检索结果-内蒙古大学图书馆

Rule-based reinforcement learning for efficient robot navigation with space reduction

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhu, Yuanyang Wang, Zhi Chen, Chunlin Dong, Daoyi Department of Control and Systems Engineering School of Management and Engineering Nanjing University Nanjing210093 China Synergistic Innovation Center of Jiangsu Modern Agricultural Equipment and Technology Zhenjiang212013 China School of Engineering and Information Technology University of New South Wales CanberraACT2600 Australia

For real-world deployments, it is critical to allow robots to navigate in complex environments autonomously. Traditional methods usually maintain an internal map of the environment, and then design several simple rules, in conjunction with a localization and planning approach, to navigate through the internal map. These approaches often involve a variety of assumptions and prior knowledge. In contrast, recent reinforcement learning (RL) methods can provide a model-free, self-learning mechanism as the robot interacts with an initially unknown environment, but are expensive to deploy in real-world scenarios due to inefficient exploration. In this paper, we focus on efficient navigation with the RL technique and combine the advantages of these two kinds of methods into a rule-based RL (RuRL) algorithm for reducing the sample complexity and cost of time. First, we use the rule of wall-following to generate a closed-loop trajectory. Second, we employ a reduction rule to shrink the trajectory, which in turn effectively reduces the redundant exploration space. Besides, we give the detailed theoretical guarantee that the optimal navigation path is still in the reduced space. Third, in the reduced space, we utilize the Pledge rule to guide the exploration strategy for accelerating the RL process at the early stage. Experiments conducted on real robot navigation problems in hex-grid environments demonstrate that RuRL can achieve improved navigation performance. Copyright © 2021, The Authors. All rights reserved.

关键词： Reinforcement learning

Complex systems Modelling of UK Winter Wheat Yield

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Pearson, Simon Hall, R.J. Wei, H.-L. Ma, Y. Fang, Shibo Hanna, Edward School of Geography and Lincoln Centre for Water and Planetary Health University of Lincoln LincolnLN6 7FL United Kingdom Department of Automatic Control and Systems Engineering University of Sheffield SheffieldS1 3JD United Kingdom Lincoln Institute of Agri-Food Technology University of Lincoln Riseholme Campus LincolnLN2 2NG United Kingdom Institute of Ecological and Agricultural Meteorology Chinese Academy of Meteorological Science No. 46 Zhongguancun South Road Beijing100081 China

Wheat is one of the most important global crops and understanding the drivers of wheat yield has important societal benefits. Climate variables are particularly important in determining interannual variations in wheat yield, either as primary factors which directly influence the stages of wheat growth, or as secondary factors through their influence on pests, diseases and soil conditions. Here we present a new approach to model wheat yield modelling;an empirical method based on nonlinear complex systems identification, known as NARMAX (Nonlinear AutoRegressive Moving Average with eXogenous inputs). We demonstrate the NARMAX analytical approach for a specific site, Rothamsted, UK, where detailed meteorological variables are available, together with specific information on site conditions and crop growth stages. An illustrative comparison of NARMAX yield forecasts is made with the WOFOST crop model. We also demonstrate how regional wheat yield forecasts might be derived from a new gridded meteorological data product. © 2022, The Authors. All rights reserved.

关键词： Machine learning

Minimum structural sensor placement for switched linear time-invariant systems and unknown inputs

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Reed, Emily A. Ramos, Guilherme Bogdan, Paul Pequito, Sérgio Ming Hsieh Electrical and Computer Engineering Department University of Southern California United States Department of Electrical and Computer Engineering Faculty of Engineering University of Porto Portugal University of Southern California Ming Hsieh Electrical and Computer Engineering Department Delft University of Technology Delft Center for Systems and Control

In this paper, we study the structural state and input observability of continuous-time switched linear time- invariant systems and unknown inputs. First, we provide necessary and sufficient conditions for their structural state and input observability that can be efficiently verified in O((m(n + p))2), where n is the number of state variables, p is the number of unknown inputs, and m is the number of modes. Moreover, we address the minimum sensor placement problem for these systems by adopting a feed-forward analysis and by providing an algorithm with a computational complexity of O((m(n + p) + α)2.373), where α is the number of target strongly connected components of the system's digraph representation. Lastly, we explore different assumptions on both the system and unknown inputs (latent space) dynamics that add more structure to the problem, and thereby, enable us to render algorithms with lower computational complexity, which are suitable for implementation in large-scale systems. Copyright © 2021, The Authors. All rights reserved.

