遇见数据集

Z1_DualArm_PourCoffee_Dataset

收藏
魔搭社区2025-11-07 更新2025-01-11 收录
官方服务:

资源简介:

This dataset was created using [LeRobot](https://github.com/huggingface/lerobot). ## Dataset Description - **Homepage:** [More Information Needed] - **Paper:** [More Information Needed] - **License:** apache-2.0 - **Task Objective:** Operate the coffee machine for brewing: First, insert a coffee capsule into the machine and initiate the brewing process; then place the filled transparent glass cup onto the serving tray. - **Operational Objects:** Transparent glass cup (7cm diameter × 8cm height) + Coffee machine (Purchase link: [【淘宝】假一赔四 https://e.tb.cn/h.60Pyz2E1LCTqd5x?tk=zmX0eJyjayl MF168 「KONMO家用办公室用胶囊咖啡机 小型迷你浓缩意式美式全自动咖啡机」点击链接直接打开 或者 淘宝搜索直接打开]) + Coffee capsules (Purchase link: [【淘宝】假一赔四 https://e.tb.cn/h.60l0WlnO41tjL0F?tk=ytAGeJylaGJ MF278 「隅田川精萃浓缩胶囊大师咖啡胶囊意式美式拿铁espresso10盒100粒」点击链接直接打开 或者 淘宝搜索直接打开]) + Capsule holder (Purchase link: [【淘宝】退货运费险 https://e.tb.cn/h.60PATchT7p44YNX?tk=iJBgeJyQu57 CA381 「可装40粒黑色现货NESPRESSO胶囊不锈钢奢华咖啡架收纳架360度旋转」点击链接直接打开 或者 淘宝搜索直接打开]) + Serving tray (Purchase link: [【淘宝】假一赔四 https://e.tb.cn/h.60VmJKagLVyLW7M?tk=QH70eJykVCR CA381 「新款小麦秸秆盘子塑料托盘家用客厅长方形加厚水果盘茶盘酒店餐盘」点击链接直接打开 或者 淘宝搜索直接打开]) - **Operation Duration:** Each operation takes approximately 40 to 60 seconds. - **Recording Frequency:** 30 Hz. - **Robot Type:** Z1 7-DOF robotic arm with parallel gripper. - **End Effector:** Parallel gripper. - **Dual-Arm Operation:** Yes. - **Image Resolution:** 640x480. - **Camera Positions:** Mount a monocular camera at the end of each robotic arm; position two additional monocular cameras side-by-side at the midpoint between the two arms, 40cm above the work surface. - **Data Content:** • Robot's current state. • Robot's next action. • Current camera view images. - **Robot Initial Posture:** The first robot state in each dataset entry. - **Object Placement:** Position the two robotic arms spaced approximately 60cm apart. Place the coffee machine centrally between the two arms, 35cm vertically from the robotic arm base. Position the water cup and serving tray on the left side of the coffee machine, and arrange the coffee capsules and capsule holder on the right side. ## Dataset Structure [meta/info.json](meta/info.json): ```json { "codebase_version": "v2.0", "robot_type": "Unitree_Z1_Dual", "total_episodes": 331, "total_frames": 443144, "total_tasks": 1, "total_videos": 993, "total_chunks": 1, "chunks_size": 1000, "fps": 30, "splits": { "train": "0:331" }, "data_path": "data/chunk-{episode_chunk:03d}/episode_{episode_index:06d}.parquet", "video_path": "videos/chunk-{episode_chunk:03d}/{video_key}/episode_{episode_index:06d}.mp4", "features": { "observation.state": { "dtype": "float32", "shape": [ 14 ], "names": [ [ "kLeftWaist", "kLeftShoulder", "kLeftElbow", "kLeftForearmRoll", "kLeftWristAngle", "kLeftWristRotate", "kLeftGripper", "kRightWaist", "kRightShoulder", "kRightElbow", "kRightForearmRoll", "kRightWristAngle", "kRightWristRotate", "kRightGripper" ] ] }, "action": { "dtype": "float32", "shape": [ 14 ], "names": [ [ "kLeftWaist", "kLeftShoulder", "kLeftElbow", "kLeftForearmRoll", "kLeftWristAngle", "kLeftWristRotate", "kLeftGripper", "kRightWaist", "kRightShoulder", "kRightElbow", "kRightForearmRoll", "kRightWristAngle", "kRightWristRotate", "kRightGripper" ] ] }, "observation.images.cam_high": { "dtype": "video", "shape": [ 3, 480, 640 ], "names": [ "channels", "height", "width" ], "info": { "video.fps": 30.0, "video.height": 480, "video.width": 640, "video.channels": 3, "video.codec": "av1", "video.pix_fmt": "yuv420p", "video.is_depth_map": false, "has_audio": false } }, "observation.images.cam_left_wrist": { "dtype": "video", "shape": [ 3, 480, 640 ], "names": [ "channels", "height", "width" ], "info": { "video.fps": 30.0, "video.height": 480, "video.width": 640, "video.channels": 3, "video.codec": "av1", "video.pix_fmt": "yuv420p", "video.is_depth_map": false, "has_audio": false } }, "observation.images.cam_right_wrist": { "dtype": "video", "shape": [ 3, 480, 640 ], "names": [ "channels", "height", "width" ], "info": { "video.fps": 30.0, "video.height": 480, "video.width": 640, "video.channels": 3, "video.codec": "av1", "video.pix_fmt": "yuv420p", "video.is_depth_map": false, "has_audio": false } }, "timestamp": { "dtype": "float32", "shape": [ 1 ], "names": null }, "frame_index": { "dtype": "int64", "shape": [ 1 ], "names": null }, "episode_index": { "dtype": "int64", "shape": [ 1 ], "names": null }, "index": { "dtype": "int64", "shape": [ 1 ], "names": null }, "task_index": { "dtype": "int64", "shape": [ 1 ], "names": null } } } ``` ## Citation **BibTeX:** ```bibtex [More Information Needed] ```

