摘要
仿人机器人的机械连杆结构在空间分布上类似于人体躯干与四肢骨骼结构，具备拟人化的双足运动形态与双手处理任务的能力，是人-机器人社会的重要组成部分。仿人机器人运动规划是任务执行与行为决策的基础，其规划方法主要分为基于运动解析方程求解方式与基于人体运动相似性方式。尽管基于运动解析方程的轨迹求解方式具有易于表述与分析的数学特征，并体现出运动轨迹平滑性等优点，但在轨迹自然过渡、复杂动作设计与能量消耗优化上无法与基于人体运动相似性的方法相比。
本文在国家863计划重点项目的子项目“竞技与娱乐多机器人系统”课题资助下，研究了基于人体运动相似性的仿人机器人运动规划关键技术，包括：机器人在相似性双足步行中实现平衡与轨迹跟踪控制，在失稳倒地时最小化地面冲击并在倒地后恢复到相似性运动姿势，自主调整固定的人体关节轨迹以适应目标环境改变。主要内容如下：
首先，完善了仿人机器人相似性运动系统，从图像捕捉与处理、相似性特征处理、运动约束与优化等方面阐述了相似性运动规划过程，分析了正向运动学与逆向运动学解算以及运动模型简化与重定向设计方法，定义了基于时空控制的相似度，提出了关键姿势判定与提取、运动协调与同步控制以及关键姿势树状结构生成等方法，对运动稳定性判据方法进行了对比，分析了相似性运动中碰撞形式及其原因，阐述了防碰撞约束、落地脚补偿以及关节角度控制等。
其次，以7连杆双足步行机器人为例，研究了相似性运动中的平衡与轨迹跟踪控制。分析了双足步行运动学与动力学特性，对相似性运动的关键姿势与基本子相施加运动学、子相衔接与物理条件等约束,建立了基于关节力矩的拉格朗日动力学模型，由机器人雅可比矩阵构建了双足地面接触控制方程，定义仿人机器人动力学模型为连续时间线性时不变系统，引入带观测器的状态反馈控制器以跟踪运动轨迹，从三维倒立摆角度分析步行平衡控制，并由无限时间线性二次型调节器建立运动参数误差最小化目标函数，实现轨迹跟踪控制。
再次，研究了仿人机器人相似性失稳倒地时的动作保护与恢复。分析了倒地过程的动力学特性并施加了运动学与物理条件等约束，引入参数化控制方法优化触地点位置，并通过强化技术实现时间变换，将指标泛函求取原时间点的导数转换在新的时间点上求取参数的导数，解决了机器人倒地时触地点位置的寻优问题，使其所受的地面冲击最小、触地位置与倒地稳定性最优；采用可变种群规模的遗传算法对机器人触地后的相似性运动姿势恢复进行了优化。
最后，以仿人机器人相似性上台阶运动为例，研究了机器人自主调整固定人体关节轨迹以适应可变目标环境。对机器人相似性上台阶运动过程施加了运动学与物理条件等约束，提出了粒子群分层强化矢量位置择优算法，通过交叉择优操作获得精英粒子，在粒子进化调整策略中选择惯性权重调整策略，并基于嵌入式单目视觉系统采集台阶宽度与高度等参数，用于仿人机器人的膝关节、踝关节轨迹调整上，实现了具有目标环境可变的相似性运动。
The spatial mechanical structure of humanoid robot is similar to the skeletalstructure of body and limb of human being, which makes it walk with biped legsand deal with task by hands just like people. For this reason, the humanoid robothas been the important part of human-robot society. The motion planning ofhumanoid robot is the basis of both task executing and behavior deciding. Thereare two planning methods–based on the locomotion analytic equation and basedon the similarity locomotion of human actor. Although there are many advantagesin the method based on locomotion analytic equation such as its easily describ ingand analyzing characteristics of mathematics as well as smooth moving track, thenatural conversion of moving track, complicated motion design and energyconsumption optimization in this method are not as good as that one based on thesimilarity locomotion of human actor.
The research is funded by the national863key project "Sports andentertainment multi-robot systems" and it mainly focuses on the key technologiesof motion planning for humanoid robot based on the similarity locomotion ofhuman actor, including keeping balance and following tracks in the biped walkingprocess, minimizing the collision from floor when falling down and recovering tothe similar pose of human actor after it, self adjusting the fixed tracks of humanactor on robot to fit the changeable environment. The main contents are as follow:
Firstly, the basic model of similarity locomotion is built up, which isconstructed by three models---image capture and dealing, feature extraction,kinematics constraint and optimization. The forward kinematics and inversekinematics are analyzed as well as the simplfied locomotion model and motionretargeting. The similarity degree based on spatio-temporal control is defined. Themethods of key posture judging and extracting, movement coordinating andsynchronization, and the hierarchy tree structure of key posture are proposed. Thestability judging cristerias are compared. The collisions and causes in similaritylocomotion are analyzied and the corresponding methods such as the collision-freecontraints, landing leg compensation and joint angle control are also described aswell.
Secondly, taking the7-link biped walking robot model as an example, thecontrol of keeping balance and following track are studied. The features ofkinametics and dynamics of biped walking are analyzied and the constraints ofkinematics, sub-phase connection and physical condition are set on the key poses and basic phases as well. The Lagrange dynamics equation based on joint torqueare established as well as the biped contacting-land equation through robotJacobian matrix. The dynamics model of humanoid robot is defined as the lineartime invariant system with continous time. The state feedback controller withobserver is used to follow the tracks of human actor. The balance control of bipedwalking is analyzied through the three dimensional inverted pendulum and thetarget function with minimum error of movement parameters is built through thelinear quadratic regulator with infinite time when following tracks.
