关键词： Robot dancing   Robot learning   Robot adaptation   Robot interaction with humans  

摘要： In this paper, we investigated an approach for robots to learn to adapt dance actions to human's preferences through interaction and feedback. Human's preferences were extracted by analysing the common action patterns with positive or negative feedback from the human during robot dancing. By using a buffering technique to store the dance actions before a feedback, each individual's preferences can be extracted even when a reward is received late. The extracted preferred dance actions from different people were then combined to generate improved dance sequences, i.e. performing more of what was preferred and less of that was not preferred. Together with Softmax action-selection method, the Sarsa reinforcement learning algorithm was used as the underlining learning algorithm and to effectively control the trade-off between exploitation of the learnt dance skills and exploration of new dance actions. The results showed that the robot learnt, using interactive reinforcement learning, the preferences of human partners, and the dance improved with the extracted preferences from more human partners.

关键词： Swarm robotics   Foraging   Self-organization   Task allocation   Swarm intelligence   Multi-agent systems  

摘要： In this article we present a self-organized method for allocating the individuals of a robot swarm to tasks that are sequentially interdependent. Tasks that are sequentially interdependent are common in natural and artificial systems. The proposed method does neither rely on global knowledge nor centralized components. Moreover, it does not require the robots to communicate. The method is based on the delay experienced by the robots working on one subtask when waiting for input from another subtask. We explore the capabilities of the method in different simulated environments. Additionally, we evaluate the method in a proof-of-concept experiment using real robots. We show that the method allows a swarm to reach a near-optimal allocation in the studied environments, can easily be transferred to a real robot setting, and is adaptive to changes in the properties of the tasks such as their duration. Finally, we show that the ideal setting of the parameters of the method does not depend on the properties of the environment.

关键词： ROBOTS   ALGORITHMS   ROBOT motion  

摘要： The article introduces topics within the issue including the coverage of central problems in algorithmic robotics such as aspects of singlerobot and multi-robot motion planning, the collision-free motion planning, and the results for versions of minimum constraint removal (MCR) problem.

关键词： TELEPRESENCE   ROBOTS -- Evaluation  

摘要： The article evaluates the Double telepresence robot from Double Robotics.

关键词： Complications   Endometrial cancer   Laparoscopy   Outcomes   Robotics   Surgery  

摘要： Study Objective: To compare the rates of intraoperative and postoperative complications of robotic surgery and laparoscopy in the surgical treatment of endometrial cancer. Design: Unicentric retrospective study (Canadian Task Force classification II-2). Setting: Tertiary teaching hospital. Patients: The study was performed from January 2002 to December 2011 and included patients with endometrial cancer who underwent laparoscopic or robotically assisted laparoscopic surgical treatment. Data collected included preoperative data, tumor characteristics, intraoperative data (route of surgery, surgical procedures, and complications), and postoperative data (early and late complications according to the Clavien-Dindo classification, and length of hospital stay). Morbidity was compared between the 2 groups. Measurements and Main Results: The study included 146 patients, of whom 106 underwent laparoscopy and 40 underwent robotically assisted surgery. The 2 groups were comparable in terms of demographic and preoperative data. Intraoperative complications occurred in 9.4% of patients who underwent laparoscopy and in none who underwent robotically assisted surgery (p = .06). There was no difference between the 2 groups in terms of postoperative events. Conclusion: Robotically assisted surgery is not associated with a significant difference in intraoperative and postoperative complications, even when there were no intraoperative complications of robotically assisted surgery. (C) 2014 AAGL. All rights reserved.

