基于机器视觉的自主机器人路径规划研究
|
摘要
自主机器人是一个集环境感知、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,体现了信息技术与人工智能技术的发展水平。随着计算机和人工智能技术的发展,自主机器人正朝着高速、高精度、开放化、智能化、网络化发展。特别是在某些特殊的场合下,如井下作业、管道检修,若以自主机器人代替人工作业,不但能够保障人身安全、降低劳动强度,而且能够提高经济效益,给人类社会带来极大方便。
自主机器人首先需要像人类一样感知周围环境,然后根据周围环境信息做出综合决策,并对自己的运动做出合理的规划,即路径规划问题。机器视觉能够为机器人提供较为丰富、较全面的环境信息,将它引入自主机器人的路径规划中,将会大大提高路径规划的效果。论文以自主机器人为研究背景,研究了以机器视觉感知导航线和障碍物,能够自主导航并避开障碍物的图像处理、目标定位、路径规划、决策控制等相关问题。
论文分析研究了机器视觉图像预处理的相关算法;分析比较了多个微分算子在边缘检测中的效果,采用Roberts算子进行边缘检测,提取出导航线以及障碍物的轮廓;根据摄像机的投影模型,提出一种基于等空间间距采样的几何定位方法,利用几何关系对障碍物进行定位。
为了研究路径规划算法,自主研发了履带式自主机器人。论文介绍了履带式自主机器人系统的总体设计方案;介绍了机械平台的设计流程以及加工、制作、安装、调试全过程;介绍了以DSP为核心的各个电路模块的设计方案与制作过程;搭建了完整的履带式自主机器人硬件平台;介绍了系统软件的设计思想,给出了软件模块的流程图。
通过对履带式自主机器人的运动及转向数学模型的分析,依据导航线的识别以及障碍物的定位,设计了自主寻迹策略和模糊避障策略。
最后,在履带式自主机器人平台上验证了路径规划算法。
Autonomous robot is an integrated system with a variety of functions such as environment-aware, dynamic decision, behavior control and implementation, which embodies the development level of information technology and artificial intelligence technology. With the development of computer and artificial intelligence technology, autonomous robot is developing towards high speed, high-precision, open, intelligent and network-based. However, in some poor conditions such as mine, pipeline maintenance, the autonomous robot replacing hand manipulation is able to guarantee public safety and reduce labor intensity as well as improving economic efficiency, which brings great convenience for human society.
Autonomous robot must apperceive surrounding environment information as humans first, and then make integrated decision in accordance with the surrounding environment to make a reasonable plan for their moving, namely, path planning problem. Machine vision provides richer and more comprehensive environmental information, which would improve the planning results if it is added into autonomous robot’s path plan. The thesis, on the background of autonomous robot, researches on the image processing, geometrical positioning, path planning, control strategy and so forth by employing the machine vision to perceive the navigation line and obstacles and ultimately navigating and avoiding obstacles automatically.
This paper focuses on several algorithms of machine vision image pre-processing. The author adapts Roberts operator for edge detection, which extracts the navigation line and the contour of obstacles after analyzing and comparing the effect of edge detection using some differential operators. The author puts forward a method of geometrical positioning based on congruence interval sampling according to the camera’s projection model.
In order to verify the algorithm under research, an autonomous tracked robot is independently developed. The thesis introduces general design of autonomous tracked robot, mechanical parts design flow and the whole process of processing, production, installation and debugging. It presents the design and producing of each circuit module based on DSP, sets up an integrated autonomous tracked robot hardware system, introduces software system design idea, and shows the flow chart of the software modules.
In accordance with the analysis of the movement of autonomous tracked robot and its turning mathematical model, as well as navigation line perception and obstacles positioning, the author designs automatic tracking and fuzzy obstacle avoidance strategies.
In the end, the author tests the algorithms on the autonomous tracked robot.
