mlsanityData to 7 Oct 2026

Multi-Step Prediction of Dynamic Systems with Recurrent Neural Networks

arXiv 1806.00526 ↗First posted 20 May 2018cs.NE cs.ROcited by 25

Not on the map. Why?

Abstract (arXiv)

Recurrent Neural Networks (RNNs) can encode rich dynamics which makes them suitable for modeling dynamic systems. To train an RNN for multi-step prediction of dynamic systems, it is crucial to efficiently address the state initialization problem, which seeks proper values for the RNN initial states at the beginning of each prediction interval. In this work, the state initialization problem is addressed using Neural Networks (NNs) to effectively train a variety of RNNs for modeling two aerial vehicles, a helicopter and a quadrotor, from experimental data. It is shown that the RNN initialized by the NN-based initialization method outperforms the state of the art. Further, a comprehensive study of RNNs trained for multi-step prediction of the two aerial vehicles is presented. The multi-step prediction of the quadrotor is enhanced using a hybrid model which combines a simplified physics-based motion model of the vehicle with RNNs. While the maximum translational and rotational velocities in the quadrotor dataset are about 4 m/s and 3.8 rad/s, respectively, the hybrid model produces predictions, over 1.9 second, which remain within 9 cm/s and 0.12 rad/s of the measured translational and rotational velocities, with 99% confidence on the test dataset

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 3; 2023: 5; 2024: 5; 2025: 5; 2026: 3.

25 papers.

Sort:

By area:

  1. 2021On Recurrent Neural Networks for learning-based control: recent results and ideas for future developmentscited by 14
  2. 2026SkyJEPA: Learning Long-Horizon World Models for Zero-Shot Sim-to-Real Control of Quadrotorscited by 9
  3. 2022Distributional Drift Adaptation with Temporal Conditional Variational Autoencoder for Multivariate Time Series Forecastingcited by 7
  4. 2024DroneDiffusion: Robust Quadrotor Dynamics Learning with Diffusion Modelscited by 6
  5. 2023Nonlinear MPC design for incrementally ISS systems with application to GRU networkscited by 5
  6. 2021Hybrid Physics and Deep Learning Model for Interpretable Vehicle State Predictioncited by 4
  7. 2021Temporal Convolutions for Multi-Step Quadrotor Motion Predictioncited by 3
  8. 2024TAEN: A Model-Constrained Tikhonov Autoencoder Network for Forward and Inverse Problemscited by 3
  9. 2023Predictions Based on Pixel Data: Insights from PDEs and Finite Differencescited by 2
  10. 2023RIOT: Recursive Inertial Odometry Transformer for Localisation from Low-Cost IMU Measurementscited by 1
  11. 2023Deep Long-Short Term Memory networks: Stability properties and Experimental validationcited by 1
  12. 2024Learning Long-Horizon Predictions for Quadrotor Dynamicscited by 1
13 more
  1. 2024A Novel Neural Filter to Improve Accuracy of Neural Network Models of Dynamic Systemscited by 1
  2. 2025A Deep-Learning Iterative Stacked Approach for Prediction of Reactive Dissolution in Porous Mediacited by 1
  3. 2025Assumed Density Filtering and Smoothing with Neural Network Surrogate Modelscited by 1
  4. 2026PnP-Corrector: A Universal Correction Framework for Coupled Spatiotemporal Forecastingcited by 1
  5. 2021Am I fit for this physical activity? Neural embedding of physical conditioning from inertial sensorscited by 0
  6. 2022Towards lifelong learning of Recurrent Neural Networks for control designcited by 0
  7. 2022Robust Recurrent Neural Network to Identify Ship Motion in Open Water with Performance Guarantees -- Technical Reportcited by 0
  8. 2023One-shot backpropagation for multi-step prediction in physics-based system identification -- EXTENDED VERSIONcited by 0
  9. 2024Forecasting the Forced van der Pol Equation with Frequent Phase Shifts Using Reservoir Computingcited by 0
  10. 2025Lipschitz-Based Robustness Certification for Recurrent Neural Networks via Convex Relaxationcited by 0
  11. 2025Unlocking Out-of-Distribution Generalization in Dynamics through Physics-Guided Augmentationcited by 0
  12. 2025Dreaming Falcon: Physics-Informed Model-Based Reinforcement Learning for Quadcopterscited by 0
  13. 2026CaLiSym: Learning Symplectic Dynamics of Real-World Systems through Structured Canonical Liftscited by 0