Thirdly, the protection and recovery of pose for humanoid robot are studedwhen the robot falls down. The dynamatics features of falling down for humanoidrobot are analyzed and the contraints of kinematics and physical conditions are setas well. When controlling the contacting position on ground, the parameterizedcontrol method is used to approach the optimal solution and the ehhancingtechnique is use to converse the differential quotient solving with original timepoint through index functional into the parameter acquirement through differentialquotient solving with new time point, which solves the optimizing problem offalling motion for humanoid robot and obtains the minimal floor collision, optimaltouching position and falling stability. After collision with floor, the geneticalgorithm with variable population is used to optimize the pose recovery ofsimilarity locomotion for humanoid robot.
Finally, taking the stepping upstairs of humanoid robot as an example, theautonomously fixing tracks obtained from human actor on humanoid robot to fitthe variable target environment is studied. The constraints of kinematics andphysical conditions are set in the process of stepping upstairs for humanoid robot.The particle swarm optimization with hierarchical reinforcement learning isproposed, in which the essence particles are obtained through the crossingselection and the strategies of adjusting inertial weight are selected in the evolvingstrategies of particles. The parameters of stair width and height are obtainedthrough the embedded monocular vision. The tracks of knee and ankle joints onhumanoid robot are adjusted through the above method to fit the changeable targetenvironment.
引文
[1]谢涛,徐建峰,张永学,强文义.仿人机器人的研究历史、现状及展望[J].机器人,2002.7,24(4):367-373.
[2]梶田秀司(日),管贻生(译).仿人机器人[M].北京:清华大学出版社,2007:50-56.
[3] Gates B. A Robot in Every Home[J]. Science American,2007,37(2):58-65.
[4] Marc S. Lavine, David Voss, Robert Coontz. A Robotic Future[J]. Science,2007.11,318:1083.
[5] Hashimoto S, Narita S, Kasahara H, et al. Humanoid Robots in WasedaUniversity-Hadaly-2and WABIAN[J]. Autonomous Robots.2004,12(1):25-38.
[6] Hirai K, Hirose M, Haikawa Y, Takenaka T. The Development of HondaHumanoid Robot[C]. IEEE International Conference on Robotics andAutomations, Leuven,1998:1321-1326.
[7]包志军,马培荪,姜山等.从两足机器人到类人型机器人的研究历史及其问题[J].机器人.1999,21(7):312-318.
[8] Yashika S, Ryujin W. The Intelligent ASIMO: System Overview andIntegration[C]. IEEE International Conference on Intelligent Robots andSystems,2002:2478-2483.
[9] Masato H, Kenichi O. Honda Humanoid Robots Development[J]. PhilosophicalTransactions of the Royal Society,2007,365(1850):11-19.
[10] Kaneko K, Kanehiro F, Kajita S, et al. Humanoid Robot HRP-2[C]. IEEEInterrnational Conference on Robotics and Automation,2004:1083-1090.
[11] Kanehiro F, Kaneko K, Fujiwara K, et al. The First Humanoid Robot That HasThe Same Size As A Human And That Can Lie Down And Get Up[C]. IEEEInternational Conference on Robotics and Automation.2003:1633-1639.
[12] Satoshi K, Masaaki M, Yoshihiro E, et al. Measurement And Comparison OfHumanoid H7Walking With Human Being[J]. Robotics and AutonomousSystems,2003,48(4),177-187.
[13] Nishiwaki K, Kuffner J, Kagami S, et al. The Experimental Humanoid RobotH7: A Research Platform For Autonomous Behaviour[J]. PhilosophicalTransactions of the Royal Society,2007,365(1850):79-107.
[14] Lengagne S, Ramdani N. Safe Motion Planning Computation For DatabasingBalanced Movement Of Humanoid Robots[C]. IEEE International Conferenceon Robotics and Automation.2009:1669-74.
[15]李允明.国外仿人机器人发展概况[J].机器人,2005,27(6):561-568.
[16] Park I W, Kim J Y, Oh J H. Online Walking Pattern Generation And ItsApplication To A Biped Humanoid Robot KHR-3(HUBO)[J]. AdvancedRobotics,2008,22:159-190.
[17] Ill-Woo P, Jung-Yup K, Jungho L, et al. Mechanical Design Of HumanoidRobot Platform KHR-3[C]. IEEE-RAS International Conference on HumanoidRobots.2005:321-326.
[18] Lohmeier S, Loffler K, Gienger M, et al. Computer System And Control OfBiped "Johnnie"[C]. IEEE International Conference on Robotics andAutomation,2004:4222-4227.
[19] Pfeiffer F, Loffler K, Gienger M. The Concept Of Jogging JOHNNIE[C].IEEE International Conference on Robotics and Automation,2002:3129-3135.
[20] Buschmann T, Lohmeier S, Ulbrich H, et al. Dynamics Simulation For ABiped Robot: Modeling And Experimental Verification[C]. IEEE InternationalConference on Robotics and Automation, Orlando, Florida.2006:2673-2678.
