关键词： 机器人学   工程教育专业认证   教学改革  

摘要： 工程教育专业认证对于保障高校工程教育质量、促进我国工程教育教学改革、培养国际工程师具有非常重要的作用。结合学校机械设计制造及自动化专业的工程教育专业认证要求和机器人学课程教学中存在的问题,从教学内容、教学手段、实验教学、科研与教学结合、教学评价体系等方面对该课程进行教学改革,通过近两年的课堂教学实践显示出改革方法的有效性。

关键词： 竞赛活动   机器人   湖南省  

关键词： 北京工商大学   机器人   青少年   竞赛   科学技术协会   中小学生   人民政府   科技创造  

摘要： 3月17日至19日，第十七届北京青少年机器人竞赛在北京工商大学良乡校区举行决赛。该竞赛由北京市科学技术协会、北京市房山区人民政府、北京工商人学联合主办，以“诚佶伴我成长，科技创造未来”为主题，吸引了全市数十万中小学生的关注，2000余人报名参赛，经过逐层选拔，共有207支队伍、581名学生成功晋级。本届竞赛是赛事举办以来规模最大的一届。

关键词： 柔性并联机器人   非线性摩擦   动力学   速度规划   误差  

摘要： 为了实现柔性并联机器人的高速、高精度控制,基于Hensens&Kostic理论,计入关节非线性摩擦力建立了Lagrange动力学误差模型,测试了补偿前后机器人的单点定位误差。基于机构最大速度和加速度约束条件,分析了S型和常用T型2种速度规划算法下机器人的位置误差和速度性能。仿真结果表明:T型速度规划位置和速度跟踪最大误差为78.1μm和11.4 mm/s,而S型速度规划分别是37.8μm和3.72 mm/s,且2个终止点定位误差仅为8.1μm和8.9μm;速度性能方面,S型速度峰值误差变化最大仅为1.74 mm/s,远小于T型速度规划的6.88 mm/s。可见,在高速下S型速度规划算法保证了较高的位置跟踪精度尤其是定位精度,速度尖峰突变小且整体曲线相对平缓,大幅提高了速度跟踪精度和运动平稳性,更易于实现机器人高速、高精度平稳控制。实验测试了机器人连续运动下定点位置误差,仿真所得位置误差小于实测数据,存在100μm左右的误差,但所得结论一致,验证了仿真分析的有效性。

关键词： Service robotics   Search strategy   Patent query   Data mining   Machine learning   Support vector machine  

摘要： Emerging technologies are often not part of any official industry, patent or trademark classification systems. Thus, delineating boundaries to measure their early development stage is a nontrivial task. This paper is aimed to present a methodology to automatically classify patents concerning service robots. We introduce a synergy of a traditional technology identification process, namely keyword extraction and verification by an expert community, with a machine learning algorithm. The result is a novel possibility to allocate patents which (1) reduces expert bias regarding vested interests on lexical query methods, (2) avoids problems with citation approaches, and (3) facilitates evolutionary changes. Based upon a small core set of worldwide service robotics patent applications, we derive apt n-gram frequency vectors and train a support vector machine, relying only on titles, abstracts, and IPC categorization of each document. Altering the utilized Kernel functions and respective parameters, we reach a recall level of 83% and precision level of 85%.

关键词： Intelligent robotics   Machine learning   Model-based reinforcement learning   Robot learning   Policy search   Transition models   Reward functions  

摘要： Reinforcement learning is an appealing approach for allowing robots to learn new tasks. Relevant literature reveals a plethora of methods, but at the same time makes clear the lack of implementations for dealing with real life challenges. Current expectations raise the demand for adaptable robots. We argue that, by employing model-based reinforcement learning, the-now limited-adaptability characteristics of robotic systems can be expanded. Also, model-based reinforcement learning exhibits advantages that makes it more applicable to real life use-cases compared to model-free methods. Thus, in this survey, model-based methods that have been applied in robotics are covered. We categorize them based on the derivation of an optimal policy, the definition of the returns function, the type of the transition model and the learned task. Finally, we discuss the applicability of model-based reinforcement learning approaches in new applications, taking into consideration the state of the art in both algorithms and hardware.

关键词： Cable-driven parallel robots   Wheeled mobile robots   Non-holonomic constraints   Gibbs-Appel formula   Input-output feedback linearization   Trajectory planning  

摘要： In comparison to the conventional parallel robots, cable-driven parallel robots (CDPRs) have generally superior features such as simple production technology, low energy consumption, large workspace, high payload to moving weight ratio, and also low cost. On the other hand, a wheeled mobile robot (WMR) which is capable of covering a vast area can be used when no specific space is designated for the stationary accessories of a robot. In this paper, the integration of a CDPR with a WMR is proposed to overcome some of the issues related to each of these robots. The kinematic equations of the robot are presented. To derive the dynamic equations, Gibbs-Appel (G-A) formulation is used, which in contrary to the Lagrange formulation benefits from advantages of quasi-velocities over generalized coordinates as well as not requiring Lagrange multipliers. The dynamic equations of the two parts are coupled, and the interacting effects are observable from the governing equations. By considering non-holonomic wheels for the robot, internal dynamics appears in the equations. However, based on some conditions, the equations are input-output linearizable via a static feedback. The platform trajectory is designed based on the given end-effector trajectory. The effectiveness of the controller is shown through simulations and experimental tests.

关键词： MEMS   stress-driven   aluminum nitride   silicon nitride   piezoelectric   piezoresistive   tactile sensing   flow sensing  

摘要： The response to different force load ranges and actuation at low energies is of considerable interest for applications of compliant and flexible devices undergoing large deformations. We present a review of technological platforms based on nitride materials (aluminum nitride and silicon nitride) for the microfabrication of a class of flexible micro-electro-mechanical systems. The approach exploits the material stress differences among the constituent layers of nitride-based (AlN/Mo, SixNy/Si and AlN/polyimide) mechanical elements in order to create microstructures, such as upwardly-bent cantilever beams and bowed circular membranes. Piezoresistive properties of nichrome strain gauges and direct piezoelectric properties of aluminum nitride can be exploited for mechanical strain/stress detection. Applications in flow and tactile sensing for robotics are described.

关键词： COMPUTATIONAL intelligence   ROBOTICS   COMPUTER vision   SPATIOTEMPORAL processes   SPANNING trees (Graph theory)  

关键词： MEDICAL education   SURGICAL robots   OPERATING rooms   MEDICAL care costs   COMPUTER simulation