pick_and_place_block
收藏资源简介:
该数据集是一个机器人操作数据集,由LeRobot项目创建。它包含150个完整的情节,总计48889帧,仅涉及一个任务。数据以Parquet文件格式存储,总数据文件大小为100 MB,视频文件大小为200 MB,帧率为30 fps。数据集仅包含训练集划分。数据特征包括:动作和观测状态均为6维浮点数组,对应机器人关节位置(如肩部平移、肩部抬升、肘部弯曲、腕部弯曲、腕部旋转、夹爪位置);观测图像来自笔记本电脑摄像头,分辨率为480x640,3通道彩色,使用AV1编解码器;还包括时间戳、帧索引、情节索引、任务索引等元数据字段。该数据集适用于机器人学习任务,如模仿学习或强化学习,特别是针对抓取与放置操作场景。
This dataset is a robot manipulation dataset created using the LeRobot project. It contains 150 complete episodes, totaling 48,889 frames, and involves only one task. The data is stored in Parquet format, with a total data file size of 100 MB and a video file size of 200 MB, at a frame rate of 30 fps. The dataset includes only a training set split. Features include: action and observation.state as 6-dimensional float arrays corresponding to robot joint positions (shoulder translation, shoulder lift, elbow bend, wrist bend, wrist rotation, gripper position); observation.images.laptop as video data from a laptop camera with a resolution of 480x640, 3-channel color, using the AV1 codec; along with metadata fields such as timestamp, frame index, episode index, and task index. The dataset is suitable for robotic learning tasks, such as imitation learning or reinforcement learning, particularly for pick-and-place operation scenarios.




