous Robots. 2006, 20(3):231~238
27 R. Russell, D. Thiel, A. Mackay-Sim. Sensing Odour Trails for Mobile Robot Navigation. IEEE International Conference on Robotics and Automation,1994:2672~2677
28 R. Russell, D. Thiel, R. Deveza, A. Mackay-Sim. A Robotic System to Locate Hazardous Chemical Leaks. IEEE International Conference on Robotics and Automation.1995: 556~561
29 Y. Kuwana, I. Shimoyama, H. Miura. Steering Control of a Mobile Robot Using Insect Antennae. Intelligent Robots and Systems 1995, 2: 530~535
30 Y. Kuwana, I. Shimoyama, Y. Sayama, H. Miura. Synthesis of Pheromone-Oriented Emergent Behavior of a Silkworm Moth. Intelligent Robots and Systems. 1996, 3:1722~1729
31 A. Loutfi, S. Coradeschi. Odor Recognition for Intelligent Systems. Intelligent Systems, IEEE. 2008, 23(1). :41-48
32 M. Iida, D. Kang, M. Taniwaki, M. Tanaka and M. Umeda. Localization of CO2 Source by a Hexapod Robot Equipped with an Anemoscope and a Gas Sensor. Computers and Electronics in Agriculture 2008, 63:73~80
33李俊彩,孟庆浩,梁琼.基于进化梯度搜索的机器人主动嗅觉仿真研究.机器人, 2007, 29(3): 234~238
34张志,单越康,项荣,于洋,张健.融合视觉和嗅觉的管道探测机器人的设计与实现.机器人. 2006, 28(5) :499~503
35 H. Ishida, T. Nakamoto and T. Moriizumi. Remote Sensing and Localization of Gas Source and Distribution Using Mobile Sensing System. IEEE.1997:559~562
36李磊.移动机器人系统设计与视觉导航控制研究.中国科学院研究生院博士学位论文. 2003:2~27
37吴玉峰等.气体传感器研究进展和发展方向.计算机测量与控制. 2003, 11(10):731~734
38江福椿等.气体浓度检测技术的现状和应用.河海大学常州分校学报. 2003,18(1):16~19
39马丽杰.日本气体传感器产业化发展现状.云南大学学报(自然科学版). 1997, 19(2):211~216
40吴春生,王丽江,刘清君,赵鲁杭,王平.嗅觉传导机理及仿生嗅觉传感器的研究.科学通报. 2007, 52(12):1362~1371
41黄素平,何清华.一种移动机器人路径规划方法.机床与液压. 2004, 5:45-46
42杨建华,候宏,王磊等.基于集成气敏传感器阵列的电子鼻系统环境响应特性分析.传感器技术学报. 2002, 3:197~203
43李广义等.基于MSP430单片机和神经网络的气体浓度检测仪.仪表技术与传感器. 2006, 2:19~20
44何勇,宋海燕.基于神经网络的作物营养诊断专家系统.农业工程学报. 2005, 21(1):110-113