关键词： Harsh environments   Unmanned Aerial Vehicle   Underwater   Autonomous underwater vehicles   robotics   Unmanned Ground Vehicle   drone honey bees   UNMANNED   Biomimetics  

摘要： It is clear that unmanned under-ter vehicles (UUVs), autonomous underwater vehicles (AUVs), and other waterborne robots are successfully addressing critical capability requirements for many customers, including those in defense and oil and gas. There remains, however, despite the best efforts of many entities, capability gaps for these systems. While UUVs share many of the same navigation, power, and logistical challenges as their unmanned ground vehicle (UGV) and unmanned aerial vehicle (UAV) counterparts, they are subject to additional challenges including limited communications and harsh environments.

关键词： Motor primitives   Episodic reinforcement learning   Motor control   Policy learning  

摘要： Many motor skills in humanoid robotics can be learned using parametrized motor primitives. While successful applications to date have been achieved with imitation learning, most of the interesting motor learning problems are high-dimensional reinforcement learning problems. These problems are often beyond the reach of current reinforcement learning methods. In this paper, we study parametrized policy search methods and apply these to benchmark problems of motor primitive learning in robotics. We show that many well-known parametrized policy search methods can be derived from a general, common framework. This framework yields both policy gradient methods and expectation-maximization (EM) inspired algorithms. We introduce a novel EM-inspired algorithm for policy learning that is particularly well-suited for dynamical system motor primitives. We compare this algorithm, both in simulation and on a real robot, to several well-known parametrized policy search methods such as episodic REINFORCE, 'Vanilla' Policy Gradients with optimal baselines, episodic Natural Actor Critic, and episodic Reward-Weighted Regression. We show that the proposed method out-performs them on an empirical benchmark of learning dynamical system motor primitives both in simulation and on a real robot. We apply it in the context of motor learning and show that it can learn a complex Ball-in-a-Cup task on a real Barrett WAM (TM) robot arm.

关键词： Robotics  

摘要： Robotics has become part of the curriculum in almost every engineering school. This is mainly because it is a topic that involves different engineering knowledge bases in a medium that fosters innovation and creativity. The educational value provided by robotics makes it an ideal activity for students to integrate technical knowledge and hard skills as well as soft skills and creativity, thereby meeting several of the criteria of the US Accreditation Board for Engineering and Technology (ABET) in one activity. Robotics is also effective in recruiting and engaging students. Robotics is, though, a very dynamic topic, directly influenced by changes in technology, among other factors. In fact, in the history of robotics education, different themes have emerged and others disappeared, resulting in a continuous challenge for educators to accommodate these themes in their courses without compromising engineering basics. One major and continuous challenge facing educators is how to balance theory and applications in robotics courses. The design and analysis of robotic systems are essential parts of robotics engineering education, while demand is increasingly shifting towards applications and the implementation of these systems. This paper is based on the author's experience in the field. It presents a summary of the methods and benefits of incorporating robotics in engineering education as well as an analysis of the challenges facing educators. It also includes a focused discussion on balancing theory and applications in a robotics course. Experience in teaching a hands-on robotics course is provided as an example of how to handle some of these challenges. The course outcomes include industrial-grade functional robotics systems and confident students ready to take on challenges, from applications to research and development in the field of robotics.

关键词： 电脑制作活动   机器人竞赛   上海市   中小学   赛中   一等奖  

摘要： 2011年7月25日～8月1日，第十二届全国中小学电脑制作活动、电脑机器人竞赛在济南举行。上海选手在竞赛中勇创佳绩，获机器人竞赛一等奖1名，二等奖和三等奖各2名；获电脑制作类作品活动一等奖4名，二等奖3名，三等奖10名；上海市获最佳组织奖。

关键词： 机器人学   iPad   咖啡   操控   力学研究所   航天中心   滚轮  

摘要： 据外媒报道，德国航空航天中心机器人学和力学研究所最新研发了一款滚轮机器人，不仅有超强的接握能力，而且善于冲咖啡。

关键词： 程序设计教学   能力的培养   学生思维   奥林匹克竞赛   信息技术教学   机器人竞赛   基本技能   思维能力  

摘要： 随着信息学奥林匹克竞赛、机器人竞赛等活动在初中的深入开展,面向初中生的程序设计教学在信息技术教学中所处的地位已越来越重要。程序设计教学不仅会让学生掌握程序设计的基本知识和基本技能,而且还能培养学生的思维能力。因此,在程序设计教学中必须更新观念、开拓思路,

关键词： CPN神经网络   网格计算   仿人机器人   可持续学习能力  

摘要： 在对CPN神经网络基本原理进行研究的基础上,用一个CPN网络模拟仿人机器人学习推理能力的例子,并分析了其在网格计算平台下实现的可能性和可持续学习能力,为进一步研究仿人机器人脑行为提供了可能。

关键词： 单腿跳跃机器人   动力学建模   连续状态   冲击时刻  

摘要： 基于SILP模型,建立了新的单腿跳跃机器人模型,并分别对模型的支撑相、飞行相两个连续运动状态,以及着地瞬间、起飞瞬间两个冲击运动时刻进行建模.通过分析比较,结合数值方法验证了建模的正确性.

关键词： 电脑制作活动   中小学生   机器人竞赛   应届高中毕业生   上海   赛中   竞赛活动   信息技术  

摘要： 2011年7月25日，第十二届全国中小学电脑制作活动、电脑机器人竞赛在山东省济南一中举行。全国中小学电脑制作活动是唯一纳人高考保送范围的国家级信息技术竞赛活动。凡高中阶段获得全国中小学电脑制作活动一、二等奖的应届高中毕业生，可获得保送资格或最高增加20分投档优先录取的资格。

关键词： 体操机器人   参数辨识   遗传算法   动力学模型  

摘要： 针对加速度驱动型三关节体操机器人,从机理和数据两方面进行了动力学模型分析,首先通过机理分析得到模型的刚体动力学分量和电机驱动分量;然后通过加速度阶跃响应曲线分析得到纯滞后分量,综合这3种分量,确定三关节体操机器人的模型结构,并利用改进的遗传算法对该综合模型进行参数辨识.将辨识后的模型与实际系统进行比较,讨论了产生误差的原因.