burger-to-plate-320x240-filteredX

该数据集使用LeRobot创建，是一个机器人演示数据集，专门用于机器人学任务。数据集包含blueberry_ros类型机器人的55个episodes，总计86277帧，涉及1个任务。数据以parquet文件格式存储，视频文件总大小为200MB，帧率为15fps。特征包括动作（26维浮点数，涵盖左右手臂的线性速度、角速度、手指位置和基座控制）、观测状态（55维浮点数，包括关节位置、力矩以及gaze坐标和有效性）、多个图像观测（左、右、用户和用户gaze视角的240x320分辨率RGB视频，编码为av1，无音频），以及时间戳、帧索引、episode索引等元数据。数据集适用于机器人控制、模仿学习或视觉导航等研究。

This dataset is created using LeRobot and is a robot demonstration dataset specifically designed for robotics tasks. It contains 55 episodes of the blueberry_ros type robot, totaling 86,277 frames, and involves 1 task. The data is stored in parquet format, with video files totaling 200MB in size and a frame rate of 15fps. Features include actions (26-dimensional floating-point numbers covering linear velocity, angular velocity, finger positions, and base control for both arms), observation states (55-dimensional floating-point numbers including joint positions, torques, gaze coordinates, and validity), multiple image observations (240x320 resolution RGB videos from left, right, user, and user gaze perspectives, encoded as av1 without audio), and metadata such as timestamps, frame indices, and episode indices. The dataset is suitable for research in robot control, imitation learning, or visual navigation.