KS325/close-lower-drawer-r2-occ-train

该数据集是一个机器人学数据集，专注于关闭下层抽屉的任务，使用LeRobot框架创建。数据集包含14个完整的情节（episodes），总计10280帧数据。它记录了so_follower类型机器人的操作，数据特征包括动作（如肩部平移、肩部提升、肘部弯曲、手腕弯曲、手腕滚动和夹爪位置）、观察状态（关节位置）、以及来自两个摄像头（camera1和camera2）的视频观测，每个视频分辨率为480x640，帧率为30fps，格式为MP4（使用av1编解码器）。数据集以parquet文件格式存储，并包含时间戳、帧索引、情节索引和任务索引等元数据。数据总大小约为100MB（数据文件）和200MB（视频文件），适用于机器人控制、模仿学习或强化学习研究。

This dataset is a robotics dataset focused on the task of closing a lower drawer, created using the LeRobot framework. It contains 14 complete episodes, totaling 10,280 frames. The data captures operations of a so_follower type robot, with features including actions (such as shoulder pan, shoulder lift, elbow flex, wrist flex, wrist roll, and gripper positions), observation states (joint positions), and video observations from two cameras (camera1 and camera2), each with a resolution of 480x640, a frame rate of 30fps, and in MP4 format (using av1 codec). The dataset is stored in parquet file format and includes metadata such as timestamps, frame indices, episode indices, and task indices. The total data size is approximately 100MB for data files and 200MB for video files, making it suitable for robotics control, imitation learning, or reinforcement learning research.