Shanghai-based robotics firm AgiBot has deployed its Real-World Reinforcement Learning (RW-RL) system on a pilot production line with Longcheer Technology. According to AgiBot, the project is the first application of real-world reinforcement learning in industrial robotics.

The AgiBot system aims to address the complex fixture design, extensive tuning, and costly reconfiguration of much current precision manufacturing.

AgiBot’s Real-World Reinforcement Learning system enables robots to learn and adapt directly on the factory floor. Within tens of minutes, robots can acquire new skills, achieve stable deployment, and maintain long-term performance without degradation. During line changes or model transitions, only minimal hardware adjustments and standardised deployment steps are required.

The validation has now been successfully demonstrated on a pilot production line in collaboration with Longcheer Technology. AgiBot and Longcheer plan to extend real-world reinforcement learning to a broader range of precision manufacturing scenarios, including consumer electronics and automotive components. The focus will be on developing modular, rapidly deployable robot solutions that integrate seamlessly with existing production systems.