移动机器人的路径规划与定位技术研究
|
摘要
移动机器人技术涉及多个研究领域，代表了高技术的发展前沿，已经在各行各业中取得了广泛的应用。移动机器人具有利用传感器感知环境信息和自身状态，在含有障碍的环境中完成某些预定任务的功能。移动机器人实现在有障碍的环境中自主地移动到目标点的运动过程被称为移动机器人的导航。在导航的过程当中，移动机器人要建立准确的环境建模，实现自身的定位以及规划出一条从起点到目标点的最优路径，因此研究移动机器人的环境建模方法、路径规划算法以及定位方法具有理论与现实的意义。
本文针对移动机器人路径规划方法以及定位技术进行了研究，主要内容包括以下几个方面：
针对移动机器人全局路径规划问题进行研究，提出了一种适用于移动机器人路径规划的简化可视图环境建模方法，通过综合考虑环境中障碍物的位置与移动机器人起点和终点的关系，剔除对路径规划结果不影响的障碍物，简化了环境模型的表示，达到了减少移动机器人候选路径数量的目的，提高了后续的路径规划算法的效率。
针对蚁群算法中收敛速度和局部最优的矛盾，提出一种基于改进蚁群算法的移动机器人路径规划方法。该改进算法将环境中局部的路径信息加入到信息素的初始化和路径选择概率中，提高了算法的收敛速度；在算法陷入停滞时，引入交叉操作，增加了算法的逃逸能力。改进的蚁群算法提高了移动机器人对最优路径的搜索效率。
针对复杂环境中移动机器人局部路径规划方法中存在的局部极小问题，提出了一种基于多行为协调的路径规划方法，该方法定义三种机器人的基本行为并通过各行为间的切换完成路径规划任务。设计了试错补偿旋转角度法，解决了机器人遇到U型障碍时产生的局部极小问题。提出的多行为协调方法提高了含有U型障碍物环境中移动机器人局部路径规划结果的可靠性。
为解决Rao-Blackwellized粒子滤波器存在的“粒子消耗”现象，提出了一种基于微粒群优化的移动机器人同时定位与建图方法。该方法在粒子重采样过程中利用微粒群优化算法获得机器人位姿的建议分布，通过粒子间的能效吸引力对求得的粒子集进行进一步的优化、调整，提升了粒子的多样性。该方法有效地减少了“粒子消耗”现象，保证了同时定位与建图结果的精度。
针对FastSLAM2.0算法中噪声的假设受统计特性限制的缺点，提出了一种改进的FastSLAM2.0算法，用H∞滤波器替代FastSLAM2.0算法中的EKF，削弱了误差对机器人位姿估计的影响。同时，在提出的改进FastSLAM2.0算法中，针对“粒子消耗”问题，提出了基于遗传算法和微粒群优化算法的粒子重采样策略。提出的改进FastSLAM2.0算法有效地提高了移动机器人位姿估计的一致性，克服了标准FastSLAM2.0算法中由于地图估计误差积累导致移动机器人位姿估计不准确的缺点。
Mobile robot technology involves multiple research areas and represents the frontier of high technology. Mobile robot technology has a wide range of applications in different walks of life. Mobile robot is capable of acquiring the information of environment and its own state to achieve the scheduled mission in the environment with obstacles. Navigation of mobile robot is the process of moving toward the target autonomously in the environment with obstacles. In the process of navigation, mobile robot has to carry out the accurate modeling of the environment, achieving the location of the pose and planning the optimal path from the starting point to the target point. Therefore, the research of environment modeling method, path planning algorithm and locationing method for mobile robot has theoretical and realistic significance.
In this dissertation, the path planning approach and location technology for mobile robot are focused on. The main contents of this dissertation are summarized as follows:
For global path planning of mobile robot, simplified visibility graph suitable for path planning algorithm of mobile robot is proposed to solve the problem of environment modeling. Considering the position of the obstacles in the environment and the relationship between starting point and end point of the mobile robot, the redundant obstacles which does not affect the result of path planning are removed. The representation of environment model is simplified. The purpose of reducing the number of alternative paths in the process of path planning is achieved, which improves the efficiency of the follow-up path planning algorithm.
To solve the contradictory between the convergence speed and the local optimum in ant colony algorithm, an improved ant colony optimization algorithm is proposed for path planning. The local path information is integrated with the initialization of pheromone and the selected probabilities of the paths, resulting in improving the convergence speed. For overcoming the stagnation phenomenon, crossover operation is drawn into the proposed algorithm, which enhances the capability of escaping stagnation phenomenon.The proposed algorithm improves the search efficiency of optimum path for mobile robot.
To solve the local minimum problem in the complex environment of local path planning for mobile robot, a multi-behaviors coordination approach is proposed. The proposed approach defines three kinds of basic behaviors. The mission of path planning is completed by switching amoung three kinds of basic behaviors. The trial-angle compensation method in escaping from the local minimum behavior is designed to solve the local minimum problem existing in the environment with the U-shaped obstacles. The proposed approach improves the reliability of results of local path planning for mobile robot in the environment with the U-shaped obstacle.
To solve the “particles degeneracy” phenomenon of the Rao-Blackwellized particle filter, a new approach based on Particle Swarm Optimization is presented to solve SLAM problem for mobile robot. During the particle re-sampling process, the proposal distribution of mobile robot’s pose is acquired by Particle Swarm Optimization. The attraction of energy efficiency is applied to optimize and adjust the obtained particle sets, which the diversity of the particles is enrished. The proposed algorithm eases the “particles degeneracy” problem and ensures the accuracy of SLAM results.
Due to the drawback of FastSLAM2.0about the noise assumption being limited by the statistical characteristics, an improved FastSLAM2.0algorithm is proposed. H∞filter is used in the improved FastSLAM2.0algorithm instead of EKF, which reduces the influnce of error of robot pose estimation. For the “particles degeneracy” problem, the particle re-sampling strategy based on genetic algorithm and particle swarm optimization is proposed in improved FastSLAM2.0algorithm. The consistency of mobile robot pose estimation is improved effectively. The proposed approach overcomes the drawbacks of standard FastSLAM2.0algorithm which the inaccurate pose estimation of mobile robot is caused by map estimation error accumulation.