关键词： Neuro-interface   Neural network   Non-holonomic mobile robot   On-line feedback-error learning   Agricultural robot  

摘要： The present study represents agricultural applications of non-holonomic mobile robots. Agricultural robots are significantly affected by various disturbances such as a loading capacity and modeling errors of robots. Abundant studies of mobile robots using online learning have investigated real-time elimination of control errors that are associated to inaccurate modeling of robots and controls of disturbance effects by online learning using neural network. However, a certain problem from errors of online learning may occur in case of the robot that is located on out of tracking path. The above problem may be resulted in the difference by control errors occurring between desired values and current values. Therefore, stepwise optimization of robot control with desired values should be necessary. Online learning for agricultural mobile robots is possibly performed with accurate calculation of control errors using the stepwise optimization of desired values as a standard. In summary, the present study demonstrates a reference robot is used to calculate accurate control errors for non-holomic mobile robot that is driven by pulse. The control error of the non-holonomic mobile robot through online feedback-error learning is almost 1.3% in agricultural application.

关键词： computational reflection   generative programming   robotics framework   dynamic languages   Python   Java Scripting API  

摘要： SUMMARY The development of service robots has gained more attention over the last years. Advanced robots have to cope with many different situations emerging at runtime, while executing complex tasks. They should be programmed as dynamically adaptive systems, capable of adapting themselves to the execution environment, including the computing, user, and physical environment. Recently, dynamic languages are becoming widely used because of the high runtime adaptability they offer. Therefore, we have analyzed the suitability of these languages to implement robotic systems with high runtime adaptability requirements, using Python as case study because of its maturity. To evaluate their suitability, we have implemented a reflective robotics framework that can be programmed in both Java and any dynamic language supported by the standard Java Scripting API. An example scenario has been developed using Python to show how its distinguishing meta-programming features have facilitated the development of runtime-adaptable robotics services. Copyright © 2012 John Wiley & Sons, Ltd. [PUBLICATION ABSTRACT]

关键词： 6R焊接机器人   轨迹规划   运动学   动力学  

摘要： 焊接作为现代制造工艺中一门非常重要的工艺技术，在机械制造领域中得到了广泛的应用，但是由于其工作时候产生的热辐射以及一些有害气体对人体的危害是比较大的，为了改善操作工人的劳动强度，提高工作效率，由此诞生了智能焊接装备—焊接机器人。本文是在广西科技厅的项目“基于机器人的车辆零部件智能焊接系统”的支撑下，针对仪表板支架焊接机器人，以日本DAI HEN生产的FD-350焊接机器人为研究对象，进行了如下的研究工作： 首先，介绍了焊接机器人学中的关于空间坐标系的旋转变换理论即D-H法。以D-H法对FD-350焊接机器人本体各连杆之间进行运动学分析，建立了运动学方程，然后运用矩阵求逆对运动学方程求解，运动学方程的求解是为了机器人的轨迹规划。 接着运用机械系统动力学中的拉格朗日方程建立了FD-350焊接机器人的动力学方程，即进行动力学分析。采用了在三维模型软件Pro/E上构建焊接机器人的实体模型，并将其导入运动学与动力学软件ADAMS/View中，在该软件中在作动力学仿真前对FD-350焊接机器人模型进行了构件重命名、给予材料、验证模型等前处理工作，最后在焊接机器人的末端操作器焊枪施加一个运动路线，进行动力学仿真，得到每个关节的位移、速度、加速度、力矩曲线图，验证动力学模型的正确性。