本数据集基于[LeRobot](https://github.com/huggingface/lerobot)构建。 ## 数据集描述 - **主页:** [更多信息待补充] - **论文:** [更多信息待补充] - **许可证:** Apache-2.0 - **任务目标:** 完成胶囊咖啡机冲泡操作:首先将咖啡胶囊放入咖啡机并启动冲泡流程,随后将盛有咖啡的透明玻璃杯放置于承接托盘上。 - **操作对象:** 透明玻璃杯(直径7cm × 高度8cm)+ 胶囊咖啡机(购买链接:[【淘宝】假一赔四 https://e.tb.cn/h.60Pyz2E1LCTqd5x?tk=zmX0eJyjayl MF168 「KONMO家用办公室用胶囊咖啡机 小型迷你浓缩意式美式全自动咖啡机」点击链接直接打开 或者 淘宝搜索直接打开])+ 咖啡胶囊(购买链接:[【淘宝】假一赔四 https://e.tb.cn/h.60l0WlnO41tjL0F?tk=ytAGeJylaGJ MF278 「隅田川精萃浓缩胶囊大师咖啡胶囊意式美式拿铁espresso10盒100粒」点击链接直接打开 或者 淘宝搜索直接打开])+ 胶囊收纳架(购买链接:[【淘宝】退货运费险 https://e.tb.cn/h.60PATchT7p44YNX?tk=iJBgeJyQu57 CA381 「可装40粒黑色现货NESPRESSO胶囊不锈钢奢华咖啡架收纳架360度旋转」点击链接直接打开 或者 淘宝搜索直接打开])+ 承接托盘(购买链接:[【淘宝】假一赔四 https://e.tb.cn/h.60VmJKagLVyLW7M?tk=QH70eJykVCR CA381 「新款小麦秸秆盘子塑料托盘家用客厅长方形加厚水果盘茶盘酒店餐盘」点击链接直接打开 或者 淘宝搜索直接打开]) - **操作时长:** 单次操作耗时约40至60秒。 - **录制频率:** 30Hz。 - **机器人类型:** 搭载平行夹爪(parallel gripper)的Z1型7自由度机械臂(7-DOF robotic arm)。 - **末端执行器:** 平行夹爪(parallel gripper)。 - **双臂操作:** 是。 - **图像分辨率:** 640×480。 - **相机布局:** 在每台机械臂末端安装单目相机(monocular camera);另在双机械臂中点处、工作台面上方40cm位置并排布置两台单目相机。 - **数据内容:** • 机器人当前状态 • 机器人下一动作 • 当前相机视角图像 - **机器人初始姿态:** 每个数据条目中的首个机器人状态。 - **物体摆放:** 两台机械臂间距约60cm。将咖啡机置于双机械臂中央位置,距机械臂基座垂直高度35cm。将水杯与承接托盘放置于咖啡机左侧,咖啡胶囊与胶囊收纳架放置于咖啡机右侧。 ## 数据集结构 `meta/info.json`: json { "codebase_version": "v2.0", "robot_type": "Unitree_Z1_Dual", "total_episodes": 331, "total_frames": 443144, "total_tasks": 1, "total_videos": 993, "total_chunks": 1, "chunks_size": 1000, "fps": 30, "splits": { "train": "0:331" }, "data_path": "data/chunk-{episode_chunk:03d}/episode_{episode_index:06d}.parquet", "video_path": "videos/chunk-{episode_chunk:03d}/{video_key}/episode_{episode_index:06d}.mp4", "features": { "observation.state": { "dtype": "float32", "shape": [ 14 ], "names": [ [ "kLeftWaist", "kLeftShoulder", "kLeftElbow", "kLeftForearmRoll", "kLeftWristAngle", "kLeftWristRotate", "kLeftGripper", "kRightWaist", "kRightShoulder", "kRightElbow", "kRightForearmRoll", "kRightWristAngle", "kRightWristRotate", "kRightGripper" ] ] }, "action": { "dtype": "float32", "shape": [ 