Adaptive Neural Network Control for Industrial Optical Tweezers With Uncertain Closed Architecture

The control of closed architecture industrial optical tweezers systems presents substantial challenges due to the limited knowledge of inner controller configurations and control gain structures. Conventional methods, such as the computed-torque approach, often prove inadequate for closed architecture robots because the torque terminal is inaccessible to end-users. This creates a disconnect between advanced control algorithms and practical industrial needs. To tackle these challenges, we propose a novel approach utilizing adaptive neural network-based control methodology. Our method employs neural networks to approximate the low-level controller, thereby bypassing the constraints of traditional closed-loop architectures. By integrating an external feedback loop that operates independently of the inner control architecture, our approach offers flexibility for design adjustments and facilitates advanced control actions. Furthermore, we conduct a comprehensive stability analysis of external feedback control systems interacting with a fixed inner loop. In summary, this study represents a pioneering effort in addressing the complexities of industrial optical tweezers systems with closed uncertain architectures, providing an innovative solution aimed at enhancing control capabilities for applications in industrial settings.