KS325/open-lower-drawer-r2-occ-test-expand

该数据集是使用LeRobot创建的，专为机器人学任务设计。数据集包含一个名为so_follower的机器人类型的数据，总共有4个episodes和2997帧，覆盖1个任务。数据以parquet文件格式存储，并包括视频文件（总大小约200MB），帧率为30fps。数据集的特征包括动作（包含6个关节位置：shoulder_pan.pos、shoulder_lift.pos、elbow_flex.pos、wrist_flex.pos、wrist_roll.pos、gripper.pos）、观察状态（同样包含6个关节位置）、两个摄像头图像（camera1和camera2，分辨率均为480x640，3通道彩色视频）、时间戳、帧索引、episode索引、索引和任务索引。数据集仅包含训练分割（splits: train），适用于机器人控制和视觉任务的研究与开发。

This dataset was created using LeRobot and is designed for robotics tasks. It contains data from a robot of type so_follower, with a total of 4 episodes and 2997 frames, covering 1 task. The data is stored in parquet format and includes video files (total size approximately 200MB) with a frame rate of 30fps. Features of the dataset include action (with 6 joint positions: shoulder_pan.pos, shoulder_lift.pos, elbow_flex.pos, wrist_flex.pos, wrist_roll.pos, gripper.pos), observation state (also with 6 joint positions), two camera images (camera1 and camera2, both with resolution 480x640 and 3-channel color video), timestamp, frame index, episode index, index, and task index. The dataset only includes a training split (splits: train) and is suitable for research and development in robot control and vision tasks.