Xiaomi Humanoid Robot Demonstrates Eight-Hour Shift Sorting Car Dashboard Side Covers at EV Factory
小米人形机器人在工厂连续工作8小时，自主完成装配任务
On November 3, Xiaomi posted a video showing its humanoid robot sorting car dashboard side covers in an electric vehicle factory. The company stated the robot completed an eight-hour shift independently, detecting and correcting errors while coordinating with production systems. However, Xiaomi did not disclose specific metrics such as parts sorted, success rates, or power supply methods during the shift.
Source: Chinese robotics — Hardware and sensing · 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.
- Control
- Reported autonomousOpen source S3
Reported numbers
Reported duration
8 hours
Reported duration
8 hours
Reported success rate
90.2%
Reported trials
Reported success rate
98%
Reported trials
seconds
76 seconds
Reported duration
100,000 hours
- paper: not_reported
- weights: not_reported
- dataset: not_reported
- code: not_reported
What remains unknown
Not established in the collected evidence: Environment, 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.
小米发布了一段视频，展示其人形机器人在电动汽车工厂中连续完成8小时工作班次，负责分拣汽车中控台侧盖板。
Open source S2
小米表示，这些机器人独立完成了全部工作，并在过程中自主发现和修正了错误。
Open source S3
连续8小时的生产线工作 小米科技于11月3日在X平台发布了该视频，当时小米正在乌镇参加世界互联网大会并获得了相关奖项。
Open source S6
小米报告称，在三小时内成功率达到90.2%，速度足以满足该工位76秒的生产周期要求。
Open source S11
到7月，公司表示成功率已提升至98%，并新增了两个难度更高的工位，其中就包括本周视频中展示的侧盖板分拣工作。
Open source S12
今年3月，小米在其北京电动汽车工厂中让一台人形机器人作为"实习生"安装自攻螺母。
Open source S10
该模型基于10万小时的真实世界机器人数据进行预训练。
Open source S15
在小米标注为"物料掉落：多机器人协作"的片段中，一个安装在轮式底盘上的人形机器人上半身滚动进入画面，协助两台双足机器人完成工作。
Open source S22
小米同时宣布，其开源的小米机器人1号AI模型（Xiaomi-Robotics-1）已在小米员工公寓中开始试运行。
Open source S14
Source：Chinese robotics — Hardware and sensing · msn.cn