mlsanityData to 7 Oct 2026

Switching Recurrent Kalman Networks

arXiv 2111.08291 ↗First posted 16 Nov 2021cs.LG cs.AI eess.SPcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 46 references that are in the map. First posted on arXiv 16 Nov 2021.

Builds on

19 of 46 references.

References · 19

  1. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
  2. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 636
  3. 2015A Recurrent Latent Variable Model for Sequential Datacited by 362
  4. 2016Structured Inference Networks for Nonlinear State Space Modelscited by 182
  5. 2015Deep Kalman Filterscited by 163
  6. 2016Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Datacited by 154
  7. 2018Disentangled Sequential Autoencodercited by 117
  8. 2016Composing graphical models with neural networks for structured representations and fast inferencecited by 113
  9. 2017A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learningcited by 107
  10. 2018Probabilistic Recurrent State-Space Modelscited by 64
  11. 2019Recurrent Kalman Networks: Factorized Inference in High-Dimensional Deep Feature Spacescited by 64
  12. 2014Learning Stochastic Recurrent Networkscited by 60
7 more
  1. 2020Deep State Space Models for Nonlinear System Identificationcited by 30
  2. 2019Collapsed Amortized Variational Inference for Switching Nonlinear Dynamical Systemscited by 26
  3. 2019Switching Linear Dynamics for Variational Bayes Filteringcited by 17
  4. 2020Deep Switching Auto-Regressive Factorization:Application to Time Series Forecastingcited by 15
  5. 2017State Space LSTM Models with Particle MCMC Inferencecited by 11
  6. 2017A Bayesian Filtering Algorithm for Gaussian Mixture Modelscited by 1
  7. 2020Variational Dynamic Mixturescited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023KARNet: Kalman Filter Augmented Recurrent Neural Network for Learning World Models in Autonomous Driving Tasks
  2. 2021ObserveNet Control: A Vision-Dynamics Learning Approach to Predictive Control in Autonomous Vehicles
  3. 2025IRNN: Innovation-driven Recurrent Neural Network for Time-Series Data Modeling and Prediction
  4. 2022Hidden Parameter Recurrent State Space Models For Changing Dynamics Scenarios
  5. 2022CARNet: A Dynamic Autoencoder for Learning Latent Dynamics in Autonomous Driving Tasks
  6. 2021Stochastic Recurrent Neural Network for Multistep Time Series Forecasting
  7. 2023Efficient Baselines for Motion Prediction in Autonomous Driving
  8. 2021Deep Switching State Space Model (DS3M) for Nonlinear Time Series Forecasting with Regime Switching