mlsanityData to 7 Oct 2026

Adaptive-Control-Oriented Meta-Learning for Nonlinear Systems

arXiv 2103.04490 ↗First posted 7 Mar 2021cs.RO cs.LG cs.SYcited by 38

Not on the map. Why?

Abstract (arXiv)

Real-time adaptation is imperative to the control of robots operating in complex, dynamic environments. Adaptive control laws can endow even nonlinear systems with good trajectory tracking performance, provided that any uncertain dynamics terms are linearly parameterizable with known nonlinear features. However, it is often difficult to specify such features a priori, such as for aerodynamic disturbances on rotorcraft or interaction forces between a manipulator arm and various objects. In this paper, we turn to data-driven modeling with neural networks to learn, offline from past data, an adaptive controller with an internal parametric model of these nonlinear features. Our key insight is that we can better prepare the controller for deployment with control-oriented meta-learning of features in closed-loop simulation, rather than regression-oriented meta-learning of features to fit input-output data. Specifically, we meta-learn the adaptive controller with closed-loop tracking simulation as the base-learner and the average tracking error as the meta-objective. With a nonlinear planar rotorcraft subject to wind, we demonstrate that our adaptive controller outperforms other controllers trained with regression-oriented meta-learning when deployed in closed-loop for trajectory tracking control.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). Builds on 35 of its 84 references that are in the map. First posted on arXiv 7 Mar 2021.

Builds on

35 of 84 references.

References · 35

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  3. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  4. 2018Neural Ordinary Differential Equationscited by 3,733
  5. 2020Meta-Learning in Neural Networks: A Surveycited by 944
  6. 2019Meta-Learning with Implicit Gradientscited by 523
  7. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  8. 2018Meta-learning with differentiable closed-form solverscited by 395
  9. 2018Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learningcited by 270
  10. 2018Model-Ensemble Trust-Region Policy Optimizationcited by 214
  11. 2018Differentiable MPC for End-to-end Planning and Controlcited by 178
  12. 2020Neural Lyapunov Controlcited by 142
23 more
  1. 2016EPOpt: Learning Robust Neural Network Policies Using Model Ensemblescited by 136
  2. 2018Model-Based Reinforcement Learning via Meta-Policy Optimizationcited by 99
  3. 2018The Lyapunov Neural Network: Adaptive Stability Certification for Safe Learning of Dynamical Systemscited by 87
  4. 2020Adaptive Checkpoint Adjoint Method for Gradient Estimation in Neural ODEcited by 76
  5. 2020Learning Certified Control using Contraction Metriccited by 48
  6. 2018Meta-Learning Priors for Efficient Online Bayesian Regressioncited by 47
  7. 2020Learning Stability Certificates from Datacited by 45
  8. 2019Stochastic Mirror Descent on Overparameterized Nonlinear Models: Convergence, Implicit Regularization, and Generalizationcited by 40
  9. 2015Control Contraction Metrics: Convex and Intrinsic Criteria for Nonlinear Feedback Designcited by 38
  10. 2019Learning Stabilizable Nonlinear Dynamics with Contraction-Based Regularizationcited by 32
  11. 2019Learning Convex Optimization Control Policiescited by 31
  12. 2018Stochastic Gradient/Mirror Descent: Minimax Optimality and Implicit Regularizationcited by 29
  13. 2020Model-Based Meta-Reinforcement Learning for Flight with Suspended Payloadscited by 27
  14. 2018Beyond Convexity -- Contraction and Global Convergence of Gradient Descentcited by 17
  15. 2018Adaptive MPC for Iterative Taskscited by 15
  16. 2019Deep Model Reference Adaptive Controlcited by 14
  17. 2020Asynchronous Deep Model Reference Adaptive Controlcited by 13
  18. 2017Linear Matrix Inequalities for Physically-Consistent Inertial Parameter Identification: A Statistical Perspective on the Mass Distributioncited by 11
  19. 2021Meta-Learning-Based Robust Adaptive Flight Control Under Uncertain Wind Conditionscited by 8
  20. 2019A robust adaptive model predictive control framework for nonlinear uncertain systemscited by 7
  21. 2019Implicit Regularization and Momentum Algorithms in Nonlinearly Parameterized Adaptive Control and Predictioncited by 7
  22. 2018Voliro: An Omnidirectional Hexacopter With Tiltable Rotorscited by 6
  23. 2020Automatic Differentiation and Continuous Sensitivity Analysis of Rigid Body Dynamicscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 11; 2023: 11; 2024: 7; 2025: 3; 2026: 2.

