Learning Relational Kalman Filtering

Authors

  • Jaesik Choi Ulsan National Institute of Science and Technology
  • Eyal Amir University of Illinois at Urbana-Champaign
  • Tianfang Xu University of Illinois at Urbana-Champaign
  • Albert Valocchi University of Illinois at Urbana-Champaign

DOI:

https://doi.org/10.1609/aaai.v29i1.9633

Keywords:

Kalman filtering, Statistical Relational Learning, Probabilistic Relational Models, Linear Gaussian Models, Lifted Inference

Abstract

The Kalman Filter (KF) is pervasively used to control a vast array of consumer, health and defense products. By grouping sets of symmetric state variables, the Relational Kalman Filter (RKF) enables us to scale the exact KF for large-scale dynamic systems. In this paper, we provide a parameter learning algorithm for RKF, and a regrouping algorithm that prevents the degeneration of the relational structure for efficient filtering. The proposed algorithms significantly expand the applicability of the RKFs by solving the following questions: (1) how to learn parameters for RKF from partial observations; and (2) how to regroup the degenerated state variables by noisy real-world observations. To our knowledge, this is the first paper on learning parameters in relational continuous probabilistic models. We show that our new algorithms significantly improve the accuracy and the efficiency of filtering large-scale dynamic systems.

Downloads

Published

2015-02-21

How to Cite

Choi, J., Amir, E., Xu, T., & Valocchi, A. (2015). Learning Relational Kalman Filtering. Proceedings of the AAAI Conference on Artificial Intelligence, 29(1). https://doi.org/10.1609/aaai.v29i1.9633

Issue

Section

Main Track: Novel Machine Learning Algorithms