RCUKF: Data-Driven Modeling Meets Bayesian Estimation
By: Kumar Anurag , Kasra Azizi , Francesco Sorrentino and more
Potential Business Impact:
Helps machines learn and predict complex movements.
Accurate modeling is crucial in many engineering and scientific applications, yet obtaining a reliable process model for complex systems is often challenging. To address this challenge, we propose a novel framework, reservoir computing with unscented Kalman filtering (RCUKF), which integrates data-driven modeling via reservoir computing (RC) with Bayesian estimation through the unscented Kalman filter (UKF). The RC component learns the nonlinear system dynamics directly from data, serving as a surrogate process model in the UKF prediction step to generate state estimates in high-dimensional or chaotic regimes where nominal mathematical models may fail. Meanwhile, the UKF measurement update integrates real-time sensor data to correct potential drift in the data-driven model. We demonstrate RCUKF effectiveness on well-known benchmark problems and a real-time vehicle trajectory estimation task in a high-fidelity simulation environment.
Similar Papers
Learning Beyond Experience: Generalizing to Unseen State Space with Reservoir Computing
Machine Learning (CS)
Lets computers predict unseen future events.
A Novel Reservoir Computing Framework for Chaotic Time Series Prediction Using Time Delay Embedding and Random Fourier Features
Neural and Evolutionary Computing
Predicts messy future events more accurately.
Next-generation reservoir computing validated by classification task
Machine Learning (CS)
Teaches computers to sort and predict information.