KS325/open-upper-drawer-r2-emp-val-spare

该数据集是一个机器人控制数据集，使用LeRobot工具创建。它包含4个episodes，总计2974个frames，涉及1个任务。数据以parquet格式存储，视频以mp4格式存储。数据集的特征包括：动作（action），包含6个浮点数值，表示机器人的关节位置（如肩部平移、肩部提升、肘部弯曲、腕部弯曲、腕部旋转和夹爪位置）；观测状态（observation.state），同样包含6个浮点数值，表示机器人的当前关节位置；两个摄像头图像（observation.images.camera1和camera2），均为480x640分辨率的RGB视频，帧率为30fps；以及时间戳、帧索引、episode索引、索引和任务索引等元数据。该数据集适用于机器人学习和控制任务，如模仿学习或强化学习。

This dataset is a robotics control dataset created using the LeRobot tool. It contains 4 episodes, totaling 2974 frames, and involves 1 task. The data is stored in parquet format, with videos in mp4 format. 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, gripper); observation.state, also with 6 float values indicating current joint positions; two camera images (observation.images.camera1 and camera2), both RGB videos at 480x640 resolution with 30 fps frame rate; and metadata such as timestamp, frame index, episode index, index, and task index. This dataset is suitable for robotics learning and control tasks, such as imitation learning or reinforcement learning.