本文针对移动机器人路径规划方法以及定位技术进行了研究，主要内容包括以下几个方面：
针对移动机器人全局路径规划问题进行研究，提出了一种适用于移动机器人路径规划的简化可视图环境建模方法，通过综合考虑环境中障碍物的位置与移动机器人起点和终点的关系，剔除对路径规划结果不影响的障碍物，简化了环境模型的表示，达到了减少移动机器人候选路径数量的目的，提高了后续的路径规划算法的效率。
针对蚁群算法中收敛速度和局部最优的矛盾，提出一种基于改进蚁群算法的移动机器人路径规划方法。该改进算法将环境中局部的路径信息加入到信息素的初始化和路径选择概率中，提高了算法的收敛速度；在算法陷入停滞时，引入交叉操作，增加了算法的逃逸能力。改进的蚁群算法提高了移动机器人对最优路径的搜索效率。
针对复杂环境中移动机器人局部路径规划方法中存在的局部极小问题，提出了一种基于多行为协调的路径规划方法，该方法定义三种机器人的基本行为并通过各行为间的切换完成路径规划任务。设计了试错补偿旋转角度法，解决了机器人遇到U型障碍时产生的局部极小问题。提出的多行为协调方法提高了含有U型障碍物环境中移动机器人局部路径规划结果的可靠性。
为解决Rao-Blackwellized粒子滤波器存在的“粒子消耗”现象，提出了一种基于微粒群优化的移动机器人同时定位与建图方法。该方法在粒子重采样过程中利用微粒群优化算法获得机器人位姿的建议分布，通过粒子间的能效吸引力对求得的粒子集进行进一步的优化、调整，提升了粒子的多样性。该方法有效地减少了“粒子消耗”现象，保证了同时定位与建图结果的精度。
针对FastSLAM2.0算法中噪声的假设受统计特性限制的缺点，提出了一种改进的FastSLAM2.0算法，用H∞滤波器替代FastSLAM2.0算法中的EKF，削弱了误差对机器人位姿估计的影响。同时，在提出的改进FastSLAM2.0算法中，针对“粒子消耗”问题，提出了基于遗传算法和微粒群优化算法的粒子重采样策略。提出的改进FastSLAM2.0算法有效地提高了移动机器人位姿估计的一致性，克服了标准FastSLAM2.0算法中由于地图估计误差积累导致移动机器人位姿估计不准确的缺点。
Mobile robot technology involves multiple research areas and represents the frontier of high technology. Mobile robot technology has a wide range of applications in different walks of life. Mobile robot is capable of acquiring the information of environment and its own state to achieve the scheduled mission in the environment with obstacles. Navigation of mobile robot is the process of moving toward the target autonomously in the environment with obstacles. In the process of navigation, mobile robot has to carry out the accurate modeling of the environment, achieving the location of the pose and planning the optimal path from the starting point to the target point. Therefore, the research of environment modeling method, path planning algorithm and locationing method for mobile robot has theoretical and realistic significance.
In this dissertation, the path planning approach and location technology for mobile robot are focused on. The main contents of this dissertation are summarized as follows:
For global path planning of mobile robot, simplified visibility graph suitable for path planning algorithm of mobile robot is proposed to solve the problem of environment modeling. Considering the position of the obstacles in the environment and the relationship between starting point and end point of the mobile robot, the redundant obstacles which does not affect the result of path planning are removed. The representation of environment model is simplified. The purpose of reducing the number of alternative paths in the process of path planning is achieved, which improves the efficiency of the follow-up path planning algorithm.
To solve the contradictory between the convergence speed and the local optimum in ant colony algorithm, an improved ant colony optimization algorithm is proposed for path planning. The local path information is integrated with the initialization of pheromone and the selected probabilities of the paths, resulting in improving the convergence speed. For overcoming the stagnation phenomenon, crossover operation is drawn into the proposed algorithm, which enhances the capability of escaping stagnation phenomenon.The proposed algorithm improves the search efficiency of optimum path for mobile robot.
To solve the local minimum problem in the complex environment of local path planning for mobile robot, a multi-behaviors coordination approach is proposed. The proposed approach defines three kinds of basic behaviors. The mission of path planning is completed by switching amoung three kinds of basic behaviors. The trial-angle compensation method in escaping from the local minimum behavior is designed to solve the local minimum problem existing in the environment with the U-shaped obstacles. The proposed approach improves the reliability of results of local path planning for mobile robot in the environment with the U-shaped obstacle.
To solve the “particles degeneracy” phenomenon of the Rao-Blackwellized particle filter, a new approach based on Particle Swarm Optimization is presented to solve SLAM problem for mobile robot. During the particle re-sampling process, the proposal distribution of mobile robot’s pose is acquired by Particle Swarm Optimization. The attraction of energy efficiency is applied to optimize and adjust the obtained particle sets, which the diversity of the particles is enrished. The proposed algorithm eases the “particles degeneracy” problem and ensures the accuracy of SLAM results.
Due to the drawback of FastSLAM2.0about the noise assumption being limited by the statistical characteristics, an improved FastSLAM2.0algorithm is proposed. H∞filter is used in the improved FastSLAM2.0algorithm instead of EKF, which reduces the influnce of error of robot pose estimation. For the “particles degeneracy” problem, the particle re-sampling strategy based on genetic algorithm and particle swarm optimization is proposed in improved FastSLAM2.0algorithm. The consistency of mobile robot pose estimation is improved effectively. The proposed approach overcomes the drawbacks of standard FastSLAM2.0algorithm which the inaccurate pose estimation of mobile robot is caused by map estimation error accumulation.
引文
[1]蔡自兴.机器人学[M].北京：清华大学出版社，2000：1-2.
[2]蔡自兴，贺汉根，陈虹.未知环境中移动机器人导航控制研究的若干问题[J].控制与决策，2002，17(04)：385-390.
[3] Ohnishi N, Imiya A. Appearance-based navigation and homing forautonomous mobile robot[J]. Image and Vision Computing.2013,31(6–7):511-532.
[4] Colle E, Galerne S. Mobile robot localization by multiangulation using setinversion[J]. Robotics and Autonomous Systems,2013,61(1):39-48.
[5]朱大奇，颜明重.移动机器人路径规划技术综述[J].控制与决策.2010(7):961-967.
[6]刘睿.飞行器惯性/地磁/天文组合导航系统研究[D].哈尔滨:哈尔滨工业大学,2011:2-3.
[7]付强文，秦永元，李四海，等.车辆运动学约束辅助的惯性导航算法[J].中国惯性技术学报,2012,26(6):640-643.
[8]王佳凤，吴伟，胡岩，等.基于四元数算法的智能轮椅MEMS惯性导航系统研究[C]//第九届沈阳科学学术年会.第九届科学学术年会论文集.北京：人民教育出版社,2012:13-18.
[9] Lou L, Xu X. An Approach to Improving Attitude Estimation Using SensorFusion for Robot Navigation[J]. Procedia Engineering,2011,15:5601-5605.
[10] Nagla K S, Uddin M, Singh D. Improved occupancy grid mapping inspecular environment[J]. Robotics and Autonomous Systems,2012,60(10):1245-1252.
[11] Zhang Q, Ma J C, Xie W. A framed-quadtree based on reversed D*pathplanning approach for intelligent mobile robot[J]. Journal of Computers,2012,2(7):464-469.
[12] Vacavant A. Fast distance transformation on irregular two-dimensionalgrids[J]. Pattern Recognition.2010,43(10):3348-3358.
[13] Shi L, Kodagoda S. Towards generalization of semi-supervised placeclassification over generalized Voronoi graph[J]. Robotics and AutonomousSystems,2013,61(8):785-796.
[14] Likhachev D. Anytime search in dynamic graphs[J]. Artificial Intelligence,2008,172(5):1613–1643.
[15] Dakulovi M, Petrovi I. Two-way D*algorithm for path planning andreplanning [J]. Robotics and Autonomous Systems,2011,59(5):329-342.
[16] Guernane R, Achour N. Generating optimized paths for motion planning[J].Robotics and Autonomous Systems,2011,59(10):789-800.