自主机器人首先需要像人类一样感知周围环境,然后根据周围环境信息做出综合决策,并对自己的运动做出合理的规划,即路径规划问题。机器视觉能够为机器人提供较为丰富、较全面的环境信息,将它引入自主机器人的路径规划中,将会大大提高路径规划的效果。论文以自主机器人为研究背景,研究了以机器视觉感知导航线和障碍物,能够自主导航并避开障碍物的图像处理、目标定位、路径规划、决策控制等相关问题。
论文分析研究了机器视觉图像预处理的相关算法;分析比较了多个微分算子在边缘检测中的效果,采用Roberts算子进行边缘检测,提取出导航线以及障碍物的轮廓;根据摄像机的投影模型,提出一种基于等空间间距采样的几何定位方法,利用几何关系对障碍物进行定位。
为了研究路径规划算法,自主研发了履带式自主机器人。论文介绍了履带式自主机器人系统的总体设计方案;介绍了机械平台的设计流程以及加工、制作、安装、调试全过程;介绍了以DSP为核心的各个电路模块的设计方案与制作过程;搭建了完整的履带式自主机器人硬件平台;介绍了系统软件的设计思想,给出了软件模块的流程图。
通过对履带式自主机器人的运动及转向数学模型的分析,依据导航线的识别以及障碍物的定位,设计了自主寻迹策略和模糊避障策略。
最后,在履带式自主机器人平台上验证了路径规划算法。
Autonomous robot is an integrated system with a variety of functions such as environment-aware, dynamic decision, behavior control and implementation, which embodies the development level of information technology and artificial intelligence technology. With the development of computer and artificial intelligence technology, autonomous robot is developing towards high speed, high-precision, open, intelligent and network-based. However, in some poor conditions such as mine, pipeline maintenance, the autonomous robot replacing hand manipulation is able to guarantee public safety and reduce labor intensity as well as improving economic efficiency, which brings great convenience for human society.
Autonomous robot must apperceive surrounding environment information as humans first, and then make integrated decision in accordance with the surrounding environment to make a reasonable plan for their moving, namely, path planning problem. Machine vision provides richer and more comprehensive environmental information, which would improve the planning results if it is added into autonomous robot’s path plan. The thesis, on the background of autonomous robot, researches on the image processing, geometrical positioning, path planning, control strategy and so forth by employing the machine vision to perceive the navigation line and obstacles and ultimately navigating and avoiding obstacles automatically.
This paper focuses on several algorithms of machine vision image pre-processing. The author adapts Roberts operator for edge detection, which extracts the navigation line and the contour of obstacles after analyzing and comparing the effect of edge detection using some differential operators. The author puts forward a method of geometrical positioning based on congruence interval sampling according to the camera’s projection model.
In order to verify the algorithm under research, an autonomous tracked robot is independently developed. The thesis introduces general design of autonomous tracked robot, mechanical parts design flow and the whole process of processing, production, installation and debugging. It presents the design and producing of each circuit module based on DSP, sets up an integrated autonomous tracked robot hardware system, introduces software system design idea, and shows the flow chart of the software modules.
In accordance with the analysis of the movement of autonomous tracked robot and its turning mathematical model, as well as navigation line perception and obstacles positioning, the author designs automatic tracking and fuzzy obstacle avoidance strategies.
In the end, the author tests the algorithms on the autonomous tracked robot.
引文
[1] Gianluca Antonelli, Stefano Chiaverini, Giuseppe Fusco. A Fuzzy-Logic-Based Approach for Mobile Robot Path Tracking[J]. IEEE TRANSACTIONS ON FUZZY SYSTEMS, VOL.15, NO.2, APRIL 2007:211-221.
[2]徐友春,王荣本,李克强,赵玉凡.一种基于直线模型的道路识别算法研究[J].中国图象图形学报, 2004, 9(7):858-864.
[3]徐江伟,岳宏,赵海文,杜春红.基于视觉和超声信息的机器人行为控制[J].仪器仪表学报, 2006, 27(7):734-738.
[4] Yahja A, Singh S Stentz. An Efficient on-line Path Planner for Outdoor Mobile Robots[J]. Robotics and Autonomous Systems, 2002, 32(2-3):129-143.