关键词： Time varying control systems

Improved Robust Predictive control for Lur'e systems Using Set-based Learning

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2018年第20期51卷 487-492页

作者： Nguyen, Hoang Hai Savchenko, Anton Yu, Shuyou Findeisen, Rolf Laboratory for Systems Theory and Automatic Control Otto-von-Guericke University Magdeburg Magdeburg39106 Germany Department of Control Science and Engineering Jilin University China

Predictive control of uncertain nonlinear systems is challenging. Existing approaches often require to find a global minima of a nonconvex optimization problem, and often are conservative, as the worst case solution is considered. This paper presents a robust model predictive control scheme for Lur'e systems subject to constraints, which improves via learning over time and allows efficient implementation using Linear Matrix Inequalities. The approach utilizes Lipschitz continuity conditions for the unknown sector bounded nonlinearity. Based on reconstructions of the unknown function from past experiments and measurements, the bound on the uncertainty is improved - learned - in an set-based way. The system is controlled by a continuous time linear feedback law, where the feedback matrix used is updated in a sampled data fashion solving an infinite horizon robust control problem that guarantees constraint satisfaction and robust stability. To improve the performance, constraints based on the learned data are added to the LMI formulation, which allows to guarantee stability and satisfaction of input and state constraints. Due to convexity of the resulting LMI formulation its computational demand is low, allowing to implement the method on systems with limited computational capabilities. The effectiveness of the approach is illustrated by an example of a flexible link robotic arm. © 2018

关键词： Learning systems Constraint satisfaction problems Continuous time systems Feedback Global optimization Linear matrix inequalities Model predictive control Robust control Robustness (control systems) Uncertainty analysis Constrained model predictive control learning Lure systems Nonconvex optimization problem Robust model predictive control Sector bounded nonlinearities Uncertain nonlinear systems uncertainty

Resilient Consensus for Multi-Agent systems under Adversarial Spreading Processes

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wang, Yuan Ishii, Hideaki Bonnet, François Défago, Xavier Division of Decision and Control Systems KTH Royal Institute of Technology Stockholm Sweden Department of Computer Science Tokyo Institute of Technology Yokohama Tokyo Japan

This paper addresses novel consensus problems for multi-agent systems operating in an unreliable environment where adversaries are spreading. The dynamics of the adversarial spreading processes follows the susceptible-infected-recovered (SIR) model, where the infection induces faulty behaviors in the agents and affects their state values. Such a problem setting serves as a model of opinion dynamics in social networks where consensus is to be formed at the time of pandemic and infected individuals may deviate from their true opinions. To ensure resilient consensus among the noninfectious agents, the difficulty is that the number of infectious agents changes over time. We assume that a local policy maker announces the local level of infection in real-time, which can be adopted by the agent for its preventative measures. It is demonstrated that this problem can be formulated as resilient consensus in the presence of the socalled mobile malicious models, where the mean subsequence reduced (MSR) algorithms are known to be effective. We characterize sufficient conditions on the network structures for different policies regarding the announced infection levels and the strength of the epidemic. Numerical simulations are carried out for random graphs to verify the effectiveness of our approach. © 2020, CC BY.

关键词： Multi agent systems

H2 model reduction of linear network systems by moment matching and optimization

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Necoara, I. Ionescu, T.C. Department of Automatic Control and Systems Engineering University Politehnica Bucharest Bucharest060042 Romania Department of Automatic Control and Systems Engineering University Politehnica Institute of Mathematical Statistics 050711 Romania

In this paper we study the problem of model reduction of linear network systems. We aim at computing a reduced order stable approximation of the network with the same topology and optimal w.r.t. H2-norm error approximation. Our approach is based on time-domain moment matching framework, where we optimize over families of parameterized reduced order models matching a set of moments at arbitrary interpolation points. The parameterization of the low order models is in terms of the free parameters and of the interpolation points. For this family of parameterized models we formulate an optimization-based model reduction problem with the H2-norm of error approximation as objective function while the preservation of some structural and physical properties yields the constraints. This problem is nonconvex and we write it in terms of the Gramians of a minimal realization of the error system. We propose two solutions for this problem. The first solution assumes that the error system admits a block diagonal observability Gramian, allowing for a simple convex reformulation as semidefinite programming, but at the cost of some performance loss. We also derive sufficient conditions to guarantee block diagonalization of the Gramian. The second solution employs a gradient projection method for a smooth reformulation yielding (locally) optimal interpolation points and free parameters. The potential of the methods is illustrated on several network examples. Copyright © 2019, The Authors. All rights reserved.

