ofekhamama/so101_pick_cube_vision_only_test

该数据集使用LeRobot工具创建，是一个机器人数据集，专门针对so_follower类型机器人。数据集包含2个episodes和606帧数据，覆盖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。数据集的特征包括：动作（action），包含6个浮点数值，代表机器人关节位置（如肩部平移、肩部提升、肘部弯曲、腕部弯曲、腕部滚动和夹爪位置）；观察状态（observation.state），同样包含6个浮点数值，表示机器人关节位置；图像观察（observation.images.top和observation.images.wrist），均为视频数据，分辨率为480x640，3通道，使用av1编解码器，无音频；以及时间戳、帧索引、episode索引、索引和任务索引等元数据。数据集主要用于机器人学习和控制任务。This dataset was created using the LeRobot tool and is a robotics dataset specifically for the so_follower type robot. It contains 2 episodes and 606 frames, covering 1 task. The data is stored in parquet format, with a total data file size of 100MB and video file size of 200MB, at a frame rate of 30fps. The dataset features include: action, consisting of 6 float values representing robot joint positions (e.g., shoulder pan, shoulder lift, elbow flex, wrist flex, wrist roll, and gripper positions); observation state, similarly with 6 float values for joint positions; image observations (observation.images.top and observation.images.wrist), both video data with a resolution of 480x640, 3 channels, using the av1 codec, without audio; and metadata such as timestamp, frame index, episode index, index, and task index. The dataset is primarily intended for robot learning and control tasks.