[21] Espiau B S. The Anthropomorphic Biped Robot BIP2000[C]. IEEEInternational Conference on Robotics and Automation,2000:3996-4001.
[22] Zheng Y F. Modeling, Control And Simulation Of Three-Dimensional RoboticSystem With Applications To Biped Locomotion[D]. Ph.D. Dissertation of TheOhio State University,1984:168-189.
[23] Zheng Y F, Shen J. Gait Synthesis For The SD-2Biped Robot To ClimbSloping Surface[J]. IEEE Transactions on Robotics and Automation,1990,6(1):86-96.
[24] Pratt G A. Legged Robot At MIT-What’s New Since Raibert[C]. InternationalConference on Climbing and Walking Robots,1999:29-33.
[25] Hu J J, Jerry P, Gill P. Stable Adaptive Control Of A Bipedal Walking RobotWith CMAC Neural Networks[C]. IEEE International Conference on Roboticsand Automation,1999,2:1050-1056.
[26] Steve C, Andy R, Russ T, et al. Efficient Bipedal Robots Based On PassiveDynamic Walkers[J]. Science,2005,307:1082-1085.
[27]马培荪,曹曦,赵群飞.两足机器人步态综合研究进展[J].西南交通大学学报,2006,41(4):407-414.
[28] McGeer T. Passive Dynamic Walking[J]. The International Journal ofRobotics Research,1990,9(2):62-82.
[29]刘志远.两足机器人的动态行走研究[D].哈尔滨:哈尔滨工业大学,1991:23-35.
[30]纪军红. HIT-III双足步行机器人步态规划研究[D].哈尔滨:哈尔滨工业大学,2000:53-65.
[31]马宏绪,张彭,张良起.两足步行机器人动态步行的步态控制与实时时位控制方法[J].机器人,1998,20(1):1-8.
[32]绳涛,马宏绪,王越.仿人机器人未知地面行走控制方法研究[J].华中科技大学学报,2004,32:161-163.
[33]刘莉,汪劲松,陈恳等. THBIP-I拟人机器人研究进展[J].机器人,2002,24(3):262-267.
[34] Xia Z Y, Liu L, Xiong J, et al. Design Aspects And Development OfHumanoid Robot THBIP-2[J]. Robotica.2008,26(1):109-116.
[35]伊强,陈恳,刘莉,付成龙.小型仿人机器人THBIP-II的研制与开发[J].机器人,2009,31(6):586-594.
[36]肖涛,黄强,杨洁,等.给定手部作业轨迹的仿人机器人推操作研究[J].机器人,2008,30(5):385-392.
[37] Huang Q, Peng Z, Zhang W, et al. Design Of Humanoid ComplicatedDynamic Motion Based On Human Motion Capture[C]. IEEE/RSJ InternationalConference on Intelligent Robots and Systems,2005:3536-3541.
[38] Huang Q, Nakamura Y. Sensory Reflex Control For Humanoid Walking[J].IEEE Transactions on Robotics,2005,21(5):977-984.
[39]姜山,程君实,陈佳品,包志军.基于遗传算法的两足步行机器人步态优化[J].上海交通大学学报,1999,33(10):1280-1283.
[40]包志军.类人型机器人运动特性研究[D].上海:上海交通大学,2000:23-34.
[41] David G, Vincent H, Pierre B. Mechatronic Design Of NAO Humanoid[C].IEEE International Conference on Robotics and Automation, Kobe, Japan,2009:486-495.
[42] Stefan C, S ren K, Oliver U. Observer-Based Dynamic Walking Control ForBiped Robots[J]. Robotics and Autonomous Systems.2009,57:839-845.
[43] Hester T, Quinlan M, Stone P. Generalized Model Learning For ReinforcementLearning On A Humanoid Robot[C]. IEEE International Conference onRobotics and Automation, Anchorage, AK,2010:2369-2374.
[44] Yoshihiro K. A Small Biped Entertainment Robot[C]. IEEE InternationalConference on Humanoid Robots.2001:181-186.
[45] Gen E, Nakanishi J, Morimoto J, Cheng G. Experimental Studies Of A NeuralOscillator For Biped Locomotion With QRIO[C]. IEEE InternationalConference on Robotics and Automation,2005:596-602.
[46] Zhong Q B, Hong B R, Pan Q S. Complex Motion Planning For HumanoidRobot Based On Embedded Vision System[J]. JOURNAL OF HARBININSTITUTE OF TECHNOLOGY,2010,17(Suppl.2),5-9.
[47]张彤.仿人机器人步行控制及路径规划方法研究[D].广州:华南理工大学,2010:22-23.
[48]康俊峰.基于嵌入式视觉的仿人机器人点球系统[D].哈尔滨:哈尔滨工业大学.2008:68-88.
[49] Dong H, Zhao M G, Zhang J, et al. Hardware Design And Gait Generation OfHumanoid Soccer Robot Stepper-3D[J]. Robotics and Autonomous Systems,2009,57:828-838.
[50] Ill-Woo Park; Jung-Yup Kim. Fourier Series-Based Walking PatternGeneration For A Biped Humanoid Robot[C]. Humanoid Robots (Humanoids),201010th IEEE-RAS International Conference on:2010.12:461-467.
