arXiv subjects

Kanghui He

Publications and source records attributed to Kanghui He.

7 recordsLinked to original sources

arXiv2026

On the Value Function of Infinite-Horizon Optimal Control of Piecewise Affine Systems

In this paper, we study the structure of the value function in constrained infinite-time optimal control (CITOC) problems of piecewise affine (PWA) systems, with $\ell_1$ or $\ell_\infty$ stage cost. Existing works, such as [1], establish that the resulting value function is PWA in the state. However, existing results do not analyze whether the value function is a proper PWA function, i.e., with a finite number of affine pieces over compact sets, or whether the number of pieces can be infinite. We show that the latter case is indeed possible by means of an explicit example, which is also instrumental in establishing rigorous and easily verifiable sufficient conditions that ensure that the resulting value function is a proper PWA function. Our theoretical findings complement well-known results, e.g., the linear-quadratic case, and serve as support for recent learning-based control schemes for PWA systems. Throughout the paper, the proposed results are illustrated by means of a numerical example.

math.OC↗

arXiv2026

Learning-Based Stochastic Optimal Control with Infinite-Horizon Probabilistic Constraints

In this paper, we consider stochastic optimal control problems with infinite-horizon joint chance constraints. By means of an appropriate state augmentation, we reformulate the original problem as a constrained Markov decision process, in which both the cost and the constraint function exhibit an additive structure. We then prove that this formulation enjoys strong duality, thereby enabling us to reformulate the problem as an equivalent unconstrained one in the Lagrange dual framework. We propose a dual-ascent algorithm to solve the resulting problem and show that it converges to a deterministic Markov policy defined over the augmented state space that is both optimal and feasible. To accommodate continuous state-input spaces, we propose a dedicated learning algorithm to approximate the value function in an offline training setting, thereby significantly reducing the computational complexity of the online control phase. We then test our approach on a numerical example and demonstrate its effectiveness compared to online predictive control methods in terms of performance and computational complexity.

math.OC↗

arXiv2025

Predictive control barrier functions for piecewise affine systems with non-smooth constraints

Obtaining control barrier functions (CBFs) with large safe sets for complex nonlinear systems and constraints is a challenging task. Predictive CBFs address this issue by using an online finite-horizon optimal control problem that implicitly defines a large safe set. The optimal control problem, also known as the predictive safety filter (PSF), involves predicting the system's flow under a given backup control policy. However, for non-smooth systems and constraints, some key elements, such as CBF gradients and the sensitivity of the flow, are not well-defined, making the current methods inadequate for ensuring safety. Additionally, for control-non-affine systems, the PSF is generally nonlinear and non-convex, posing challenges for real-time computation. This paper considers piecewise affine systems, which are usually control-non-affine, under nonlinear state and polyhedral input constraints. We solve the safety issue by incorporating set-valued generalized Clarke derivatives in the PSF design. We show that enforcing CBF constraints across all elements of the generalized Clarke derivatives suffices to guarantee safety. Moreover, to lighten the computational overhead, we propose an explicit approximation of the PSF. The resulting control methods are demonstrated through numerical examples.

eess.SY↗

arXiv2025

From learning to safety: A Direct Data-Driven Framework for Constrained Control

Ensuring safety in the sense of constraint satisfaction for learning-based control is a critical challenge, especially in the model-free case. While safety filters address this challenge in the model-based setting by modifying unsafe control inputs, they typically rely on predictive models derived from physics or data. This reliance limits their applicability for advanced model-free learning control methods. To address this gap, we propose a new optimization-based control framework that determines safe control inputs directly from data. The benefit of the framework is that it can be updated through arbitrary model-free learning algorithms to pursue optimal performance. As a key component, the concept of direct data-driven safety filters (3DSF) is first proposed. The framework employs a novel safety certificate, called the state-action control barrier function (SACBF). We present three different schemes to learn the SACBF. Furthermore, based on input-to-state safety analysis, we present the error-to-state safety analysis framework, which provides formal guarantees on safety and recursive feasibility even in the presence of learning inaccuracies. The proposed control framework bridges the gap between model-free learning-based control and constrained control, by decoupling performance optimization from safety enforcement. Simulations on vehicle control illustrate the superior performance regarding constraint satisfaction and task achievement compared to model-based methods and reward shaping.

