【摘要】：近年來,人工智能取得較大進(jìn)展,機(jī)器人與人的聯(lián)系越來越緊密,人類和機(jī)器人的交互方式種類逐漸增多,但是不管是哪種方式,機(jī)器人都是通過傳感器來感知人體以及人機(jī)交互,這些目標(biāo)依靠單一的傳感器是難以完成的,基于多傳感器的信息融合技術(shù)是機(jī)器人人機(jī)交互過程中不可或缺的手段。多傳感器的信息融合技術(shù),其實(shí)質(zhì)是對(duì)多傳感器的信息進(jìn)行協(xié)同優(yōu)化處理,消除冗余信息,綜合各傳感器的有效信息形成互補(bǔ)、更加全面的信息,更好的表征機(jī)器人的內(nèi)外環(huán)境狀態(tài)。本文的目標(biāo)在于研究在人機(jī)交互過程中,通過多信息融合的手段,完成機(jī)器人對(duì)人體目標(biāo)的跟隨功能,使得人機(jī)交互更加友好。機(jī)器人感知到目標(biāo)人體之后,在機(jī)器人對(duì)人體目標(biāo)的跟隨過程中,利用深度信息和顏色信息融合的手段提高機(jī)器人視覺跟蹤的精度;在后續(xù)的人體目標(biāo)運(yùn)動(dòng)跟隨過程中,通過基于條件的位姿信息融合的手段,提高機(jī)器人運(yùn)動(dòng)跟隨的精度。本文提出了一種面向人機(jī)交互的機(jī)器人信息融合系統(tǒng)設(shè)計(jì)方案,該系統(tǒng)分為三大模塊:人體感知模塊、機(jī)器人視覺跟蹤模塊、機(jī)器人運(yùn)動(dòng)跟隨模塊。本文的工作和創(chuàng)新點(diǎn)如下:1.人體感知模塊,我們利用基于運(yùn)動(dòng)補(bǔ)償?shù)膸g差分法檢測(cè)運(yùn)動(dòng)目標(biāo),通過骨架驗(yàn)證目標(biāo)是否為人體目標(biāo),以確定機(jī)器人后續(xù)的動(dòng)作;2.機(jī)器人視覺跟蹤模塊,研究了小波變換融合算法,我們提出了將Depth圖像和反向投影圖融合的方式應(yīng)用在機(jī)器人視覺跟蹤中的應(yīng)用,該方案能提高機(jī)器人對(duì)人體目標(biāo)質(zhì)心的視覺跟蹤的精度;3.運(yùn)動(dòng)跟隨模塊,在確定人體目標(biāo)質(zhì)心運(yùn)動(dòng)狀態(tài)之后,我們提出了機(jī)器人視覺位姿和慣性導(dǎo)航位姿信息融合的方式應(yīng)用在機(jī)器人運(yùn)動(dòng)跟隨中的應(yīng)用。機(jī)器人在運(yùn)動(dòng)跟隨過程中,實(shí)時(shí)修正機(jī)器人位姿,有效的提高了運(yùn)動(dòng)跟隨的精度;本文設(shè)計(jì)和實(shí)現(xiàn)了面向人機(jī)交互的機(jī)器人信息融合系統(tǒng)。并在機(jī)器人上實(shí)現(xiàn)了該系統(tǒng)和進(jìn)行相關(guān)測(cè)試。
[Abstract]:In recent years, artificial intelligence has made great progress, robots are more and more closely connected with human beings, and the types of interaction between human beings and robots are gradually increasing, but no matter which way it is, Robots are aware of human body and human-computer interaction through sensors. It is difficult to achieve these goals by a single sensor. Multi-sensor based information fusion technology is an indispensable means in the process of robot human-computer interaction. The essence of multi-sensor information fusion technology is to optimize the multi-sensor information, eliminate redundant information, synthesize the effective information of each sensor to form complementary and more comprehensive information. A better representation of the robot's internal and external environment state. The purpose of this paper is to study the following function of robot to human body by means of multi-information fusion in the process of human-computer interaction, and make human-computer interaction more friendly. After the robot perceives the target body, it uses depth information and color information fusion method to improve the robot visual tracking accuracy in the process of robot following the human body target. The precision of robot motion following is improved by the method of position and pose information fusion based on condition. In this paper, a design scheme of robot information fusion system for human-computer interaction is proposed. The system is divided into three modules: human perception module, robot visual tracking module, robot motion following module. The work and innovation of this paper are as follows: 1. In the human perception module, we use the motion compensation based inter-frame differential method to detect the moving target, and verify whether the target is a human object through the skeleton, so as to determine the robot's subsequent action. In the robot vision tracking module, the wavelet transform fusion algorithm is studied, and the fusion method of Depth image and reverse projection image is put forward in the robot vision tracking. This scheme can improve the accuracy of robot visual tracking of human target centroid. In the motion following module, after determining the motion state of the human body's center of mass, we put forward the application of robot vision pose and inertial navigation position and pose information fusion in the robot motion following. In the process of robot motion following, the robot position and pose are corrected in real time, which effectively improves the precision of motion following. In this paper, a robot information fusion system oriented to human-computer interaction is designed and implemented. The system is implemented on the robot and related tests are carried out.
【學(xué)位授予單位】：電子科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41;TP242

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 李志奇;王濱;劉宏;;基于支持向量回歸的乒乓球機(jī)器人擊球策略學(xué)習(xí)方法[J];機(jī)器人;2014年01期

2 譚民;王碩;;機(jī)器人技術(shù)研究進(jìn)展[J];自動(dòng)化學(xué)報(bào);2013年07期

3 王英潔;李斌;田方;;高嶺背靠背工程換流閥電氣設(shè)計(jì)[J];高壓電器;2011年06期

4 陳輝;鄧記才;吳曉輝;宋楊;;多傳感器信息融合在輪式機(jī)器人運(yùn)動(dòng)控制中的應(yīng)用[J];傳感技術(shù)學(xué)報(bào);2011年06期

5 王相海;方玲玲;叢志環(huán);;卡爾曼粒子濾波的視頻車輛跟蹤算法研究[J];中國圖象圖形學(xué)報(bào);2010年11期

6 韋勇;連一峰;馮登國;;基于信息融合的網(wǎng)絡(luò)安全態(tài)勢(shì)評(píng)估模型[J];計(jì)算機(jī)研究與發(fā)展;2009年03期

7 羅元;李玲;張百勝;楊紅梅;;基于CamShift和Kalman濾波混合的視頻手勢(shì)跟蹤算法[J];計(jì)算機(jī)應(yīng)用研究;2009年03期

8 劉國海;李沁雪;施維;李康吉;;動(dòng)態(tài)卡爾曼濾波在導(dǎo)航試驗(yàn)狀態(tài)估計(jì)中的應(yīng)用[J];儀器儀表學(xué)報(bào);2009年02期

9 虞旦;韋巍;張遠(yuǎn)輝;;一種基于卡爾曼預(yù)測(cè)的動(dòng)態(tài)目標(biāo)跟蹤算法研究[J];光電工程;2009年01期

10 肖濤;黃強(qiáng);楊潔;余張國;張偉民;;給定手部作業(yè)軌跡的仿人機(jī)器人推操作研究[J];機(jī)器人;2008年05期

相關(guān)碩士學(xué)位論文 前1條

1 葛偉亮;機(jī)器人系統(tǒng)的模型辨識(shí)與控制器的研究與設(shè)計(jì)[D];電子科技大學(xué);2016年

，

本文編號(hào)：2218435