[17] Bayili S, Polat F. Limited-Damage A*: A path search algorithm thatconsiders damage as a feasibility criterion[J]. Knowledge-Based Systems,2011,24(5):501–512.
[18]祖伟.基于粒子群优化算法的水下潜器实时路径规划技术研究[D].哈尔滨工程大学,2008.
[19] Zhang Q, Ma J C, Liu Q. Path planning based quadtree representation formobile robot using hybrid-simulated annealing and ant colony optimizationalgorithm[C]//Proceedings of the World Congress on Intelligent Controland Automation (WCICA). Beijing: IEEE Press,2012:2537-2542.
[20] Zhang J H, Gong D W, Zhang Y. A niching PSO-based multi-robotcooperation method for localizing odor sources[J]. Neurocompting.2014(123):308-317.
[21]梁毓明，徐立鸿.基于改进模拟退火混合算法的移动机器人全局路径规划[J].控制与决策,2010,25(2):237-240.
[22] Faigl J, Kulich M, Vonásek V, et al. An application of the self-organizingmap in the non-Euclidean Traveling Salesman Problem[J]. Neurocomputing.2011,74(5):671-679.
[23] Fu Y G, Ding M Y, Zhou C P. Route Planning for Unmanned Aerial Vehicle(UAV) on the Sea Using Hybrid Differential Evolution andQuantum-Behaved Particle Swarm Optimization[J]. Systems, Man, andCybernetics: Systems, IEEE Transactions on.2013,43(6):1451-1465.
[24]张航，刘梓溪.基于量子行为粒子群算法的微型飞行器三维路径规划[J].中南大学学报(自然科学版),2013(S2):58-62.
[25]王雪松，高阳，程玉虎等.知识引导遗传算法实现机器人路径规划[J].控制与决策,2009(07):1043-1049.
[26]赵娟平，高宪文，刘金刚，等.移动机器人路径规划的参数模糊自适应窗口蚁群优化算法[J].控制与决策,2011,26(7):1096-1100.
[27]朱庆保.复杂环境下的机器人路径规划蚂蚁算法[J].自动化学报,2006,32(4):586-593.
[28]金飞虎，高会军，钟啸剑.自适应蚁群算法在空间机器人路径规划中的应用[J].哈尔滨工业大学学报,2010,42(7):1014-1018.
[29]赵娟平，高宪文，符秀辉.移动机器人路径规划的改进蚁群优化算法[J].控制理论与应用,2011,28(4):457-461.
[30] Yang J, Zhuang Y. An improved ant colony optimization algorithm forsolving a complex combinatorial optimization problem[J]. Applied SoftComputing,2010,10(2):653-660.
[31]张培艳，吕恬生，宋立博.基于案例学习的排球机器人运动规划及其支持向量回归实现[J].上海交通大学学报.2006(3):461-465.
[32] Marefat M, Britanik J. Cased-based process planning using anobject-oriented model representation[J]. Robotics and Computer-IntegratedManufacturing,1997,13(3):3-25.
[33]张小川,纪钢.基于事例的足球机器人学习[J].哈尔滨工业大学学报,2004,2(7):905-907.
[34]翁敏，杜清运，瞿嵘，等.基于典型事例推理的路径规划方法研究[J].武汉大学学报(信息科学版).2008(12):1263-1266.
[35] Mucientes M, Alcalá-Fdez J, Alcalá R, et al. A case study for learningbehaviors in mobile robotics by evolutionary fuzzy systems[J]. ExpertSystems with Applications，2010,37(2):1471-1493.
[36]仲训昱，彭侠夫，缪孟良.基于环境建模与自适应窗口的机器人路径规划[J].华中科技大学学报(自然科学版).2010(06):107-111.
[37]任敏，霍霄华.基于异步双精度滚动窗口的无人机实时航迹规划方法[J].中国科学:信息科学.2010(04):561-568.
[38]刘春明，李兆斌，黄振华，等.基于LSPI和滚动窗口的移动机器人反应式导航方法[J].中南大学学报(自然科学版).2013(03):970-977.
[39] Chou C, Lian F, Wang C. Characterizing indoor environment for robotnavigation using velocity space approach with region analysis andlook-ahead verification[J]. Instrumentation and Measurement, IEEETransactions on.2011,60(2):442-451.
[40] Berti H, Sappa A D. Autonomous robot navigation with a global andasymptotic convergence [C]//IEEE International Conference on Roboticsand Automation. USA: IEEE Press,2007:2712-2717.
[41]邱雪娜，刘士荣，宋加涛，等.不确定动态环境下移动机器人的完全遍历路径规划[J].机器人.2006(06):586-592.
[42] Mcfetridge L, Ibrahim M Y. A new methodology of mobile robot navigation:The agoraphilic algorithm[J]. Robotics and Computer-IntegratedManufacturing,2009,25(3):545-551.
[43]齐勇,魏志强等.增强蚁群算法的机器人最优路径规划[J].哈尔滨工业大学学报,2009,41(3):130-133.
[44] Zhang Q S, Chen D D, Chen T. An Obstacle Avoidance Method of SoccerRobot Based on Evolutionary Artificial Potential Field[J]. Energy ProcediaPart C，2012,16:1792-1798.
[45]张建英，刘暾.基于人工势场法的移动机器人最优路径规划[J].航空学报,2007,28(8):183-188.
[46]王芳，万磊，徐玉如，等.基于改进人工势场的水下机器人路径规划[J].华中科技大学学报(自然科学版),2011,39(S2):184-185.
[47]朱毅，张涛，宋靖雁.非完整移动机器人的人工势场法路径规划[J].控制理论与应用,2010,27(2):152-158.
[48]杜广龙，张平.基于人工势场的机器人遥操作安全预警域动态生成方法[J].机器人,2012,34(1):44-49.
[49]李擎，王丽君，陈博，等.一种基于遗传算法参数优化的改进人工势场法[J].北京科技大学学报,2012,34(2):202-206.
[50]杨毅，刘亚辰，刘明阳，等.一种基于凸壳的智能服务机器人路径规划算法[J].北京理工大学学报.2011,31(1):54-58.
[51]丁华胜，王华忠.基于PSO的人工势场法在移动机器人路径规划中的应用[J].华东理工大学学报(自然科学版),2010,36(5):727-731.
[52] Parhi D R, Mohanta J C. Navigational control of several mobile roboticagents using Petri-potential-fuzzy hybrid controller[J]. Applied SoftComputing,2011,11(4):3546-3557.
[53] Luh G, Liu W. An immunological approach to mobile robot reactivenavigation[J]. Applied Soft Computing,2008,8(1):30-45.
[54] Daoyi D, Chunlin C, Jian C, et al. Robust Quantum-Inspired ReinforcementLearning for Robot Navigation [J]. IEEE/ASME Transactions onMechatronics,2012,17(1):86-97.
[55] Ozcelik S, Sukumaran S. Implementation of An Artificial Immune Systemon a Mobile Robot[J]. Procedia Computer Science,2011,6:317-322.
[56] Das Sharma K, Chatterjee A, Rakshit A. A PSO-Lyapunov Hybrid StableAdaptive Fuzzy Tracking Control Approach for Vision-Based RobotNavigation[J]. Instrumentation and Measurement, IEEE Transactions on.2012,61(7):1908-1914.
