关键词： 机器人竞赛   以赛促学  

摘要： 为贯彻落实国务院发布的《新一代人工智能发展规划》,引导高等学校加强相关专业和课程建设,加强科研和工程实践的训练,注重培养大学生的创新能力、理论知识应用能力、动手能力和协作精神,学院积极组织学生参加机器人竞赛,通过比赛来提升学生对机器人课程的兴趣,并将课堂所学的基础知识和核心课程应用到机器人竞赛实践中,从而增强学生的创新思维,达到以赛促学的目的.

关键词： 轮腿机器人   球面并联机构   动力学模型   自由度   螺旋理论  

摘要： 为适应现代工程领域对移动机器人的新要求,拓展移动机器人的作业场合,该文提出了一种轮-腿复合式移动机器人球面并联腿机构。首先,基于球面并联腿机构的闭环约束方程和旋转变换矩阵构建了其位置逆解数学模型;接着,采用代数消元法推导出了球面并联腿机构的位置正解的解析解;然后,运用影响系数法推导出了球面并联腿机构的速度和加速度影响系数矩阵;在此基础上,运用拉格朗日方法建立了球面并联腿机构的动力学模型。运用数值仿真对运动学和动力学模型进行了验证,仿真得到了给定位姿数据与计算位姿数据之间的最大误差为0.012 7 rad,误差不超过实际值的2.43%,发现了球面并联腿机构驱动力的理论曲线和虚拟样机仿真曲线吻合,两者之间的误差稳定在0~1 N的合理范围内,验证了运动学和动力学模型的正确性。研究结果为轮-腿复合式移动机器人的步态规划和运动控制提供了理论参考。

关键词： 机器人   科普教育   高等教育   研修教育   产业化  

摘要： 随着国家对人工智能和机器人产业的高度重视,加上工业4.0时代社会对于智能化生产生活的普遍需求,机器人学科以前所未有的速度迅猛发展。与此同时机器人行业人才缺口日益凸显。近年来机器人已经作为新生专业或新颖课程逐步引入中小学乃至大学教育中。但国内高校本科机器人专业设置时间较晚,尚不足以评估培养效果;中小学的科学教育课程以机器人为实例的情况普及程度仍有欠缺。提出了产学研用融合的机器人学科教育体系架构,从用人单位的岗位需求和人才能力需求以及教育机器人产业化的实际大型持续性项目出发,分析人才培养的具体方向和课程及内容设置。开展机器人科普教育系列课程、高等教育系列课程和高级研修系列课程,将课堂教学与科学研究、产业化项目、学生就业融合成有机的整体,使机器人学科建设真正切实可行地服务社会并滋生科研成果,同时从中培养出用人单位急需的专业化应用型人才。

关键词： 机器人   柔体动力学   刚度系数辨识   柔性位置   前馈补偿  

摘要： 为解决机器人由于结构复杂、关节耦合以及控制的非线性时变等因素给其带来的动态响应迟滞,以及关节的柔性因素引起的机械谐振的问题,改进了刚体前馈力矩补偿方法,提出了基于柔体动力学模型的柔性力矩前馈补偿控制。该方法通过建立机器人柔性关节的动力学模型,辨识得到柔性关节的扭转刚度参数以及最小惯性参数,获取更为准确的柔性因素下的预设轨迹的位置、速度、加速度信息,从而计算出柔性关节下所需的力矩值;将计算值作为前馈量,以周期为T的形式发送到伺服驱动器的底层,实时刷新驱动器,采用补偿的形式与电流环输出量进行叠加,从而实现机器人的柔性控制,使得机器人末端振动加速度幅值下降60%,提高了定位精度。实验验证了柔体动力学模型的机器人柔性力矩前馈控制的工程应用价值。

关键词： 机器人竞赛   果园喷药   自主寻迹   平面定位系统   单片机控制  

摘要： 文章设计了一种面向中国机器人大赛的果园喷药机器人,根据竞赛要求,结合平面四杆机构的工作原理,设计了机器人的机械系统;以STM32F103ZET6单片机为控制核心,通过搭载电机驱动器、循迹传感器、平面定位系统以及喷药系统,设计了竞赛机器人的控制系统,其中,以步进电机控制器、丝杠滑台、电磁继电器、电磁阀、增压泵等构建了机器人喷药系统。最后,设计了控制算法,实现了果园喷药机器人的竞赛功能。

关键词： Robots  

摘要： This article surveys 21 studies of how ethologists characterize the environment for arthropods, reptiles, mammals, and birds traversing above ground, below ground, and burrowing in order to provide insights in selecting or designing a robot for a complex work envelope, for example, the 2018 Thailand Cave rescue. Roboticists are currently forced to rely on empirical expertise to select or design robots and to construct ad hoc testbeds for expected environments due to the lack of comprehensive quantitative metrics. Fortunately, ethologists have been grappling with how to quantify environmental factors that impact the traversability of different animals. That community has collectively identified 21 characteristics which this article discusses and groups into a novel taxonomy of three broad categories: local navigational constraints, surface properties, and global layout properties. One conclusion is that the set of appropriate characteristics for a specific environment depends on the scale of the environment to the agent. The article also makes four recommendations to aid roboticists in a) selecting a particular robot suitable for the environmental characteristics, b) building testbeds that are more representative of the target environment or to objectively compare different robotics, and c) collecting data about an environment for use cases or work analyses. It also discusses the limitations of the ethological studies for robotics and the remaining gaps. (C) 2019 Published by Elsevier B.V.

