Unknown Input

Research on unknown input (UI) estimation focuses on accurately determining unmeasured or unexpected influences affecting dynamic systems, particularly in robotics and autonomous systems. Current efforts concentrate on developing robust estimation algorithms, such as Kalman filters adapted for nonlinear systems and data-driven approaches, often incorporating prior knowledge or employing techniques like data augmentation to handle missing data. These advancements aim to improve the accuracy and reliability of state estimation in complex scenarios, leading to better control and decision-making in applications ranging from soft robotics to natural language processing tasks like sentiment analysis in low-resource languages.