[5]张捍东,董保华,岑豫皖,郑睿.栅格编码新方法在机器人路径规划中的应用[J].华中科技大学学报, 2007, 35(1):50-53.
[6]郑秀敏,顾大鹏,刘相术.基于栅格法-模拟退火法的机器人路径规划[J].机器人技术, 2007, 23(2-2):247-249.
[7]禹建丽, V. Kroumov,孙增圻,成久洋之.一种快速神经网络路径规划算法[J].机器人, 2001, 23(3):201-205.
[8]刘玲,王耀南,况菲,张辉.基于神经网络和遗传算法的移动机器人路径规划[J].计算机应用研究, 2007, 2:264-265,268.
[9] Wen Zhiqiang, CAI Zixing. Global path planning approach based on ant colony optimization algorithm[J]. J.Cent.South.Univ.Tech, 2006, 13(6):707-712.
[10] Fan Xiaoping. Optimal path planning for mobile robots based on intensified ant colony optimization algorithm[C]. Proceedings of 2003 IEEE International Conference on Robotics, Intelligence Systems and Signal Processing, 2003:131-136.
[11]孙秀云.基于遗传模拟退火算法的机器人全局路径规划[J].机械工程与自动化, 2007, 8(4):104-106.
[12]袁杨,陈雄.基于群集智能算法的移动机器人路径规划研究[J].计算机工程与应用, 2007, 43(5):52-55.
[13] Watanabe K, Izumi K. A survey of robotic control systems constructed by using evolutionary computations[C]. In :Proc IEEE Int Conf on Systems, Man and Cybernetics, Tokyo Japan, 1999:758-763.
[14] Nelson H C , Ye Y C. An intelligent mobile vehicle navigator based on fuzzy logic and reinforcement learning [J]. IEEE Trans on Systems, Man and Cybernetics, Part B:Cybernetics, 1999, 29(2):314– 321.
[15] Koren Y, Borenstein J. Potential field methods and their inherent limitations for mobile robot navigation[C]. Proceedings of the 1991 IEEE International Conference on Robotics and Automation. Sacrament, California: IEEE, 1991:1398- 1404.
[16]金雷泽,杜振军,贾凯.基于势场法的移动机器人路径规划仿真研究[J].计算机工程与应用, 2007, 43(24):226-229.
[17]吴镜开,黄远灿,王世兴.基于势场法的移动机器人避障路径规划[J].机器人技术, 2007, 23(2-2):228-230.
[18]谢雅,彭军,吴敏.足球机器人路径规划的改进型人工势场算法研究[J].计算机工程与应用, 2006, (9):176-179.
[19]李磊,曹志强,侯增广,谭民.基于行为的轮式移动机器人导航控制[J].控制与决策, 2004, 19(6):707-710.
[20] Priti K. Gaonkar, Anthony DelSorbo and Kuldip S. Rattan. Fuzzy Navigation for an Autonomous Mobile Robot[J]. M.S.thesis,Wright State University, Dayton, 2005.
[21] Castro, A.P.A, Simoes Da Silva, J.D, Simoni, P.O. Image based autonomous navigation with fuzzy logic control[C]. Proceedings of the International Joint Conference on Neural Networks, 2001, 3:2200-2205.
[22] Eugenio Aguirre, Antonio Gonz_alez. Fuzzy behaviors for mobile robot navigation:design, coordination and fusion. International Journal of Approximate Reasoning[J], 2000, 25:255-289.
[23]宋晓静,范宁军.基于几何和模糊控制合成算法的小型移动机器人局部路径规划[J].合肥工业大学学报(自然科学版), 2007, 30(1):49-52.
[24]付宜利,顾晓宇,王树国.基于模糊控制的自主机器人路径规划策略研究[J].机器人, 2004, 26(6): 548-512.
[25]庄晓东,孟庆春,殷波.动态环境中基于模糊概念的机器人路径搜索方法[J].机器人, 2001, 23(5): 397-399.
