Provably safe and robust learning-based model predictive control
From MaRDI portal
Publication:490551
DOI10.1016/J.AUTOMATICA.2013.02.003zbMATH Open1319.93047arXiv1107.2487OpenAlexW2006859604MaRDI QIDQ490551FDOQ490551
S. Shankar Sastry, H. González, Claire Tomlin, Anil Aswani
Publication date: 27 August 2015
Published in: Automatica (Search for Journal in Brave)
Abstract: Controller design faces a trade-off between robustness and performance, and the reliability of linear controllers has caused many practitioners to focus on the former. However, there is renewed interest in improving system performance to deal with growing energy constraints. This paper describes a learning-based model predictive control (LBMPC) scheme that provides deterministic guarantees on robustness, while statistical identification tools are used to identify richer models of the system in order to improve performance; the benefits of this framework are that it handles state and input constraints, optimizes system performance with respect to a cost function, and can be designed to use a wide variety of parametric or nonparametric statistical tools. The main insight of LBMPC is that safety and performance can be decoupled under reasonable conditions in an optimization framework by maintaining two models of the system. The first is an approximate model with bounds on its uncertainty, and the second model is updated by statistical methods. LBMPC improves performance by choosing inputs that minimize a cost subject to the learned dynamics, and it ensures safety and robustness by checking whether these same inputs keep the approximate model stable when it is subject to uncertainty. Furthermore, we show that if the system is sufficiently excited, then the LBMPC control action probabilistically converges to that of an MPC computed using the true dynamics.
Full work available at URL: https://arxiv.org/abs/1107.2487
Recommendations
- Learning for MPC with stability \& safety guarantees
- Robust learning-based MPC for nonlinear constrained systems
- ABC-LMPC: Safe Sample-Based Learning MPC for Stochastic Nonlinear Dynamical Systems with Adjustable Boundary Conditions
- Online learning with stability guarantees: a memory-based warm starting for real-time MPC
- Safe control of nonlinear systems in LPV framework using model-based reinforcement learning
Cites Work
- Hybrid Systems: Computation and Control
- Variational Analysis
- Ridge Regression: Biased Estimation for Nonorthogonal Problems
- Title not available (Why is that?)
- Title not available (Why is that?)
- Linear Model Selection by Cross-Validation
- Title not available (Why is that?)
- Asymptotic Properties of Non-Linear Least Squares Estimators
- On adaptive estimation
- Multivariate locally weighted least squares regression
- A distribution-free theory of nonparametric regression
- Nonlinear systems. Analysis, stability, and control
- Linear and nonlinear iterative learning control
- Constrained model predictive control: Stability and optimality
- A time-dependent Hamilton-Jacobi formulation of reachable sets for continuous dynamic games
- Input-to-state stability for discrete-time nonlinear systems
- Robust model predictive control using tubes.
- Estimating the Error Rate of a Prediction Rule: Improvement on Cross-Validation
- Parameterized Robust Control Invariant Sets for Linear Systems: Theoretical Advances and Computational Remarks
- A converse Lyapunov theorem for discrete-time systems with disturbances
- MPC for tracking piecewise constant references for constrained linear systems
- Weighted Local Regression and Kernel Methods for Nonparametric Curve Fitting
- Title not available (Why is that?)
- SNOPT: An SQP Algorithm for Large-Scale Constrained Optimization
- Title not available (Why is that?)
- Title not available (Why is that?)
- Sensitivity analysis for nonlinear programming using penalty methods
- Theory and computation of disturbance invariant sets for discrete-time linear systems
- Problems of identification and control
- Dual mode predictive tracking of piecewise constant references for constrained linear systems
- Systems with persistent disturbances: Predictive control with restricted constraints
- Adaptive control of linearizable systems
- Regression on manifolds: estimation of the exterior derivative
- Robustness and Robust Design of MPC for Nonlinear Discrete-Time Systems
- Title not available (Why is that?)
- The Consistency of Nonlinear Regressions
- Robust adaptive MPC for constrained uncertain nonlinear systems
- Adaptive control of unknown plants using dynamical neural networks
- Linear time‐varying model predictive control and its application to active steering systems: Stability analysis and experimental validation
- Estimation theory and uncertainty intervals evaluation in presence of unknown but bounded errors: Linear families of models and estimators
- Title not available (Why is that?)