摘要： "Robotics in Japan" is a science, technology, engineering, and math (STEM) based program design for The Experiment in International Living (The Experiment). This design is for a four-week program for high school students. It is grounded in The Experiment's mission and basic program structure. The purpose of Robotics in Japan is to add a STEM-based program to The Experiment's portfolio in one of The Experiment's most popular and marketable countries. In addition, this design adds a computer and technology theme, an area within STEM that has even less representation in The Experiment's portfolio. In this paper, all necessary aspects to run this program are addressed. This includes pre-program aspects such as recruitment, marketing, staffing, and health and safety as well as on and after program information such as a basic program itinerary, goals and objectives, curriculum, crisis management, budget, and evaluation plan. This program design is informed by research and literature on study abroad, adolescent development, STEM, robotics, and curriculum design. It is also informed by two needs assessment surveys, one completed by former Experiment Group Leaders and one completed by former Experiment participants. These assessments were anonymously completed online with no incentives for participation. The surveys showed successful student growth outcomes in a variety of identity development areas. The surveys also showed a primary participant interest in program destination and a perceived parent interest in computer and technology-themed programs. Robotics in Japan aims to capitalize on the student interest in Japan and the parent interest in computers and technology to add a STEM program grounded in theory to The Experiment's 2021 catalog.

关键词： Reinforcement learning   Policy iteration   Continuous actions   Robotics   Sparsification  

摘要： Reinforcement learning (RL) is a general framework to acquire intelligent behavior by trial-and-error and many successful applications and impressive results have been reported in the field of robotics. In robot control problem settings, it is oftentimes characteristic that the algorithms have to learn online through interaction with the system while it is operating, and that both state and action spaces are continuous. Least-squares policy iteration (LSPI) based approaches are therefore particularly hard to employ in practice, and parameter tuning is a tedious and costly enterprise. In order to mitigate this problem, we derive an automatic online LSPI algorithm that operates over continuous action spaces and does not require an a-priori, hand-tuned value function approximation architecture. To this end, we first show how the kernel least-squares policy iteration algorithm can be modified to handle data online by recursive dictionary and learning update rules. Next, borrowing sparsification methods from kernel adaptive filtering, the continuous action-space approximation in the online least-squares policy iteration algorithm can be efficiently automated as well. We then propose a similarity-based information extrapolation for the recursive temporal difference update in order to perform the dictionary expansion step efficiently in both algorithms. The performance of the proposed algorithms is compared with respect to their batch or hand-tuned counterparts in a simulation study. The novel algorithms require less prior tuning and data is processed completely on the fly, yet the results indicate that similar performance can be obtained as by careful hand-tuning. Therefore, engineers from both robotics and AI can benefit from the proposed algorithms when an LSPI algorithm is faced with online data collection and tuning by experiment is costly.

关键词： Knowledge representation   Robot learning   Task planning   Domestic robots   Service robotics  

摘要： Within the realm of service robotics, researchers have placed a great amount of effort into learning, understanding, and representing motions as manipulations for task execution by robots. The task of robot learning and problem-solving is very broad, as it integrates a variety of tasks such as object detection, activity recognition, task/motion planning, localization, knowledge representation and retrieval, and the intertwining of perception/vision and machine learning techniques. In this paper, we solely focus on knowledge representations and notably how knowledge is typically gathered, represented, and reproduced to solve problems as done by researchers in the past decades. In accordance with the definition of knowledge representations, we discuss the key distinction between such representations and useful learning models that have extensively been introduced and studied in recent years, such as machine learning, deep learning, probabilistic modeling, and semantic graphical structures. Along with an overview of such tools, we discuss the problems which have existed in robot learning and how they have been built and used as solutions, technologies or developments (if any) which have contributed to solving them. Finally, we discuss key principles that should be considered when designing an effective knowledge representation. (C) 2019 Elsevier B.V. All rights reserved.

关键词： mobile manipulation   navigation   perception  

摘要： The ground robotics challenge in the Mohammed Bin Zayed International Robotics Challenge required a ground vehicle equipped with a robotic arm to autonomously locate a panel, select a proper size wrench among several options mounted on the panel, and use the wrench to rotate a valve. Autonomy was the critical factor in this challenge, which required the teams to devise algorithms that can operate successfully in a semistructured environment without human supervision. This paper presents the approaches taken by team KAUST to meet this challenge, ranging from in-house hardware designs to algorithm integration and customization. We separated the whole objective into three interconnected tasks: Navigation, perception, and manipulation. For the navigation task, we developed a basic robotic exploration scheme to find the panel front side where the wrenches were present. For the perception task, we integrated common object detection algorithms with neural networks to identify the proper size wrench precisely. For successful manipulation, we designed and built a custom gripper, which was inspired by the common grasping behavior of a human hand under tight clearance conditions. The modular structure of the proposed approach allowed the team to progress in several subtasks simultaneously. However, the interconnection between the subtasks necessitated a reliable integration framework between these modules for effective implementation. We tuned our algorithms in extensive experimental studies and eventually obtained 10 consecutive successful navigation runs, 96% true wrench detection rate, and high success rate in wrench grasping. Furthermore, successful complete tests proved the reliability and repeatability of our system.