[57]付宜利，靳保，王树国，等.未知环境下基于行为的机器人模糊路径规划方法[J].机械工程学报.2006,42(5):120-125.
[58] Huq R, Mann G K I, Gosine R G. Mobile robot navigation using motorschema and fuzzy context dependent behavior modulation[J]. Applied SoftComputing.2008,8(1):422-436.
[59] Toibero J M, Roberti F, Carelli R, et al. Switching control approach forstable navigation of mobile robots in unknown environments[J]. Roboticsand Computer-Integrated Manufacturing.2011,27(3):558-568.
[60]李寿涛.基于行为的智能体避障控制以及动态协作方法研究[D].长春：吉林大学学位论文,2007:58-81.
[61] Fernandez-Leon J A, Acosta G G, Mayosky M A. Behavioral controlthrough evolutionary neurocontrollers for autonomous mobile robotnavigation[J]. Robotics and Autonomous Systems,2009,57(4):411-419.
[62] Shi C, Wang Y, Yang J. A local obstacle avoidance method for mobile robotsin partially known environment[J]. Robotics and Autonomous Systems,2010,58(5):425-434.
[63] Chia F J, Yu C C. Evolutionary-Group-Based Particle-Swarm-OptimizedFuzzy Controller With Application to Mobile-Robot Navigation inUnknown Environments[J]. IEEE Transactions on Fuzzy Systems,2011,19(2):379-392.
[64] Whitbrook A M, Aickelin U, Garibaldi J M. Idiotypic Immune Networks inMobile-Robot Control[J]. IEEE Transactions on Systems, Man, andCybernetics, Part B: Cybernetics,2007,37(6):1581-1598.
[65] Iocchi L, Nardi D. Hough Localization for mobile robots in polygonalenvironments[J]. Robotics and Autonomous Systems.2002,40(1):43-58.
[66] Falomir Z, Museros L, Castelló V, et al. Qualitative distances andqualitative image descriptions for representing indoor scenes in robotics[J].Pattern Recognition Letters.2013,34(7):731-743.
[67] Huang C, Chan C. ZigBee-based indoor location system by k-nearestneighbor algorithm with weighted RSSI[J]. Procedia Computer Science.2011,5:58-65.
[68] Rashid M M, Saidahbtmohdzain N, Zain F M. Development of OmniDirectional Mobile Robot Navigation System using RFID for MultipleObject[J]. AASRI Procedia.2012,3:474-480.
[69] Lee H, Jung J, Choi K, et al. Fuzzy-logic-assisted interacting multiplemodel (FLAIMM) for mobile robot localization[J]. Robotics andAutonomous Systems,2012,60(12):1592-1606.
[70] Herrero-Pérez D, Martínez-Barberá H, Leblanc K, et al. Fuzzy uncertaintymodeling for grid based localization of mobile robots [J]. InternationalJournal of Approximate Reasoning,2010,51(8):912-932.
[71] Moreno L, Garrido S, Mu oz M L. Evolutionary filter for robust mobilerobot global localization[J]. Robotics and Autonomous Systems,2006,54(7):590-600.
[72] Loevsky I, Shimshoni I. Reliable and efficient landmark-based localizationfor mobile robots[J]. Robotics and Autonomous Systems,2010,58(5):520-528.
[73] Aubry C, Desmare R, Jaulin L. Loop detection of mobile robots usinginterval analysis[J]. Automatica,2013,49:463-470.
[74] Kaess M, Dellaert F. Covariance recovery from a square root informationmatrix for data association[J]. Robotics and Autonomous Systems,2009,57(12):1198-1210.
[75] Booij O, Zivkovic Z, Kr se B. Efficient data association for view basedSLAM using connected dominating sets[J]. Robotics and AutonomousSystems,2009,57(12):1225-1234.
[76] Williams B, Cummins M, Neira J, et al. A comparison of loop closingtechniques in monocular SLAM[J]. Robotics and Autonomous Systems,2009,57(12):1188-1197.
[77] Jauregi E, Irigoien I, Sierra B, et al. Loop-closing: A typicality approach[J].Robotics and Autonomous Systems,2011,59(3–4):218-227.
[78] Li H P, Xu D M, Zhang F B, et al. Consistency analysis of EKF-basedSLAM by measurement noise and observation times[J]. Acta AutomaticaSinica,2009,35(9):1177-1184.
[79] Castellanos J A, Martinez-Cantin R, Tardós J D, et al. Robocentric mapjoining: Improving the consistency of EKF-SLAM[J]. Robotics andAutonomous Systems,2007,55(1):21-29.
[80] Movafaghpour M A, Masehian E. Poly line map extraction in sensor-basedmobile robot navigation using a consecutive clustering algorithm[J].Robotics and Autonomous Systems,2012,60(8):1078-1092.
[81] Lee J, Ko H. Gradient-based local affine invariant feature extraction formobile robot localization in indoor environments[J]. Pattern RecognitionLetters,2008,29(14):1934-1940.
[82] Bakar M N A, Saad A R M. A Monocular Vision-based Specific PersonDetection System for Mobile Robot Applications[J]. Procedia Engineering,2012,41:22-31.
[83] Lee D, Kim G, Kim D, et al. Vision-based object detection and tracking forautonomous navigation of underwater robots[J]. Ocean Engineering,2012,48:59-68.
[84] Jose G, Eduardo N. Optimization of Simultaneous Location and PamBuilding Algorithm for Real Time Implementation[J]. IEEE Transactions onRobot and Automation,2001,8(4):242-257.
[85] Paz L M, Tardos J D, Jose N. Divide and Conquer: EKF SLAM in O(n)[J].IEEE Transactions on Robotics,2008,5(24):1107-1120.
[86]张海强，窦丽华，方浩，等.基于压缩型EKF的SLAM改进算法[J].系统仿真学报,2009,31(10):5668-5671.
[87]弋英民，刘丁.有色过程噪声下的轮式机器人同步定位与地图构建[J].电子学报,2010,38(6):1339-1343.
[88]钱臻，齐英杰.迭代中心差分粒子滤波的SLAM算法[J].哈尔滨工程大学学报,2012,33(3):355-360.
[89]王宏健，王晶，边信黔，等.基于组合EKF的自主水下航行器SLAM[J].机器人,2012,34(1):56-64.
[90] Petsios M N, Alivizatos E G, Uzunoglu N K. Manoeuvring target trackingusing multiple bistatic range and range-rate measurements[J]. SignalProcessing,2007,87(4):665-686.
[91] Kim C, Sakthivel R, Chung W K. Unscented FastSLAM: a robust andefficient solution to the SLAM problem[J]. IEEE Transactions on Robotics,2008,24(4):808-820.
[92]杜航原，郝燕玲，高忠强，等.基于鲁棒非线性卡尔曼滤波的自适应SLAM算法[J].宇航学报,2012,33(5):620-627.
[93] Song Q, Han J. An Adaptive UKF Algorithm for the State and ParameterEstimations of a Mobile Robot[J]. Acta Automatica Sinica,2008,34(1):72-79.
[94]赵琳，闫鑫，郝勇.基于迭代平方根UKF的SLAM算法[J].弹箭与制导学报,2011,31(1):157-160.