eess.SY↗

arXiv2023

State-action control barrier functions: Imposing safety on learning-based control with low online computational costs

Learning-based control with safety guarantees usually requires real-time safety certification and modifications of possibly unsafe learning-based policies. The control barrier function (CBF) method uses a safety filter containing a constrained optimization problem to produce safe policies. However, finding a valid CBF for a general nonlinear system requires a complex function parameterization, which in general, makes the policy optimization problem difficult to solve in real time. For nonlinear systems with nonlinear state constraints, this paper proposes the novel concept of state-action CBFs, which not only characterize the safety at each state but also evaluate the control inputs taken at each state. State-action CBFs, in contrast to CBFs, enable a flexible parameterization, resulting in a safety filter that involves a convex quadratic optimization problem. This, in turn, significantly alleviates the online computational burden. To synthesize state-action CBFs, we propose a learning-based approach exploiting Hamilton-Jacobi reachability. The effect of learning errors on the effectiveness of state-action CBFs is addressed by constraint tightening and introducing a new concept called contractive CBFs. These contributions ensure formal safety guarantees for learned CBFs and control policies, enhancing the applicability of learning-based control in real-time scenarios. Simulation results on an inverted pendulum with elastic walls validate the proposed CBFs in terms of constraint satisfaction and CPU time.

eess.SY↗

arXiv2023

Approximate Dynamic Programming for Constrained Piecewise Affine Systems with Stability and Safety Guarantees

Infinite-horizon optimal control of constrained piecewise affine (PWA) systems has been approximately addressed by hybrid model predictive control (MPC), which, however, has computational limitations, both in offline design and online implementation. In this paper, we consider an alternative approach based on approximate dynamic programming (ADP), an important class of methods in reinforcement learning. We accommodate non-convex union-of-polyhedra state constraints and linear input constraints into ADP by designing PWA penalty functions. PWA function approximation is used, which allows for a mixed-integer encoding to implement ADP. The main advantage of the proposed ADP method is its online computational efficiency. Particularly, we propose two control policies, which lead to solving a smaller-scale mixed-integer linear program than conventional hybrid MPC, or a single convex quadratic program, depending on whether the policy is implicitly determined online or explicitly computed offline. We characterize the stability and safety properties of the closed-loop systems, as well as the sub-optimality of the proposed policies, by quantifying the approximation errors of value functions and policies. We also develop an offline mixed-integer linear programming-based method to certify the reliability of the proposed method. Simulation results on an inverted pendulum with elastic walls and on an adaptive cruise control problem validate the control performance in terms of constraint satisfaction and CPU time.

eess.SY↗

arXiv2022

Approximate Dynamic Programming for Constrained Linear Systems: A Piecewise Quadratic Approximation Approach

Approximate dynamic programming (ADP) faces challenges in dealing with constraints in control problems. Model predictive control (MPC) is, in comparison, well-known for its accommodation of constraints and stability guarantees, although its computation is sometimes prohibitive. This paper introduces an approach combining the two methodologies to overcome their individual limitations. The predictive control law for constrained linear quadratic regulation (CLQR) problems has been proven to be piecewise affine (PWA) while the value function is piecewise quadratic. We exploit these formal results from MPC to design an ADP method for CLQR problems. A novel convex and piecewise quadratic neural network with a local-global architecture is proposed to provide an accurate approximation of the value function, which is used as the cost-to-go function in the online dynamic programming problem. An efficient decomposition algorithm is developed to speed up the online computation. Rigorous stability analysis of the closed-loop system is conducted for the proposed control scheme under the condition that a good approximation of the value function is achieved. Comparative simulations are carried out to demonstrate the potential of the proposed method in terms of online computation and optimality.

eess.SY↗