检索结果-内蒙古大学图书馆

5th International Conference on Distributed Artificial Intelligence (DAI)

作者： Lin, Yunfeng Liu, Minghuan Yu, Yong Shanghai Jiao Tong Univ Shanghai Peoples R China

ISBN: (纸本)9798400708480

Wheeled robots have gained significant attention due to their wide range of applications in manufacturing, logistics, and service industries. However, due to the difficulty of building a highly accurate dynamics model for wheeled robots, developing and testing control algorithms for them remains challenging and time-consuming, requiring extensive physical experimentation. To address this problem, we propose D4W, i.e., Dependable data-driven dynamics for Wheeled Robots, a simulation framework incorporating data-driven methods to accelerate the development and evaluation of algorithms for wheeled robots. The key contribution of D4W is a solution that utilizes real-world sensor data to learn accurate models of robot dynamics. The learned dynamics can capture complex robot behaviors and interactions with the environment throughout simulations, surpassing the limitations of analytical methods, which only work in simplified scenarios. Experimental results show that D4W achieves the best simulation accuracy compared to traditional approaches, allowing for rapid iteration of wheel robot algorithms with less or no need for fine-tuning in reality. We further verify the usability and practicality of the proposed framework through integration with existing simulators and controllers.

关键词： data-driven dynamics wheeled mobile robots physical simulation

来源：评论

学校读者我要写书评

暂无评论

data-driven learning and control of nonlinear system dynamics

引用

NONLINEAR dynamics 2024年第7期113卷 6605-6625页

作者： Becerra-Mora, Yeyson A. Acosta, Jose angel CUN Dept Elect Engn Bogota 111711 Colombia Univ Seville Dept Ingn Sistemas & Automatica Seville Spain

This work falls into the field of discovering the dynamic equations of stabilizable nonlinear systems, via a learning-and-control algorithm to process the data sets of trajectories previously obtained. To this end, an interlaced method to learn and control nonlinear system dynamics from a set of demonstrations is proposed, under a constrained optimization framework for the unsupervised learning process. The nonlinear system is modeled as a mixture of Gaussians and Sontag's formula together with its associated Control Lyapunov Function is proposed for learning and control. Lyapunov stability and robustness in noisy data environments are guaranteed, as a result of the inclusion of control in the learning-optimization problem. The performances are validated through a well-known dataset of demonstrations with handwriting complex trajectories, succeeding in all of them and outperforming previous methods under bounded disturbances, possibly coming from inaccuracies, imperfect demonstrations, or noisy datasets. As a result, the proposed interlaced solution yields a good performance trade-off between reproductions and robustness. Therefore, this work sheds some more light on the automatic discovery of nonlinear dynamics from noisy raw data.

关键词： data-driven dynamics Control Lyapunov functions Unsupervised machine learning

来源：评论

学校读者我要写书评

暂无评论

data-driven Modeling of the Nonlinear dynamics of Passive Lower-Limb Prosthetic Systems

引用

JOURNAL OF MECHANISMS AND ROBOTICS-TRANSACTIONS OF THE ASME 2024年第8期16卷 081012-081012页

作者： Donahue, Seth Kingsbury, Trevor Takahashi, Kota Major, Matthew J. Northwestern Univ Dept Phys Med & Rehabil 680 Lake Shore Dr Suite 1100 Chicago IL 60611 USA Jesse Brown VA Med Ctr 820 S Damen Ave Chicago IL 60612 USA Naval Med Ctr 34800 Bob Wilson Dr San Diego CA 92134 USA Univ Utah Dept Hlth & Kinesiol 250 South 1850 East Salt Lake City UT 84112 USA Northwestern Univ Dept Biomed Engn 2145 Sheridan RdE310 Evanston IL 60208 USA

