共创中国机器人学的合作发展新路

本文简介国内外机器人学科学和机器人技术的发展情况,着重概述了机器人学学科和机器人技术合作发展的历史,并从中得到三点启示,即国际上机器人技术和机器人学学科是依靠大联合大合作实现大发展的;没有进行全国性的"产学研"大合作是中国机器人技术未能获得长足发展的重要原因;建立全国性的机器人学学术组织是我国机器人产业大发展必不可少的要素。基于这些启示,提出了尽快成立中国机器人学联合会、设立中国机器人协会和发展机器人学教育等历史使命。     

夯实机器人发展基础 全方位培养高素质机器人学人才

本文在简介近年来国内外工业机器人销量快速增长之后,首先总结了我国机器人研究开发的经验教训,特别是机器人学人才培养方面的教训;接着论述夯实我国机器人发展基础的主要举措,包括培养高素质机器人学人才;然后对培养我国高素质机器人学人才提出决策建议,可供制定我国机器人学中长期发展规划参考。     

新年贺词 新年贺词

向您致敬!中国机器人学的研究者! 为您加油!中国机器人学的研究生! 互相鼓劲!中国机器人产业的开拓者! 从事机器人学研究或开发,好辛苦好累,请多多保重身体! 新世纪的钟声里,让我们一起品味机器人学与机器人产业独有的魅力 “昆虫战士”昆虫机器人 “昆虫战士”昆虫机器人是广茂达公司研制的全自主的爬行式移动机器人,有三种版本,IR-100是研究版,IR-200是博物馆展示版。 第一台全自主的昆虫机器人Genghis于1989年在MIT AI实验室研制成功,主要用于研究行为控制。昆虫机器人是复杂机构学、运动学、动力学、昆虫步态、控制、 神经网络、 多生命体(agent)系统、 群体机器人学、基于行为的机器人学,智能结构、图象处理、人工生命等领域的优秀研究平台。昆虫机器人的应用领域有太空探险、科学探险、排雷、教学科研平台、博物馆展示、娱乐等等。 下面介绍“昆虫战士”昆虫机器人的性能特点。     

机器人学中的学习问题

将学习机制引入机器人学.从而改善机器人系统的性能,提高其智能水平和适应能力,已成为机器人学领域重要研究课题.一个完善的机器人系统可以采用决策级、策略级和执行级三级递阶结构实现。以此划分为基础,本文介绍了应用学习概念研究机器人学中有关问题的进展情况及其发展趋势。     

多关节机器人的运动学动态仿真研究

机器人运动学是机器人学的一个重要分支，是实现机器人运动控制的基础。文中主要针对PUMA560机器人运动学正问题分析，以D-H坐标系理论为基础并建模，利用MATLAB／ROBOTICS工具，实现了简单的运动学动态仿真，有助于对机器人关节运动角度的深入理解，并为工程人员提供一种有效的分析手段。     

广茂达个人机器人专栏

新年贺词向您致敬 !中国机器人学的研究者 !为您加油 !中国机器人学的研究生 !互相鼓劲 !中国机器人产业的开拓者 !从事机器人学研究或开发 ,好辛苦好累 ,请多多保重身体 !经过数载努力 ,广茂达个人机器人产量已居世界前列 ,广茂达长大了 ,谢谢您的关心和支持 !新世纪的钟声里 ,让我们一起品味机器人学与机器人产业独有的魅力！“昆虫战士”昆虫机器人“昆虫战士”昆虫机器人是广茂达公司研制的全自主的爬行式移动机器人 ,有三种版本 ,ＩＲ -１００是研究版 ,ＩＲ -２００是博物馆展示版。第一台全自主的昆虫机器人Ｇｅｎｇｈｉｓ于１９８９…     

基于传感器信息的多机器人任务分配研究

多机器人协作是当前机器人学和人工智能的研究热点之一。针对多机器人系统中的任务分配问题,提出一种基于集中式和分布式的混合式控制结构,在机器人得到传感器信息后,使用合同网协议来完成任务分配,最终实现多机器人协作。在player/stage仿真平台进行的实验表明:多机器人系统能够有效地进行任务分配与协作,提出的解决方案是行之有效的。     

可重构模块化机器人研究

可重构模块化机器人是机器人学的一个新的发展方向,其研究的核心和基础问题是可重构机器人的模块设计以及模块组合的运动规划。设计了一种新型可重构模块化机器人,该机器人具有独特的平面连接机构,实现了结构、驱动、运动和功能的模块化,能够根据需要重新构形,完成实时任务。分别介绍了模块单元的机械结构设计、连接机构以及基于CAN总线的控制系统结构。构建了基于OpenGL技术和VC++开发平台的机器人仿真实验系统,仿真机器人构形和运动,验证了模块设计的正确性和整体运动构形规划方法的有效性。     

