arXiv subjects

Prabhat K. Mishra

Publications and source records attributed to Prabhat K. Mishra.

12 recordsLinked to original sources

arXiv2026

LQG solution for POMDP without estimating states: A minimum variance approach

This paper investigates the control of discrete-time linear time-invariant (LTI) systems subject to incomplete and corrupted measurements. Specifically, we focus on designing a Linear Quadratic Gaussian (LQG) controller without relying on explicit state estimation. By leveraging minimum variance duality, our approach allows the current control input to be represented as a linear function of available measurements and previously applied inputs, successfully reducing the task to a tractable deterministic optimization problem. We provide theoretical justification for this framework and demonstrate its practical effectiveness through numerical experiments.

math.OC↗

arXiv2026

Polynomial Chaos-based Stochastic Model Predictive Control: An Overview and Future Research Directions

This article is devoted to providing a review of mathematical formulations in which Polynomial Chaos Theory (PCT) has been incorporated into stochastic model predictive control (SMPC). In the past decade, PCT has been shown to provide a computationally tractable way to perform complete and accurate uncertainty propagation through (smooth) nonlinear dynamic systems. As such, it represents a very useful computational tool for accelerating the computations needed in SMPC with time invariant uncertainties. It turns out that it can also be used to reduce complexity of chance constraints, which are an important component of SMPC. In this paper, we provide an overview of PCT and discuss how it can be applied in such time invariant settings.

eess.SY↗

arXiv2025

Algorithmic design and implementation considerations of deep MPC

Deep Model Predictive Control (Deep MPC) is an evolving field that integrates model predictive control and deep learning. This manuscript is focused on a particular approach, which employs deep neural network in the loop with MPC. This class of approaches distributes control authority between a neural network and an MPC controller, in such a way that the neural network learns the model uncertainties while the MPC handles constraints. The approach is appealing because training data collected while the system is in operation can be used to fine-tune the neural network, and MPC prevents unsafe behavior during those learning transients. This manuscript explains implementation challenges of Deep MPC, algorithmic way to distribute control authority and argues that a poor choice in distributing control authority may lead to poor performance. A reason of poor performance is explained through a numerical experiment on a four-wheeled skid-steer dynamics.

eess.SY↗

arXiv2023

Unmatched uncertainty mitigation through neural network supported model predictive control

This paper presents a deep learning based model predictive control (MPC) algorithm for systems with unmatched and bounded state-action dependent uncertainties of unknown structure. We utilize a deep neural network (DNN) as an oracle in the underlying optimization problem of learning based MPC (LBMPC) to estimate unmatched uncertainties. Generally, non-parametric oracles such as DNN are considered difficult to employ with LBMPC due to the technical difficulties associated with estimation of their coefficients in real time. We employ a dual-timescale adaptation mechanism, where the weights of the last layer of the neural network are updated in real time while the inner layers are trained on a slower timescale using the training data collected online and selectively stored in a buffer. Our results are validated through a numerical experiment on the compression system model of jet engine. These results indicate that the proposed approach is implementable in real time and carries the theoretical guarantees of LBMPC.

cs.LG↗

arXiv2023

Deep Model Predictive Control

This paper presents a deep learning based model predictive control algorithm for control affine nonlinear discrete time systems with matched and bounded state-dependent uncertainties of unknown structure. Since the structure of uncertainties is not known, a deep neural network (DNN) is employed to approximate the disturbances. In order to avoid any unwanted behavior during the learning phase, a tube based model predictive controller is employed, which ensures satisfaction of constraints and input-to-state stability of the closed-loop states.

eess.SY↗

arXiv2021

Minimum variance constrained estimator

This paper is concerned with the problem of state estimation for discrete-time linear systems in the presence of additional (equality or inequality) constraints on the state (or estimate). By use of the minimum variance duality, the estimation problem is converted into an optimal control problem. Two algorithmic solutions are described: the full information estimator (FIE) and the moving horizon estimator (MHE). The main result is to show that the proposed estimator is stable in the sense of an observer. The proposed algorithm is distinct from the standard algorithm for constrained state estimation based upon the use of the minimum energy duality. The two are compared numerically on the benchmark batch reactor process model.

