KS325/open-upper-drawer-r2-occ-test-spare

该数据集是一个机器人学习数据集，使用LeRobot框架创建，专注于机器人任务（具体为so_follower类型机器人）。数据集包含2个episodes、1500帧数据，涉及1个任务。数据以parquet文件格式存储，总数据文件大小为100MB，视频文件大小为200MB，帧率为30fps。特征包括动作（6个浮点值，对应机器人关节位置如肩部平移、肩部提升、肘部弯曲、手腕弯曲、手腕滚动和夹爪位置）、观测状态（与动作相同的6个关节位置）、两个摄像头图像（camera1和camera2，均为480x640分辨率、3通道的RGB视频），以及时间戳、帧索引、episode索引等元数据。数据集主要用于训练或评估机器人控制算法，支持视觉和状态观测。

This dataset is a robotics learning dataset created using the LeRobot framework, focusing on robot tasks (specifically for so_follower type robot). It contains 2 episodes, 1500 frames, and involves 1 task. Data is stored in parquet format, with total data file size of 100MB and video file size of 200MB, at a frame rate of 30fps. Features include actions (6 float values corresponding to robot joint positions such as shoulder pan, shoulder lift, elbow flex, wrist flex, wrist roll, and gripper position), observation states (same 6 joint positions), two camera images (camera1 and camera2, both RGB videos with 480x640 resolution and 3 channels), and metadata such as timestamp, frame index, episode index, etc. The dataset is primarily used for training or evaluating robot control algorithms, supporting visual and state observations.