关键词： Robotics  

摘要： The emergence of deep learning, access to large amounts of data and powerful computing hardware have led to great strides in the state-of-the-art in robotics, computer vision, and AI. Unlike traditional methods that are strongly model-based with priors and explicit structural constraints, these newer learning approaches tend to be data-driven and often neglect the underlying problem structure. As a consequence, while they usually outperform their traditional counterparts on many problems, achieving good generalisation, interpretability, task transfer and data-efficiency has been challenging. Combining the strengths of the two paradigms, the flexibility of modern learning techniques, and the domain knowledge and structure of traditional methods should help bridge this gap. In this thesis, we will present work that combines these two paradigms, specifically in the context of learning visual dynamics models for robot manipulation tasks. This thesis is divided into two parts. In the first part, we discuss a structured approach to designing visual dynamics models for manipulation tasks. We propose a specific class of deep visual dynamics models (SE3-Nets) that explicitly encode strong physical and 3D geometric priors (specifically, rigid body physics) in their structure. As opposed to deep models that reason about motion a pixel level, SE3-Nets model the dynamics of observed scenes at the object level - they identify objects in the scene and predict rigid body rotation and translation per object. This leads to an interpretable architecture that can robustly model the dynamics of complex interactions. Next, we discuss SE3-Pose-Nets, an extension of SE3-Nets that additionally learns to estimate a latent, globally-consistent pose representation for objects and use the corresponding representation for real-time closed-loop visuomotor control of a Baxter robot. We show that the structure inherent in SE3-Pose-Nets allows them to be robust to visual perturbations and noise, gen

关键词： Language arts   Education   Robotics  

摘要： Two areas in education that researchers continue to address are: (1) the search for best practices to support students who are language learners with academic success (Lesaux & Geva, 2006; Lesaux, Kieffer, Kelley, & Harris, 2014; Wilson, Fang, Rollins, & Valadez, 2016); and (2) the increased inclusion of STEM-related activities in educational settings (Barak & Zadok, 2009; Mitnik, Nussbaum, & Soto, 2008; Sullivan, 2008). The purpose of this qualitative, case study was to examine the use of robotics – a STEM-related activity – with connections to the literacy development of students identified as language learners during an eight-week, community-based robotics program. Additional attention was paid towards the students’ development and application of academic vocabulary within the program. The theoretical framework for this study was framed by Papert’s (1993) theory of constructionism and Long’s (1996) interaction hypothesis for language acquisition. The major findings from this study collapsed into the following themes: (1) informational texts; (2) writing; and (3) dialogue. Overall, findings from this study showed providing students with a specific task (i.e., constructing and programming a LEGO® MINDSTORMS® robot) promoted research, writing, and communication, in which the students encountered and used academic vocabulary. This study demonstrates the potential robotics has in supporting the literacy and academic vocabulary development of students who are language learners, and encourages the need for additional research on the use of robotics in educational settings and non-STEM-related fields.

关键词： Community college education   Law   Educational technology   Artificial intelligence  

摘要： This study was an examination of the systemization of, and law and ethics concepts incorporated into, robotics and computer science courses that offered artificial intelligence as part of the curriculum of selected community colleges. The researcher completed a mixed-methods study using surveys and document analysis. The first area of investigation focused on the systemization of the curriculum between computer science and robotics courses that included artificial intelligence. Eight markers were used to measure systemization. The researcher used surveys to explore whether legal and ethical reasoning in technical practices in artificial intelligence were considered and understood by administration, instructors, and students at the community colleges. The researcher used the results of the surveys, and document analysis of course syllabi and course descriptions from computer science and robotics courses that offered artificial intelligence at the selected community colleges to investigate systematization of these courses and consideration of legal and ethical reasoning in technical practices. The researcher concluded that there was not systemization among computer science and robotics courses. Furthermore, student, instructors, and administrators have only minimal understanding of ethical issues surrounding the development of artificial intelligence in education in community colleges.