[95] Moreno L, Garrido S, Blanco D, et al. Differential evolution solution to theSLAM problem[J]. Robotics and Autonomous Systems,2009,57(4):441-450.
[96]田翔，张亮，陈耀武.基于中心差分卡尔曼滤波器的快速SLAM算法[J].哈尔滨工业大学学报,2010,42(9):1454-1461.
[97] Ryan A, Hedrick J K. Particle filter based information-theoretic activesensing[J]. Robotics and Autonomous Systems.2010,58(5):574-584.
[98] Montemerlo M. Thrun S. Roller D. FastSLAM: A factored solution tosimultaneous localization and mapping[C]//Proceedings of the NationalConference on Artificial Intelligence (AAAI). USA: IEEE Press,2002:593–598.
[99]陈白帆，蔡自兴，袁成.基于粒子群优化的移动机器人SLAM方法[J].机器人,2009,31(6):513-517.
[100]周武，赵春霞，张浩峰.一种基于AMPF和FastSLAM的复合SLAM算法[J].模式识别与人工智能,2009,22(5):718-725.
[101]张亮.移动机器人同步定位与地图重建算法研究[D].杭州：浙江大学学位论文,2009:58-62.
[102]陈家乾，何衍，蒋静坪.基于权值平滑的改良FastSLAM算法[J].浙江大学学报(工学版),2010,44(8):1454-1459.
[103]朱磊，樊继壮，赵杰，等.未知环境下的移动机器人SLAM方法[J].华中科技大学学报(自然科学版),2011,39(7):9-13.
[104]刘洞波，刘国荣，王迎旭，等.基于区间分析无迹粒子滤波的移动机器人SLAM方法[J].农业机械学报,2012,43(10):155-160.
[105] Montemerlo M. Thrun S. Roller D. FastSLAM2.0: An improved particlefiltering algorithm for simultaneous localization and mapping that provablyconverges [C]//Proceedings of the International Conference on ArtificialIntelligence (IJCAI). USA: IEEE Press,2003:1151–1156.
[106] Tomas L P, Michael W. An algorithm for planning collision-free pathsamong polyhedral obstacles[J]. Communications of the ACM,1979,22(10):560-570.
[107] Liu Y H, Arimoto S. Computation of the tangent graph of polygonalobstacles by moving-line processing[J]. IEEE Transactions on Robotics andAutomation,1994,10(6):823-830.
[108] Huang H P, Chuang S Y. Dynamic visibility graph for path planning[C]//IEEE International Conference on Intelligent Robots and Systems. Japan:Institute of Electrical and Electronics Engineers Inc2004,3:2813-2818.
[109]蔡自兴，贺汉根，陈虹.未知环境中移动机器人导航控制理论与方法[M].北京：科学出版社，2009:8-12.
[110]李士勇.蚁群算法及其应用[M].哈尔滨：哈尔滨工业大学出版社，2004：181-185.
[111]陈凌，沈洁,秦玲,等.基于分布均匀度的自适应蚁群算法[J].软件学报,2013,14(8):1379-1387.
[112] Garcia M A P, Montiel O, Castillo O, et al. Path planning for autonomousmobile robot navigation with ant colony optimization and fuzzy costfunction evaluation[J]. Applied Soft Computing,2009,9(3):1102-1110.
[113] Huq R, Mann G K I, Gosine R G. Mobile robot navigation using motorschema and fuzzy context dependent behavior modulation[J]. Applied SoftComputing,2008,8(1):422-436.
[114] Zhu A, Yang S X. A fuzzy logic approach to reactive navigation ofbehavior-based mobile robots[C]//IEEE International Conference onRobotics and Automation. USA: IEEE Press,2004:5045–5050.
[115] Krishna K M, Kalra P K. Perception and remembrance of the environmentduring real-time navigation of a mobile robot[J]. Robot and AutonomousSystem,2001,37(4):25–51.
[116] Wang M, Liu J. Fuzzy logic-based real-time robot navigation in unknownenvironment with dead ends[J]. Robotics and Autonomous Systems,2008,56(7):625-643.
[117] Motlagh O, Hong T S, Ismail N. Development of a new minimum avoidancesystem for a behavior-based mobile robot[J]. Fuzzy Sets and Systems,2009,160(13):1929-1946.
[118] Navalertporn T, Afzulpurkar N V. Optimization of tile manufacturingprocess using particle swarm optimization[J]. Swarm and EvolutionaryComputation,2011,1(2):97-109.
[119] Gordon N J, Salmond D J, Smith A F M. Novel approach tononlinear/non-Gaussian Bayesian state estimation[J]. IEE Proceedings F(Radar and Signal Processing),1993,140(2):107-113.
[120]蒋蔚.粒子滤波改进算法研究与应用[D].哈尔滨工业大学,2010.
[121] Arnaud D, Nando D F, Neil G. Sequential Monte Carlo Methods inPractice[M]. New York: Springe-Verlag,2001:171-174.
[122]朱伟.时边离散动态系统的渐近稳定性和几何速度稳定性[J].应用科学学报,2004,22(2):252-254.
[123] Tim B, Juan N, Eduardo N. Consistency of the FastSLAM Algorithm[C]//Proceedings of the2006IEEE International Conference on Robotics andAutomation. Orlando: IEEE Press,2006:424-429.
[124] Hassibi B, Sayed A H, Kailath T. Linear estimation in Krein spaces-part I:applications[J]. IEEE Transactions on Automatic Control,1996,41(1):18-33.
[125] Hassibi B, Sayed A H, Kailath T. Linear estimation in Krein spaces-part II:applications[J]. IEEE Transactions on Automatic Control,1996,41(1):34-49.
[126] Simon D. Optimal state estimation: Kalman, H infinity, and nonlinearapproaches[M].USA: Wiley-Interscience press,2006：343-353.
[127] http://www-personal.acfr.usyd.edu.au/nebot/victoria_park.htm.
[2]蔡自兴，贺汉根，陈虹.未知环境中移动机器人导航控制研究的若干问题[J].控制与决策，2002，17(04)：385-390.
[3] Ohnishi N, Imiya A. Appearance-based navigation and homing forautonomous mobile robot[J]. Image and Vision Computing.2013,31(6–7):511-532.
[4] Colle E, Galerne S. Mobile robot localization by multiangulation using setinversion[J]. Robotics and Autonomous Systems,2013,61(1):39-48.
[5]朱大奇，颜明重.移动机器人路径规划技术综述[J].控制与决策.2010(7):961-967.
[6]刘睿.飞行器惯性/地磁/天文组合导航系统研究[D].哈尔滨:哈尔滨工业大学,2011:2-3.
[7]付强文，秦永元，李四海，等.车辆运动学约束辅助的惯性导航算法[J].中国惯性技术学报,2012,26(6):640-643.
[8]王佳凤，吴伟，胡岩，等.基于四元数算法的智能轮椅MEMS惯性导航系统研究[C]//第九届沈阳科学学术年会.第九届科学学术年会论文集.北京：人民教育出版社,2012:13-18.
[9] Lou L, Xu X. An Approach to Improving Attitude Estimation Using SensorFusion for Robot Navigation[J]. Procedia Engineering,2011,15:5601-5605.
