Skip to content
Chinese robotics — Dataset and collection discovery·· 4 days agoSignalEditorial score85

Humanoid Robots Enter Production Lines Regularly; Real-World Data Open-Sourced

人形机器人“进厂”常态化 真实产线数据开源

Summary

At the 2026 Sustainable Global Leaders Conference, the collaboration between Luju Robotics and Zhao Feng Machinery revealed a transition from pilot testing to regular operation of humanoid robots in automotive manufacturing. The robots, operating in a dynamic production environment, completed a full workflow of preparation, material retrieval, transportation, and loading with high reliability and success rates. The project also open-sourced real production line data, addressing the scarcity of real-world industrial data and enabling continuous model improvement through real-world feedback.

Editorial context

The event highlights a significant step in industrial deployment of humanoid robots, with real-world data collection and open-sourcing of production line data marking a shift from simulation-based training to real-world training. This approach enables continuous model iteration and improves robustness in real factory environments.

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

  • running_hours

    ≈1,000 hours

    View original evidence
    “目前，完成一次上料循环的时间稳定控制在40秒以内，可适配工厂15个工位、覆盖10余种零件，上料成功率稳定在98%，已在现场连续无故障运行超过2个月，累计运行约1000小时，协助生产超过6万个零部件。
    Open source S10

  • components_produced

    >60,000

    View original evidence
    “目前，完成一次上料循环的时间稳定控制在40秒以内，可适配工厂15个工位、覆盖10余种零件，上料成功率稳定在98%，已在现场连续无故障运行超过2个月，累计运行约1000小时，协助生产超过6万个零部件。
    Open source S10

  • Reported success rate

    98%

    View original evidence
    “目前，完成一次上料循环的时间稳定控制在40秒以内，可适配工厂15个工位、覆盖10余种零件，上料成功率稳定在98%，已在现场连续无故障运行超过2个月，累计运行约1000小时，协助生产超过6万个零部件。
    Open source S10

  • robots_deployed

    15 robots

    View original evidence
    从试点验证到常态化作业 在兆丰机电产线，车间机器轰鸣，15台人形机器人在金属丝网框、多工位、上料台交错的狭窄动态环境中，完成10余个动作序列，稳定抓取内径的小型零件，打通“预备—取料—转运—上料”全流程。
    Open source S8

  • tasks_performed

    >10

    View original evidence
    从试点验证到常态化作业 在兆丰机电产线，车间机器轰鸣，15台人形机器人在金属丝网框、多工位、上料台交错的狭窄动态环境中，完成10余个动作序列，稳定抓取内径的小型零件，打通“预备—取料—转运—上料”全流程。
    Open source S8

  • training_modules

    >30

    View original evidence
    乐聚机器人常务副总裁柯真东说，技能开发工具链把上料技能拆分为30余个基础模块，可像拼积木一样组合，不需要编写底层代码，开发周期从数月缩短到数周，多机调度平台可将标准技能一键同步到多台设备，部署时间从天级缩短到小时级，现场作业数据全流程回传，零件掉落、碰撞、过速检测等安全管理模块，保障机器人可靠、连续作业。
    Open source S13

  • cycle_time

    40 seconds

    View original evidence
    “目前，完成一次上料循环的时间稳定控制在40秒以内，可适配工厂15个工位、覆盖10余种零件，上料成功率稳定在98%，已在现场连续无故障运行超过2个月，累计运行约1000小时，协助生产超过6万个零部件。
    Open source S10
  • paper: not_reported
  • code: not_reported
  • weights: not_reported
  • dataset: not_reported

What remains unknown

Not established in the collected evidence: Environment, Control, Data origin.

Dataset licensing and commercial-use rights are not established here.

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.

标志着人形机器人在汽车制造场景中完成从“试点验证”到“常态化作业”的关键跨越，也探索出一条从真实产线中积累数据、迭代模型、复制推广的路径。

Open source S7

“目前，完成一次上料循环的时间稳定控制在40秒以内，可适配工厂15个工位、覆盖10余种零件，上料成功率稳定在98%，已在现场连续无故障运行超过2个月，累计运行约1000小时，协助生产超过6万个零部件。

Open source S10

柯真东介绍，按当前数据产能测算，单月采集超过4万条，并随产线运行持续累积，让机器人交付后能够持续进化，越用越“聪明”。

Open source S16

从试点验证到常态化作业 在兆丰机电产线，车间机器轰鸣，15台人形机器人在金属丝网框、多工位、上料台交错的狭窄动态环境中，完成10余个动作序列，稳定抓取内径的小型零件，打通“预备—取料—转运—上料”全流程。

Open source S8

乐聚机器人常务副总裁柯真东说，技能开发工具链把上料技能拆分为30余个基础模块，可像拼积木一样组合，不需要编写底层代码，开发周期从数月缩短到数周，多机调度平台可将标准技能一键同步到多台设备，部署时间从天级缩短到小时级，现场作业数据全流程回传，零件掉落、碰撞、过速检测等安全管理模块，保障机器人可靠、连续作业。

Open source S13

Implications for data suppliers

RoboSignal interpretation and collection questions, not statements of buyer demand.

  • Confirm the required data type and collection setting with the buyer; this source does not establish a complete collection specification.
  • Compare the reported units and scope before using these quantities in a budget. Recording hours, sensor-hours and trajectories are different measures.
  • Validate demand and acceptance criteria with a buyer before scaling. Publication, popularity and a research result do not establish a purchase commitment.

Source：Chinese robotics — Dataset and collection discovery · finance.sina.com.cn

#Dataset#Open source#Industry
Timezone · UTC

Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).