关键词： Swarm robotics   Search tasks   Benchmark   Performance analysis  

摘要： This paper presents a survey on multi-robot search inspired by swarm intelligence by further classifying and discussing the theoretical advantages and disadvantages of the existing studies. Subsequently, the most attractive techniques are evaluated and compared by highlighting their most relevant features. This is motivated by the gradual growth of swarm robotics solutions in situations where conventional search cannot find a satisfactory solution. For instance, exhaustive multi-robot search techniques, such as sweeping the environment, allow for a better avoidance of local solutions but require too much time to find the optimal one. Moreover, such techniques tend to fail in finding targets within dynamic and unstructured environments. This paper presents experiments conducted to benchmark five state-of-the-art algorithms for cooperative exploration tasks. The simulated experimental results show the superiority of the previously presented Robotic Darwinian Particle Swarm Optimization (RDPSO), evidencing that sociobiological inspiration is useful to meet the challenges of robotic applications that can be described as optimization problems (e.g., search and rescue). Moreover, the RDPSO is further compared with the best performing algorithms within a population of 14 e-pucks. It is observed that the RDPSO algorithm converges to the optimal solution faster and more accurately than the other approaches without significantly increasing the computational demand, memory and communication complexity. (C) 2013 Elsevier B.V. All rights reserved.

摘要： The article evaluates the Integrated Vision smart camera system from ABB Robotics, a supplier of industrial robots.

关键词： ROBOTS   ROBOTICS   AUTOMATION   MAINTENANCE   INDUSTRIAL technicians  

摘要： The article offers information on the role of robots and robotics technician that install, service, maintain, troubleshoot, and repair robots and automated production systems. It discusses skills and characteristics of robotics various facts which includes good mechanical and electrical aptitude, good eyesight and color vision techs must inspect and work on small, delicate parts and ability to work without close supervision.

关键词： 10   10.4   RL   VATS   VATS lobectomy   VL   robotic lobectomy   video-assisted thoracic surgery  

摘要： Objectives: To determine if there are advantages to transitioning to robotics by a surgeon who is already proficient in performing video-assisted thoracic surgical (VATS) lobectomy. Methods: A single surgeon proficient in VATS lobectomy initiated a robotic lobectomy program, and a retrospective review was conducted of his patients undergoing minimally invasive lobectomy (robotics or VATS) for lung cancer between 2011 and 2012. Data collected included patient/tumor characteristics, morbidity, mortality, operative times, and length of hospital stay. Results: Over a 24-month period, a total of 69 patients underwent minimally invasive lobectomy (35 robotic, 34 VATS). Patients in each group were similar in age and clinical stage. Robotic upper lobectomy operative times were longer than VATS (172 vs 134 minutes;P - .001), with no significant difference in lower lobectomies noted (140 vs 123 minutes;P = .1). Median length of stay was 3 days in both groups, and the median number of lymph nodes harvested was 18 (robotic) versus 16 (VATS;P = .42). Morbidity and mortality for robotic versus VATS were 11% versus 18% (P = .46) and 0% versus 3% (P = .49), respectively. Conclusions: There does not seem to be a significant advantage for an established VATS lobectomy surgeon to transition to robotics based on clinical outcomes. The learning curve for robotic upper lobectomies seems to be more significant than that for lower lobectomies.

关键词： development   robotics   intrinsic motivation   staged learning   constraints  

摘要： A major challenge in robotics is the ability to learn, from novel experiences, new behavior that is useful for achieving new goals and skills. Autonomous systems must be able to learn solely through the environment, thus ruling out a priori task knowledge, tuning, extensive training, or other forms of pre-programming. Learning must also be cumulative and incremental, as complex skills are built on top of primitive skills. Additionally, it must be driven by intrinsic motivation because formative experience is gained through autonomous activity, even in the absence of extrinsic goals or tasks. This paper presents an approach to these issues through robotic implementations inspired by the learning behavior of human infants. We describe an approach to developmental learning and present results from a demonstration of longitudinal development on an iCub humanoid robot. The results cover the rapid emergence of staged behavior, the role of constraints in development, the effect of bootstrapping between stages, and the use of a schema memory of experiential fragments in learning new skills. The context is a longitudinal experiment in which the robot advanced from uncontrolled motor babbling to skilled hand/eye integrated reaching and basic manipulation of objects. This approach offers promise for further fast and effective sensory-motor learning techniques for robotic learning.

关键词： macroscopic mathematical model   swarm robotic system   resource location   68T01   68T40   68T05  

摘要： In recent years, there has been a growing interest in resource location in unknown environments for robotic systems, which are composed of multiple simple robots rather than one highly capable robot [M. Sempere, F. Aznar, M. Pujol, and R. Rizo, On cooperative swarm foraging for simple, non explicitly connected, agents, 2010]. This tradeoff reduces the design and hardware complexity of the robots and removes single point failures, but adds complexity in algorithm design. The challenge is to programme a swarm of simple robots, with minimal intercommunication and individual capability, to perform a useful task as a group. This paper is focused on finding the highest intensity area of a radiofrequency (RF) signal in urban environments. These signals are usually more intense near the city centre and its proximity, since in these zones the risk of signal saturation is high. RF radiation (RFR) is boosted or blocked mainly depending on orography or building structures. RF providers need to supply enough coverage, setting up different antennas to be able to provide a minimum quality of service. We will define a micro/macroscopic mathematical model to efficiently study a swarm robotic system, predict their long-term behaviour and gain insight into the system design. The macroscopic model will be obtained from Rate Equations, describing the dynamics of the swarm collective behaviour. In our experimental section, the Campus of the University of Alicante will be used to simulate our model. Three RFR antennas will be taken into account, one inside our Campus and the other two in its perimeter. Several tests, that show the convergence of the swarm towards the RFR, will be presented. In addition, the obtained RFR maps and the macroscopic behaviour of the swarm will be discussed. View full text

