538 Hours of 'Extremely Messy' Human Data, Real Robot Takes Less Than an Hour: Hong Kong University Teaches Robots to Unpack Packages, Use Hot Glue Guns, and Make Cold Drinks
538小时「极脏」人类数据，真机不到1小时：港大让机器人学会拆快递、打胶枪、做冷饮
The MMLab team at the University of Hong Kong proposes the EgoWild2Dex method, which uses uncurated real human first-person operation data to train robots, enabling complex dual-arm dexterous tasks such as unpacking packages, using hot glue guns to fix figurines, and making cold drinks, with an average success rate of 96.7%. The method transfers natural human operation data to robotic execution space through GeoFormer perspective alignment and progressive training.
The EgoWild2Dex dataset and method demonstrate how raw, uncurated human-first-person data can be effectively used to train robots for complex tasks, bridging the gap between human experience and robotic execution through geometric alignment and progressive training.
Source: Chinese robotics — Dataset and collection discovery · Read original article ↗
English translation unavailable. Choose the original article to read it.
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
hours_of_human_data
538 hours
hours_of_real_robot_data
<1 hours
View original evidence
在每个下游任务使用不到 1 小时真机数据的情况下，机器人能够连续完成拆快递、使用热熔胶枪固定手办、制作冷饮等复杂双臂灵巧长时序任务，平均成功率达到 96.7%。
Open source S5Reported success rate
96.7%
View original evidence
在每个下游任务使用不到 1 小时真机数据的情况下，机器人能够连续完成拆快递、使用热熔胶枪固定手办、制作冷饮等复杂双臂灵巧长时序任务，平均成功率达到 96.7%。
Open source S5head_rotation_angle_per_second_degrees
15.93
object_instances_per_frame
34.78
- code: not_reported
- dataset: not_reported
- paper: not_reported
- weights: not_reported
- code: Reported pending Open source S8
- dataset: Reported pending Open source S8
What remains unknown
Not established in the collected evidence: Environment, Control, Data origin.
Reported performance applies to the described task. It does not establish general autonomy or deployment readiness.
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
538小时「极脏」人类数据，真机不到1小时：港大让机器人学会拆快递、打胶枪、做冷饮
Open source S1
在每个下游任务使用不到 1 小时真机数据的情况下，机器人能够连续完成拆快递、使用热熔胶枪固定手办、制作冷饮等复杂双臂灵巧长时序任务，平均成功率达到 96.7%。
Open source S5
数据显示，EgoWild 中，每秒累计头部旋转角度平均达到 15.93° ，每帧图像平均包含 34.78 个不同的物体实例。
Open source S16
按传统机器人数据采集的标准来看，这批数据确实相当 「脏」 。
Open source S17
但这里的「脏」并非指标注错误或数据质量差，而是指它 保留了真实世界本来的复杂性 。
Open source S18
数据集、模型与代码计划后续开放。
Open source S8
Source：Chinese robotics — Dataset and collection discovery · news.qq.com