检索结果-内蒙古大学图书馆

Admissibility of retarded diagonal systems with one-dimensional input space

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Kapica, Rafal Partington, Jonathan R. Zawiski, Radoslaw Faculty of Applied Mathematics Agh University of Science and Technology al. Mickiewicza 30 Kraków30-059 Poland School of Mathematics University of Leeds LeedsLS2 9JT United Kingdom Department of Automatic Control and Robotics Silesian University of Technology ul. Akademicka 16 Gliwice44-100 Poland

We investigate infinite-time admissibility of a control operator B in a Hilbert space state-delayed dynamical system setting of the form z(t) = Az(t) + A1z(t - τ) + Bu(t), where A generates a diagonal C0-semigroup, A1∈ L(X) is also diagonal and u ∈ L2(0, ∞;ℂ). Our approach is based on the Laplace embedding between L2and the Hardy space H2(ℂ+). The results are expressed in terms of the eigenvalues of A and A1and the sequence representing the control *** Codes 34k35 (Primary) 34K30, 47D06, 93C23 (Secondary) © 2022, CC BY.

关键词： Dynamical systems

Learning by Doing: controlling a Dynamical System using Causality, control, and Reinforcement Learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Weichwald, Sebastian Mogensen, Søren Wengel Lee, Tabitha Edith Baumann, Dominik Kroemer, Oliver Guyon, Isabelle Trimpe, Sebastian Peters, Jonas Pfister, Niklas Department of Mathematical Sciences University of Copenhagen Denmark Department of Automatic Control Lund University Sweden The Robotics Institute Carnegie Mellon University United States Department of Information Technology Uppsala University Sweden LISN INRIA CNRS Université Paris-Saclay France ChaLearn United States Institute for Data Science in Mechanical Engineering RWTH Aachen University Germany

Questions in causality, control, and reinforcement learning go beyond the classical machine learning task of prediction under i.i.d. observations. Instead, these fields consider the problem of learning how to actively perturb a system to achieve a certain effect on a response variable. Arguably, they have complementary views on the problem: In control, one usually aims to first identify the system by excitation strategies to then apply model-based design techniques to control the system. In (non-model-based) reinforcement learning, one directly optimizes a reward. In causality, one focus is on identifiability of causal structure. We believe that combining the different views might create synergies and this competition is meant as a first step toward such synergies. The participants had access to observational and (offline) interventional data generated by dynamical systems. Track CHEM considers an open-loop problem in which a single impulse at the beginning of the dynamics can be set, while Track ROBO considers a closed-loop problem in which control variables can be set at each time step. The goal in both tracks is to infer controls that drive the system to a desired state. Code is open-sourced (***/LearningByDoingCompetition/learningbydoingcomp) to reproduce the winning solutions of the competition and to facilitate trying out new methods on the competition tasks. Copyright © 2022, The Authors. All rights reserved.

关键词： Dynamical systems

Well Convergent and Computationally Efficient Quaternion Loss 20th

学校读者我要写书评

暂无评论

Well Convergent and Computationally Efficient Quaternion Los...

20th Polish control Conference, PCC 2020

作者： Lelowicz, Kamil Derbisz, Jakub Department of Automatic Control and Robotics AGH University of Science and Technology al. A. Mickiewicza 30 Kraków30-059 Poland APTIV Services Poland S.A. ul. Podgorki Tynieckie 2 Kraków30-399 Poland

ISBN: (纸本)9783030509354

Rotation estimation, i.e. the ability to predict angles describing 3D positioned object, is an omnipresent problem in computer vision, computer graphics and 3D object detection task in automotive industry. Deep learning algorithms usually parameterise rotation using only the yaw angle. This paper presents detailed comparison of several 3D rotation distance functions using quaternions. We propose a computationally efficient quaternion loss function for neural network training. We conclude that function respects the topology of SO(3) and is bi-invariant. We also show the geometrical representation of presented functions. Lastly, we evaluate the effectiveness of the proposed loss function and compare its performance with other methods using a public large-scale dataset. © 2020, Springer Nature Switzerland AG.