Modeling the nonlinear dynamics of prosthetic feet is an important tool for linking prosthesis mechanical properties to end-user outcomes. There has been a renewed interest in data-driven modeling of dynamical systems, with the development of the Extended Dynamic Mode Decomposition with control (eDMDc) and the Sparse Identification of Nonlinear dynamics with Control (SINDYc). These algorithms do not require prior information about the system, including mechanical configuration, and are data-driven. The aim of this study was to assess the feasibility and accuracy of applying these data-driven algorithms to model prosthesis nonlinear load response dynamics. Different combinations of a dynamic response foot, a hydraulic ankle unit, and three shock-absorbing pylons of varying resistance were tested loaded and unloaded at three orientations reflecting critical positions during the stance phase of walking. We tested two different data-driven algorithms, the eDMDc, with two different kernels, and the SINDYc, which regresses the coefficients for a nonlinear ordinary differential equation. Each algorithm was able to model the nonlinear prosthesis dynamics, but the SINDYc outperformed the eDMDc methods with a root mean square error across orientations < 1.50 mm and a maximum error in peak displacement of 1.28 mm or 4% relative error. From the estimated SINDYc governing equation of the system dynamics, we were able to simulate different mechanical behavior by systematically varying parameter values, which offers a novel foundation for designing, controlling, and classifying prosthetic systems ultimately aimed at improving prosthesis user outcomes.

关键词： prosthetics data-driven dynamics

来源：评论

学校读者我要写书评

暂无评论

Efficient pseudometrics for data-driven comparisons of nonlinear dynamical systems

引用

NONLINEAR dynamics 2025年第11期113卷 12465-12486页

作者： Glaz, Bryan DEVCOM Army Res Lab Weap Sci Div Aberdeen Proving Ground MD 20783 USA

Computationally efficient solutions for pseudometrics quantifying deviation from topological conjugacy between dynamical systems with diagonalizable data-driven Koopman operators are presented. Deviation from conjugacy is quantified in a Pareto optimal sense that accounts for spectral properties of Koopman operators as well as trajectory geometry. Theoretical justification is provided for computing such pseudometrics in Koopman eigenfunction space rather than observable space. Furthermore, it is shown that theoretical consistency with topological conjugacy can be maintained when restricting the search for optimal transformations between systems to the unitary group. Resulting pseudometrics are based on analytical solutions for unitary transformations in Koopman eigenfunction space. Geometric considerations for the deviation from conjugacy Pareto optimality problem are used to develop scalar pseudometrics that account for all possible optimal solutions given just two Pareto points. The approach is demonstrated on two example problems;the first being a simple benchmarking problem and the second an engineering example comparing the dynamics of morphological computation of biological nonlinear muscle actuators to simplified man-made (including bioinspired) approaches. The benefits of considering operator and trajectory geometry based dissimilarity measures in a unified and consistent formalism are demonstrated. Overall, the deviation from conjugacy pseudometrics provide practical advantages in terms of computational efficiency and scalability, while maintaining theoretical consistency.

关键词： data-driven dynamics Topological conjugacy Dissimilarity measures Koopman eigenfunctions Machine learning metrics

来源：评论

学校读者我要写书评

暂无评论

Learning global linear representations of nonlinear dynamics

引用

NONLINEAR dynamics 2025年第9期113卷 9529-9549页

作者： Breunung, Thomas Kogelbauer, Florian Univ Maryland Dept Mech Engn College Pk MD 20742 USA Swiss Fed Inst Technol Dept Mech & Proc Engn Zurich Switzerland Univ Wisconsin Madison Dept Mech Engn Madison WI 53706 USA

While linear systems are well-understood, no explicit solution for general nonlinear systems exists. A classical approach to make the understanding of linear system available in the nonlinear setting is to represent a nonlinear system by a linear model. While progress has been made in extending linearization techniques to larger domains and more complex attractor geometries, recent work has highlighted the limitations of these techniques when applied to nonlinear dynamics, such as those with coexisting attractors. In this work, we show nonlinear dynamics with a continuous Koopman spectrum, a limit cycle, and coexisting solutions that can be globally linearized. To this end, we explicitly construct linear systems mimicking these nonlinear behaviors. Subsequently, we approximate transformations between linear and nonlinear systems with deep neural networks. This approach yields finite dimensional linearizations exceeding the phase space dimension of the underlying linear system by one at most.