math.OC↗

arXiv2021

Deep Model Predictive Control with Stability Guarantees

This paper presents a deep learning based model predictive control algorithm for control affine nonlinear discrete time systems with matched and bounded state dependent uncertainties of unknown structure. Since the structure of uncertainties is not known, a deep learning based adaptive mechanism is utilized to mitigate disturbances. In order to avoid any unwanted behavior during the learning phase, a tube based model predictive controller is employed, which ensures satisfaction of constraints and input-to-state stability of the closed-loop states. In addition, the proposed approach guarantees the convergence of states to origin under certain verifiable conditions. To ensure stability and undesirable learning transients, a dual-timescale adaptation mechanism is proposed, where the weights of the last layer of the neural network are updated each time instant while the inner layers are trained on a slower timescale using training data collected online and selectively stored in a buffer on the basis of singular value maximization criterion. Our results are validated through numerical experiments on wing-rock dynamics. These results indicate that the proposed deep-MPC architecture is effective in learning to control safety critical systems without suffering instability drawbacks.

math.OC↗

arXiv2020

Reference tracking stochastic model predictive control over unreliable channels and bounded control actions

A stochastic model predictive control framework over unreliable Bernoulli communication channels, in the presence of unbounded process noise and under bounded control inputs, is presented for tracking a reference signal. The data losses in the control channel are compensated by a carefully designed transmission protocol, and that of the sensor channel by a dropout compensator. A class of saturated, disturbance feedback policies is proposed for control in the presence of noisy dropout compensation. A reference governor is employed to generate trackable reference trajectories and stability constraints are employed to ensure mean-square boundedness of the reference tracking error. The overall approach yields a computationally tractable quadratic program, which can be iteratively solved online.

math.OC↗

arXiv2020

Centralized model predictive control with distributed adaptation

A centralized model predictive controller (MPC), which is unaware of local uncertainties, for an affine discrete time nonlinear system is presented. The local uncertainties are assumed to be matched, bounded and structured. In order to encounter disturbances and to improve performance, an adaptive control mechanism is employed locally. The proposed approach ensures input-to-state stability of closed-loop states and convergence to the equilibrium point. Moreover, uncertainties are learnt in terms of the given feature basis by using adaptive control mechanism. In addition, hard constraints on state and control are satisfied.

math.OC↗

arXiv2020

Stochastic Predictive Control under Intermittent Observations and Unreliable Actions

We propose a provably stabilizing and tractable approach for control of constrained linear systems under intermittent observations and unreliable transmissions of control commands. A smart sensor equipped with a Kalman filter is employed for the estimation of the states from incomplete and corrupt measurements, and an estimator at the controller side optimally feeds the intermittently received sensor data to the controller. The remote controller iteratively solves constrained stochastic optimal control problems and transmits the control commands according to a carefully designed transmission protocol through an unreliable channel. We present a (globally) recursively feasible quadratic program, which is solved online to yield a stabilizing controller for Lyapunov stable linear time invariant systems under any positive bound on control values and any non-zero transmission probabilities of Bernoulli channels.

math.OC↗

arXiv2017

Sparse and Constrained Stochastic Predictive Control for Networked Systems

This article presents a novel class of control policies for networked control of Lyapunov-stable linear systems with bounded inputs. The control channel is assumed to have i.i.d. Bernoulli packet dropouts and the system is assumed to be affected by additive stochastic noise. Our proposed class of policies is affine in the past dropouts and saturated values of the past disturbances. We further consider a regularization term in a quadratic performance index to promote sparsity in control. We demonstrate how to augment the underlying optimization problem with a constant negative drift constraint to ensure mean-square boundedness of the closed-loop states, yielding a convex quadratic program to be solved periodically online. The states of the closed-loop plant under the receding horizon implementation of the proposed class of policies are mean square bounded for any positive bound on the control and any non-zero probability of successful transmission.

math.OC↗

arXiv2017

Stabilizing Stochastic Predictive Control under Bernoulli Dropouts

This article presents tractable and recursively feasible optimization-based controllers for stochastic linear systems with bounded controls. The stochastic noise in the plant is assumed to be additive, zero mean and fourth moment bounded, and the control values transmitted over an erasure channel. Three different transmission protocols are proposed having different requirements on the storage and computational facilities available at the actuator. We optimize a suitable stochastic cost function accounting for the effects of both the stochastic noise and the packet dropouts over affine saturated disturbance feedback policies. The proposed controllers ensure mean square boundedness of the states in closed-loop for all positive values of control bounds and any non-zero probability of successful transmission over a noisy control channel.

math.OC↗