关键词： 丝网印刷油墨   移送机器人   负载转矩   动力学方程  

摘要： 近年来,工业机器人的发展十分迅速,在各个领域被广泛应用。本课题应企业要求,设计了一种四自由度移送机器人机构,该机器人作为丝网印刷生产线上的移送辅助设备,用于移送盛有印刷油墨的容器。然而该移送机器人在运动的过程中出现关节驱动力矩不足,并且,由于刚度问题,该机器人在运动过程中发生明显的振动和颤抖。因此,本文对该丝网印刷油墨移送机器人进行分析与研究。　　本课题完成的主要内容如下:　　(1)通过Pro/E建立了此丝网印刷油墨移送机器人的三维模型,计算了机器人在典型位置运动过程中肩关节和肘关节处的动态负载转矩,并选用了合适的驱动电机。　　(2)用D-H法对该机器人进行运动学分析,求解出机器人的末端执行器(手掌)相对于参考坐标系(肩关节处)的位姿矩阵,并得出手掌末端在参考坐标系下的速度、加速度解析式。　　(3)通过有限元方法建立了机器人的动力学模型,经过Matlab程序编程计算,得出丝网印刷油墨移送机器人的动力学方程表达式。　　(4)通过有限元仿真软件ANSYS对移送机器人的整机进行动力学计算仿真分析,得出机器人前七阶模态固有频率和振型云图,并从振型图中分析了在每阶固有频率下机器人的振动情况,指出机器人的刚度薄弱环芾。　　(5)用实验模态分析的方法对所研究的丝网印刷油墨移送机器人进行了动力学实验分析,得出了移送机器人整机前七阶的固有频率及振型,并对比有限元仿真与实验的分析结果,验证了有限元计算机仿真方法的可行性与正确性,然后确定出移送机器人的刚度薄弱环节部位,最后给出优化建议,并通过仿真证明了优化结果的合理性。

关键词： 绳牵引并联机器人   强迫振荡   动力学   机电耦合系统   控制  

摘要： 为了实现对低速风洞中飞行器模型的5种单自由度强迫振荡运动的控制，论文采用理论分析和实验研究相结合的方法，展开绳牵引并联机器人系统的动力学和飞行器模型的运动控制研究，取得了一些有意义的结果和结论，如下： 首先，对用于低速风洞强迫振荡实验的绳牵引并联机器人的机构系统的工作原理进行说明，采用局部坐标系和全局坐标系描述该机构系统的构型参数关系;在此基础之上，分析了该机构系统的运动学问题，为进行系统动力学分析做准备。由于绳索的弹性对驱动控制力和飞行器位姿不可忽略，本文将绳索视为无阻尼线性弹簧。为了满足强迫振荡试验的频率要求，通过对绳牵引并联机器人系统的机构系统进行振动特性分析，研究机构系统的固有频率，以避免共振，得到满足强迫振荡试验要求的绳索的刚度参数，为实验样机的绳索参数的选择提供理论依据。 其次，对绳牵引并联机器人机械系统进行动力学分析，该系统是一个复杂的非线性系统，求解困难，于是采用专业的多体动力学软件ADAMS建立绳牵引并联机器人的机械系统动力学模型，首次利用ADAMS软件建立以线性弹簧理论为基础的绳索模型，对该机器人机构系统进行刚柔耦合多体动力学建模。采用ADAMS软件进行动力学仿真时，飞行器模型能够基本实现期望的振荡运动，但是运动轨迹存在明显的波动和滞后。 再次，为了实现对低速风洞中进行飞行器模型强迫振荡运动的精确控制，交流伺服驱动系统对末端运动控制效果的影响不能忽略，建立了该机器人电机控制系统模型，并提出了基于永磁同步电机矢量控制的PI控制策略。由于绳牵引并联机器人动力学系统是一个高度耦合的、本质非线性系统;将基于ADAMS软件所建立的机械系统与基于MATLAB/Simulink建立的电机驱动控制模型联合起来构成机电耦合系统，再采用MATLAB/Simulink建立基于PI控制策略的机电耦合系统的控制仿真模型并进行仿真研究;控制仿真结果表明，绞盘转角能够较好地跟随期望的角位置指令，飞行器模型的运动轨迹接近期望轨迹，取得了良好的仿真结果。 最后，搭建了该绳牵引并联机器人的实验样机，由于实验条件的限制，仅采用位置控制模式对该机器人系统进行运动学级控制研究。实验结果表明飞行器模型的实际轨迹与期望轨迹存在一定的差距;并对该误差进行分析，为后续的改进工作指明了方向，具有一定的实际意义。