关键词： data-driven dynamics Global methods Koopman operator Linearizing transformations Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Modeling nonlinear dynamics from videos

引用

NONLINEAR dynamics 2025年第10期113卷 10881-10909页

作者： Yang, Antony Axas, Joar Kadar, Fanni Stepan, Gabor Haller, George Swiss Fed Inst Technol Inst Mech Syst Leonhardstr 21 CH-8092 Zurich Switzerland Univ Cambridge Ctr Math Sci Dept Appl Math & Theoret Phys Wilberforce Rd Cambridge CB3 0WA England Budapest Univ Technol & Econ Fac Mech Engn Dept Appl Mech Muegyetem Rkp 3 H-1111 Budapest Hungary Budapest Univ Technol & Econ MTA BME Lendulet Momentum Global Dynam Res Grp Muegyetem Rkp 3 H-1111 Budapest Hungary

We introduce a method for constructing reduced-order models directly from videos of dynamical systems. The method uses non-intrusive tracking to isolate the motion of a user-selected part in the video of an autonomous dynamical system. In the space of delayed observations of this motion, we reconstruct a low-dimensional attracting spectral submanifold (SSM) whose internal dynamics serves as a mathematically justified reduced-order model for nearby motions of the full system. We obtain this model in a simple polynomial form that allows explicit identification of important physical system parameters, such as natural frequencies, linear and nonlinear damping and nonlinear stiffness. Beyond faithfully reproducing attracting steady states and limit cycles, our SSM-reduced models can also uncover hidden motion not seen in the video, such as unstable fixed points and unstable limit cycles forming basin boundaries. We demonstrate all these features on experimental videos of five physical systems: a double pendulum, an inverted flag in counter-flow, water sloshing in tank, a wing exhibiting aeroelastic flutter and a shimmying wheel.

关键词： Object tracking data-driven dynamics Computer vision Reduced-order modeling Spectral submanifolds

来源：评论

学校读者我要写书评

暂无评论

data-driven nonlinear state observation for controlled systems: A kernel method and its analysis

引用

CANADIAN JOURNAL OF CHEMICAL ENGINEERING 2025年第3期103卷 1122-1138页

作者： Woelk, Moritz Tang, Wentao North Carolina State Univ Dept Chem & Biomol Engn Raleigh NC 27695 USA

This work proposes a data-driven state observation algorithm for nonlinear dynamical systems, when the true state trajectory is not measurable and hence the states information needs to be reconstructed from input and output measurements. Such a reduction is formed by kernel canonical correlation analysis (KCCA), which (i) implicitly maps the available input-output data into a higher-dimensional feature space, namely the reproducing kernel Hilbert space (RKHS);(ii) finds a projection of the past input-output data and a projection of the future input-output data with maximal correlation;and (iii) identifies the projected inputs and outputs, namely the canonical variates, as the observed states. We adopt a least squares support vector machine (LS-SVM) formulation for KCCA, which imposes regularization on the vectors that specify the projections and is amenable to convex optimization. We prove theoretically that, based on the statistical consistency of KCCA, the observed states determined by the proposed state observer has a guaranteed correlativity with the actual states (when properly transformed). Furthermore, such observed states, when supplemented with the information of succeeding inputs, can be used to predict the succeeding outputs with guaranteed upper bound on the prediction error. Case studies are performed on two numerical examples and an exothermic continuously stirred tank reactor (CSTR).

关键词： canonical correlation data-driven dynamics kernel methods nonlinear systems state observation

来源：评论

学校读者我要写书评

暂无评论

Robust data-driven dynamic model discovery of industrial robots with spatial manipulation capability using simple trajectory

引用

NONLINEAR dynamics 2024年第11期112卷 9155-9177页

作者： Omar, Mohamed Wang, Ke Kun, Dai Li, Ruifeng Asker, Ahmed Harbin Inst Technol State Key Lab Robot & Syst Harbin 150001 Peoples R China Mansoura Univ Fac Engn Prod & Mech Design Engn Dept Mansoura 35516 Egypt Nile Univ Sch Engn & Appl Sci Giza 12573 Egypt