[10] Nagla K S, Uddin M, Singh D. Improved occupancy grid mapping inspecular environment[J]. Robotics and Autonomous Systems,2012,60(10):1245-1252.
[11] Zhang Q, Ma J C, Xie W. A framed-quadtree based on reversed D*pathplanning approach for intelligent mobile robot[J]. Journal of Computers,2012,2(7):464-469.
[12] Vacavant A. Fast distance transformation on irregular two-dimensionalgrids[J]. Pattern Recognition.2010,43(10):3348-3358.
[13] Shi L, Kodagoda S. Towards generalization of semi-supervised placeclassification over generalized Voronoi graph[J]. Robotics and AutonomousSystems,2013,61(8):785-796.
[14] Likhachev D. Anytime search in dynamic graphs[J]. Artificial Intelligence,2008,172(5):1613–1643.
[15] Dakulovi M, Petrovi I. Two-way D*algorithm for path planning andreplanning [J]. Robotics and Autonomous Systems,2011,59(5):329-342.
[16] Guernane R, Achour N. Generating optimized paths for motion planning[J].Robotics and Autonomous Systems,2011,59(10):789-800.
[17] Bayili S, Polat F. Limited-Damage A*: A path search algorithm thatconsiders damage as a feasibility criterion[J]. Knowledge-Based Systems,2011,24(5):501–512.
[18]祖伟.基于粒子群优化算法的水下潜器实时路径规划技术研究[D].哈尔滨工程大学,2008.
[19] Zhang Q, Ma J C, Liu Q. Path planning based quadtree representation formobile robot using hybrid-simulated annealing and ant colony optimizationalgorithm[C]//Proceedings of the World Congress on Intelligent Controland Automation (WCICA). Beijing: IEEE Press,2012:2537-2542.
[20] Zhang J H, Gong D W, Zhang Y. A niching PSO-based multi-robotcooperation method for localizing odor sources[J]. Neurocompting.2014(123):308-317.
[21]梁毓明，徐立鸿.基于改进模拟退火混合算法的移动机器人全局路径规划[J].控制与决策,2010,25(2):237-240.
[22] Faigl J, Kulich M, Vonásek V, et al. An application of the self-organizingmap in the non-Euclidean Traveling Salesman Problem[J]. Neurocomputing.2011,74(5):671-679.
[23] Fu Y G, Ding M Y, Zhou C P. Route Planning for Unmanned Aerial Vehicle(UAV) on the Sea Using Hybrid Differential Evolution andQuantum-Behaved Particle Swarm Optimization[J]. Systems, Man, andCybernetics: Systems, IEEE Transactions on.2013,43(6):1451-1465.
[24]张航，刘梓溪.基于量子行为粒子群算法的微型飞行器三维路径规划[J].中南大学学报(自然科学版),2013(S2):58-62.
[25]王雪松，高阳，程玉虎等.知识引导遗传算法实现机器人路径规划[J].控制与决策,2009(07):1043-1049.
[26]赵娟平，高宪文，刘金刚，等.移动机器人路径规划的参数模糊自适应窗口蚁群优化算法[J].控制与决策,2011,26(7):1096-1100.
[27]朱庆保.复杂环境下的机器人路径规划蚂蚁算法[J].自动化学报,2006,32(4):586-593.
[28]金飞虎，高会军，钟啸剑.自适应蚁群算法在空间机器人路径规划中的应用[J].哈尔滨工业大学学报,2010,42(7):1014-1018.
[29]赵娟平，高宪文，符秀辉.移动机器人路径规划的改进蚁群优化算法[J].控制理论与应用,2011,28(4):457-461.
[30] Yang J, Zhuang Y. An improved ant colony optimization algorithm forsolving a complex combinatorial optimization problem[J]. Applied SoftComputing,2010,10(2):653-660.
[31]张培艳，吕恬生，宋立博.基于案例学习的排球机器人运动规划及其支持向量回归实现[J].上海交通大学学报.2006(3):461-465.
[32] Marefat M, Britanik J. Cased-based process planning using anobject-oriented model representation[J]. Robotics and Computer-IntegratedManufacturing,1997,13(3):3-25.
[33]张小川,纪钢.基于事例的足球机器人学习[J].哈尔滨工业大学学报,2004,2(7):905-907.
[34]翁敏，杜清运，瞿嵘，等.基于典型事例推理的路径规划方法研究[J].武汉大学学报(信息科学版).2008(12):1263-1266.
[35] Mucientes M, Alcalá-Fdez J, Alcalá R, et al. A case study for learningbehaviors in mobile robotics by evolutionary fuzzy systems[J]. ExpertSystems with Applications，2010,37(2):1471-1493.
[36]仲训昱，彭侠夫，缪孟良.基于环境建模与自适应窗口的机器人路径规划[J].华中科技大学学报(自然科学版).2010(06):107-111.
[37]任敏，霍霄华.基于异步双精度滚动窗口的无人机实时航迹规划方法[J].中国科学:信息科学.2010(04):561-568.
[38]刘春明，李兆斌，黄振华，等.基于LSPI和滚动窗口的移动机器人反应式导航方法[J].中南大学学报(自然科学版).2013(03):970-977.
[39] Chou C, Lian F, Wang C. Characterizing indoor environment for robotnavigation using velocity space approach with region analysis andlook-ahead verification[J]. Instrumentation and Measurement, IEEETransactions on.2011,60(2):442-451.
[40] Berti H, Sappa A D. Autonomous robot navigation with a global andasymptotic convergence [C]//IEEE International Conference on Roboticsand Automation. USA: IEEE Press,2007:2712-2717.
[41]邱雪娜，刘士荣，宋加涛，等.不确定动态环境下移动机器人的完全遍历路径规划[J].机器人.2006(06):586-592.
[42] Mcfetridge L, Ibrahim M Y. A new methodology of mobile robot navigation:The agoraphilic algorithm[J]. Robotics and Computer-IntegratedManufacturing,2009,25(3):545-551.
[43]齐勇,魏志强等.增强蚁群算法的机器人最优路径规划[J].哈尔滨工业大学学报,2009,41(3):130-133.
[44] Zhang Q S, Chen D D, Chen T. An Obstacle Avoidance Method of SoccerRobot Based on Evolutionary Artificial Potential Field[J]. Energy ProcediaPart C，2012,16:1792-1798.
[45]张建英，刘暾.基于人工势场法的移动机器人最优路径规划[J].航空学报,2007,28(8):183-188.
[46]王芳，万磊，徐玉如，等.基于改进人工势场的水下机器人路径规划[J].华中科技大学学报(自然科学版),2011,39(S2):184-185.
[47]朱毅，张涛，宋靖雁.非完整移动机器人的人工势场法路径规划[J].控制理论与应用,2010,27(2):152-158.
[48]杜广龙，张平.基于人工势场的机器人遥操作安全预警域动态生成方法[J].机器人,2012,34(1):44-49.
[49]李擎，王丽君，陈博，等.一种基于遗传算法参数优化的改进人工势场法[J].北京科技大学学报,2012,34(2):202-206.