关键词： Linear networks

Incorporating forecasting and peer-to-peer negotiation frameworks into a distributed model predictive control approach for meshed electric networks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Monasterios, Pablo Baldivieso R. Verba, Nandor Morris, Euan A. Morstyn, Thomas Konstantopoulos, George C. Gaura, Elena McArthur, Stephen The School of Engineering University of Edinburgh EdinburghEH9 3JL United Kingdom The Department of Automatic Control & Systems Engineering University of Sheffield Sheffield United Kingdom The Faculty Research Centre for Computational Science & Mathematical Modelling Coventry University Coventry United Kingdom The Department of Electronic and Electrical Engineering University of Strathclyde Glasgow United Kingdom

The continuous integration of renewable energy sources into power networks is causing a paradigm shift in energy generation and distribution with regards to trading and control;the intermittent nature of renewable sources affects pricing of energy sold or purchased;the networks are subject to operational constraints, voltage limits at each node, rated capacities for the power electronic devices, current bounds for distribution lines. These economic and technical constraints coupled with intermittent renewable injection may pose a threat to system stability and performance. We propose a novel holistic approach to energy trading composed of a distributed predictive control framework to handle physical interactions, i.e., voltage constraints and power dispatch, together with a negotiation framework to determine pricing policies for energy transactions. We study the effect of forecasting generation and consumption on the overall network’s performance and market behaviours. We provide a rigorous convergence analysis for both the negotiation framework and the distributed control. Lastly, we assess the impact of forecasting in the proposed system with the aid of testing scenarios. © 2021, CC BY-SA.

关键词： Forecasting

Bruce Francis: A Personal Tribute

学校读者我要写书评

暂无评论

IEEE control systems MAGAZINE 2018年第5期38卷 92-108页

作者： Vidyasagar, Mathukumalli Georgiou, Tryphon T. Tannenbaum, Allen R. Yamamoto, Yutaka Morse, A. Stephen Glover, Keith Ishii, Hideaki Khargonekar, Pramod P. Kwong, Raymond Chen, Tongwen Postlethwaite, Ian Department of Automatic Control and Robotics Bialystok University of Technology Bialystok Poland

Bruce Allen Francis was born on October 8, 1947 in Toronto to Jim and Eileen and grew up in Hamilton and Grimsby, Ontario, Canada along with his two younger sisters, Lee and Kim. He passed away on March 27, 2018, due to complications brought on by Parkinson's disease. He is survived by his wife Jingwen, his daughter Lian, and his sisters.

关键词： History Francis, Bruce Allen

Strategic trip planning for commuting considering user preferences of employees in organizations 1

学校读者我要写书评

暂无评论

Cities 2025年 165卷

作者： Balázs Varga Tamás Ormándi Tamás Tettamanti Attila Aba Domokos Esztergár-Kiss Department of Control for Transportation and Vehicle Systems Faculty of Transportation Engineering and Vehicle Engineering Budapest University of Technology and Economics Megyetem rkp. 3. Budapest H-1111 Hungary Department of Transport Technology and Economics Faculty of Transportation Engineering and Vehicle Engineering Budapest University of Technology and Economics Megyetem rkp. 3. Budapest H-1111 Hungary

Organizations implement mobility plans to promote sustainable mobility among their employees. However, there is a lack of a comprehensive, quantitative tool that organizations can use to analyze their employees' commuting patterns. This paper introduces a strategic trip planning application which can support long-term decision-making and better-targeted interventions. In contrast to classical trip planning applications, the introduced application does not focus on a particular trip. Instead, it simultaneously plans general trips for multiple transport modes (i.e., walking, cycling, public transport, and driving). The application ranks these modes through a utility function by quantifying travel time, costs, environmental impacts, and health benefits. Moreover, the data can be aggregated to include the employees (e.g., the monthly expenses of commuting) and organizations (e.g., the total cost of commuting). This study applies the strategic trip planner to evaluate the employees' commuting patterns and preferences in two organizations. The paper explores and compares hypothetical mode choice scenarios to assess the impact of alternative policies on the evaluated metrics. The results indicate a notable divergence between the mode employees use (public transport) and the mode that would suit them most based on their preferences (cycling). This suggests that both organizations should put an emphasis on promoting cycling when executing their mobility strategies.

关键词： Mode choice User preference Sustainable transportation Strategic trip planning Commuting