put_box_1

该数据集是一个机器人数据集，使用LeRobot工具创建。它包含15个episodes，总共16952帧，帧率为30fps。数据集涉及so_follower机器人类型，数据以parquet和mp4格式存储。特征包括：动作（6维浮点数组，对应肩部平移、肩部升降、肘部弯曲、腕部弯曲、腕部旋转和夹爪位置）、状态观测（6维浮点数组，与动作相同）、图像观测（来自上方和手腕的两个摄像头，分辨率均为480x640，3通道彩色视频），以及时间戳、帧索引、episode索引、索引和任务索引等元数据。数据用于机器人任务，从特征名称推断可能涉及放置盒子任务，但具体任务未明确说明。

This is a robotic dataset developed using the LeRobot toolkit. It includes 15 episodes, totaling 16,952 frames with a frame rate of 30 fps. The dataset targets the so_follower robotic variant, and the data is stored in both Parquet and MP4 formats. The dataset features are as follows: actions (6-dimensional floating-point arrays corresponding to shoulder translation, shoulder lift, elbow flexion, wrist flexion, wrist rotation, and gripper position), state observations (6-dimensional floating-point arrays matching the dimensions of the action features), image observations captured by two cameras (overhead and wrist-mounted, both with a resolution of 480×640 as 3-channel color video), and metadata including timestamps, frame indices, episode indices, indices, and task indices. This dataset is designed for robotic manipulation tasks. Although the specific task is not explicitly stated, it can be inferred from the feature names that it may involve box placement-related tasks.