xarm7_ds6
收藏资源简介:
该数据集是一个机器人学数据集,使用LeRobot工具创建。它针对7关节机械臂(xarm7)的操作任务,包含机器人控制相关的数据。数据结构包括动作(action)、观察状态(observation.state),以及来自前部和腕部摄像头的图像观察(observation.images.front和wrist)。动作特征涉及8个维度,包括7个关节的位置和夹爪位置;观察状态特征同样包括8个维度,涉及关节位置和驱动关节位置。图像数据以视频格式存储,分辨率为480x640,帧率为30fps,采用h264编码。数据集总共有1个episode、3帧、1个任务,数据以parquet文件格式组织,并包含时间戳、帧索引、episode索引等元数据。适用于机器人学习、强化学习或控制算法研究。
This dataset is a robotics dataset created using the LeRobot tool. It contains data related to robot control, specifically for manipulation tasks with a 7-joint robotic arm (xarm7). The dataset structure includes actions (action), observation states (observation.state), and image observations from front and wrist cameras (observation.images.front and wrist). The action features involve 8 dimensions, including the positions of 7 joints and the gripper position; the observation state features also include 8 dimensions, covering joint positions and actuated joint positions. The image data is stored in video format with a resolution of 480x640, a frame rate of 30fps, and h264 encoding. The dataset consists of 1 episode, 3 frames, and 1 task, organized in parquet file format, and includes metadata such as timestamps, frame indices, and episode indices. It is suitable for robotics learning, reinforcement learning, or control algorithm research.
数据集概述
- 名称: xarm7_ds6
- 主页: [More Information Needed]
- 许可证: Apache-2.0
- 任务类别: 机器人学 (Robotics)
- 标签: LeRobot
数据集规模
- 总片段数: 1
- 总帧数: 3
- 总任务数: 1
- 帧率: 30 FPS
- 数据文件大小: 100 MB
- 视频文件大小: 200 MB
数据集结构
- 数据路径:
data/*/*.parquet - 数据集划分: 仅训练集,范围为
0:1
特征 (Features)
| 特征名 | 数据类型 | 形状 | 说明 |
|---|---|---|---|
| action | float32 | [8] | 包含7个关节位置和1个夹爪位置 |
| observation.state | float32 | [8] | 包含7个关节位置和1个驱动关节位置 |
| observation.images.front | video | [480, 640, 3] | 前视摄像头视频,H264编码,30 FPS |
| observation.images.wrist | video | [480, 640, 3] | 腕部摄像头视频,H264编码,30 FPS |
| timestamp | float32 | [1] | 时间戳 |
| frame_index | int64 | [1] | 帧索引 |
| episode_index | int64 | [1] | 片段索引 |
| index | int64 | [1] | 数据索引 |
| task_index | int64 | [1] | 任务索引 |
数据来源
- 该数据集使用 LeRobot 创建。
- 可视化工具: Visualize this dataset



