Leobinus/Cup-to-Tray_20260522_133907

该数据集是一个机器人操作数据集，专注于杯子到托盘的搬运任务。它包含63个episodes，总计115382帧数据，采样频率为30fps。数据集记录了机器人（类型为so_follower）的动作和观察状态，动作包括6个关节位置（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），观察状态包括相同的关节位置以及来自腕部和顶部摄像头的图像数据（分辨率为480x640，3通道RGB视频）。数据以parquet格式存储，视频以mp4格式存储，总数据大小约为300MB（数据文件100MB，视频文件200MB）。数据集适用于机器人学习任务，如模仿学习或强化学习，并基于Apache 2.0许可证发布。This dataset is a robotics manipulation dataset focused on a cup-to-tray task. It contains 63 episodes with a total of 115382 frames, sampled at 30fps. The dataset records actions and observation states of a robot (type so_follower), where actions include 6 joint positions (shoulder pan, shoulder lift, elbow flex, wrist flex, wrist roll, and gripper position), and observation states include the same joint positions as well as image data from wrist and top cameras (resolution 480x640, 3-channel RGB videos). Data is stored in parquet format, videos in mp4 format, with a total size of approximately 300MB (100MB for data files and 200MB for video files). The dataset is suitable for robotics learning tasks such as imitation learning or reinforcement learning, and is released under the Apache 2.0 license.