Robotic Packaging Optimization with Reinforcement Learning
This addresses productivity and flexibility issues in intelligent manufacturing for the food packaging industry, but it is incremental as it applies reinforcement learning to a specific domain problem.
The paper tackled the problem of varying product supply in robotic food packaging, which causes productivity drops, by proposing a reinforcement learning framework to optimize conveyor belt speed. The result was exceeding performance requirements with 99.8% packed products and 100% filled boxes, improving productivity and reducing computation time compared to existing solutions.
Intelligent manufacturing is becoming increasingly important due to the growing demand for maximizing productivity and flexibility while minimizing waste and lead times. This work investigates automated secondary robotic food packaging solutions that transfer food products from the conveyor belt into containers. A major problem in these solutions is varying product supply which can cause drastic productivity drops. Conventional rule-based approaches, used to address this issue, are often inadequate, leading to violation of the industry's requirements. Reinforcement learning, on the other hand, has the potential of solving this problem by learning responsive and predictive policy, based on experience. However, it is challenging to utilize it in highly complex control schemes. In this paper, we propose a reinforcement learning framework, designed to optimize the conveyor belt speed while minimizing interference with the rest of the control system. When tested on real-world data, the framework exceeds the performance requirements (99.8% packed products) and maintains quality (100% filled boxes). Compared to the existing solution, our proposed framework improves productivity, has smoother control, and reduces computation time.