Real-time optimal control with shallow recurrent decoder networks

• URL: http://arxiv.org/abs/2607.19302v1
• Date: Tue, 21 Jul 2026 17:13:49 GMT
• Title: Real-time optimal control with shallow recurrent decoder networks
• Abstract summary: We exploit SHallow REcurrent-based Reduced Order Modeling networks to synthesize a real-time closed-loop controller for high-dimensional dynamics.<n>After training the model on a few optimal examples, SHRED-ROM mimics the expert behavior with effective distributed control actions in new scenarios.<n>A sensor forecaster is synthesized and used to close the loop at the latent level, thus efficiently mitigating possible sensor failures or delays.
• Score: 4.952983248701927
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Controlling dynamical systems in real-time across multiple scenarios is critical to enabling adaptive control strategies, ensuring stability and efficiency. However, to tailor control actions in response to varying scenarios, traditional optimal control problems typically require several system simulations, which are often computationally demanding due to the high-dimensionality of the underlying spatio-temporal dynamics. In this work, we exploit SHallow REcurrent Decoder networks-based Reduced Order Modeling (SHRED-ROM) to synthesize a real-time closed-loop controller for high-dimensional and parametric dynamics, relying solely on limited state sensor readings. After training the model on a few optimal examples given by an expert demonstrator, SHRED-ROM mimics the expert behavior with effective distributed control actions in new scenarios, alleviating the curse of dimensionality. Moreover, a sensor forecaster is synthesized and used to close the loop at the latent level, thus efficiently mitigating possible sensor failures or delays. The performance of the proposed optimal control strategy is finally assessed on three challenging high-dimensional cases dealing with either parametric density control or fluid flow control.

Related papers

• Physics-enhanced reinforcement learning for real-time optimal control of dynamical systems [0.3499870393443268]
  Reinforcement learning (RL) has emerged as a promising feedback control strategy for nonlinear and complex dynamical systems.<n>In this work, we bridge RL and traditional optimal control for dynamical system with a novel Physics-EnhAnced Reinforcement Learning (PEARL) paradigm.
  arXiv  Detail & Related papers  (2026-07-17T17:56:05Z)
• End-to-End Learning of Quantum Control on Latent Dynamical Manifold [13.119254069186034]
  Traditional quantum control relies on an iterative "simulate-then-optimize" paradigm.<n>We propose an end-to-end quantum control framework based on long short-term memory.
  arXiv  Detail & Related papers  (2026-06-26T09:57:12Z)
• SkyJEPA: Learning Long-Horizon World Models for Zero-Shot Sim-to-Real Control of Quadrotors [48.60897189520386]
  We introduce the JEPA-style model for real-time quadrotor control.<n>We combine a latent dynamics model with a novel physics-inspired prober that maps frozen latents to interpretable state.<n>To reduce the dependence on expensive and unsafe real-world data collection, we develop a structured pipeline for automated dataset generation.
  arXiv  Detail & Related papers  (2026-06-22T15:00:59Z)
• Multi-scale Coarse-to-fine Modeling for Test-time Human Motion Control [51.92884966472683]
  MSCoT is a multi-scale, coarse-to-fine model for test-time human motion synthesis and control.<n> MSCoT discretizes motion into a multi-scale hierarchical representation and predicts the entire token sequence at each temporal scale.
  arXiv  Detail & Related papers  (2026-05-14T15:09:49Z)
• Hypersonic Flow Control: Generalized Deep Reinforcement Learning for Hypersonic Intake Unstart Control under Uncertainty [0.34376560669160394]
  Unstart is a major challenge to reliable air-breathing propulsion at Mach 5 and above.<n>We show a strategy to control unstart in a canonical two-dimensional hypersonic inlet at Mach 5 and Reynolds number $5times 106$.<n>Results establish a data-driven approach for real-time hypersonic flow control under realistic operational uncertainties.
  arXiv  Detail & Related papers  (2026-01-27T22:38:52Z)
• Latent feedback control of distributed systems in multiple scenarios through deep learning-based reduced order models [3.5161229331588095]
  Continuous monitoring and real-time control of high-dimensional distributed systems are crucial in applications to ensure a desired physical behavior.<n>Traditional feedback control design that relies on full-order models fails to meet these requirements due to the delay in the control computation.<n>We propose a real-time closed-loop control strategy enhanced by nonlinear non-intrusive Deep Learning-based Reduced Order Models (DL-ROMs)
  arXiv  Detail & Related papers  (2024-12-13T08:04:21Z)
• Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection [56.66677293607114]
  We propose Code-as-Monitor (CaM) for both open-set reactive and proactive failure detection.<n>To enhance the accuracy and efficiency of monitoring, we introduce constraint elements that abstract constraint-related entities.<n>Experiments show that CaM achieves a 28.7% higher success rate and reduces execution time by 31.8% under severe disturbances.
  arXiv  Detail & Related papers  (2024-12-05T18:58:27Z)
• Real-time optimal control of high-dimensional parametrized systems by deep learning-based reduced order models [3.5161229331588095]
  We propose a non-intrusive Deep Learning-based Reduced Order Modeling (DL-ROM) technique for the rapid control of systems described in terms of parametrized PDEs in multiple scenarios. After (i) data generation, (ii) dimensionality reduction, and (iii) neural networks training in the offline phase, optimal control strategies can be rapidly retrieved in an online phase for any scenario of interest.
  arXiv  Detail & Related papers  (2024-09-09T15:20:24Z)
• Growing Q-Networks: Solving Continuous Control Tasks with Adaptive Control Resolution [51.83951489847344]
  In robotics applications, smooth control signals are commonly preferred to reduce system wear and energy efficiency. In this work, we aim to bridge this performance gap by growing discrete action spaces from coarse to fine control resolution. Our work indicates that an adaptive control resolution in combination with value decomposition yields simple critic-only algorithms that yield surprisingly strong performance on continuous control tasks.
  arXiv  Detail & Related papers  (2024-04-05T17:58:37Z)
• Regret-optimal Estimation and Control [52.28457815067461]
  We show that the regret-optimal estimator and regret-optimal controller can be derived in state-space form. We propose regret-optimal analogs of Model-Predictive Control (MPC) and the Extended KalmanFilter (EKF) for systems with nonlinear dynamics.
  arXiv  Detail & Related papers  (2021-06-22T23:14:21Z)
• Adaptive Control and Regret Minimization in Linear Quadratic Gaussian (LQG) Setting [91.43582419264763]
  We propose LqgOpt, a novel reinforcement learning algorithm based on the principle of optimism in the face of uncertainty. LqgOpt efficiently explores the system dynamics, estimates the model parameters up to their confidence interval, and deploys the controller of the most optimistic model.
  arXiv  Detail & Related papers  (2020-03-12T19:56:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.