[51] Nobuya Yao, Takubo T., Ohara K., Mae Y., Arai T. Gait Planning For A BipedRobot By A Nonholonomic System With Difference Equation Constraints[C].Intelligent Robots and Systems (IROS),2010IEEE/RSJ InternationalConference on,2010.10:4471-4476.
[52]钟秋波,朴松昊,方宝富,洪炳镕.仿人机器人实时步态控制系统设计[J].华中科技大学学报(自然科学版),2011.9,9:53-56.
[53]伊强,陈恳,刘莉,付成龙.考虑综合步行约束的仿人机器人参数化3D步态规划方法[J].机器人,2009.7,31(4):342-350.
[54] Harada K, Hattori S, Hirukawa H, et al.Two-Stage Time-Parametrized GaitPlanning For Humanoid Robots[J]. Mechatronics, IEEE/ASME Transactions onMechatronics,2010(10),15(5):694-703.
[55] Miura Kanako, Morisawa Mitsuharu, Kanehiro Fumio, Kajita Shuuji, KanekoKenji, Yokoi. Human-Like Walking With Toe Supporting For Humanoids[C].Intelligent Robots and Systems (IROS),2011IEEE/RSJ InternationalConference on,2011.9:4428-4435.
[56] Yamada K., Sayama K., Yoshida T., Hun-ok Lim. Mechanisms Of BipedHumanoid Robot And Online Walking Pattern Generation[C]. Control,Automation and Systems (ICCAS),201111th International Conference on,2011.10:1117-1122.
[57]王险峰,洪炳镕,朴松昊,钟秋波.一种仿人机器人跑步状态分析模型[J].计算机研究与发展,2011.9,9:1740-1747.
[58] Chenglong Fu, Feng Tan, Ken Chen. A Simple Walking Strategy For BipedWalking Based On An Intermittent Sinusoidal Oscillator[J]. Robotica,2010,28:869-884.
[59] L. Hu, C. Zhou, Z. Sun. Estimating Biped Gait Using Spline-BasedProbability Distribution Function With Q-Learning[J]. IEEE Transactions onIndustrial Electronics.2008,55(3):1444-1452.
[60] Tlalolini D, Chevallereau C, Aoustin Y. Optimal Reference Walking WithRotation Of The Stance Feet In Single Support For A3D Biped[C]. Proceedingsof IEEE/RSJ International Conference on Robotics and Intelligent System,Piscataway, NJ, USA,2008:1091-1096.
[61]汤哲.人形机器人的步态研究[D].北京:清华大学,2006.
[62] M. Black, D. Fleet. Probabilistic Detection and Tracking of MotionBoundaries[J]. International Journal of Computer Vision,2000,38(3),231-245,2000.
[63] Andrea Fossati, Miodrag Dimitrijevic, Vincent Lepetit, Pascal Fua. FromCanonical Poses to3D Motion Capture Using a Single Camera[J]. IEEETRANSACTIONS ON PATTERN ANALYSIS AND MACHINEINTELLIGENCE,2010.7,32(7):1165-1181.
[64] E.-J. Ong, A.S. Micilotta, R. Bowden, and A. Hilton. Viewpoint InvariantExemplar-Based3D Human Tracking[J]. Computer Vision and ImageUnderstanding,2006,104(2):178-189.
[65] D. Ormoneit, H. Sidenbladh, M.J. Black, and T. Hastie. Learning and TrackingCyclic Human Motion[C]. Proc. Neural Information Processing Systems,2001:894-900.
[66] R. Urtasun, D. Fleet, P. Fua. Temporal Motion Models for Monocular andMultiview3D Human Body Tracking[J]. Computer Vision and ImageUnderstanding,2006,104(2):157-177.
[67] K. Murata, K. Nakadai, et al. A robot singer with music recognition based onreal-time beat tracking[C]. Proc. of ISMIR2008-Session2b-Music Recognitionand Visualization,2008,199-204.
[68] A. G. Bharatkumar, K. E. Daigle, M. G. Pandy, Q, Cai, J, K. Aggarwal. LowLimb Kinematics Of Human Walking With The Medial Axis Transformation. InProc.Of IEEE Computer SocietyWorkshop on Motion of No-Rigid andArticulated Objects.70-76, Austin Tx,1994:174-179.
[69]胡琴.基于标志点的三维人体步态捕获技术研究[D].湘潭,湘潭大学,2008.
[70] Ju S, Black M, Yaccob Y. Cardboard People: A Parameterized Model OfArticulated Image Motion[C]. In: Proc IEEE International Conference onAutomatic Face and gesture Recognition, Killington, Vermont USA,1996:38-44.
[71] Deutscher J, Blake A, Reid I. Articulated Body Motion Capture By AnnealedParticle Filtering [C]. Proceedings of IEEE Conference on Computer Vision andPattern Recognition, Hilton Head Island,2000:126-133.
[72] Haritaoglu I, Harwood D, Davis L S.W4:Real-Time Surveillance Of PeopleAnd Their Activities[J]. IEEE Transactions on Pattern Analysis and MachineIntelligence,2000,22(8):809-830.
[73] Agarwal A, Triggs B.3D Human Pose From Silhouettes By Relevance VectorRegression[C]. Proceedings of IEEE International Conference on ComputerVision and Pattern Recognition, Washington,D C,2004:882-888.
[74]罗忠祥,庄越挺,潘云鹤,等.基于视频的运动捕获[J].中国图像图形学报:A版,2002,7(8):752-758.
