Dataset For: "Incremental Semiparametric Inverse Dynamics Learning"
收藏资源简介：
Dataset used in the experimental section of the paper: R. Camoriano, S. Traversaro, L. Rosasco, G. Metta and F. Nori, "<strong>Incremental semiparametric inverse dynamics learning,</strong>" <em>2016 IEEE International Conference on Robotics and Automation (ICRA)</em>, Stockholm, 2016, pp. 544-550.<br> <br> doi: 10.1109/ICRA.2016.7487177<br> <br> Abstract: This paper presents a novel approach for incremental semiparametric inverse dynamics learning. In particular, we consider the mixture of two approaches: Parametric modeling based on rigid body dynamics equations and nonparametric modeling based on incremental kernel methods, with no prior information on the mechanical properties of the system. The result is an incremental semiparametric approach, leveraging the advantages of both the parametric and nonparametric models. We validate the proposed technique learning the dynamics of one arm of the iCub humanoid robot.<br> <br> URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7487177&isnumber=7487087<br> <strong>Description</strong> The file "iCubDyn_2.0.mat" contains data collected from the right arm of the iCub humanoid robot, considering as input the positions, velocities and accelerations of the 3 shoulder joints and of the elbow joint, and as outputs the 3 force and 3 torque components measured by the six-axis F/T sensor in-built in the upper arm. The dataset is collected at 10Hz at as the end-effector tracks circumferences with 10cm radius on the transverse (XY) and sagittal (XZ) planes (For more information on the iCub reference frames, see [4]) at approximately 0.6 m/s. The total number of points for each dataset is 10000, corresponding to approximately 17 minutes of continuous operation. Trajectories are generated by means of the Cartesian Controller presented in [5]. Input (X) columns 1-4: Joint (3 shoulder joints + 1 elbow joint) positions<br> columns 5-8: Joint (3 shoulder joints + 1 elbow joint) velocities<br> columns 9-12: Joint (3 shoulder joints + 1 elbow joint) accelerations Output (Y) Columns 1-3: Measured forces (N) along the X, Y, Z axes by the force-torque (F/T) sensor placed in the upper arm<br> Columns 4-6: Measured torques (N*m) along the X, Y, Z axes by the force-torque (F/T) sensor placed in the upper arm <strong>Preprocessing</strong><br> <br> - Velocities and accelerations are computed by an Adaptive Window Polynomial Fitting Estimator, implemented through a least-squares based algorithm on a adpative window (see [2], [3]). Velocity estimation max window size: 16. Acceleration estimation max window size: 25.<br> - Positions, velocities and accelerations are recorded at 9Hz and oversampled to 20 Hz via cubic spline interpolation.<br> - Forces and torques are directly recorded at 20Hz. This dataset was used in [1] for experimental purposes. See section IV therein for further details. For more information, please contact:<br> Raffaello Camoriano - raffaello.camoriano@iit.it<br> Silvio Traversaro - silvio.traversaro@iit.it <strong>References</strong><br> <br> [1] Camoriano, Raffaello; Traversaro, Silvio; Rosasco, Lorenzo; Metta, Giorgio; Nori, Francesco, "Incremental Semiparametric Inverse Dynamics Learning", eprint arXiv:1601.04549, 01/2016<br> [2] F. Janabi-Sharifi ; Dept. of Mech. Eng., Ryerson Polytech. Univ., Toronto, Ont., Canada ; V. Hayward ; C. -S. J. Chen, "Discrete-time adaptive windowing for velocity estimation", IEEE Transactions on Control Systems Technology, 1003 - 1009, Vol. 8, Issue 6, Nov 2000<br> [3] https://github.com/robotology/icub-main/blob/master/src/libraries/ctrlLib/include/iCub/ctrl/adaptWinPolyEstimator.h<br> [4] http://wiki.icub.org/wiki/ICubForwardKinematics<br> [5] U. Pattacini; F. Nori; L. Natale; G. Metta; and G. Sandini; “An experimental evaluation of a novel minimum-jerk cartesian controller for humanoid robots,” in Intelligent Robots and Systems (IROS), 2010 IEEE/RSJ International Conference on, Oct 2010, pp. 1668–1674.