[26] Y.S.Zhou and L.Y.Lai. Optimal design for fuzzy controllers by genetic algorithms[J]. IEEE Trans on Industry Application, Jan 2000,Vol 36.No.1:93-97.
[27]王强,姚进,王进戈.基于遗传算法的移动机器人的一种路径规划方法[J].哈尔滨工业大学学报, 2004, 36(7):867-870.
[28]刘国栋,谢宏斌,李春光.动态环境中基于遗传算法的移动机器人路径规划的方法[J].机器人, 2003, 25(4):327-330,343.
[29]席裕庚,张纯刚.一类动态不确定环境下机器人的滚动路径规划[J].自动化学报, 2002, 28(2): 161-175.
[30]孙斌,韩大鹏,韦庆.基于滚动窗口算法的机器人路径规划应用研究[J].计算机仿真, 2006, 23(6): 159-162.
[31]张文志,吕恬生.基于改进的遗传算法和模糊逻辑控制的移动机器人导航[J].机器人, 2003, 25(1):1-6.
[32]刘祚时,胡翠娜.基于神经网络和遗传算法的足球机器人路径规划[J].计算机应用与软件, 2007, 24(5):156-157,186.
[33] Xiaowei Ma,Xiaoli Li,Hong Qiao. Fuzzy Neural Network-based Real-time Self-reaction of Mobile Robot in Unknown Environment[J]. Mechatronics, 2002:1039-1052.
[34] X.-C. Lai, C.-Y. Kong, S.S. Ge, A.A. Mamun. Online map building for autonomous mobile robots by fusing laser and sonar data[C]. Proceedings of 2005 IEEE International Conference on Mechatronics and Automation, July 2005:993-998.
[35]何东健.数字图像处理[M].西安:西安电子科技大学出版社, 2003.
[36]郭磊,徐友春,李克强,连小珉.基于单目视觉的实时测距方法研究[J].中国图象图形学报, 2006, 11(1):74-81.
[37] LM2940 data sheet, 2005.
[38] MC34063A data sheet, 2000, 4.
[39] TPS767D301 data sheet, 2000, 4.
[40]万山明. TMS320F281x DSP原理及应用实例[M].北京:北京航空航天大学出版社, 2007.
[41]张军,李含善.可编程视频信号输入处理器SAA7111[J].国外电子元器件, 2002, 8:39-42.
[42]张庆磊.基于DSP的通用实时图像处理系统设计与研究[D].浙江大学硕士学位论文, 2004.
[43] STP75NF75 data sheet, 2003.
[44] MAX620 data sheet, 1991.
[45]张克满,何格夫.用虚拟I2C总线技术实现SAA7111的初始化[J] .国外电子元器件, 2005, 1:26-29.
[46] Eric N Moret. Dynamic Modeling and Control of a Car-Like Robot[D]. Master of Science in Electrical Engineering’s thesis, Virginia Polytechnic Institute and State University, 2003.
[47] Benjamin Shamah. Experimental Comparison of Skid Steering Vs. Explicit Steering for a Wheeled Mobile Robot[D]. Master’s thesis, Tech. Report CMU-RI-TR-99-06,Robotics Institute, Carnegie Mellon University,March,1999.
[48] Al-Milli Said, Althoefer Kaspar, Seneviratne Lakmal D. Dynamic analysis and traversability prediction of tracked vehicles on soft terrain[C]. Proc. IEEE International Conference on Networking,Sensing and Control, 2007, 1:279-284.
[49]李彩虹,张景元,李贻斌.基于模糊控制的移动机器人的路径规划[J].淄博学院学报(自然科学与工程版), 2001, 3(3):27-30.
[50]温素芳.基于模糊控制的移动机器人动态避碰的研究[D].哈尔滨工程大学硕士学位论文, 2005.
[2]徐友春,王荣本,李克强,赵玉凡.一种基于直线模型的道路识别算法研究[J].中国图象图形学报, 2004, 9(7):858-864.