- Input-to-State Stability: A Unifying Framework for Robust Model Predictive Control
- Title not available (Why is that?)
- Examples when nonlinear model predictive control is nonrobust
- Reachability Analysis of Discrete-Time Systems With Disturbances
- Large‐Scale Inverse Problems and Quantification of Uncertainty
- Title not available (Why is that?)
- Title not available (Why is that?)
- Four encounters with system identification
- Strong consistency of least squares estimates in multiple regression II
- Adaptive model predictive control for a class of constrained linear systems based on the comparison model
Cited In (54)
- Learning for MPC with stability \& safety guarantees
- Model predictive control for nonlinear systems with time‐varying dynamics and guaranteed Lyapunov stability
- Adaptive control Lyapunov function based model predictive control for continuous nonlinear systems
- A Q-learning predictive control scheme with guaranteed stability
- Robust MPC with recursive model update
- Rolling self-triggered distributed MPC for dynamically coupled nonlinear systems
- Adaptive receding horizon control for constrained MIMO systems
- Learning-based predictive control for linear systems: a unitary approach
- Robust adaptive model predictive control with persistent excitation conditions
- Statistics with set-valued functions: applications to inverse approximate optimization
- SAMBA: safe model-based \& active reinforcement learning
- Stabilizing predictive control with persistence of excitation for constrained linear systems
- Separation of learning and control for cyber-physical systems
- Adaptive‐optimal control under time‐varying stochastic uncertainty using past learning
- Behavioral analytics for myopic agents
- Bayesian optimization with safety constraints: safe and automatic parameter tuning in robotics
- Learning-based state estimation and control using MHE and MPC schemes with imperfect models
- Online learning‐based model predictive control with Gaussian process models and stability guarantees
- Online learning constrained model predictive control based on double prediction
- Learning model predictive control with long short‐term memory networks
- Safe Formation Control with Constrained Linear Model Predictive Control
- Safe reward‐based deep reinforcement learning control for an electro‐hydraulic servo system
- Learning‐based adaptive‐scenario‐tree model predictive control with improved probabilistic safety using robust Bayesian neural networks
- Adaptive stochastic model predictive control via network ensemble learning
- Stability-constrained Markov decision processes using MPC
- Robust adaptive tube tracking model predictive control for piece‐wise constant reference signals
- Nonlinear learning‐based model predictive control supporting state and input dependent model uncertainty estimates
- Adaptive model predictive control for linear time varying MIMO systems
- Robust adaptive model predictive control: Performance and parameter estimation
- Safe learning-based model predictive control using the compatible models approach
- ABC-LMPC: Safe Sample-Based Learning MPC for Stochastic Nonlinear Dynamical Systems with Adjustable Boundary Conditions
- Model-based Reinforcement Learning: A Survey
- Indirect adaptive model predictive control and its application to uncertain linear systems
- Almost surely safe exploration and exploitation for deep reinforcement learning with state safety estimation
- Model reference safety-critical adaptive control for nonlinear and switched systems
- Learning-Based MPC-Architecture Satisfying Constraints During Open Loop Identification
- Robust learning-based MPC for nonlinear constrained systems
- Lazily adapted constant kinky inference for nonparametric regression and model-reference adaptive control
- Data‐enabled predictive control for quadcopters
- Safe control of nonlinear systems in LPV framework using model-based reinforcement learning
- Inverse Optimization with Noisy Data
- Minimum time learning model predictive control
- Online learning with stability guarantees: a memory-based warm starting for real-time MPC
- Online learning based risk-averse stochastic MPC of constrained linear uncertain systems
- Economic Lyapunov‐based model predictive control with event‐triggered parametric identification
- Constrained robust model predictive control embedded with a new data-driven technique
- A General Safety Framework for Learning-Based Control in Uncertain Robotic Systems
- Performance bounds of adaptive MPC with bounded parameter uncertainties
- On the construction of safe controllable regions for affine systems with applications to robotics
- Data-driven safe gain-scheduling control
- A learning- and scenario-based MPC design for nonlinear systems in LPV framework with safety and stability guarantees
- Sampled-data funnel control and its use for safe continual learning
- Combining learning and control in linear systems
- Adaptive learning-based model predictive control for uncertain interconnected systems: a set membership identification approach
Uses Software
This page was built for publication: Provably safe and robust learning-based model predictive control
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q490551)
