Scalable Identification of Partially Observed Systems with Certainty-Equivalent EM
Abstract
System identification is a key step for model-based control, estimator design, and output prediction. This work considers the offline identification of partially observed nonlinear systems. We empirically show that the certainty-equivalent approximation to expectation-maximization can be a reliable and scalable approach for high-dimensional deterministic systems, which are common in robotics. We formulate certainty-equivalent expectation-maximization as block coordinate-ascent, and provide an efficient implementation. The algorithm is tested on a simulated system of coupled Lorenz attractors, demonstrating its ability to identify high-dimensional systems that can be intractable for particle-based approaches. Our approach is also used to identify the dynamics of an aerobatic helicopter. By augmenting the state with unobserved fluid states, a model is learned that predicts the acceleration of the helicopter better than state-of-the-art approaches. The codebase for this work is available at https://github.com/sisl/CEEM.
Cite
@article{arxiv.2006.11615,
title = {Scalable Identification of Partially Observed Systems with Certainty-Equivalent EM},
author = {Kunal Menda and Jean de Becdelièvre and Jayesh K. Gupta and Ilan Kroo and Mykel J. Kochenderfer and Zachary Manchester},
journal= {arXiv preprint arXiv:2006.11615},
year = {2020}
}
Comments
First three authors contributed equally. Accepted at ICML 2020. Website: https://sites.google.com/stanford.edu/ceem/