14 ], "names": [ [ "kLeftWaist", "kLeftShoulder", "kLeftElbow", "kLeftForearmRoll", "kLeftWristAngle", "kLeftWristRotate", "kLeftGripper", "kRightWaist", "kRightShoulder", "kRightElbow", "kRightForearmRoll", "kRightWristAngle", "kRightWristRotate", "kRightGripper" ] ] }, "observation.images.cam_high": { "dtype": "video", "shape": [ 3, 480, 640 ], "names": [ "channels", "height", "width" ], "info": { "video.fps": 30.0, "video.height": 480, "video.width": 640, "video.channels": 3, "video.codec": "av1", "video.pix_fmt": "yuv420p", "video.is_depth_map": false, "has_audio": false } }, "observation.images.cam_left_wrist": { "dtype": "video", "shape": [ 3, 480, 640 ], "names": [ "channels", "height", "width" ], "info": { "video.fps": 30.0, "video.height": 480, "video.width": 640, "video.channels": 3, "video.codec": "av1", "video.pix_fmt": "yuv420p", "video.is_depth_map": false, "has_audio": false } }, "observation.images.cam_right_wrist": { "dtype": "video", "shape": [ 3, 480, 640 ], "names": [ "channels", "height", "width" ], "info": { "video.fps": 30.0, "video.height": 480, "video.width": 640, "video.channels": 3, "video.codec": "av1", "video.pix_fmt": "yuv420p", "video.is_depth_map": false, "has_audio": false } }, "timestamp": { "dtype": "float32", "shape": [ 1 ], "names": null }, "frame_index": { "dtype": "int64", "shape": [ 1 ], "names": null }, "episode_index": { "dtype": "int64", "shape": [ 1 ], "names": null }, "index": { "dtype": "int64", "shape": [ 1 ], "names": null }, "task_index": { "dtype": "int64", "shape": [ 1 ], "names": null } } } ## 引用 **BibTeX:** bibtex [更多信息待补充]

提供机构:
maas
创建时间:
2025-01-06
搜集汇总
数据集介绍
Z1_DualArm_PourCoffee_Dataset 数据集图片
背景与挑战
背景概述
该数据集聚焦于双机械臂操作咖啡机冲泡咖啡的任务,使用Z1 7-DOF机械臂和并行夹爪,记录频率为30 Hz,包含机器人状态、动作和640x480分辨率的相机视图图像。数据涵盖331个episodes,总计443144帧和993个视频,适用于机器人学习与操控研究。
以上内容由遇见数据集搜集并总结生成
二维码
社区交流群
二维码
科研交流群
商业服务