[3]徐江伟,岳宏,赵海文,杜春红.基于视觉和超声信息的机器人行为控制[J].仪器仪表学报, 2006, 27(7):734-738.
[4] Yahja A, Singh S Stentz. An Efficient on-line Path Planner for Outdoor Mobile Robots[J]. Robotics and Autonomous Systems, 2002, 32(2-3):129-143.
[5]张捍东,董保华,岑豫皖,郑睿.栅格编码新方法在机器人路径规划中的应用[J].华中科技大学学报, 2007, 35(1):50-53.
[6]郑秀敏,顾大鹏,刘相术.基于栅格法-模拟退火法的机器人路径规划[J].机器人技术, 2007, 23(2-2):247-249.
[7]禹建丽, V. Kroumov,孙增圻,成久洋之.一种快速神经网络路径规划算法[J].机器人, 2001, 23(3):201-205.
[8]刘玲,王耀南,况菲,张辉.基于神经网络和遗传算法的移动机器人路径规划[J].计算机应用研究, 2007, 2:264-265,268.
[9] Wen Zhiqiang, CAI Zixing. Global path planning approach based on ant colony optimization algorithm[J]. J.Cent.South.Univ.Tech, 2006, 13(6):707-712.
[10] Fan Xiaoping. Optimal path planning for mobile robots based on intensified ant colony optimization algorithm[C]. Proceedings of 2003 IEEE International Conference on Robotics, Intelligence Systems and Signal Processing, 2003:131-136.
[11]孙秀云.基于遗传模拟退火算法的机器人全局路径规划[J].机械工程与自动化, 2007, 8(4):104-106.
[12]袁杨,陈雄.基于群集智能算法的移动机器人路径规划研究[J].计算机工程与应用, 2007, 43(5):52-55.
[13] Watanabe K, Izumi K. A survey of robotic control systems constructed by using evolutionary computations[C]. In :Proc IEEE Int Conf on Systems, Man and Cybernetics, Tokyo Japan, 1999:758-763.
[14] Nelson H C , Ye Y C. An intelligent mobile vehicle navigator based on fuzzy logic and reinforcement learning [J]. IEEE Trans on Systems, Man and Cybernetics, Part B:Cybernetics, 1999, 29(2):314– 321.
[15] Koren Y, Borenstein J. Potential field methods and their inherent limitations for mobile robot navigation[C]. Proceedings of the 1991 IEEE International Conference on Robotics and Automation. Sacrament, California: IEEE, 1991:1398- 1404.
[16]金雷泽,杜振军,贾凯.基于势场法的移动机器人路径规划仿真研究[J].计算机工程与应用, 2007, 43(24):226-229.
[17]吴镜开,黄远灿,王世兴.基于势场法的移动机器人避障路径规划[J].机器人技术, 2007, 23(2-2):228-230.
[18]谢雅,彭军,吴敏.足球机器人路径规划的改进型人工势场算法研究[J].计算机工程与应用, 2006, (9):176-179.
[19]李磊,曹志强,侯增广,谭民.基于行为的轮式移动机器人导航控制[J].控制与决策, 2004, 19(6):707-710.
[20] Priti K. Gaonkar, Anthony DelSorbo and Kuldip S. Rattan. Fuzzy Navigation for an Autonomous Mobile Robot[J]. M.S.thesis,Wright State University, Dayton, 2005.
[21] Castro, A.P.A, Simoes Da Silva, J.D, Simoni, P.O. Image based autonomous navigation with fuzzy logic control[C]. Proceedings of the International Joint Conference on Neural Networks, 2001, 3:2200-2205.
[22] Eugenio Aguirre, Antonio Gonz_alez. Fuzzy behaviors for mobile robot navigation:design, coordination and fusion. International Journal of Approximate Reasoning[J], 2000, 25:255-289.
[23]宋晓静,范宁军.基于几何和模糊控制合成算法的小型移动机器人局部路径规划[J].合肥工业大学学报(自然科学版), 2007, 30(1):49-52.
[24]付宜利,顾晓宇,王树国.基于模糊控制的自主机器人路径规划策略研究[J].机器人, 2004, 26(6): 548-512.