关键词： Aerospace   Teleoperation   Artificial Intelligence   Simulation   Haptic devices   Subsea robotics  

摘要： Purpose The following paper is a Q&A interview conducted by Joanne Pransky of Industrial Robot Journal as a method to impart the combined technological, business and personal experience of a prominent, robotic industry PhD and innovator regarding his pioneering efforts and his personal journey of bringing a technological invention to market. This paper aims to discuss these issues. Design/methodology/approach The interviewee is Dr Howard Chizeck, Professor of Electrical and Computer Engineering and Adjunct Professor of Bioengineering at the University of Washington (UW). Professor Chizeck is a research testbed leader for the Center for Neurotechnology (a National Science Foundation Engineering Research Center) and also co-director of the UW BioRobotics Laboratory. In this interview, Chizeck shares the details on his latest startup, Olis Robotics. Findings Howard Jay Chizeck received his BS and MS degrees from Case Western Reserve University and the ScD degree in Electrical Engineering and Computer Science from the Massachusetts Institute of Technology. He served as Chair of the Department of Systems, Control and Industrial Engineering at Case Western Reserve University and was also the Chair of the Electrical and Computer Engineering Department at the University of Washington. His telerobotic research includes haptic navigation and control for telerobotic devices, including robotic surgery and underwater systems. His neural engineering work involves the design and security of brain-machine interfaces and the development of devices to control symptoms of essential tremor and Parkinson's disease. Originality/value Professor Chizeck was elected as a Fellow of the IEEE in 1999 for contributions to the use of control system theory in biomedical engineering and he was elected to the American Institute for Medical and Biological Engineering (AIMBE) College of Fellows in 2011 for contributions to the use of control system theory in functional electrical stimulation assisted

关键词： 平面3-(?)RR并联机器人   刚柔耦合   绝对节点坐标法   自然坐标法   不变矩阵   generalized-alpha法  

摘要： 随着我国社会快速发展,经济结构加速升级,制造业中机器人保有量屡创新高。本文中所研究的平面3-(?)RR刚柔耦合并联机器人,在快速运动过程中,轻质杆件由于内力作用不可避免地会发生柔性大变形,使其力学特性应和刚性模型有所差别。文章以轻质杆件在运动中会变形为先决条件,以绝对节点坐标法与自然坐标法描述了刚柔耦合系统的逆动力学模型,利用generalized-alpha法与牛顿迭代法结合进行数值求解。另外,本文还将机器人刚柔耦合模型与刚性模型的力学特征做出了比较。本文主要工作如下:(1)平面3-(?)RR刚体逆运动学与逆动力学分析。本文介绍了该机器人的构型,应用矢量环路法对关节角、关节角速度、关节角加速度进行了分析。通过仿真图像可知关节角速度图像关节与角位移图像,关节角加速度图像与关节角速度图像皆成导数关系,证明了逆运动学模型的正确性。根据柯尼希原理分别计算各杆件与动平台的动能,进而得到了机构动能。利用刚体尺寸不变原理,约束方程即利用动平台外接圆半径固定不变的约束条件来建立。逆动力学模型依据拉格朗日原理利用拉格朗日乘子来建立,并应用MATLAB软件对其力学性能进行仿真。(2)平面3-(?)RR刚柔耦合逆动力学模型分析。采用自然坐标法描述刚性构件,可推导出刚性构件的质量矩阵。采用绝对节点坐标法描述柔性构件,需先利用待定系数法求得形函数,从而推导出柔性构件质量矩阵。由此可对各构件质量矩阵进行装配,得到整个机器人的质量矩阵,以推导出惯性力。利用等效力偶,依据虚功原理可推导出广义驱动力。依据刚性构件几何尺寸不变原理,构建约束方程即刚性杆杆长方程与刚性动平台边长方程,从而推导出约束力。加入弹性力与轨迹约束方程即可构建机器人刚柔耦合逆动力学模型。(3)平面3-(?)RR刚柔耦合逆动力学建模数值求解。采用了缩减积分的方法来分割应变能以规避泊松闭锁问题,应用不变矩阵来提高求解运算速度。以S-型加减速圆周轨迹为算例,结合generalized-alpha法、牛顿迭代法与刚体校正法来求解并联机器人的逆动力学模型。实验迭代结果满足设定精度要求。所求柔性梁中点处最大横向变形为4.701mm,其剪切角的变化规律具有对称性,驱动关节角速度与理想刚性模型相比变化明显,驱动关节变量的变化规律比较平滑,由此验证了建模方法、求解算法的正确性和使用S-型加减速的必要性,对将来控制具有重要的理论意义。