[75] Aristidou A., Lasenby J. Motion Capture With Constrained InverseKinematics For Real-Time Hand Tracking[C]. Communications, Control andSignal Processing (ISCCSP),20104th International Symposium on,2010.3:1-5.
[76] Hsin-Yu Liu, Wen-June Wang, Rong-Jyue Wang, Cheng-Wei Tung, Pei-JuiWang, I-Ping Chang. Image Recognition And Force Measurement ApplicationIn The Humanoid Robot Imitation[J]. Instrumentation and Measurement, IEEETransactions on,2012.1,61(1):149–161.
[77] Albrecht S., Ramirez-Amaro K., Ruiz-Ugalde F., Weikersdorfer D., LeiboldM., Ulbrich, M., Beetz, M. Imitating Human Reaching Motions UsingPhysically Inspired Optimization Principles[C]. Humanoid Robots (Humanoids),201111th IEEE-RAS International Conference on,2011.10:2164-2172.
[78] Kajita Shuuji, Nakano Tomoyasu, Goto Masataka, Matsusaka Yosuke,Nakaoka Shin'ichiro, Yokoi Kazuhito. Vocawatcher: Natural Singing MotionGenerator For A Humanoid Robot[C]. Intelligent Robots and Systems (IROS),2011IEEE/RSJ International Conference on,2011.9:2000-2007.
[79] Mistry M., Murai A., Yamane K., Hodgins J. Sit-To-Stand Task On AHumanoid Robot From Human Demonstration[C]. Humanoid Robots(Humanoids),201010th IEEE-RAS International Conference on,2010.12:218-223.
[80]刘晨光,刘家锋,黄剑华,唐降龙.基于多特征融合的分块采样粒子滤波算法在人体姿态跟踪中的应用[J].计算机研究与发展,2359-2368.
[81] Tony X H, Thomas S H. Articulated Body Tracking Using Dynamic BeliefPropagation[G]. LNCS3766: Computer Vision in Human-Computer Interaction.Berlin: Springer,2005:26-35.
[82] M. Glercher. Retargeting Motion To New Characters[C]. SIGGRAPH'98Conference Proceedings, July1998.33-42.
[83] Kwang-jin Choi, Hyeong-seok Ko. Online Motion Retargetting[J]. TheJournal of Visualization and Computer Animation,2000.11,5:223-235.
[84] Tak Seyoon, Hyeong-Seok Ko. Example Guided Kinematics[C]. In: theProceedings of the International Conference on Computer on Computer Graphics and Imaging(CGIM)2000, Las Vegas, Nevada, USA, November2000:19-23.
[85] Dariush, B, Gienger M, Arumbakkam A, Goerick. Online And MarkerlessMotion Retargeting With Kinematic Constraints[C]. Intelligent Robots andSystems,2008. IROS2008. IEEE/RSJ International Conference on,2008.9:191-198.
[86]张利格,黄强,杨洁,时有,等.仿人机器人复杂动态动作设计及相似性研究[J].自动化学报.2007.5,33(5):522-528.
[87]颜庆聪,陈益强,刘军发.面向广电节目的虚拟人手语合成显示平台研究[J].计算机研究与发展,2009.11,11:305-309.
[88] Fossati A, Dimitrijevic M, Lepetit V, Fua P. From Canonical Poses To3DMotion Capture Using A Single Camera[J]. Pattern Analysis and MachineIntelligence, IEEE Transactions on,2010.7,37(7):1165-1181.
[89]谷军霞,丁晓青,王生进.基于人体行为3D模型的2D行为识别[J].自动化学报,2010.1,1:46-53.
[90] Connaghan, Damien, O Conaire, Ciaran, Kelly, Philip, O'Connor, Noel E.Recognition Of Tennis Strokes Using Key Postures[C], Signals and SystemsConference (ISSC2010), IET Irish,2010.4:245-248.
[91] Jun-Wei Hsieh, Sin-Yu Chen, Chi-Hung Chuang, Miao-Fen Chueh,Shiaw-Shian Yu. Occluded Human Body Segmentation And Its Application ToBehavior Analysis[C]. Circuits and Systems (ISCAS), Proceedings of2010IEEE International Symposium on,2010.4:3433-3436.
[92] Jun-Wei Hsieh, Chi-Hung Chuang, Sin-Yu Chen, Chih-Chiang Chen,Kuo-Chin Fan. Segmentation Of Human Body Parts Using DeformableTriangulation[J]. Systems, Man and Cybernetics, Part A: Systems and Humans,IEEE Transactions on,2010.5,40(3):1083-4427.
[93] Ruchanurucks M, Nakaoka S, Kudoh S, Ikeuchi K. Generation Of HumanoidRobot Motions With Physical Constraints Using Hierarchical B-Spline[C]. In:Proceedings of2005IEEE/RSJ International Conference on Intelligent Robotsand Systems. IEEE,2005,674-679.
[94] Takano W, Yamane K, Nakamura Y. Capture Database Through Symbolization,Recognition And Generation Of Motion Patterns[C]. In: Proceedings of IEEEInternational Conference on Robotics and Automation. Roma, Italy: IEEE,2007:3092-3097.
[95] Hajimirsadeghi H. Conceptual Imitation Learning Based On FunctionalEffects Of Action[C]. EUROCON-International Conference on Computer as aTool (EUROCON),2011IEEE,2011.4:1-6.
