mytest9551
收藏资源简介:
该数据集是一个使用LeRobot创建的机器人学数据集,专门针对so_follower机器人类型。它包含机器人的动作数据,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;观察状态,如关节位置;以及来自webcam和realsense摄像头的图像观察,分辨率为480x640。数据以parquet文件和视频文件格式存储,帧率为30fps,并包括时间戳、帧索引、剧集索引和任务索引等元数据。数据集结构旨在支持机器人控制和学习任务,适用于强化学习和机器人模拟研究。
This dataset is a robotics dataset created using LeRobot, specifically designed for the so_follower robot type. It includes robot action data such as shoulder translation, shoulder lift, elbow bend, wrist bend, wrist rotation, and gripper position; observation states such as joint positions; and image observations from webcam and realsense cameras with a resolution of 480x640. The data is stored in parquet files and video files at a frame rate of 30fps, and includes metadata such as timestamps, frame indices, episode indices, and task indices. The dataset structure supports robot control and learning tasks, making it suitable for reinforcement learning and robotics simulation research.
数据集概述
- 名称:mytest9551(未明确给出)
- 许可证:Apache-2.0
- 任务类别:机器人学(Robotics)
- 标签:LeRobot
- 创建工具:使用 LeRobot 创建
数据集结构
- 元数据文件:
meta/info.json - 数据文件格式:Parquet,路径格式为
data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet - 视频文件格式:MP4,路径格式为
videos/{video_key}/chunk-{chunk_index:03d}/file-{file_index:03d}.mp4 - 代码基础版本:v3.0
- 机器人类型:so_follower
- 总剧集数:0
- 总帧数:0
- 总任务数:0
- 分块大小:1000
- 数据文件大小:约 100 MB
- 视频文件大小:约 200 MB
- 帧率(FPS):30
- 数据集划分(Splits):无
特征(Features)
| 特征名称 | 数据类型 | 形状 | 说明 |
|---|---|---|---|
| action | float32 | [6] | 包含6个动作维度:shoulder_pan.pos, shoulder_lift.pos, elbow_flex.pos, wrist_flex.pos, wrist_roll.pos, gripper.pos |
| observation.state | float32 | [6] | 与action类似的状态观测,包含6个维度 |
| observation.images.webcam | video | [480, 640, 3] | 网络摄像头图像,分辨率480x640,3通道 |
| observation.images.realsense | video | [480, 640, 3] | RealSense相机图像,分辨率480x640,3通道 |
| timestamp | float32 | [1] | 时间戳 |
| frame_index | int64 | [1] | 帧索引 |
| episode_index | int64 | [1] | 剧集索引 |
| index | int64 | [1] | 索引 |
| task_index | int64 | [1] | 任务索引 |
引用信息
- 论文:[需要更多信息]
- BibTeX:[需要更多信息]