[50]杨毅，刘亚辰，刘明阳，等.一种基于凸壳的智能服务机器人路径规划算法[J].北京理工大学学报.2011,31(1):54-58.
[51]丁华胜，王华忠.基于PSO的人工势场法在移动机器人路径规划中的应用[J].华东理工大学学报(自然科学版),2010,36(5):727-731.
[52] Parhi D R, Mohanta J C. Navigational control of several mobile roboticagents using Petri-potential-fuzzy hybrid controller[J]. Applied SoftComputing,2011,11(4):3546-3557.
[53] Luh G, Liu W. An immunological approach to mobile robot reactivenavigation[J]. Applied Soft Computing,2008,8(1):30-45.
[54] Daoyi D, Chunlin C, Jian C, et al. Robust Quantum-Inspired ReinforcementLearning for Robot Navigation [J]. IEEE/ASME Transactions onMechatronics,2012,17(1):86-97.
[55] Ozcelik S, Sukumaran S. Implementation of An Artificial Immune Systemon a Mobile Robot[J]. Procedia Computer Science,2011,6:317-322.
[56] Das Sharma K, Chatterjee A, Rakshit A. A PSO-Lyapunov Hybrid StableAdaptive Fuzzy Tracking Control Approach for Vision-Based RobotNavigation[J]. Instrumentation and Measurement, IEEE Transactions on.2012,61(7):1908-1914.
[57]付宜利，靳保，王树国，等.未知环境下基于行为的机器人模糊路径规划方法[J].机械工程学报.2006,42(5):120-125.
[58] Huq R, Mann G K I, Gosine R G. Mobile robot navigation using motorschema and fuzzy context dependent behavior modulation[J]. Applied SoftComputing.2008,8(1):422-436.
[59] Toibero J M, Roberti F, Carelli R, et al. Switching control approach forstable navigation of mobile robots in unknown environments[J]. Roboticsand Computer-Integrated Manufacturing.2011,27(3):558-568.
[60]李寿涛.基于行为的智能体避障控制以及动态协作方法研究[D].长春：吉林大学学位论文,2007:58-81.
[61] Fernandez-Leon J A, Acosta G G, Mayosky M A. Behavioral controlthrough evolutionary neurocontrollers for autonomous mobile robotnavigation[J]. Robotics and Autonomous Systems,2009,57(4):411-419.
[62] Shi C, Wang Y, Yang J. A local obstacle avoidance method for mobile robotsin partially known environment[J]. Robotics and Autonomous Systems,2010,58(5):425-434.
[63] Chia F J, Yu C C. Evolutionary-Group-Based Particle-Swarm-OptimizedFuzzy Controller With Application to Mobile-Robot Navigation inUnknown Environments[J]. IEEE Transactions on Fuzzy Systems,2011,19(2):379-392.
[64] Whitbrook A M, Aickelin U, Garibaldi J M. Idiotypic Immune Networks inMobile-Robot Control[J]. IEEE Transactions on Systems, Man, andCybernetics, Part B: Cybernetics,2007,37(6):1581-1598.
[65] Iocchi L, Nardi D. Hough Localization for mobile robots in polygonalenvironments[J]. Robotics and Autonomous Systems.2002,40(1):43-58.
[66] Falomir Z, Museros L, Castelló V, et al. Qualitative distances andqualitative image descriptions for representing indoor scenes in robotics[J].Pattern Recognition Letters.2013,34(7):731-743.
[67] Huang C, Chan C. ZigBee-based indoor location system by k-nearestneighbor algorithm with weighted RSSI[J]. Procedia Computer Science.2011,5:58-65.
[68] Rashid M M, Saidahbtmohdzain N, Zain F M. Development of OmniDirectional Mobile Robot Navigation System using RFID for MultipleObject[J]. AASRI Procedia.2012,3:474-480.
[69] Lee H, Jung J, Choi K, et al. Fuzzy-logic-assisted interacting multiplemodel (FLAIMM) for mobile robot localization[J]. Robotics andAutonomous Systems,2012,60(12):1592-1606.
[70] Herrero-Pérez D, Martínez-Barberá H, Leblanc K, et al. Fuzzy uncertaintymodeling for grid based localization of mobile robots [J]. InternationalJournal of Approximate Reasoning,2010,51(8):912-932.
[71] Moreno L, Garrido S, Mu oz M L. Evolutionary filter for robust mobilerobot global localization[J]. Robotics and Autonomous Systems,2006,54(7):590-600.
[72] Loevsky I, Shimshoni I. Reliable and efficient landmark-based localizationfor mobile robots[J]. Robotics and Autonomous Systems,2010,58(5):520-528.
[73] Aubry C, Desmare R, Jaulin L. Loop detection of mobile robots usinginterval analysis[J]. Automatica,2013,49:463-470.
[74] Kaess M, Dellaert F. Covariance recovery from a square root informationmatrix for data association[J]. Robotics and Autonomous Systems,2009,57(12):1198-1210.
[75] Booij O, Zivkovic Z, Kr se B. Efficient data association for view basedSLAM using connected dominating sets[J]. Robotics and AutonomousSystems,2009,57(12):1225-1234.
[76] Williams B, Cummins M, Neira J, et al. A comparison of loop closingtechniques in monocular SLAM[J]. Robotics and Autonomous Systems,2009,57(12):1188-1197.
[77] Jauregi E, Irigoien I, Sierra B, et al. Loop-closing: A typicality approach[J].Robotics and Autonomous Systems,2011,59(3–4):218-227.
[78] Li H P, Xu D M, Zhang F B, et al. Consistency analysis of EKF-basedSLAM by measurement noise and observation times[J]. Acta AutomaticaSinica,2009,35(9):1177-1184.
[79] Castellanos J A, Martinez-Cantin R, Tardós J D, et al. Robocentric mapjoining: Improving the consistency of EKF-SLAM[J]. Robotics andAutonomous Systems,2007,55(1):21-29.
[80] Movafaghpour M A, Masehian E. Poly line map extraction in sensor-basedmobile robot navigation using a consecutive clustering algorithm[J].Robotics and Autonomous Systems,2012,60(8):1078-1092.
[81] Lee J, Ko H. Gradient-based local affine invariant feature extraction formobile robot localization in indoor environments[J]. Pattern RecognitionLetters,2008,29(14):1934-1940.
[82] Bakar M N A, Saad A R M. A Monocular Vision-based Specific PersonDetection System for Mobile Robot Applications[J]. Procedia Engineering,2012,41:22-31.
[83] Lee D, Kim G, Kim D, et al. Vision-based object detection and tracking forautonomous navigation of underwater robots[J]. Ocean Engineering,2012,48:59-68.
[84] Jose G, Eduardo N. Optimization of Simultaneous Location and PamBuilding Algorithm for Real Time Implementation[J]. IEEE Transactions onRobot and Automation,2001,8(4):242-257.
[85] Paz L M, Tardos J D, Jose N. Divide and Conquer: EKF SLAM in O(n)[J].IEEE Transactions on Robotics,2008,5(24):1107-1120.
[86]张海强，窦丽华，方浩，等.基于压缩型EKF的SLAM改进算法[J].系统仿真学报,2009,31(10):5668-5671.