[96] Ramos O.E., Saab L., Hak S., Mansard N. Dynamic Motion Capture AndEdition Using A Stack Of Tasks[C]. Humanoid Robots (Humanoids),201111thIEEE-RAS International Conference on,2011.10:224-230.
[97] Carlos A. Acosta Calderon, Rajesh E. Mohan, Lingyun Hu, et al. GeneratingHuman-Like Soccer Primitives From Human Data[J]. Robotics andAutonomous Systems,2009,57:860-869.
[98] Kim S, Kim C H, Park J H. Human-Like Arm Motion Generation ForHumanoid Robots Using Motion Capture Database[C]. In: Proceedings ofIEEE/RSJ International Conference on Intelligent Robots and Systems. Beijing,China: IEEE,2006:3486-3491.
[99] Boutin L., Eon A., Zeghloul S., Lacouture P. An Auto-Adaptable Algorithm ToGenerate Human-Like Locomotion For Different Humanoid Robots Based OnMotion Capture Data[C]. Intelligent Robots and Systems (IROS),2010IEEE/RSJ International Conference on,2010.10:1256-1261.
[100] Boutin L., Eon A., Lacouture P, Zeghloul S. HRP-2Reproducing A HumanSlalom-The Whole Process[C]. Humanoid Robots,2009. Humanoids2009.9thIEEE-RAS International Conference on,2009.12:349-354.
[101] Jung-Yup Kim, Young-Seog Kim. Walking Pattern Mapping Algorithm UsingFourier Fitting And Geometric Approach For Biped Humanoid Robots[C].9thIEEE-RAS International Conference on Humanoid Robots,2009:243-249.
[102] Buzurovic I. M., Debeljkovic D.L. A Geometric Approach To TheInvestsggation Of The Dynamics Of Constrained Robotic Systems[C].Intelligent Systems and Informatics (SISY),20108th International Symposiumon,2010.9:133-138.
[103] Huan Tan, Kawamura K. A Computational Framework For IntegratingRobotic Exploration And Human Demonstration In Imitation Learning[C].Systems, Man, and Cybernetics (SMC),2011IEEE International Conference on,2011.10:2501-2506.
[104] Chalodhorn R., Rao R.P.N. Using Eigenposes For Lossless Periodic HumanMotion Imitation[C]. Intelligent Robots and Systems,2009. IROS2009.IEEE/RSJ International Conference on,2009.10:2502-2509.
[105] Calderon C.A.A., Mohan R.E., Changjiu Zhou. Teaching New Tricks To ARobot Learning To Solve A Task By Imitation[C]. Robotics Automation andMechatronics (RAM),2010IEEE Conference on,2010.4:256-262.
[106]张利格,毕树生,高金磊.仿人机器人复杂动作设计中人体运动数据提取及分析方法[J].自动化学报,2010.1,36(1):107-112.
[107]赵晓军,黄强,彭朝琴,张利格,等.基于人体运动的仿人型机器人动作的运动学匹配[J].机器人,2005.7,27(4):358-361.
[108] Qiang Huang, Zhangguo Yua, Weimin Zhang, et al. Design And SimilarityEvaluation On Humanoid Motion Based On Human Motion Capture[J].Robotica,2010,28:737-745.
[109] Yamane K., Hodgins J. Simultaneous Tracking And Balancing Of HumanoidRobots For Imitating Human Motion Capture Data[C]. Intelligent Robots andSystems,2009. IROS2009. IEEE/RSJ International Conference on,2009.10:2510-2517.
[110]庄越挺,刘小明,潘云鹤,杨骏.运动图像序列的人体三维运动骨架重建[J].计算机辅助设计与图形学学报,2000,12(4):245-251.
[111]季白桦,袁修干,温文彪.三维人体运动数据提取的人机交互方法及实验[J].北京航空航天大学学报,2000,26(1):91-94.
[112] Nakazawa A, Nakaoka S, Ikeuchi K. Matching And Blending HumanMotions Using Temporal Scaleable Dynamic Programming[C]. In: Proceedingsof IEEE/RSJ International Conference on Intelligent Robots and Systems.Osaka, Japan: IEEE,2004.287-294.
[113] Nakazawa A, Nakaoka S, Shiratori T, Ikeuchi K. Analysis And Synthesis OfHuman Dance Motions[C]. In: Proceedings of IEEE International Conferenceon Multisensor Fusion and Integration for Intelligent Systems. WashingtonD.C.,USA: IEEE,2003.83-88.
[114] K. Grochow, S. L. Martin, A. Hertzmann, Z. Popovic. Stylebased inversekinematics[J]. ACM Trans. Graph.,2004,23(3):522-531.
[115] M. Gleicher. Retargetting Motion To New Characters[C]. Proceedings of the25th annual conference on Computer graphics and interactive techniques(SIGGRAPH98), Orlando, FL, USA, July1998,33-42.
[116] K. Grochow, S. Martin, A. Hertzmann, and Z. Popovi′c. Style-Based InverseKinematics[J]. ACM Transactions on Graphics (TOG),2004.8,23(3):522-531
[117] GONG Guanghong, LI Ning. Measure Of Human Body Sports And DataCorrect[J]. Measure Technology,2003,22(4):21-23.
[118]钟秋波.类人机器人运动规划关键技术研究[D].哈尔滨,哈尔滨工业大学,2011.