关键词： 冗余驱动   并联机器人动力学建模驱动力协调分配  

摘要： 冗余驱动可有效降低并联机构的最大瞬时驱动力,提高其承载能力,然而驱动力协调分配不当或冗余驱动力控制误差过大不仅使上述功能无法实现,甚至产生过大内力而对机构造成破坏。为此,以冗余驱动6PUS-UPU并联机器人为例,对驱动分支、约束分支和动平台的速度、加速度进行分析,引入偏速度和偏角速度,使用Kane方法建立系统的动力学方程。提出以最小化最大瞬时驱动力为目标,使用加权最小二乘法对驱动力进行协调分配,通过数值算例获得给定运动轨迹情况下各分支驱动力。采用DSP控制器和运动控制器相结合的方式提高驱动力协调分配的实时性,实现对冗余驱动力的控制。实验结果表明:在冗余驱动力作用下,瞬时最大驱动力明显降低,且驱动力分配更加均衡,证明了所提出的驱动力协调分配方法和冗余驱动力控制策略的有效性。

关键词： 机器人竞赛   比赛活动   创新能力   创意   学生   培养   电子信息技术   综合设计  

摘要： 机器人创意比赛是每年一度的中国青少年机器人竞赛的重要项目。参赛学生要花费6个月左右的时间，在课题导师或教练员的指导下，在学校．家庭、校外机器人工作室或科技实验室，以个人或小组的方式，进行机器人的创意。设计、编程与制作，最后提交机器人实体作品参加比赛活动。机器人创意比赛对于培养学生学习与综合运用机器人技术、电子信息技术、工程技术，激发创新思维潜能，提高综合设计和制作的能力极为有益。本文撰写背景是基于2013年主题为“社区机器人”的创意比赛，我校学生根据主题选取的研究内容是浇花机器人的设计与实现。

关键词： 大型人形機器人   機器學習   認知心理學  

摘要： 本论文旨在设计一演算法，其允许人形机器人模仿人类思考行为以用於学习投球姿态，并实际应用於FIRA国际机器人竞赛之篮球比赛；本系统主要由影像处理、学习演算法与大型人形机器人之硬体架构等构成。其中，影像处理与学习行为均采用笔记型电脑为中央运算模组；在影像处理部分，除连接一台网路摄影机做为视觉感知器，亦於篮框上方及旁侧装置两台网路摄影机加以监测。为了辨识各式的物体特徵及追踪特定目标，我们应用快速且简易的搜寻与追踪法加以实现。接着，根据2002年诺贝尔经济学奖得主丹尼尔‧卡内曼所着“Thinking, Fast and Slow”书中之概念设计一创新的学习演算法，其核心思想是将人类的认知心理学分为两种模式：快思与慢想，快思系统倾向直觉式思考，而慢想系统属逻辑式思考；另外，此演算法亦将书中所提之锚点效应与峰终定律等概念加诸於设计与应用，目的为使机器人得以藉学习过程获得经验曲线，并完成FIRA国际机器人竞赛之篮球竞赛之任务。最後经实验结果可充分展现此仿生的学习方法应用於机器人上是合理且效能优越的。

关键词： 工业机器人   冗余自由度   位姿分离法   运动控制   动力学优化  

摘要： 随着工业技术的快速发展，机器人的适用范围越来越大，对它的各种指标要求也越来越严格，对操作环境和任务要求更加复杂化，因此工业机器人越来越引起学者们的注意。随着工作任务复杂程度的提高，普通的非冗余自由度机器人已经无法满足工作空间的避障要求。\n 冗余度机器人，简单的说就是在实际使用过程中，机器人的关节自由度大于完成特定的任务所需要的自由度数。在三维欧式空间中，任意物体需要三个位置参数和三个姿态参数才能确定位姿，因此，非冗余情况下，最多只需要六个自由度就足够了。冗余的自由度可以改善机器人各方面的特征，使其具有更好的灵活性、更大的作业空间、更优的躲避障碍能力等。\n 首先，根据机器人实物参数建立数学模型。依据机器人运动学的理论，采用D-H法建立机器人的数学模型、连杆坐标系及相应的杆件参数表。\n 其次，以本实验中心自主研制的七自由度工业机器人作为研究对象，在建立的模型基础上对其运动学进行研究，基于梯度投影法求解冗余自由度运动学逆解，进一步研究七自由度机器人运动控制方法，以位姿分离法形成七自由度逆运动学求解的新方法，简化计算量，便于实时控制。并在动力学层面上对其进行优化。\n 最后，对前面进行的研究进行仿真，来验证算法的正确性，并利用C++语言设计出内部的算法。为使仿真结果更便于观察，利用QNX设计人机交互界面。进一步研究冗余自由度机器人运动学的研究。