15 Humanoid Robots 'Stably Deployed' in Industrial Setting, Leju Robotics and Zhao Feng Machinery Release Embodied Intelligence Solution
15台机器人“常态化上岗” 乐聚机器人与兆丰机电联合发布具身智能解决方案
Leju Robotics and Zhao Feng Machinery have deployed 15 humanoid robots in a complex industrial environment, achieving a 98% success rate in part handling and completing over 60,000 components in two months. The solution includes open-sourced real-world data and tools for skill development, aiming to lower the barriers for embodied AI research and deployment.
The collaboration between Leju Robotics and Zhao Feng Machinery marks a significant step in the commercialization of embodied intelligence, with 15 humanoid robots achieving 98% success rate in part handling and contributing to over 60,000 components produced. The open-sourcing of real-world data further supports industry-wide development of embodied AI models.
Source: Robotics — Chinese web 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
robot_trajectories
>10
Trajectory count
View original evidence
记者在兆丰机电产线现场看到，15台人形机器人在金属丝网框、多工位、上料台交错的狭窄复杂动态环境中，可完成10余个动作序列，稳定抓取内径80至120毫米的小型零件，完成“预备—取料—转运—上料”的全流程动作。
Open source S4Reported success rate
98%
elapsed_hours
≈1,000 hours
number_of_parts
>60,000
number_of_skills
>30
View original evidence
例如，技能开发工具链把上料技能拆分为30余个基础模块，可将技能像拼积木一样组合，使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，令部署时间从天级缩短到小时级；一键叫料系统降低工人操作门槛，可同时启动多台设备…… “现在我们的机器人已经可以适配兆丰工厂的15个工位。
Open source S11number_of_workstations
15
View original evidence
例如，技能开发工具链把上料技能拆分为30余个基础模块，可将技能像拼积木一样组合，使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，令部署时间从天级缩短到小时级；一键叫料系统降低工人操作门槛，可同时启动多台设备…… “现在我们的机器人已经可以适配兆丰工厂的15个工位。
Open source S11number_of_robots
15 robots
number_of_data_records
>40,000
View original evidence
15台人形机器人在兆丰产线作业的同时，还能形成规模化并行数据采集能力，按当前数据产能测算，单月采集超过4万条，并随着产线运行持续累积。
Open source S17
- dataset: not_reported
- code: not_reported
- weights: not_reported
- paper: not_reported
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.
记者在兆丰机电产线现场看到，15台人形机器人在金属丝网框、多工位、上料台交错的狭窄复杂动态环境中，可完成10余个动作序列，稳定抓取内径80至120毫米的小型零件，完成“预备—取料—转运—上料”的全流程动作。
Open source S4
据介绍，目前，这15台人形机器人完成一次上料循环的时间约在40秒内，可覆盖10余种零件，上料成功率达到98%。
Open source S5
该项目已在现场连续运行超过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 S6
例如，技能开发工具链把上料技能拆分为30余个基础模块，可将技能像拼积木一样组合，使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，令部署时间从天级缩短到小时级；一键叫料系统降低工人操作门槛，可同时启动多台设备…… “现在我们的机器人已经可以适配兆丰工厂的15个工位。
Open source S11
15台机器人“常态化上岗” 乐聚机器人与兆丰机电联合发布具身智能解决方案
Open source S1
15台人形机器人在兆丰产线作业的同时，还能形成规模化并行数据采集能力，按当前数据产能测算，单月采集超过4万条，并随着产线运行持续累积。
Open source S17
Source：Robotics — Chinese web discovery · news.qq.com