[119] Goswami A. Foot Rotation Indicator (FRI) Point: A New Gait Planning ToolTo Evaluate Postural Stability Of Biped Robots[C]. IEEE InternationalConference on Robotics and Automation,1999:47-52.
[120] Goswami A. Postural Stability Of Biped Robots And The Foot RotationIndicator (FRI) Point[J]. International Journal of Robotics Research,1999,18(6):523-533.
[121] Kim J H, Oh J H. Walking Control Of The Humanoid Platform KHR-1BasedOn Torque Feedback Control[C]. Proceedings of the2004IEEE InternationalConference on Robotics&Automation,2004:623-628.
[122] Kim Y D, Lee B J, Yoo J K, et al. Compensation For The Landing ImpactForce Of A Humanoid Robot By Time Domain Passivity Approach[C].Proceedings of the2006IEEE International Conference on Robotics andAutomation,2006:1225-1230.
[123] Dragomir N, Nenchev, Akinori N. Experimental Validation Of Ankle AndHip Strategies For Balance Recovery With A Biped Subjected To An Impact[C].Proceedings of the2007IEEE/RSJ International Conference on IntelligentRobots and Systems,2007:4035-4040.
[124]赵建东,王自上,付成龙,陈恳.仿人机器人摆动脚落地碰撞补偿控制研究[J].2009.2,33(1):45-49.
[125] A. Shon, K. Grochow, R. Rao. Robotic Imitation From Human MotionCapture Using Gaussian Processes[C]. Proceedings of International Conferenceon Humanoid Robots,2005:129–134.
[126] T. Inamura, I. Toshima, H. Tanie, and Y. Nakamura. Embodied SymbolEmergence Based On Mimesis Theory[J]. International Journal of RoboticsResearch,2004,24:363-378.
[127] O. Jenkins, M. Mataric. Deriving Action And Behavior Primitives FromHuman Motion Data[C]. Proceedings of IEEE/RSJ International Conferenceon Intelligent Robots and Systems,2002:2551-2556.
[128] S. Kajita, F. Kanehiro, K. Kaneko, K. Fujiwara, K. Harada, K. Yokoi, H.Hirukawa. Biped Walking Pattern Generation By Using Preview Control OfZero-Moment Point[C]. Proceedings of IEEE International Conference onRobotics and Automation,2003:1620-1626.
[129] K. Loffler, M. Gienger, F. Pfeiffer. Sensor And Control Design Of ADynamically Stable Biped Robot[C]. Proceedings of IEEE InternationalConference on Robotics and Automation,2003:484-490.
[130] T. Sugihara. Simulated Regulator To Synthesize ZMP Manipulation And FootLocation For Autonomous Control Of Biped Robots[C]. Proceedings of IEEEInternational Conference on Robotics and Automation,2008:1264-1269.
[131] S. Kudoh, T. Kumura, K. Ikeuchi. Stepping Motion For A Human-LikeCharacter To Maintain Balance Against Large Peturbations[C]. Proceedings ofIEEE International Conference on Robotics and Automation,2006:2661-2666.
[132] B. Stephens. Integral Control Of Humanoid Balance[C]. Proceedings ofIEEE/RSJ International Conference on Intelligent Robots and Systems,2007:4020-4027.
[133] T. Sugihara, W. Takano, K. Yamane, K. Yamamoto, and Y. Nakamura. OnlineDynamical Retouch Of Motion Patterns Towards Animatronic HumanoidRobots[C]. Proceedings of IEEE-RAS International Conference on HumanoidRobots,2005:117-122.
[134] A. Safonova, J. Hodgins, N. Pollard. Synthesizing Physically Realistic HumanMotion In Low-Dimensional, Behavior-Specific Spaces[J]. ACM Transactionson Graphics,2004,23(3):514-521.
[135] Hurmuzlu Y, Moskowitz G D. Bipedal Locomotion Stabilized By Impact AndSwitching: Two And Three Dimensional, The Element Models[J]. Dynamicsand Stability of Systems,1987,2:73-96.
[136] Mousavi P N, Bagheri A. Mathematical Simulation Of A Seven Link BipedRobot On Various Surfaces And ZMP Considerations[J]. Applied MathematicalModelling,2007:18-37.
[137]郑大钟.线性系统理论[M].北京,清华大学出版社,2002:324-327.
[138] Katsu Yamane, Jessica Hodgins. Simultaneous Tracking And Balancing OfHumanoid Robots For Imiatating Human Motion Capture Data[C]. the2009IEEE/RSJ International Conference on Intelligent Robots and Systems, October11-15,2009, St. Louis, USA:2510-2517.
[139] Ishida T, Kuroki Y, Takahashi T. Analysis Of Motion Of A Small BipedEntertainment Robot[C]. International Conference on Intelligent Robots andSystems,2004:142-147.
[140] Kiyoshi F, Shuuji K, Kensuke H, et al. An Optimal Planning Of FallingMotions Of A Humanoid Robot[C]. IEEE/RSJ International Conference onIntelligent Robots and Systems,2007:456-463.
[141] Mitsuharu M, Kenji K, Fumio K, et al. Motion Planning Of Emergency StopFor Humanoid Robot By State Space Approach[C]. IEEE/RSJ InternationalConference on Intelligent Robots and Systems,2007:2986-2992.
[142] Teo K L, Goh C J, Wong K H. A Unified Computational Approach ToOptimal Control Problems[M]. Longman Scientific and Technical.1991:265-271.