Industrial standard model-based controllers need an accurate dynamic model to perform reliably. The classical technique for dynamics modeling of industrial robots relies on deriving the closed-form dynamic equations and then identifying the inertial parameters on the assumption that all the kinematic and geometric details of the robot are known. This study extends the recently developed data-driven SINDy method to obtain the dynamic model of industrial robots with spatial manipulation capabilities. The proposed method is applied to the 6-DOF UR10 robot in simulated and experimental environments. Furthermore, payload and friction are considered in both situations. Contrary to other techniques that rely on optimizing the trajectory to improve the regressor matrix conditionality, the proposed method uses a simple trajectory constructed using a combination of quintic polynomial and sinusoidal trajectory. Three distinct trajectories are used to assess the accuracy of the proposed method in modeling the robot's dynamics. Although simple trajectories result in an ill-conditioned regressor matrix, the proposed method accurately identified the dynamic model. The identified dynamic model has accurately replicated the performance of the robot in both simulation and experimental settings. The model parameters obtained by the proposed method in the simulation settings are compared with the parameters of the Euler-Lagrange closed-form model, and good conformance has been found. To assess the robustness of the proposed method, different levels of noise are added to the simulation data. For noise levels in the range of sigma=0.001\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\sigma =0.001$$\end{document} to sigma=0.08\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{a

关键词： SINDy Euler-Lagrange Industrial robots dynamics of industrial robots data-driven dynamics

来源：评论

学校读者我要写书评

暂无评论

data-driven DISCOVERY OF THE EQUATIONS OF MOTION OF TWIN-TAILED FIGHTER AIRCRAFT 28

DATA-DRIVEN DISCOVERY OF THE EQUATIONS OF MOTION OF TWIN-TAI...

引用

28th International Conference on System Theory Control and Computing

作者： Elsayed, Ezzeldeen El-Badawy, Ayman Zometa, Pablo German Univ Cairo Dept Mechatron Engn Cairo Egypt German Int Univ Fac Engn Berlin Germany

ISBN: (纸本)9798350364309;9798350364293

This paper investigates the data-driven discovery of equations of motion for twin-tailed fighter aircraft, with a specific focus on addressing challenges posed by buffeting-induced vibrations in the F-15 model. Employing the Sparse Identification of Nonlinear dynamics (SINDy) algorithm, our research delves into the complexities of F-15 twin-tail dynamics. The utilized nonlinear model takes into account critical factors such as aerodynamic damping, cubic nonlinearities and intertail coupling. While the SINDy algorithm demonstrates promise in capturing the original dynamics, its sensitivity to wind disturbances prompts the application of the SINDYc algorithm. This enhanced approach accurately predicts system dynamics and provides valuable insights into effective control inputs. In this study we follow a step-by-step process, initially excluding wind disturbances to focus on intrinsic dynamics, followed by their introduction to assess adaptability. Coefficients derived from the system identification algorithm closely align with the original synthetic data we generated using an existing model and the observed negligible error underscores the success of our data-driven methodology. This research contributes to advancing data-driven dynamics in aerospace engineering, providing an insight of how data-driven approaches could be utilized in the field.

关键词： data-driven dynamics twin-tailed fighter aircraft buffeting-induced vibrations Sparse Identification of Nonlinear dynamics with Control (SINDYc).

来源：评论

学校读者我要写书评

暂无评论

Cutting force estimation from machine learning and physics-inspired data-driven models utilizing accelerometer measurements

引用

Procedia CIRP 2024年 126卷 318-323页

作者： Gregory W. Vogl Yongzhi Qu Reese Eischens Gregory Corson Tony Schmitz Andrew Honeycutt Jaydeep Karandikar Scott Smith Engineering Laboratory National Institute of Standards and Technology (NIST) 100 Bureau Drive Gaithersburg Maryland 20899-8220 USA (Official contribution of the National Institute of Standards and Technology not subject to copyright in the United States.) Mechanical & Industrial Engineering Department University of Minnesota Duluth Duluth MN 55812 USA Department of Mechanical Aerospace and Biomedical Engineering University of Tennessee Knoxville Tennessee 37996 USA Manufacturing Demonstration Facility Oak Ridge National Laboratory Knoxville Tennessee 37932 USA

Monitoring cutting forces for process control may be challenging because force measurements typically require invasive instrumentation. To remedy this situation, two new methods were recently developed to estimate cutting forces in real time based on the use of on-machine accelerometer measurements. One method uses machine learning, while another uses a physics-inspired data-driven approach, to generate a model that estimates cutting forces from on-machine accelerations. The estimated forces from both approaches were compared against cutting force data collected during various milling operations on several machine tools. The results reveal the advantages and disadvantages of each model to estimate real-time cutting forces.

关键词： Smart manufacturing Industry 4.0 data-driven dynamics Frequency response function Machine tool Modeling dynamics Machining processes Sensing Monitoring Diagnostics

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：