本文關(guān)鍵詞：基于軌跡匹配的模仿學(xué)習(xí)在類人機(jī)器人運(yùn)動(dòng)行為中的研究　出處：《北京工業(yè)大學(xué)》2016年碩士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 模仿學(xué)習(xí) 類人機(jī)器人 軌跡匹配 概率模型 動(dòng)態(tài)系統(tǒng)

【摘要】：模仿是人與動(dòng)物技能學(xué)習(xí)的一種方法,將模仿學(xué)習(xí)機(jī)制賦予機(jī)器人系統(tǒng),使其具有類似人的運(yùn)動(dòng)技能學(xué)習(xí)行為,快速地實(shí)現(xiàn)復(fù)雜運(yùn)動(dòng)技能的獲取,是機(jī)器人仿生研究的重點(diǎn)內(nèi)容之一。本文基于生物模仿的仿生機(jī)制,構(gòu)建了機(jī)器人模仿學(xué)習(xí)的框架,以該框架為指導(dǎo),圍繞基于軌跡匹配的模仿學(xué)習(xí)在類人機(jī)器人中的運(yùn)動(dòng)行為進(jìn)行研究,具體如下:(1)基于概率模型的機(jī)器人模仿學(xué)習(xí)研究對(duì)基于概率模型的模仿學(xué)習(xí)算法進(jìn)行研究,利用高斯混合模型(GMM)進(jìn)行軌跡編碼,學(xué)習(xí)示教行為的特征,通過(guò)高斯混合回歸(GMR)進(jìn)行泛化處理,實(shí)現(xiàn)行為再現(xiàn)。針對(duì)書寫任務(wù)中運(yùn)動(dòng)軌跡較復(fù)雜的問(wèn)題,引入概率模型的模仿學(xué)習(xí)對(duì)書寫軌跡進(jìn)行表征和泛化,進(jìn)而實(shí)現(xiàn)機(jī)器人書寫技能的獲取。實(shí)驗(yàn)結(jié)果表明,該方法具有良好的行為編碼能力和抗干擾性,能夠?qū)崿F(xiàn)軌跡可連續(xù)的漢字書寫,通過(guò)對(duì)GMM的擴(kuò)展能夠進(jìn)行多任務(wù)學(xué)習(xí),進(jìn)而實(shí)現(xiàn)軌跡不可連續(xù)漢字的書寫,泛化效果良好。(2)基于Kinect的Nao機(jī)器人動(dòng)作模仿系統(tǒng)的開(kāi)發(fā)與實(shí)現(xiàn)為避開(kāi)復(fù)雜繁瑣的底層運(yùn)動(dòng)控制,使機(jī)器人能夠通過(guò)學(xué)習(xí)實(shí)現(xiàn)運(yùn)動(dòng)技能的獲取,有效提高其智能性,將體態(tài)感知技術(shù)與仿人機(jī)器人NAO相結(jié)合,以機(jī)器人的模仿學(xué)習(xí)框架為指導(dǎo),開(kāi)發(fā)并實(shí)現(xiàn)了基于Kinect的Nao機(jī)器人動(dòng)作模仿系統(tǒng)。利用Kinect體感攝像機(jī)的骨骼跟蹤技術(shù),采集示教者骨骼點(diǎn)信息,計(jì)算各骨骼向量間的夾角得到各關(guān)節(jié)角變化信息,將其作為示教數(shù)據(jù),通過(guò)高斯混合模型對(duì)示教數(shù)據(jù)進(jìn)行表征學(xué)習(xí),經(jīng)高斯混合回歸泛化處理后,映射到Nao機(jī)器人中,實(shí)現(xiàn)動(dòng)作的模仿。實(shí)驗(yàn)結(jié)果表明,Nao機(jī)器人能夠進(jìn)行實(shí)時(shí)和離線的動(dòng)作模仿,運(yùn)動(dòng)軌跡平滑而穩(wěn)定,動(dòng)作模仿的效果較好。(3)機(jī)器人模仿學(xué)習(xí)的在線調(diào)整問(wèn)題研究為使機(jī)器人能夠在任務(wù)環(huán)境發(fā)生變化的情況下,根據(jù)任務(wù)參數(shù)的變化作出相應(yīng)的動(dòng)態(tài)調(diào)整,使其具備在線調(diào)整能力,完成預(yù)定任務(wù),將高斯混合模型與動(dòng)態(tài)系統(tǒng)法相結(jié)合,對(duì)機(jī)器人模仿學(xué)習(xí)的在線調(diào)整問(wèn)題進(jìn)行研究。將動(dòng)態(tài)系統(tǒng)的在線調(diào)整能力與高斯混合模型(GMM)的復(fù)雜軌跡的編碼能力相結(jié)合,使動(dòng)態(tài)系統(tǒng)的參數(shù)學(xué)習(xí)問(wèn)題轉(zhuǎn)化為高斯混合回歸問(wèn)題(GMR),為動(dòng)態(tài)系統(tǒng)法提供了一種概率形式的表述;引入?yún)?shù)化高斯混合模型,基于DS-GMR模仿學(xué)習(xí)方法,重點(diǎn)對(duì)目標(biāo)位置發(fā)生變化的任務(wù)場(chǎng)景下的機(jī)器人在線調(diào)整問(wèn)題進(jìn)行了研究與仿真實(shí)現(xiàn)。仿真實(shí)驗(yàn)結(jié)果表明,該方法在一定程度上具備高斯混合模型的軌跡編碼能力和動(dòng)態(tài)系統(tǒng)的動(dòng)態(tài)調(diào)整能力,當(dāng)任務(wù)環(huán)境發(fā)生變化時(shí),能夠作出相應(yīng)的調(diào)整,具備一定的在線調(diào)整能力,且軌跡匹配性能較好,泛化能力進(jìn)一步增強(qiáng)。本文對(duì)基于軌跡匹配的模仿學(xué)習(xí)在類人機(jī)器人中的運(yùn)動(dòng)行為進(jìn)行了研究,對(duì)目前存在的模仿學(xué)習(xí)方法進(jìn)行了較為系統(tǒng)地分析、總結(jié),并在已有方法的基礎(chǔ)上進(jìn)行了一定的優(yōu)化和擴(kuò)展,對(duì)模仿學(xué)習(xí)的研究及其在類人機(jī)器人運(yùn)動(dòng)行為中的應(yīng)用具有一定的參考價(jià)值。
[Abstract]:Imitation is a way to learn human and animal skills. It imparts the imitation learning mechanism to the robot system, making it have similar human movement skills learning behavior, and quickly achieve the acquisition of complex motor skills, which is one of the key contents of robot bionic research. In this paper, based on the biological mechanism of bionic imitation, construct a framework for robot imitation learning, based on the framework as a guide, around the trajectory, imitation motion behavior in humanoid robot in the study, based on the specific as follows: (1) the robot imitation probability model for study of imitation learning algorithm based on probabilistic model based on the Gauss mixture model (GMM) trajectory encoding, learning characteristics of teaching behavior, by