[143] Lee H W J, Teo K L, Jennings LS, et al. Control Parameterization EnhancingTechnique For Time Optimal Control Problem[J]. Dynamical System,1977,6:243-261.
[144] Teo K L, Jennings L S, Lee H W, et al. The Control ParameterizationEnhancing Transform For Constrained Optimal Control Problems[J]. Journal ofAustralia Mathethatic Society,1999,40:314-335.
[145]钟秋波,潘启树,洪炳镕,朴松昊.基于参数化最优的仿人机器人动地运动控制[J].机器人,2009.11,31(6):594-598.
[146] Michalewicz Z, et.al. A Modified Genetic Algorithm For Optimal ControlProblems. Computers Math. Application,1992,23(12):83-94.
[147] Onwubolu, Godfrey C., Mutingi, Michael. A Genetic Algorithm ApproachFor The Cutting Stock Problem[J]. Journal of Intelligent Manufacturing.2003,14(2):209-218.
[148] Kivijarvi, Juha, Franti, Pasi, Nevalainen, Olli. Self-Adaptive GeneticAlgorithm For Clustering[J]. Journal of Intelligent Manufacturing.2003,9(2):113-129.
[149] Yun, Youngsu, Gen, Mitsuo, Seo, Seuglock. Sizing Populations For SerialAnd Parallel Genetic Algorithms[J]. Journal of Intelligent Manufacturing.1989,14(3):70-79.
[150] Bi Sheng, Min Huaqing; Liu Qifeng; Zheng Xijing. Multi-ObjectiveOptimization For A Humanoid Robot Climbing Stairs Based On GeneticAlgorithms[C]. Information and Automation,2009. ICIA '09. InternationalConference on,2009.6:66-71.
[151] Kim S.H. Stair Climbing Task Of Humanoid Robot By Phase CompositionAnd Phase Sequence[C]. Robot and Human Interactive Communication,2005.ROMAN2005. IEEE International Workshop on,2005.8:531-536.
[152] Gutmann J. S., Fukuchi M., Fujita M. Stair Climbing For Humanoid RobotsUsing Stereo Vision[C]. Intelligent Robots and Systems,2004.(IROS2004).Proceedings.2004IEEE/RSJ International Conference on,2004,2:1407-1413.
[153] Eun-Su Kim, Jo-Hwan Kim; Jong-Wook Kim. Generation Of OptimalTrajectories For Ascending And Descending A Stair Of A Humanoid Based OnUdeas[C]. Fuzzy Systems,2009. FUZZ-IEEE2009. IEEE InternationalConference on,2009.8:660-665.
[154] Pandu R V, Sahu S K, Pratihar DK. On-Line Dynamically Balanced AscendingAnd Descending Gaits Of A Biped Robot Using Soft Computing[J].International Journal of Humanoid Robot,2007,4(4):777-814.
[155] Ren H E, Zhong Q B, Kang J F. Object Recognition Algorithm ResearchBased On Variable Illumination[C]. IEEE International Conference onAutomation and Logistics, Shenyang, China,2009:1609-1613.
[156] Roussel L, Canudas-de-Wit C, Goswami A. Generation Of Energy OptimalComplete Gait Cycles For Biped Robots[C]. IEEE International Conference onRobotics and Automation,1998:1468-1476.
[157] Kennedy J, Eberhart R C. Particle Swarm Optimization[C]. IEEEInternational. Conference on Neural Networks,1995:1942-1948.
[158] Kennedy J, Eberhart RC. A Discrete Binary Version Of The Particle SwarmAlgorithm[C]. Proceeding of Conference on Systems, Man, and Cybernetics,1997:4104-4109.
[159] Shi Y, Eberhart R C. A Modified Particle Swarm Optimizer[C]. IEEEInternational Conference on Evolutionary Computation,1998:69-73.
[160] Chatterjee A, Siarry P. Nonlinear Inertia Weight Variation For DynamicAdaptation In Particle Swarm Optimization[J]. Computers and OperationsResearch,2006,33(3):859-871.
[161]胡建秀,曾建潮.微粒群算法中惯性权重的调整策略[J].计算机工程,2007,33(11):192-195.
[162]邢长明,刘方爱.基于强化学习的适应性微粒群算法[J].控制与决策.2011.1:26(1):54-58,64.
[163]高芳.智能粒子群优化算法研究[D].哈尔滨:哈尔滨工业大学,2008:42-57.
[164]李珺.基于强化学习的多机器人追捕问题研究[D].哈尔滨,哈尔滨工业大学,2010.
[165] Mannnor S, Menache I, Hoze A, Klein U. Dynamic Abstraction InReinforcement Learning Via Clustering[C]. The Proceedings of the21stInternational Conference on Machine learning, Banff, Alberta, Canada,2004:560-567.
[166]沈晶.分层强化学习方法研究[D].哈尔滨,哈尔滨工程大学,2006.
[167] Kretchmar R M, Feil T, Bansal R. Improved Automatic Discovery OfSubgoals For Options In Hierarchical Reinforcement Learning[J]. Journal ofComputer Science and Technology,2003,3(3):9-14.
[168] Precup D, Sutton R S. Multi-time Models for Temporally Abstract Planning.Advanceds in Neural Information Processing Systems10, MIT Press,1998:1050-1056.