Switching Recurrent Kalman Networks
This addresses the challenge of modeling multimodal distributions in time-series data for autonomous driving systems, though it appears incremental as it builds on existing Kalman filter and deep state-space model approaches.
The paper tackled the problem of forecasting nonlinear, noisy, and multimodal multivariate time series, such as driving behavior, by proposing the Switching Recurrent Kalman Network (SRKN), which switches among multiple Kalman filters in a factorized latent state. The model was tested on toy datasets and real taxi driving data from Porto, where it successfully captured the multimodal dynamics in all cases.
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.