ARKOMA: The Dataset to Build Neural Networks-Based Inverse Kinematics for NAO Robot Arms

The dataset that we published in this data repository can be used to build neural networks-based inverse kinematics for NAO robot arms. This dataset is named ARKOMA. ARKOMA is an acronym for ARif eKO MAuridhi, all of whom are the creators of this dataset. This dataset contains input-output data pairs. In this dataset, the input data is the end-effector position and orientation in the three-dimensional cartesian space, and the output data is a set of joint angular positions. These joint angular positions are in radians. For further applications, this dataset was split into the training dataset, validation dataset, and testing dataset. The training dataset is used to train neural networks. The validation dataset is utilized to validate neural networks’ performance during the training process. Meanwhile, the testing dataset is employed after the training process to test the performance of trained neural networks. From a set of 10000 data, 60% of data was allocated for the training dataset, 20% of data for the validation dataset, and the other 20% of data for the testing dataset. It should be noted, this dataset is compatible with NAO H25 v3.3 or later.本数据仓库中发布的数据集可用于构建适用于NAO机器人手臂的基于神经网络的逆运动学模型。该数据集命名为ARKOMA，其为创作者Arif eKO Mauridhi姓名的首字母缩写。本数据集包含输入-输出数据配对样本：其中输入数据为三维笛卡尔空间下的末端执行器位姿，输出数据为一组以弧度为单位的关节角位置。为适配后续应用需求，本数据集被划分为训练数据集、验证数据集与测试数据集：训练数据集用于训练神经网络，验证数据集用于在训练过程中验证神经网络的性能，测试数据集则在训练完成后用于检验已训练神经网络的性能。本数据集共包含10000组数据，其中60%分配至训练数据集，20%分配至验证数据集，剩余20%分配至测试数据集。需要说明的是，本数据集与NAO H25 v3.3及后续版本兼容。