本论文实验部分所用数据集： R. Camoriano、S. Traversaro、L. Rosasco、G. Metta与F. Nori，《增量半参数逆动力学学习》，发表于2016年IEEE国际机器人与自动化会议（ICRA），斯德哥尔摩，2016年，第544-550页。 doi: 10.1109/ICRA.2016.7487177 摘要：本文提出一种全新的增量半参数逆动力学学习方法。具体而言，我们将两种建模思路相结合：基于刚体动力学方程的参数化建模，以及无需系统机械特性先验知识、基于增量核方法的非参数化建模。最终得到的增量半参数方法可同时兼顾参数化模型与非参数化模型的优势。我们通过学习iCub人形机器人单臂的动力学特性，对所提技术进行了验证。 URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7487177&isnumber=7487087 描述 文件"iCubDyn_2.0.mat"包含从iCub人形机器人右臂采集的数据：输入为3个肩关节与1个肘关节的位置、速度与加速度，输出为上臂内置六轴力扭矩（F/T）传感器测得的3个力分量与3个扭矩分量。 本数据集以10Hz采样率采集，此时机械臂末端执行器以约0.6 m/s的速度，在横向（XY）与矢状（XZ）平面内沿半径10cm的圆周运动（关于iCub参考坐标系的更多信息，请参见文献[4]）。每个数据集共包含10000个数据点，对应约17分钟的连续运行时长。运动轨迹通过文献[5]中提出的笛卡尔控制器生成。 输入（X） 第1-4列：3个肩关节与1个肘关节的关节位置 第5-8列：3个肩关节与1个肘关节的关节速度 第9-12列：3个肩关节与1个肘关节的关节加速度 输出（Y） 第1-3列：上臂内置力扭矩（F/T）传感器沿X、Y、Z轴测得的力（单位：牛，N） 第4-6列：上臂内置力扭矩（F/T）传感器沿X、Y、Z轴测得的扭矩（单位：牛·米，N·m） 数据预处理 - 速度与加速度通过自适应窗口多项式拟合估计器计算得到，该估计器基于最小二乘算法在自适应窗口上实现（参见文献[2]、[3]）。速度估计的最大窗口尺寸为16，加速度估计的最大窗口尺寸为25。 - 位置、速度与加速度以9Hz采样率记录，并通过三次样条插值上采样至20Hz。 - 力与扭矩数据直接以20Hz采样率记录。 本数据集已在文献[1]中用于实验研究，更多细节请参见该文献的第IV部分。 如需更多信息，请联系： Raffaello Camoriano - raffaello.camoriano@iit.it Silvio Traversaro - silvio.traversaro@iit.it 参考文献 [1] Camoriano, Raffaello; Traversaro, Silvio; Rosasco, Lorenzo; Metta, Giorgio; Nori, Francesco，《增量半参数逆动力学学习》，arXiv预印本：1601.04549，2016年1月 [2] F. Janabi-Sharifi（加拿大多伦多瑞尔森理工大学机械工程系）；V. Hayward；C.-S.J. Chen，《用于速度估计的离散时间自适应窗口方法》，IEEE控制系统技术汇刊，第8卷第6期，1003-1009页，2000年11月 [3] https://github.com/robotology/icub-main/blob/master/src/libraries/ctrlLib/include/iCub/ctrl/adaptWinPolyEstimator.h [4] http://wiki.icub.org/wiki/ICubForwardKinematics [5] U. Pattacini、F. Nori、L. Natale、G. Metta与G. Sandini，《人形机器人新型最小加加速度笛卡尔控制器的实验评估》，发表于2010年IEEE/RSJ国际智能机器人与系统会议（IROS），2010年10月，第1668-1674页
