green_block_in_cup_20260530_140450

该数据集是一个机器人学数据集，使用LeRobot工具创建，包含90个总片段和41910个总帧。数据以parquet格式存储，视频文件为mp4格式。特征包括动作和观察：动作和状态观察均包含6个浮点数值，分别对应机器人的关节位置（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）。观察部分还包括两个视角的图像：前视和腕部图像，分辨率为480x640，3通道，帧率为30fps。机器人类型为so_follower，数据集主要用于训练和评估机器人控制任务。This dataset is a robotics dataset created using the LeRobot tool. It contains 90 total episodes and 41910 total frames, with data stored in parquet format and video files in mp4 format. The features include action and observation: both action and state observation consist of 6 floating-point values corresponding to the robots joint positions (shoulder translation, shoulder lift, elbow bend, wrist bend, wrist roll, and gripper position). Observations also include two perspective images: front and wrist views, with a resolution of 480x640, 3 channels, and a frame rate of 30fps. The robot type is so_follower, and the dataset is primarily used for training and evaluating robot control tasks.