burger-to-plate-320x240-filteredX-filtered

该数据集是一个机器人学数据集，使用LeRobot工具创建。它包含了机器人执行任务时的多模态数据，具体特征包括：动作向量（26维，表示左右手臂的线性和角速度、手部关节控制等）、观察状态（52维，表示左右手臂和手部关节的位置和力矩）、左右图像和用户图像（视频格式，分辨率为320x240，3通道，帧率15fps），以及时间戳、帧索引、episode索引、任务索引等元数据。数据集总共有55个episodes，86277帧，1个任务，数据文件大小为100MB，视频文件大小为200MB，机器人类型为blueberry_ros。数据以parquet文件格式存储，用于机器人学习和控制任务。This is a robotics dataset created using the LeRobot toolkit. It contains multimodal data collected during robot task execution, with specific components including: a 26-dimensional action vector representing linear and angular velocities of the left and right arms, hand joint control commands, etc.; a 52-dimensional observation state representing positions and torques of the left and right arms and hand joints; left, right and user images in video format with a resolution of 320×240, 3 channels and a frame rate of 15 fps; and metadata such as timestamps, frame indices, episode indices and task indices. The dataset comprises 55 episodes and 86277 frames in total, corresponding to 1 single task, with a data file size of 100 MB and a video file size of 200 MB. The robot platform used is blueberry_ros. The data is stored in Parquet file format and is intended for robotics learning and control tasks.