yusenluo9z/orange_cup_expert_w_reward_differential

该数据集是通过LeRobot创建的，主要用于机器人技术领域。数据集包含30个episodes，总计10933帧，数据文件大小为100MB，视频文件大小为200MB，帧率为30fps。数据集的结构包括动作数据、状态观测、图像观测（顶部和侧面视角）、时间戳、帧索引、episode索引、任务索引、奖励、完成标志以及robometer的进度和成功标志。动作和状态观测包含12个自由度，图像观测的分辨率为480x640，3通道。

This dataset was created using LeRobot and is primarily used in the field of robotics. It contains 30 episodes, totaling 10933 frames, with data files size of 100MB and video files size of 200MB, at a frame rate of 30fps. The dataset structure includes action data, state observations, image observations (top and side views), timestamps, frame indices, episode indices, task indices, rewards, done flags, and robometer progress and success flags. The action and state observations include 12 degrees of freedom, and the image observations have a resolution of 480x640 with 3 channels.