Gauss (GMR) mixed regression generalization, realize the behavior of reproduction. Aiming at the complexity of the trajectory in writing task, we introduce the imitation learning of probabilistic model to represent and generalize the writing trajectory, and then achieve the acquisition of robot's writing skills. The experimental results show that this method has good behavior coding ability and anti-interference ability, and can achieve continuous Chinese character writing. It can carry out multi task learning through the extension of GMM, and then achieve the writing of track non continuous Chinese characters. The generalization effect is good. (2) based on the development of Nao robot action Kinect imitation system and the realization of the bottom movement to avoid complicated control, the robot can obtain through learning exercise skills, improve their intelligence, body perception technology and humanoid robot NAO combined with imitation learning framework for robot guidance and development the simulation system of Nao robot movement based on Kinect. The skeletal tracking technique using the Kinect somatosensory camera, collecting demonstrator skeleton point information, calculate the angle between the skeletal vector between the joint angle change information, as the teaching data, through the Gauss mixture model to characterize the teaching data through learning, generalization to processing to Gauss after mixing, mapping to the Nao robot in the implementation of action imitation. The experimental results show that the Nao robot can simulate the action of real time and off-line, the trajectory is smooth and stable, and the effect of action imitates is better. (3) study on the on-line adjustment problem of robot imitation learning for the robot can in the task environment, make corresponding adjustment according to the change of task parameters, which has the ability to adjust online, is scheduled to complete the task, combining the Gauss mixture model and the dynamic system method, on-line adjustment of learning to imitate robot research. The dynamic system of the online adjustment ability and Gauss mixture model (GMM) complex locus encoding combined with the ability to make the parameters of the dynamic system of learning problem into the Gauss mixture regression problem (GMR), provides a form of probability expressions for the dynamic system method; introduced the parametric Gauss mixture model, DS-GMR imitation learning based on the method of research and Simulation on robot online adjustment of the target position changes of task scenarios focus. The simulation results show that this method has the ability to dynamically adjust the Gauss mixture model trajectory encoding ability and dynamic system to a certain extent, when the task environment changes, to make appropriate adjustments, have certain ability of adjustment, and the trajectory matching can further enhance the generalization ability. This paper studied the learning movement behavior in humanoid robot's trajectory matching based on the imitation of imitation, learning methods are systematically analyzed and summarized, and the optimization and expansion of some are based on the existing method, and its application in humanoid robot motion behavior has a certain the reference value for the study of learning.
【學(xué)位授予單位】：北京工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類號(hào)】：TP242
，

本文編號(hào)：1342004