Abstract: Disclosed are systems and methods directed to transfer learning of cascaded EDFA models error accumulations in a multi-span system in which a two-step method using transfer learning is employed to reduce EDFA model error accumulation in a multi-span system. A first step of employs existing pretrained component-level ML-based EDFA models in chain to create a large synthetic dataset. The synthetic dataset includes all related features and labels for a specific end-to-end link. A source model is trained based on the large synthetic dataset. To accommodate a performance prediction gap between real link condition and the source model, which is trained on synthetic dataset, our method employs a second step that collects a few measurements from the real end-to-end link and makes few-shots learning to transfer the synthesis-data-based source model to real-data-based target model.

Abstract: The subject invention pertains to a novel aerial manipulation system with a flying continuum robotic manipulator (AeCoM). A lightweight tendon-driven continuum robotic arm is coupled with an unmanned aerial vehicle. An attitude sensor (IMU) is used to assist in PCC (Piecewise Constant Curvature) configuration. A tension-based closed-loop control method is used to avoid tendon slacking in manipulating the shape of the continuum arm. The system can achieve improved relative payload capability and motion dexterity. Experimental results validate the performance of tendon-slacking avoidance and kinematics accuracy with different tip loading and tip positioning accuracy for aerial grasping.