so101_picking_task_20260724_172228

该数据集是使用LeRobot创建的机器人抓取任务数据集，专为机器人学习设计。数据集包含6个episodes，总计3326帧数据，采样频率为30fps。数据特征包括动作（action）和观测状态（observation.state），均表示机械臂的6个关节位置（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）。观测部分还包括工作空间摄像头图像（observation.images.workspace_cam），分辨率为480x640的RGB视频，编码为av1格式。此外，数据集提供时间戳、帧索引、episode索引、任务索引等信息。机器人类型为so_follower，数据以parquet文件格式存储，总数据大小约100MB，视频文件大小约200MB。数据集适用于训练和评估机器人抓取任务模型。This dataset is a robot grasping task dataset created using LeRobot, specifically designed for robot learning. It contains 6 episodes, totaling 3326 frames of data with a sampling frequency of 30fps. The data features include actions (action) and observation states (observation.state), both representing the 6 joint positions of the robotic arm (such as shoulder translation, shoulder lift, elbow bend, wrist bend, wrist rotation, and gripper position). The observation part also includes workspace camera images (observation.images.workspace_cam), which are RGB videos with a resolution of 480x640, encoded in av1 format. Additionally, the dataset provides timestamps, frame indices, episode indices, task indices, and other information. The robot type is so_follower, and the data is stored in parquet file format, with a total data size of approximately 100MB and video file size of about 200MB. The dataset is suitable for training and evaluating models for robot grasping tasks.