cell1_20260524_mohamed-salah_grocery_bagging_cycle_20260524_101239

该数据集是一个机器人操作数据集，使用LeRobot框架创建，采集自starpilot_yam_gripper型机器人。它包含5个完整回合（episodes）、1286帧数据，帧率为30fps，专注于单一任务（总任务数为1）。数据以Parquet格式存储，总数据文件大小为100MB，视频文件大小为200MB。数据特征包括：14维动作向量，用于控制两个机械臂的x、y、z位置、旋转角度和夹爪宽度；32维状态观测向量，包括两个机械臂的编码器角度、IMU加速度和角速度、位姿（位置和四元数）、夹爪开合状态和距离；以及多视角图像观测，包括左腕部0号相机的RGB图像和深度图像、右腕部0号相机的RGB图像和深度图像、基座0号和1号相机的RGB图像（分辨率分别为480x640和768x1024），所有图像均为30fps H.264编码视频格式。此外，数据集还包含时间戳、帧索引、回合索引、总索引和任务索引等元数据，主要用于训练和评估机器人学习模型，特别是在操作任务中。This is a robotic manipulation dataset developed using the LeRobot framework and collected with a starpilot_yam_gripper robot. It contains 5 full episodes and 1286 frames of data at 30 fps, focusing on a single task (total task count: 1). The data is stored in Parquet format, with a total size of 100 MB for the structured dataset and 200 MB for the video files. The dataset features include: a 14-dimensional action vector for controlling the x, y, z positions, rotation angles, and gripper width of the two robotic arms; a 32-dimensional state observation vector covering the encoder angles of the two robotic arms, IMU acceleration and angular velocity, poses (positions and quaternions), gripper opening state and distance; and multi-view image observations. The multi-view images consist of RGB and depth images from the left wrist camera 0, RGB and depth images from the right wrist camera 0, and RGB images from the base camera 0 and 1 (with resolutions of 480x640 and 768x1024 respectively). All image data is formatted as 30 fps H.264 encoded video. Additionally, the dataset includes metadata such as timestamps, frame index, episode index, global index, and task index. It is primarily designed for training and evaluating robotic learning models, particularly for manipulation tasks.