38 papers.

Sort:

By area:

  1. 2022Neural-Fly Enables Rapid Learning for Agile Flight in Strong Windscited by 80
  2. 2023Finetuning Offline World Models in the Real Worldcited by 39
  3. 2022A System-Level View on Out-of-Distribution Data in Roboticscited by 33
  4. 2023Physics-Informed Machine Learning for Modeling and Control of Dynamical Systemscited by 28
  5. 2024ASID: Active Exploration for System Identification in Robotic Manipulationcited by 27
  6. 2021Meta-Adaptive Nonlinear Control: Theory and Algorithmscited by 23
  7. 2022Multi-Task Imitation Learning for Linear Dynamical Systemscited by 22
  8. 2022Control-oriented meta-learningcited by 17
  9. 2023Optimal Exploration for Model-Based RL in Nonlinear Systemscited by 17
  10. 2023Sample-Efficient Linear Representation Learning from Non-IID Non-Isotropic Datacited by 12
  11. 2022Meta-Learning of Neural State-Space Models Using Data From Similar Systemscited by 11
  12. 2021Adaptive Robust Model Predictive Control with Matched and Unmatched Uncertaintycited by 7
26 more
  1. 2021Adaptive Control of SE(3) Hamiltonian Dynamics with Learned Disturbance Featurescited by 6
  2. 2023Data-Driven Control with Inherent Lyapunov Stabilitycited by 6
  3. 2022Optimizing Closed-Loop Performance with Data from Similar Systems: A Bayesian Meta-Learning Approachcited by 5
  4. 2023Learning Control-Oriented Dynamical Structure from Datacited by 5
  5. 2023Safe Navigation in Unstructured Environments by Minimizing Uncertainty in Control and Perceptioncited by 5
  6. 2023On the adaptation of in-context learners for system identificationcited by 5
  7. 2024Projected Neural Differential Equations for Learning Constrained Dynamicscited by 5
  8. 2025Meta-Learning for Physically-Constrained Neural System Identificationcited by 5
  9. 2022Meta-SysId: A Meta-Learning Approach for Simultaneous Identification and Predictioncited by 3
  10. 2021Online Algorithms and Policies Using Adaptive and Machine Learning Approachescited by 2
  11. 2022Adaptive Asynchronous Control Using Meta-learned Neural Ordinary Differential Equationscited by 2
  12. 2022Neural-Rendezvous: Provably Robust Guidance and Control to Encounter Interstellar Objectscited by 2
  13. 2022Graph Neural Network Expressivity and Meta-Learning for Molecular Property Regressioncited by 2
  14. 2024Combining Federated Learning and Control: A Surveycited by 2
  15. 2024Predictive Control and Regret Analysis of Non-Stationary MDP with Look-ahead Informationcited by 2
  16. 2025Context-Aware Deep Lagrangian Networks for Model Predictive Controlcited by 2
  17. 2022Adaptive Robust Model Predictive Control via Uncertainty Cancellationcited by 1
  18. 2023Model-Assisted Probabilistic Safe Adaptive Control With Meta-Bayesian Learningcited by 1
  19. 2024LeARN: Learnable and Adaptive Representations for Nonlinear Dynamics in System Identificationcited by 1
  20. 2023Efficient Deep Learning of Robust, Adaptive Policies using Tube MPC-Guided Data Augmentationcited by 0
  21. 2023A Reinforcement Learning Approach for Robust Supervisory Control of UAVs Under Disturbancescited by 0
  22. 2024Proto-MPC: An Encoder-Prototype-Decoder Approach for Quadrotor Control in Challenging Windscited by 0
  23. 2024Extremum-Seeking Action Selection for Accelerating Policy Optimizationcited by 0
  24. 2025Adaptive MPC-based quadrupedal robot control under periodic disturbancescited by 0
  25. 2026T2S-MPC: Time-Embedded Online Adaptive Model Predictive Control for Time-Varying Dynamicscited by 0
  26. 2026Neural ODEs Meet Concurrent Learning: Stable Online Learning with Lyapunov Guaranteescited by 0