Switching Recurrent Kalman Networks

TL;DR

The paper introduces the Switching Recurrent Kalman Network (SRKN), a scalable deep state-space model that effectively captures nonlinear and multimodal dynamics in multivariate time series data, such as driving behavior.

Contribution

It proposes a novel model that switches among multiple Kalman filters to handle multimodal and nonlinear time series data, improving inference and prediction accuracy.

Findings

Successfully models multimodal driving data

Captures nonlinear dynamics effectively

Demonstrates scalability and interpretability

Abstract

Forecasting driving behavior or other sensor measurements is an essential component of autonomous driving systems. Often real-world multivariate time series data is hard to model because the underlying dynamics are nonlinear and the observations are noisy. In addition, driving data can often be multimodal in distribution, meaning that there are distinct predictions that are likely, but averaging can hurt model performance. To address this, we propose the Switching Recurrent Kalman Network (SRKN) for efficient inference and prediction on nonlinear and multi-modal time-series data. The model switches among several Kalman filters that model different aspects of the dynamics in a factorized latent state. We empirically test the resulting scalable and interpretable deep state-space model on toy data sets and real driving data from taxis in Porto. In all cases, the model can capture the multimodal nature of the dynamics in the data.