关键词： Neural networks

Asymptotic Trajectory Tracking of Stratospheric Airships Based on RISE controllers Under External Uncertainties

学校读者我要写书评

暂无评论

IEEE Transactions on Aerospace and Electronic Systems 2025年

作者： Liu, Can Li, Baoquan Dai, Fengzhi Shi, Wuxi Zhang, Xuebo Tiangong University School of Control Science and Engineering Tianjin Key Laboratory of Autonomous Intelligence Technology and Systems Tianjin300387 China Tianjin University of Science and Technology College of Electronic Information and Automation Tianjin300222 China Nankai University Institute of Robotics and Automatic Information Systems Tianjin Key Laboratory of Intelligent Robotics Tianjin300071 China

For a stratospheric airship under internal and external uncertainties, controller strategies with robust integral sign of the error (RISE) are proposed for asymptotic trajectory tracking control. Specifically, a fully connected neural network (FCNN) is constructed with adaptive weight updating to estimate internal uncertainties of the airship system. Then, a self-tuning RISE controller is designed to track trajectories with compensating external disturbance, which enables gain adjustment in realtime according to system feedback. Based on Lyapunov technique and LaSalle-Yoshizawa corollary extension, system stability is strictly analyzed, and asymptotic convergence performance is obtained for trajectory tracking by the designed controller. Moreover, a RISE controller is designed with fixed gain matrices for the airship based on classic control strategies, and asymptotic tracking is also proved. Finally, numerical simulations are conducted with spiral and hovering control to verify performance of the proposed strategies. © 1965-2011 IEEE.

关键词： Lyapunov methods

Deep Learning-based Algorithm for Mobile Robot control in Textureless Environment

学校读者我要写书评

暂无评论

Deep Learning-based Algorithm for Mobile Robot Control in Te...

Mechatronics Systems and Materials (MSM)

作者： Milica Petrović Arkadiusz Mystkowski Aleksandar Jokić Lazar Đokić Zoran Miljković Production Engineering Department University of Belgrade Belgrade Serbia Department of Automatic Control and Robotics Bialystok University of Technology Bialystok Poland

ISBN: (数字)9781728169569

ISBN: (纸本)9781728169576

For the implementation of stereo image-based visual servoing algorithm in the eye-in-hand robotics applications, one of the main concerns is the accurate point feature detection and matching algorithm. Since the visual servoing is carried out in the textureless environment, the feature detection process is even more challenging. To fulfill the requirement of a robust and reliable point feature detection process, in this paper we present the novel deep learning-based algorithm. The approach based on convolutional neural networks and algorithm for detection of manufacturing entities is proposed and detected regions of interest are utilized for the improvement of the point feature detection algorithm. The proposed algorithm is experimentally evaluated in real-world settings by using wheeled nonholonomic mobile robot RAICO equipped with stereo vision system. The experimental results show the improvement of 58% in the accuracy of matched point features in the images obtained during the visual servoing process. Moreover, with the implementation of the proposed deep learning-based approach, the number of successful experimental runs has increased by 80%.

关键词： Feature extraction Mobile robots Visual servoing Manufacturing Classification algorithms Cameras

A sliding mode controller design for thermal comfort in buildings

学校读者我要写书评

暂无评论

Engineering Transactions 2019年第4期67卷 475-489页

作者： Skruch, Pawel Dlugosz, Marek AGH University of Science and Technology Faculty of Electrical Engineering Automatics Computer Science and Biomedical Engineering Department of Automatic Control and Robotics Al. Mickiewicza 30 Kraków30-059 Poland

One of the factors determining comfort in buildings is the indoor air temperature of the rooms. A control system, part of the home automation system, should stabilise air temperature to the desired level, despite various disturbances such as the presence of random or occasional sources of heat. Inaccurate models of the dynamics of air temperature changes in buildings prescribe the use of robust control methods, a type of which is the sliding mode controller. This article presents the application of a sliding mode controller (SMC) to home automation systems, designed to control air temperature inside a building. The sliding-mode controller makes use of sliding surfaces, which are defined by the assumed trajectory and the system output. The control law is designed in such a way that the trajectory of the system tends to the sliding surface from any initial point and remains on it after reaching the sliding surface. In this article, a model at air temperature change dynamics inside a building is presented. The modelling approach relies on the lumped-parameter methodology, in which distributed physical properties are represented by lumped parameters (such as thermal capacity or resistance). The model takes into account the loss of heat through conduction and ventilation, as well as internal heat gain. The parameters of the model can be obtained easily from the thermal properties of the construction materials. Theoretical considerations were applied in simulation experiments and the results of these experiments confirm the performance improvement achieved by the proposed solutions. © 2019, Polish Academy of Sciences. All rights reserved.

