8期

最新文章

• Safe Guaranteed Exploration for Nonlinear Systems AI翻译
  作者：Prajapat, Manish; Kohler, Johannes; Turchetta, Matteo; Krause, Andreas; Zeilinger, Melanie N.
  作者单位：Swiss Federal Institutes of Technology Domain; ETH Zurich
  摘要：Safely exploring environments with a-priori unknown constraints is a fundamental challenge that restricts the autonomy of robots. While safety is paramount, guarantees on sufficient exploration are also crucial for ensuring autonomous task completion. To address these challenges, we propose a novel safe guaranteed exploration framework using optimal control, which achieves first-of-its-kind results: guaranteed exploration for nonlinear systems with finite-time sample complexity bounds, while b...
• Real-Time Estimation of DoS Duration and Frequency for Security Control AI翻译
  作者：Sun, Yifan; Lu, Jianquan; Ho, Daniel W. C.; Li, Lulu
  作者单位：Southeast University - China; Southeast University - China; City University of Hong Kong
  摘要：In this article, we develop a new denial-of-service (DoS) estimator, enabling defenders to identify duration and frequency parameters of any DoS attacker, except for three edge cases, exclusively using real-time data. The key advantage of the estimator lies in its capability to facilitate security control in a wide range of practical scenarios, even when the attacker's information is previously unknown. We demonstrate the advantage and application of our new estimator in the context of two cla...
• Deep Model Predictive Control With Stability Guarantees AI翻译
  作者：Mishra, Prabhat K.; Gasparino, Mateus V.; Chowdhary, Girish
  作者单位：Indian Institute of Technology System (IIT System); Indian Institute of Technology (IIT) - Kharagpur; University of Illinois System; University of Illinois Urbana-Champaign
  摘要：This article presents a deep learning-based model predictive control (MPC) 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 is employed to approximate them. In order to avoid any unwanted behavior during the learning phase, a tube-based nonlinear model predictive controller is employed, which ensures satisfaction of constraints and in...
• Distributed Cutting Plane Method via Sample Point Consensus AI翻译
  作者：Zhong, Tianyi; Angeli, David
  作者单位：Imperial College London; University of Florence
  摘要：This article considers a general setup for the constrained convex optimization problem over jointly fully connected time-varying networks. We propose a novel cutting plane-based method that embeds a proximity-based consensus scheme for solving this (potentially nonsmooth) optimization problem. The consensus mechanism allows agents to select the same sample point and therefore reconstruct the centralized cut individually. Under convexity, we prove that agents' sample points converge to the opti...
• ADMM-Tracking Gradient for Distributed Optimization Over Asynchronous and Unreliable Networks AI翻译
  作者：Carnevale, Guido; Bastianello, Nicola; Notarstefano, Giuseppe; Carli, Ruggero
  作者单位：University of Bologna; Royal Institute of Technology; University of Padua
  摘要：In this article, we propose a novel distributed algorithm for consensus optimization over networks and a robust extension tailored to deal with asynchronous agents and packet losses. Indeed, to robustly achieve dynamic consensus on the solution estimates and the global descent direction, we embed in our algorithms a distributed implementation of the alternating direction method of multipliers. Such a mechanism is suitably interlaced with a local proportional action steering each agent estimate...
• Setwise Coordinate Descent for Dual Asynchronous Decentralized Optimization AI翻译
  作者：Costantini, Marina; Liakopoulos, Nikolaos; Mertikopoulos, Panayotis; Spyropoulos, Thrasyvoulos
  作者单位：IMT - Institut Mines-Telecom; EURECOM; Communaute Universite Grenoble Alpes; Institut National Polytechnique de Grenoble; Universite Grenoble Alpes (UGA); Centre National de la Recherche Scientifique (CNRS); Inria; Technical University of Crete
  摘要：In decentralized optimization over networks, synchronizing the updates of all nodes incurs significant communication overhead. Therefore, much of the recent literature has focused on designing asynchronous algorithms where nodes can activate anytime and contact a single neighbor to complete an iteration. However, most works assume that the neighbor selection is done randomly based on a fixed probability distribution, a choice that ignores the optimization landscape at the activation time. Inst...
• Closed-Loop Finite-Time Analysis of Suboptimal Online Control AI翻译
  作者：Karapetyan, Aren; Balta, Efe C.; Iannelli, Andrea; Lygeros, John
  作者单位：Swiss Federal Institutes of Technology Domain; ETH Zurich; University of Stuttgart
  摘要：Suboptimal methods in optimal control arise due to a limited computational budget, unknown system dynamics, or a short prediction window among other reasons. In this work, we study the transient closed-loop performance of such methods by providing finite-time suboptimality gap guarantees. We consider the control of discrete-time, nonlinear time-varying dynamical systems and establish sufficient conditions for such guarantees. These allow the control design to distribute a limited computational...
• Safety-Critical Learning of Robot Control With Temporal Logic Specifications AI翻译
  作者：Cai, Mingyu; Vasile, Cristian-Ioan
  作者单位：University of California System; University of California Riverside; Lehigh University
  摘要：Reinforcement learning (RL) is a promising control approach in many scenarios. However, safety-critical applications are still a challenge due to lack of safety guarantees during exploration and subsequent deployment. The learning problem becomes even more difficult for complex tasks with temporal and logical constraints. In this article, we introduce a modular deep RL architecture as a control framework to satisfy complex tasks specified using linear temporal logic (LTL). To enhance safety, w...
• Cooperative Trajectory Tracking of Heterogeneous Networks by Distributed Learning AI翻译
  作者：Meng, Deyuan; Zhang, Jingyao
  作者单位：Beihang University; Beihang University
  摘要：This article presents a distributed learning approach to achieve the high-precision cooperative trajectory tracking tasks for heterogeneous networks at all time in the presence of changing topologies. An updating law of distributed learning is proposed by leveraging the cooperative tracking error trajectories of agents at all time samples, thanks to which a monotonic convergence result is established for heterogeneous networks of linear agents without iteration-varying uncertainties. When cons...
• Self-Triggered Stabilization of Contracting Systems Under Quantization AI翻译
  作者：Wakaiki, Masashi
  作者单位：Kobe University
  摘要：We propose self-triggered control schemes for nonlinear systems with quantized state measurements. Our focus lies on scenarios where both the controller and the self-triggering mechanism receive only the quantized state at each sampling time. We assume that the ideal closed-loop system without quantization or self-triggered sampling is contracting. Moreover, an upper bound on the growth rate of the open-loop system is assumed to be known. We present two control schemes that achieve closed-loop...