群机器人学

介绍了群机器人学的含义、特点和发展现状,分析了研究群机器人系统的相关理论和方法,总结了群机器人学研究的主要内容,并指出其发展趋势。     

基于无线网络的云医疗机器人系统仿真

医疗机器人是一门集医学、仿生学、机械力学、材料学、计算机科学、运筹学、机器人学等学科于一体的新兴交叉学科。随着传感器技术、通信设备,尤其是云计算的发展,云医疗机器人应运而生。一个云医疗机器人只需要少量的硬件和软件配置,它所需的大部分资源和计算过程由连接的云端提供。云医疗机器人从计算或者资源配置密集型转化为效率和功能密集型,从而可以更高效地完成复杂任务。本文设计一种云医疗机器人系统平台,该平台由医疗云平台层和远程云机器人层组成。以系统平台为基础,利用无线网络技术设计2个云医疗机器人系统案例,并进行仿真。仿真结果表明,云医疗机器人系统具有效率高、成本低和应用性强等特点。     

ROBO_SIM: A robotics simulation environment on personal computers

A Robotics Toolbox has been developed for the MATLAB matrix manipulation program. The Toolbox encompasses a set of routines to perform calculations in matrix notation. The package consists of callable routines for performing specific calculations. Some of the routines are configuration specific for common robot configurations such as the Puma. In each area, configuration independent routines are also provided, which are applicable to any robot configuration. The routines include the functions of Forward and Inverse Kinematics, Arm Dynamics, Trajectory Planning, Control, and Simulation.     

Combining Simulation and Reality in Evolutionary Robotics

Evolutionary Robotics (ER) is a promising methodology, intended for the autonomous development of robots, in which their behaviors are obtained as a consequence of the structural coupling between robot and environment. It is essential that there be a great amount of interaction to generate complex behaviors. Thus, nowadays, it is common to use simulation to speed up the learning process; however simulations are achieved from arbitrary off-line designs, rather than from the result of embodied cognitive processes. According to the reality gap problem, controllers evolved in simulation usually do not allow the same behavior to arise once transferred to the real robot. Some preliminary approaches for combining simulation and reality exist in the ER literature; nonetheless, there is no satisfactory solution available. In this work we discuss recent advances in neuroscience as a motivation for the use of environmentally adapted simulations, which can be achieved through the co-evolution of robot behavior and simulator. We present an algorithm in which only the differences between the behavior fitness obtained in reality versus that obtained in simulations are used as feedback for adapting a simulation. The proposed algorithm is experimentally validated by showing the successful development and continuous transference to reality of two complex low-level behaviors with Sony AIBO¹ robots: gait optimization and ball-kicking behavior. ¹AIBO is a trademark of Sony Corporation     

The Fifth EURON/EUnited Robotics Technology Transfer Award [Regional]

The European Robotics Research Network (EURON) and the European Robotics Association EUnited Robotics have now for the fifth time presented their joint Technology Transfer Award in the recognition of outstanding achievements in the European robot technology. At their annual meeting in Prague on 28 March, the first prize was awarded to Nicola Canelli and Giancarlo Teti from the Italian startup company RoboTech for its successful I-Droid 01 robotic kit. More than 100,000 units of this small humanoid robot have been sold worldwide in the form of collect-and-build kits available in around 90 consecutive issues from newspaper kiosks.     

典型安装方式的协作机器人基坐标系标定方法

针对地面式、侧墙式、顶棚式三种典型安装方式下的协作机器人的基坐标系标定问题,采用了一种新的操作步骤简单、标定结果精确的机器人基坐标系标定方法。该方法通过在协作机器人的公共空间中构造四点"握手"动作并分别记录接触点在每个机器人的基坐标系下的坐标,求解协作机器人基坐标系间的旋转矩阵和平移矩阵,从而得到协作机器人基坐标系间的位姿关系。针对工业机器人常见的地面式、侧墙式、顶棚式三种典型安装方式进一步分析了机器人基坐标系间的约束关系,并利用这些约束关系对标定结果做出进一步的优化处理。为验证提出的标定方法的有效性,基于Matlab的机器人工具箱完成了仿真实验,仿真实验的标定误差控制在2mm以内,该精度可满足一般弧焊、搬运、切割等生产过程的定位精度要求。仿真实验的结果验证了提出的标定方法的正确性,表明该方法可有效的解决生产环境下的协作机器人的基坐标系标定问题。     

Design of robotic visual servo control based on neural network and genetic algorithm

A new visual servo control scheme for a robotic manipulator is presented in this paper, where a back propagation (BP) neural network is used to make a direct transition from image feature to joint angles without requiring robot kinematics and camera calibration. To speed up the convergence and avoid local minimum of the neural network, this paper uses a genetic algorithm to find the optimal initial weights and thresholds and then uses the BP algorithm to train the neural network according to the data given. The proposed method can effectively combine the good global searching ability of genetic algorithms with the accurate local searching feature of BP neural network. The Simulink model for PUMA560 robot visual servo system based on the improved BP neural network is built with the Robotics Toolbox of Matlab. The simulation results indicate that the proposed method can accelerate convergence of the image errors and provide a simple and effective way of robot control.     

