8期

最新文章

• Cautious Bayesian MPC: Regret Analysis and Bounds on the Number of Unsafe Learning Episodes AI翻译
  作者：Wabersich, Kim Peter; Zeilinger, Melanie N.
  作者单位：Swiss Federal Institutes of Technology Domain; ETH Zurich
  摘要：This article investigates the combination of model predictive control (MPC) concepts and posterior sampling techniques and proposes a simple constraint tightening technique to introduce cautiousness during explorative learning episodes. The provided theoretical analysis in terms of cumulative regret focuses on previously stated sufficient conditions of the resulting Cautious Bayesian MPC algorithm and shows Lipschitz continuity of the future reward function in the case of linear MPC problems. ...
• On-the-Fly Control of Unknown Systems: From Side Information to Performance Guarantees Through Reachability AI翻译
  作者：Djeumou, Franck; Vinod, Abraham P.; Goubault, Eric; Putot, Sylvie; Topcu, Ufuk
  作者单位：University of Texas System; University of Texas Austin; Institut Polytechnique de Paris; Ecole Polytechnique; Centre National de la Recherche Scientifique (CNRS)
  摘要：In this article, we develop data-driven algorithms for reachability analysis and control of systems with a priori unknown nonlinear dynamics. The resulting algorithms not only are suitable for settings with real-time requirements but also provide provable performance guarantees. To this end, they merge noisy data from only a single finite-horizon trajectory and, if available, various forms of side information. Such side information may include knowledge of the regularity of the dynamics, algeb...
• On Stochastic Stabilization via Nonsmooth Control Lyapunov Functions AI翻译
  作者：Osinenko, Pavel; Yaremenko, Grigory; Malaniya, Georgiy
  作者单位：Skolkovo Institute of Science & Technology
  摘要：Control Lyapunov function is a central tool in stabilization. It generalizes an abstract energy function-a Lyapunov function-to the case of controlled systems. It is a known fact that most control Lyapunov functions are nonsmooth-so is the case in nonholonomic systems, like wheeled robots and cars. Frameworks for stabilization using nonsmooth control Lyapunov functions exist, such as Dini aiming and steepest descent. This work generalizes the related results to the stochastic case. As the grou...
• On the Existence of Invariantly Differentiable Functionals for Globally Exponentially Stable Time-Delay Systems AI翻译
  作者：Talebi, Soroush; Ataei, Mohammad; Pepe, Pierdomenico
  作者单位：University of Isfahan; University of L'Aquila
  摘要：This note argues over the existence of invariantly differentiable functionals for globally exponentially stable time-delay systems. We show that the existence of invariantly differentiable, Lipschitz on bounded sets Lyapunov-Krasovskii functional is a necessary and sufficient condition for the global exponential stability of time-invariant nonlinear systems described by retarded functional differential equations with discrete type delay. The presented converse results are in terms of the invar...
• On the Sample Complexity of Decentralized Linear Quadratic Regulator With Partially Nested Information Structure AI翻译
  作者：Ye, Lintao; Zhu, Hao; Gupta, Vijay
  作者单位：Huazhong University of Science & Technology; Huazhong University of Science & Technology; University of Texas System; University of Texas Austin; Purdue University System; Purdue University
  摘要：In this article, we study the problem of control policy design for decentralized state-feedback linear quadratic control with a partially nested information structure, when the system model is unknown. We propose a model-based learning solution, which consists of two steps. First, we estimate the unknown system model from a single system trajectory of finite length, using least squares estimation. Next, based on the estimated system model, we design a decentralized control policy that satisfie...
• Global Feedback Regulation for a Class of Uncertain Nonlinear Systems via Integral Control: A Gain Control Technique AI翻译
  作者：Zhang, Xianfu; Chen, Xiandong; Wen, Changyun
  作者单位：Shandong University; Nanyang Technological University
  摘要：This article studies the global feedback regulation problems for triangular nonlinear systems perturbed by matched disturbances and modeling uncertainties with unknown system parameters. Instead of constructing extended state observers, new integral controllers composed of an integral dynamic are constructed to make all states of the uncertain systems bounded and asymptotically converge to zero. First, an integral dynamic is constructed and a new state transformation is introduced, which trans...
• Efficient Strategy Synthesis for MDPs With Resource Constraints AI翻译
  作者：Blahoudek, Frantisek; Novotny, Petr; Ornik, Melkior; Thangeda, Pranay; Topcu, Ufuk
  作者单位：University of Texas System; University of Texas Austin; Masaryk University; University of Illinois System; University of Illinois Urbana-Champaign; University of Texas System; University of Texas Austin
  摘要：We consider qualitative strategy synthesis for the formalism called consumption Markov decision processes. This formalism can model the dynamics of an agent that operates under resource constraints in a stochastic environment. The presented algorithms work in time polynomial with respect to the representation of the model and they synthesize strategies ensuring that a given set of goal states will be reached (once or infinitely many times) with probability 1 without resource exhaustion. In par...
• Nonlinear Two-Time-Scale Stochastic Approximation: Convergence and Finite-Time Performance AI翻译
  作者：Doan, Thinh T. T.
  作者单位：Virginia Polytechnic Institute & State University
  摘要：Two-time-scale stochastic approximation, a generalized version of the popular stochastic approximation, has found broad applications in many areas including stochastic control, optimization, and machine learning. Despite its popularity, theoretical guarantees of this method, especially its finite-time performance, are mostly achieved for the linear case while the results for the nonlinear counterpart are very sparse. Motivated by the classic control theory for singularly perturbed systems, we ...
• On Consistency, Viability, and Admissibility in Constrained Ensemble and Hierarchical Control Systems AI翻译
  作者：Aschenbruck, Tim; Petzke, Felix; Rumschinski, Philipp; Streif, Stefan
  作者单位：Technische Universitat Chemnitz
  摘要：Several control architectures, such as decentralized, distributed, and hierarchical control, have been elaborated over the past decades for controlling systems composed of a set of subsystems. However, computational complexity and constraint satisfaction are still challenging tasks. We present an approach to control an ensemble of similar heterogeneous systems with input and state constraints via an identical control input. This control input is globally admissible and computed based on an agg...
• On the Design of Regularized Explicit Predictive Controllers From Input-Output Data AI翻译
  作者：Breschi, Valentina; Sassella, Andrea; Formentin, Simone
  作者单位：Polytechnic University of Milan
  摘要：On the wave of recent advances in data-driven predictive control, we present an explicit controller that can be constructed from a batch of input/output data only. The proposed explicit law is built upon a regularized data-driven control problem, so as to guarantee the uniqueness of the explicit predictive controller and to endow it with noise handling capabilities. The effectiveness of the retrieved explicit law and the repercussions of regularization on noise handling is analyzed on a benchm...