关键词： 机器人技术  

ISBN: (纸本)9787561267196

摘要： 动力学分析是设计并联机器人尺寸的基础。同时基于模型控制方法的应用也需要建立并联机器人的动力学反解模型。本书共分八章, 内容包括: 绪论 ; 运动学分析基础 ; 对非冗余并联机器人奇异性分析和检测的一种工程方法等。

关键词： STEM education   Science activities   Robotics   Inquiry method   Floors   Boundaries   School buildings   Wheelchairs   Prototypes   Technical education   Students  

摘要： In an age of information where students have the world quite literally at their fingertips, and with the ever-growing momentum of integrated science, technology, engineering, and mathematics (STEM), it is not enough that students experience STEM subjects exclusively in silos. Instead, teachers need to provide students with integrated opportunities for learning, which can be beneficial to student achievement. To be well positioned for the future, students must be able to work productively in environments that transcend disciplinary boundaries to generate novel solutions to improve our world. Here, Edelen et al share an afterschool STEM inquiry that transformed 22 third-, fourth-, and fifth-grade students by positioning them as engineers solving an authentic problem. These students modeled, designed, and tested robotic prototypes as solutions to getting a student in a wheelchair from the first floor to the third floor of a school building.

关键词： 机器人工作室   泉州市   信息技术中心   机器人竞赛  

摘要： 庄月芳荣膺泉州市教委举办的征文比赛桂冠的那一年,是她在福建省泉州市第七中学任教的第十八年。次年,她接任校长,成为该校迄今唯一一位女校长。"教育正如一场光合作用,课堂中要有生命拔节的声音。"正如她在获奖征文中所写,多年来,庄月芳与七中的老师们一起,带着七中"爱拼敢赢"的精神特质出发,用明师的眼、心、功,指引七中的学子在素质教育的光合作用下,追寻属于自己的道路,活出生命最好的可能。而站在他们背后的泉州七中,今年刚过完88岁大寿。雄鸡一唱天下白。校徽上那只昂首打鸣的大公鸡,见证了七中的种种"不一般"。

关键词： 管道检测机器人   ADAMS   过弯   变径   仿真  

摘要： 管道检测机器人是可以在管道内部行走并且搭配其他设备对管道内部进行检测并能将检测结果反馈给外界的一种机电一体化装置。管道检测机器人工作的环境多种多样,比如直管、弯管、变径管、U形管、T形管等,并且管道中时常会存在一些障碍物,管道检测机器人能够适应如此多种环境的关键在于它的行走方式和变径方式。当前的管道检测机器人存在机械结构比较复杂,变径能力弱,越障能力不足等问题。本文针对这些问题以及机器人的工作环境对轮式和履带式两种行走方式的管道检测机器人分别作出研究以期选择出相对较好的一种,并且摒弃了以往的平行四边形变径方式,采用对称变径方式,提出轮式管道检测机器人以及履带式管道检测机器人的整体研究方案,并对它们的变径能力与过弯能力作出理论分析,分析表明:所设计的轮式管道检测机器人能够适应内径为130mm—150mm的管道,当管道内径为150mm时最小转弯半径为280mm;所设计的履带式管道检测机器人能够适应内径为135mm—160mm的管道,当管道内径为150mm时最小转弯半径为180mm。然后按照整体研究方案分别将两种管道机器人通过三维软件建立模型并导入ADAMS中进行仿真,分析了两种管道机器人的变径能力、过弯能力、越障能力以及对称式变径的特点验证,仿真结果表明:两种管道机器人具有良好的变径能力与过弯能力并且对称式变径的特点也得到验证,但发现履带式管道检测机器人的越障能力明显强于轮式管道检测机器人,因此将履带式管道检测机器人作为最后样机进行制作。对履带式管道机器人样机进行水平管道爬行实验、竖直管道爬行实验以及转弯爬行实验并分别测得机器人在水平管道中的牵引力以及在竖直管道中的牵引力,实验得出管道机器人水平爬行速度约为22mm/s,牵引力约为5.02N;管道机器人在竖直管道中上升的平均速度为19mm/s,牵引力约为0.8N;下降的平均速度为21mm/s,牵引力约为10.8N;管道机器人转弯前进的平均速度为21mm/s,转弯后退的平均速度为22mm/s。实验表明该履带式管道机器人能够竖直爬行,可顺利通过弯道并且爬行速度稳定可在管道中正常工作。