KS325/close-upper-drawer-r2-emp-train

该数据集是一个机器人学数据集，专注于关闭上层抽屉任务（具体为close-upper-drawer-r2-emp-train），使用LeRobot框架创建。数据集包含14个完整episodes，总计10210帧，以parquet文件格式存储，总数据文件大小为100MB，视频文件大小为200MB。数据特征包括：动作数据（6维浮点数组，表示机器人关节位置，如肩部平移、肩部提升、肘部弯曲、腕部弯曲、腕部旋转和夹爪位置）；观察状态（同样为6维关节位置）；两个摄像头图像观察（camera1和camera2），每个为480x640分辨率、3通道的30fps视频，使用AV1编解码器；以及元数据如时间戳、帧索引、episode索引等。数据集适用于机器人控制、模仿学习或强化学习任务，旨在模拟真实世界抽屉关闭操作。

This dataset is a robotics dataset focused on the close upper drawer task (specifically close-upper-drawer-r2-emp-train), created using the LeRobot framework. It contains 14 total episodes with 10210 frames, stored in parquet format, with a total data file size of 100MB and video file size of 200MB. Features include: action data (6-dimensional float32 array representing robot joint positions such as shoulder pan, shoulder lift, elbow flex, wrist flex, wrist roll, and gripper positions); observation state (similarly 6-dimensional joint positions); two camera image observations (camera1 and camera2), each as 480x640 resolution, 3-channel videos at 30fps using AV1 codec; and metadata such as timestamp, frame index, episode index, etc. The dataset is suitable for robotics control, imitation learning, or reinforcement learning tasks, aiming to simulate real-world drawer closing operations.