# Safe and Near-Optimal Policy Learning for Model Predictive Control using Primal-Dual Neural Networks

@article{Zhang2019SafeAN,
title={Safe and Near-Optimal Policy Learning for Model Predictive Control using Primal-Dual Neural Networks},
author={Xiaojing Zhang and Monimoy Bujarbaruah and Francesco Borrelli},
journal={2019 American Control Conference (ACC)},
year={2019},
pages={354-359}
}
• Published 19 June 2019
• Computer Science
• 2019 American Control Conference (ACC)
In this paper, we propose a novel framework for approximating the explicit MPC law for linear parameter-varying systems using supervised learning. In contrast to most existing approaches, we not only learn the control policy, but also a “certificate policy”, that allows us to estimate the sub-optimality of the learned control policy online, during execution-time. We learn both these policies from data using supervised learning techniques, and also provide a randomized method that allows us to…

## Tables from this paper

• Computer Science, Mathematics
IEEE Transactions on Control Systems Technology
• 2021
A novel framework for approximating the MPC policy for linear parameter-varying systems using supervised learning that enables the deployment of MPC on resource-constrained systems and demonstrates a speedup of up to up to \$62\times on a desktop computer and on an automotive-grade electronic control unit, while maintaining high control performance.
• Computer Science, Mathematics
• 2021
DPC can learn to stabilize constrained neural control policies for systems with unstable dynamics, and it is demonstrated that DPC scales linearly with problem size, compared to exponential scalability of classical explicit MPC based on multiparametric programming.
• Computer Science
• 2020
Differentiable predictive control is presented, a method for learning constrained neural control policies for linear systems with probabilistic performance guarantees that is scalable and computationally more efficient than implicit, explicit, and approximate MPC.
This technical article aims to address the challenge of generating large training samples to learn the MPC policy by exploiting the parametric sensitivities to cheaply generate additional training samples in the neighborhood of the existing samples.
This work bases its work on a novel robust model predictive control scheme guaranteeing constraint satisfaction and recursive feasibility under disturbances, and extends it by practical useful additions, such as robust dynamic set point tracking and the handling of nonlinear constraints in the output function.
• Computer Science, Mathematics
2022 IEEE 61st Conference on Decision and Control (CDC)
• 2022
This paper proposes a primal-dual framework to learn a stable estimator for linear constrained estimation problems leveraging the moving horizon approach, and is the first learning-based state estimator with feasibility and near- optimality guarantees forlinear constrained systems.
• Mathematics
International Journal of Robust and Nonlinear Control
• 2020
This work builds on existing LMPC methodologies and it guarantees finite time convergence properties for the closed-loop system and it demonstrates that, for a class of nonlinear system and convex constraints, the convex LMPC formulation guarantees recursive constraint satisfaction and non-decreasing performance.
• Computer Science, Mathematics
ArXiv
• 2022
This paper proposes a primal-dual framework to learn a stable estimator for linear constrained estimation problems leveraging the moving horizon approach, and is likely the first learning-based state estimator with feasibility and near-optimality guarantees forlinear constrained systems.

## References

SHOWING 1-10 OF 36 REFERENCES

• Computer Science
2016 IEEE International Conference on Robotics and Automation (ICRA)
• 2016
This work proposes to combine MPC with reinforcement learning in the framework of guided policy search, where MPC is used to generate data at training time, under full state observations provided by an instrumented training environment, and a deep neural network policy is trained, which can successfully control the robot without knowledge of the full state.
• Computer Science
IEEE Conference on Decision and Control and European Control Conference
• 2011
A new synthesis method for low-complexity suboptimal MPC controllers based on function approximation from randomly chosen point-wise sample values that renders the approach particularly suitable for highly concurrent embedded platforms such as FPGAs.
• Mathematics, Engineering
IEEE Control Systems Letters
• 2018
A robust MPC design is combined with statistical learning bounds, and Hoeffding's Inequality is used to validate that the learned MPC satisfies these bounds with high confidence, and the result is a closed-loop statistical guarantee on stability and constraint satisfaction for thelearned MPC.
• Mathematics, Computer Science
IEEE Transactions on Automatic Control
• 2010
This paper compute approximate explicit control laws that trade-off complexity against approximation error for MPC controllers that give rise to convex parametric optimization problems.
• Computer Science, Engineering
2018 Annual American Control Conference (ACC)
• 2018
A modified reinforcement learning policy gradient algorithm is introduced that utilizes knowledge of the system model to efficiently train the neural network and guarantees that the network generates feasible control inputs by projecting onto polytope regions derived from the maximal control invariant set of theSystem.
• Mathematics
• 2017
Predictive Control for Linear and Hybrid Systems is an ideal reference for graduate, postgraduate and advanced control practitioners interested in theory and/or implementation aspects of predictive control.
• Computer Science
IEEE Transactions on Cybernetics
• 2020
We show that artificial neural networks with rectifier units as activation functions can exactly represent the piecewise affine function that results from the formulation of model predictive control
• Engineering
ArXiv
• 2018
This paper proposes an Adaptive Robust Model Predictive Control strategy for lateral control in lane keeping problems, where we continuously learn an unknown, but constant steering angle offset