Trajectory prediction using Extended Kalman Filter (EKF) training

Trajectory prediction using Extended Kalman Filter (EKF) training

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.

要查看或添加评论,请登录

Gustavo Sánchez Hurtado的更多文章

社区洞察

其他会员也浏览了