Trajectory prediction using Extended Kalman Filter (EKF) training
Gustavo Sánchez Hurtado
Award-Winning Engineer, Researcher & Educator | Digital Transformation: Control Systems, IoT, and Machine Learning | PLC/SCADA programmer | Python/MATLAB | Node Red | Global Speaker, Author & Podcaster
Trajectory prediction is one the classic problems in estimation and control theory. In this note we follow the approach described in:
Simon Haykin. "Kalman Filtering and Neural Networks". First published:1 October 2001. Print ISBN:9780471369981. Online ISBN:9780471221548. DOI:10.1002/0471221546. Copyright ? 2001 John Wiley & Sons, Inc.
to predict a circular trajectory with noisy measurements, based on a neural network trained using the extended Kalman filter appoach.
Furthermore, we use the class published by J. Nezvadovitz in his Github repos:
You can test the code here:
Feel free to leave your comments here below, I would be happy to answer.
At?MYWAI?we promote agile, explainable, reliable and affordable ML at the edge.