[25]庄晓东,孟庆春,殷波.动态环境中基于模糊概念的机器人路径搜索方法[J].机器人, 2001, 23(5): 397-399.
[26] Y.S.Zhou and L.Y.Lai. Optimal design for fuzzy controllers by genetic algorithms[J]. IEEE Trans on Industry Application, Jan 2000,Vol 36.No.1:93-97.
[27]王强,姚进,王进戈.基于遗传算法的移动机器人的一种路径规划方法[J].哈尔滨工业大学学报, 2004, 36(7):867-870.
[28]刘国栋,谢宏斌,李春光.动态环境中基于遗传算法的移动机器人路径规划的方法[J].机器人, 2003, 25(4):327-330,343.
[29]席裕庚,张纯刚.一类动态不确定环境下机器人的滚动路径规划[J].自动化学报, 2002, 28(2): 161-175.
[30]孙斌,韩大鹏,韦庆.基于滚动窗口算法的机器人路径规划应用研究[J].计算机仿真, 2006, 23(6): 159-162.
[31]张文志,吕恬生.基于改进的遗传算法和模糊逻辑控制的移动机器人导航[J].机器人, 2003, 25(1):1-6.
[32]刘祚时,胡翠娜.基于神经网络和遗传算法的足球机器人路径规划[J].计算机应用与软件, 2007, 24(5):156-157,186.
[33] Xiaowei Ma,Xiaoli Li,Hong Qiao. Fuzzy Neural Network-based Real-time Self-reaction of Mobile Robot in Unknown Environment[J]. Mechatronics, 2002:1039-1052.
[34] X.-C. Lai, C.-Y. Kong, S.S. Ge, A.A. Mamun. Online map building for autonomous mobile robots by fusing laser and sonar data[C]. Proceedings of 2005 IEEE International Conference on Mechatronics and Automation, July 2005:993-998.
[35]何东健.数字图像处理[M].西安:西安电子科技大学出版社, 2003.
[36]郭磊,徐友春,李克强,连小珉.基于单目视觉的实时测距方法研究[J].中国图象图形学报, 2006, 11(1):74-81.
[37] LM2940 data sheet, 2005.
[38] MC34063A data sheet, 2000, 4.
[39] TPS767D301 data sheet, 2000, 4.
[40]万山明. TMS320F281x DSP原理及应用实例[M].北京:北京航空航天大学出版社, 2007.
[41]张军,李含善.可编程视频信号输入处理器SAA7111[J].国外电子元器件, 2002, 8:39-42.
[42]张庆磊.基于DSP的通用实时图像处理系统设计与研究[D].浙江大学硕士学位论文, 2004.
[43] STP75NF75 data sheet, 2003.
[44] MAX620 data sheet, 1991.
[45]张克满,何格夫.用虚拟I2C总线技术实现SAA7111的初始化[J] .国外电子元器件, 2005, 1:26-29.
[46] Eric N Moret. Dynamic Modeling and Control of a Car-Like Robot[D]. Master of Science in Electrical Engineering’s thesis, Virginia Polytechnic Institute and State University, 2003.
[47] Benjamin Shamah. Experimental Comparison of Skid Steering Vs. Explicit Steering for a Wheeled Mobile Robot[D]. Master’s thesis, Tech. Report CMU-RI-TR-99-06,Robotics Institute, Carnegie Mellon University,March,1999.
[48] Al-Milli Said, Althoefer Kaspar, Seneviratne Lakmal D. Dynamic analysis and traversability prediction of tracked vehicles on soft terrain[C]. Proc. IEEE International Conference on Networking,Sensing and Control, 2007, 1:279-284.
[49]李彩虹,张景元,李贻斌.基于模糊控制的移动机器人的路径规划[J].淄博学院学报(自然科学与工程版), 2001, 3(3):27-30.
[50]温素芳.基于模糊控制的移动机器人动态避碰的研究[D].哈尔滨工程大学硕士学位论文, 2005.