关键词： Atmospheric temperature

Environment-Driven Online LiDAR-Camera Extrinsic Calibration

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Huang, Zhiwei Li, Jiaqi Zhong, Ping Fan, Rui The Department of Control Science & Engineering The College of Electronics & Information Engineering Tongji University Shanghai201804 China The School of Computer Science and Engineering Central South University Hunan Changsha410083 China The National Key Laboratory of Science and Technology on Automatic Target Recognition National University of Defense Technology Hunan Changsha410073 China The Department of Control Science & Engineering The College of Electronics & Information Engineering Shanghai Research Institute for Intelligent Autonomous Systems The State Key Laboratory of Intelligent Autonomous Systems Frontiers Science Center for Intelligent Autonomous Systems Tongji University Shanghai201804 China The National Key Laboratory of Human-Machine Hybrid Augmented Intelligence Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Shaanxi Xi’an710049 China

LiDAR-camera extrinsic calibration (LCEC) is the core for data fusion in computer vision. Existing methods typically rely on customized calibration targets or fixed scene types, lacking the flexibility to handle variations in sensor data and environmental contexts. This paper introduces EdO-LCEC, the first environment-driven, online calibration approach that achieves human-like adaptability. Inspired by the human perceptual system, EdO-LCEC incorporates a generalizable scene discriminator to actively interpret environmental conditions, creating multiple virtual cameras that capture detailed spatial and textural information. To overcome cross-modal feature matching challenges between LiDAR and camera, we propose dual-path correspondence matching (DPCM), which leverages both structural and textural consistency to achieve reliable 3D-2D correspondences. Our approach formulates the calibration process as a spatial-temporal joint optimization problem, utilizing global constraints from multiple views and scenes to improve accuracy, particularly in sparse or partially overlapping sensor views. Extensive experiments on real-world datasets demonstrate that EdO-LCEC achieves state-of-the-art performance, providing reliable and precise calibration across diverse, challenging environments. Copyright © 2025, The Authors. All rights reserved.

关键词： Spatio-temporal data

Influence of the variables describing brain signals on the performance of the Naive Bayesian Classifier

学校读者我要写书评

暂无评论

Influence of the variables describing brain signals on the p...

Progress in Applied Electrical Engineering (PAEE)

作者： Aleksandra Kawala-Sterniuk Jaroslaw Zygarlicki Adam Lysiak Barbara Grochowicz Mariusz Pelc Waldemar Bauer Dawid Baczkowicz Krzysztof Krecisz Katarzyna A. Dylag Wiktoria Wieczorek Radana Kahankova Radek Martinek Faculty of Electrical Engineering Automatic Control and Informatics Opole University of Technology Opole Poland School of Computing and Mathematical Sciences University of Greenwich London UK Department of Automatic Control and Robotics AGH University of Science and Technology Krakow Poland Faculty of Physical Education and Physiotherapy Opole University of Technology Opole Poland St. Louis Children Hospital Krakow Poland Department of Pathophysiology Jagiellonian University in Krakow–Collegium Medicum Krakow Poland Department of Bioinformatics and Telemedicine Jagiellonian University in Krakow–Collegium Medicum Krakow Poland Department of Cybernetics and Biomedical Engineering–FEECS VSB—Technical University Ostrava Ostrava–Poruba Czech Republic

ISBN: (数字)9781665455152

ISBN: (纸本)9781665455169

In this paper various variables describing brain signals such as near-infrared spectroscopy (NIRS) and electroencephalography (EEG) on the Naive Bayesian Classifier were presented. Analysis of biomedical signals is a very challenging task – therefore the authors of this work decided to analyse two types of brain signals – EEG and NIRS, which have different features, character, nature and are differently prone to various artifacts occurrence. The applied classifiers can be applied for various features extraction and pattern comparisons, which is useful in diagnostic processes.

关键词： Electrical engineering Feature extraction Electroencephalography Bayes methods Task analysis Functional near-infrared spectroscopy

Optimisation of a siamese neural network for real-time energy efficient object tracking

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Przewlocka, Dominika Wasala, Mateusz Szolc, Hubert Blachut, Krzysztof Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Krakow Poland

In this paper the research on optimisation of visual object tracking using a Siamese neural network for embedded vision systems is presented. It was assumed that the solution shall operate in real-time, preferably for a high resolution video stream, with the lowest possible energy consumption. To meet these requirements, techniques such as the reduction of computational precision and pruning were considered. Brevitas, a tool dedicated for optimisation and quantisation of neural networks for FPGA implementation, was used. A number of training scenarios were tested with varying levels of optimisations - from integer uniform quantisation with 16 bits to ternary and binary networks. Next, the influence of these optimisations on the tracking performance was evaluated. It was possible to reduce the size of the convolutional filters up to 10 times in relation to the original network. The obtained results indicate that using quantisation can significantly reduce the memory and computational complexity of the proposed network while still enabling precise tracking, thus allow to use it in embedded vision systems. Moreover, quantisation of weights positively affects the network training by decreasing overfitting. Copyright © 2020, The Authors. All rights reserved.

关键词： Field programmable gate arrays (FPGA)