[87]弋英民，刘丁.有色过程噪声下的轮式机器人同步定位与地图构建[J].电子学报,2010,38(6):1339-1343.
[88]钱臻，齐英杰.迭代中心差分粒子滤波的SLAM算法[J].哈尔滨工程大学学报,2012,33(3):355-360.
[89]王宏健，王晶，边信黔，等.基于组合EKF的自主水下航行器SLAM[J].机器人,2012,34(1):56-64.
[90] Petsios M N, Alivizatos E G, Uzunoglu N K. Manoeuvring target trackingusing multiple bistatic range and range-rate measurements[J]. SignalProcessing,2007,87(4):665-686.
[91] Kim C, Sakthivel R, Chung W K. Unscented FastSLAM: a robust andefficient solution to the SLAM problem[J]. IEEE Transactions on Robotics,2008,24(4):808-820.
[92]杜航原，郝燕玲，高忠强，等.基于鲁棒非线性卡尔曼滤波的自适应SLAM算法[J].宇航学报,2012,33(5):620-627.
[93] Song Q, Han J. An Adaptive UKF Algorithm for the State and ParameterEstimations of a Mobile Robot[J]. Acta Automatica Sinica,2008,34(1):72-79.
[94]赵琳，闫鑫，郝勇.基于迭代平方根UKF的SLAM算法[J].弹箭与制导学报,2011,31(1):157-160.
[95] Moreno L, Garrido S, Blanco D, et al. Differential evolution solution to theSLAM problem[J]. Robotics and Autonomous Systems,2009,57(4):441-450.
[96]田翔，张亮，陈耀武.基于中心差分卡尔曼滤波器的快速SLAM算法[J].哈尔滨工业大学学报,2010,42(9):1454-1461.
[97] Ryan A, Hedrick J K. Particle filter based information-theoretic activesensing[J]. Robotics and Autonomous Systems.2010,58(5):574-584.
[98] Montemerlo M. Thrun S. Roller D. FastSLAM: A factored solution tosimultaneous localization and mapping[C]//Proceedings of the NationalConference on Artificial Intelligence (AAAI). USA: IEEE Press,2002:593–598.
[99]陈白帆，蔡自兴，袁成.基于粒子群优化的移动机器人SLAM方法[J].机器人,2009,31(6):513-517.
[100]周武，赵春霞，张浩峰.一种基于AMPF和FastSLAM的复合SLAM算法[J].模式识别与人工智能,2009,22(5):718-725.
[101]张亮.移动机器人同步定位与地图重建算法研究[D].杭州：浙江大学学位论文,2009:58-62.
[102]陈家乾，何衍，蒋静坪.基于权值平滑的改良FastSLAM算法[J].浙江大学学报(工学版),2010,44(8):1454-1459.
[103]朱磊，樊继壮，赵杰，等.未知环境下的移动机器人SLAM方法[J].华中科技大学学报(自然科学版),2011,39(7):9-13.
[104]刘洞波，刘国荣，王迎旭，等.基于区间分析无迹粒子滤波的移动机器人SLAM方法[J].农业机械学报,2012,43(10):155-160.
[105] Montemerlo M. Thrun S. Roller D. FastSLAM2.0: An improved particlefiltering algorithm for simultaneous localization and mapping that provablyconverges [C]//Proceedings of the International Conference on ArtificialIntelligence (IJCAI). USA: IEEE Press,2003:1151–1156.
[106] Tomas L P, Michael W. An algorithm for planning collision-free pathsamong polyhedral obstacles[J]. Communications of the ACM,1979,22(10):560-570.
[107] Liu Y H, Arimoto S. Computation of the tangent graph of polygonalobstacles by moving-line processing[J]. IEEE Transactions on Robotics andAutomation,1994,10(6):823-830.
[108] Huang H P, Chuang S Y. Dynamic visibility graph for path planning[C]//IEEE International Conference on Intelligent Robots and Systems. Japan:Institute of Electrical and Electronics Engineers Inc2004,3:2813-2818.
[109]蔡自兴，贺汉根，陈虹.未知环境中移动机器人导航控制理论与方法[M].北京：科学出版社，2009:8-12.
[110]李士勇.蚁群算法及其应用[M].哈尔滨：哈尔滨工业大学出版社，2004：181-185.
[111]陈凌，沈洁,秦玲,等.基于分布均匀度的自适应蚁群算法[J].软件学报,2013,14(8):1379-1387.
[112] Garcia M A P, Montiel O, Castillo O, et al. Path planning for autonomousmobile robot navigation with ant colony optimization and fuzzy costfunction evaluation[J]. Applied Soft Computing,2009,9(3):1102-1110.
[113] Huq R, Mann G K I, Gosine R G. Mobile robot navigation using motorschema and fuzzy context dependent behavior modulation[J]. Applied SoftComputing,2008,8(1):422-436.
[114] Zhu A, Yang S X. A fuzzy logic approach to reactive navigation ofbehavior-based mobile robots[C]//IEEE International Conference onRobotics and Automation. USA: IEEE Press,2004:5045–5050.
[115] Krishna K M, Kalra P K. Perception and remembrance of the environmentduring real-time navigation of a mobile robot[J]. Robot and AutonomousSystem,2001,37(4):25–51.
[116] Wang M, Liu J. Fuzzy logic-based real-time robot navigation in unknownenvironment with dead ends[J]. Robotics and Autonomous Systems,2008,56(7):625-643.
[117] Motlagh O, Hong T S, Ismail N. Development of a new minimum avoidancesystem for a behavior-based mobile robot[J]. Fuzzy Sets and Systems,2009,160(13):1929-1946.
[118] Navalertporn T, Afzulpurkar N V. Optimization of tile manufacturingprocess using particle swarm optimization[J]. Swarm and EvolutionaryComputation,2011,1(2):97-109.
[119] Gordon N J, Salmond D J, Smith A F M. Novel approach tononlinear/non-Gaussian Bayesian state estimation[J]. IEE Proceedings F(Radar and Signal Processing),1993,140(2):107-113.
[120]蒋蔚.粒子滤波改进算法研究与应用[D].哈尔滨工业大学,2010.
[121] Arnaud D, Nando D F, Neil G. Sequential Monte Carlo Methods inPractice[M]. New York: Springe-Verlag,2001:171-174.
[122]朱伟.时边离散动态系统的渐近稳定性和几何速度稳定性[J].应用科学学报,2004,22(2):252-254.
[123] Tim B, Juan N, Eduardo N. Consistency of the FastSLAM Algorithm[C]//Proceedings of the2006IEEE International Conference on Robotics andAutomation. Orlando: IEEE Press,2006:424-429.
[124] Hassibi B, Sayed A H, Kailath T. Linear estimation in Krein spaces-part I:applications[J]. IEEE Transactions on Automatic Control,1996,41(1):18-33.
[125] Hassibi B, Sayed A H, Kailath T. Linear estimation in Krein spaces-part II:applications[J]. IEEE Transactions on Automatic Control,1996,41(1):34-49.
[126] Simon D. Optimal state estimation: Kalman, H infinity, and nonlinearapproaches[M].USA: Wiley-Interscience press,2006：343-353.
[127] http://www-personal.acfr.usyd.edu.au/nebot/victoria_park.htm.
© 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 |