KS325/open-lower-drawer-r2-emp-val-expand

该数据集是一个机器人学数据集，专门用于训练机器人执行打开下层抽屉的任务（任务标识：open-lower-drawer-r2-emp-val）。数据集包含8个完整的情节（episodes），总计5971帧数据，以parquet文件格式存储，并附带MP4格式的视频文件。数据特征包括机器人的动作（如肩部平移、肩部提升、肘部弯曲等6个关节位置）、状态观察（同样为6个关节位置）、来自两个摄像头（camera1和camera2）的图像观察（分辨率480x640，30帧/秒，RGB通道），以及时间戳、帧索引、情节索引等元数据。机器人类型为so_follower，适用于强化学习或模仿学习场景，旨在通过视觉和状态信息学习抽屉开启操作。数据集由LeRobot工具创建，采用Apache 2.0许可证。

This is a robotics dataset specifically developed for training robots to complete the task of opening the lower drawer, with the task identifier: open-lower-drawer-r2-emp-val. The dataset contains 8 full episodes, totaling 5971 frames of data, stored in Parquet file format, and is accompanied by MP4-format video files. The data features include robot actions (6 joint positions such as shoulder translation, shoulder lift, elbow flexion, etc.), state observations (also consisting of 6 joint positions), image observations from two cameras (camera1 and camera2) with a resolution of 480×640, 30 frames per second, and RGB channels, as well as metadata such as timestamps, frame indices, and episode indices. The robot type is so_follower, which is applicable to reinforcement learning or imitation learning scenarios, aiming to enable the robot to learn drawer opening operations through visual and state information. This dataset was created using the LeRobot tool and is released under the Apache 2.0 license.