The Robotic Autonomy Mobile Robotics Course: Robot Design, Curriculum Design and Educational Assessment

Robotic Autonomy is a seven-week, hands-on introduction to robotics designed for high school students. The course presents a broad survey of robotics, beginning with mechanism and electronics and ending with robot behavior, navigation and remote teleoperation. During the summer of 2002, Robotic Autonomy was taught to twenty eight students at Carnegie Mellon West in cooperation with NASA/Ames (Moffett Field, CA). The educational robot and course curriculum were the result of a ground-up design effort chartered to develop an effective and low-cost robot for secondary level education and home use. Cooperation between Carnegie Mellon's Robotics Institute, Gogoco, LLC. and Acroname Inc. yielded notable innovations including a fast-build robot construction kit, indoor/outdoor terrainability, CMOS vision-centered sensing, back-EMF motor speed control and a Java-based robot programming interface. In conjunction with robot and curriculum design, the authors at the Robotics Institute and the University of Pittsburgh's Learning Research and Development Center planned a methodology for evaluating the educational efficacy of Robotic Autonomy, implementing both formative and summative evaluations of progress as well as an in-depth, one week ethnography to identify micro-genetic mechanisms of learning that would inform the broader evaluation. This article describes the robot and curriculum design processes and then the educational analysis methodology and statistically significant results, demonstrating the positive impact of Robotic Autonomy on student learning well beyond the boundaries of specific technical concepts in robotics.     

交互式机器人建模与仿真系统

研究并实现交互式机器人建模与仿真系统iRMSS(interactive robotics modeling & simulation system),为机器人仿真提供了精确实时的实验平台.iRMSS 包含两个子系统:一是3D 机器人建模子系统iRMS(interactive robotics modeling sub-system),完成机器人连杆和物理模型建模;二是基于MSRS(microsoft robotics studio)的交互式仿真子系统iRSS(interactive robotics simulation sub-system),完成实时的机器人动力学仿真并获取仿真动力学参数.iRMSS 充分发挥MSRS 集成一体化、精确度高、通用性强的优势,同时解决MSRS 在机器人建模和物理参数获取两方面存在的问题,实验结果证实了iRMSS 系统的可行性.     

Concurrent controller and Simulator Neural Network development for a differentially-steered robot in Evolutionary Robotics

Evolutionary Robotics (ER) strives for the automatic creation of robotic controllers and morphologies. The ER process is normally performed in simulation in order to reduce the time required and robot wear. Simulator development is a time consuming process which requires expert knowledge and must traditionally be completed before the ER process can commence. Traditional simulators have limited accuracy, can be computationally expensive and typically do not account for minor operational differences between physical robots.This research proposes the automatic creation of simulators concurrently with the normal ER process. The simulator is derived from an Artificial Neural Network (ANN) to remove the need for formulating an analytical model for the robot. The ANN simulator is improved concurrently with the ER process through real-world controller evaluations which continuously generate behavioural data. Simultaneously, the ER process is informed by the improving simulator to evolve better controllers which are periodically evaluated in the real-world. Hence, the concurrent processes provide further targeted behavioural data for simulator improvement.The concurrent and real-time creation of both controllers and ANN-based simulators is successfully demonstrated for a differentially-steered mobile robot. Various parameter settings in the proposed algorithm are investigated to determine factors pertinent to the success of the proposed approach.     

Molecular Robotics: A New Paradigm for Artifacts

The rapid progress of molecular nanotechnology has opened the door to molecular robotics, which uses molecules as robot components. In order to promote this new paradigm, the Molecular Robotics Research Group was established in the Systems and Information Division of the Society of Instrument and Control Engineers (SICE) in 2010. The group consists of researchers from various fields including chemistry, biophysics, DNA nanotechnology, systems science and robotics, challenging this emerging new field. Last year, the group proposed a research project focusing on molecular robotics, and it was recently awarded a Grant-in-Aid for Scientific Research on Innovative Areas (FY2012-16), one of the large-scale research projects in Japan, by MEXT (Ministry of Education, Culture, Sports, Science and Technology, JAPAN). Here, we wish to clarify the fundamental concept and research direction of molecular robotics. For this purpose, we present a comprehensive view of molecular robotics based on the discussions held in the Molecular Robotics Research Group.     

Beyond Asimov: The Three Laws of Responsible Robotics

Asimov's Three Laws of Robotics have been inculcated so successfully into our culture that they now appear to shape expectations as to how robots should act around humans. However, there has been little serious discussion as to whether the Laws really do provide a framework for human-robot interactions. Asimov actually used his laws as a literary device to explore the lack of resilience in the interplay between people and robots in a range of situations. This paper briefly reviews some of the practical shortcomings of each of Asimov's Laws for framing the relationships between people and robots, including reminders about what robots can't do. The main focus of the paper is to propose an alternative, parallel set of Laws of Responsible Robotics as a means to stimulate debate about the accountability relationships for robots when their actions can result in harm to people or human interests. The alternative laws emphasize (1) systems safety in terms of the responsibilities of those who develop and deploy robotic systems, (2) robots' responsiveness as they participate in dynamic social and cognitive relationships, and (3) smooth transfer of control as a robot encounters and initially responds to disruptions, impasses, or opportunities in context.