Moving Horizon

Moving horizon estimation (MHE) is a powerful state estimation technique that uses measurements over a sliding time window to infer the current state of a system, particularly useful for nonlinear and complex systems where traditional methods struggle. Current research focuses on integrating MHE with neural networks (NeuroMHE) to improve accuracy and efficiency, particularly for applications like robotics and flight control, and on developing computationally efficient MHE algorithms for high-dimensional systems such as those described by partial differential equations (PDEs). These advancements are significantly impacting fields like robotics, where accurate state estimation is crucial for safe and effective operation, and are leading to more robust and adaptable control systems.