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，可用于构建基于神经网络的逆运动学模型，以应用于NAO机器人手臂。该数据集命名为ARKOMA，系由其创建者ARif eKO MAuridhi的首字母缩写而成。此数据集包含输入输出数据对，其中输入数据为三维笛卡尔空间中末端执行器的位置与姿态，而输出数据为一系列关节角位置，其单位为弧度。为便于进一步应用，该数据集被划分为训练集、验证集和测试集。训练集用于神经网络的训练，验证集用于在训练过程中验证神经网络的性能，而测试集则在训练完成后用于测试训练神经网络的性能。在10000组数据中，60%的数据分配给了训练集，20%的数据分配给了验证集，剩余的20%数据分配给了测试集。值得注意的是，此数据集与NAO H25 v3.3或更高版本兼容。