检索结果-内蒙古大学图书馆

23rd International Conference on control, Automation and Systems, ICCAS 2023

作者： Diepers, Florian Polke, Dominik Ahle, Elmar Softker, Dirk University of Applied Sciences Niederrhein Faculty of Electrical Engineering and Computer Science Krefeld Germany University of Duisburg-Essen Chair of Dynamics and Control Duisburg Germany

ISBN: (纸本)9788993215274

Most advanced control methods require a sufficiently accurate model of the system to be controlled. These models are becoming increasingly difficult to generate due to the increasing complexity of the underlying systems. To address this problem, data-driven models can be used. These kind of models are trained based on data of the dynamic system. They can be used for controller design and also be applied directly to control the system. In this work, a stochastic model predictive controller (SMPC) with a Gaussian process model (GP) is utilized. The main advantage of GPs is the construction of a dynamic system model with the possibility of determining the uncertainty of its own prediction. In this contribution, three different utilizations of prediction uncertainty in SMPC are compared. Additionally, two different implementations of dynamic GPs, nonlinear autoregressive exogenous GPs (GP-NARX) and a state-space model based on GPs (GP-SSM), are considered. All six test cases are compared based on an evaluation criterion that describes the resulting control performance. A simulated inverted pendulum, a benchmark for nonlinear and unstable systems, is used as test system. In this work, the combinations of different dynamic GPs and the application of their uncertainty prediction in SMPC are evaluated and compared. © 2023 ICROS.

关键词： Stochastic models

来源：评论

学校读者我要写书评

暂无评论

Multi-task lane-free driving strategy for Connected and Automated Vehicles: A multi-agent deep reinforcement learning approach

引用

engineering Applications of Artificial Intelligence 2025年 154卷

作者： Berahman, Mehran Karalakou, Athanasia Rostami-Shahrbabaki, Majid Bogenberger, Klaus Department of Electrical and Computer Engineering Shiraz University Shiraz Iran Chair of Traffic Engineering and Control Technical University of Munich Munich Germany

Deep reinforcement learning has shown promise in various engineering applications, including vehicular traffic control. The non-stationary nature of traffic, especially in the lane-free environment with more degrees of freedom in vehicle behaviors, poses challenges for decision-making since a wrong action might lead to a catastrophic failure. In this paper, we propose a novel driving strategy for Connected and Automated Vehicles (CAVs) based on a competitive Multi-Agent Deep Deterministic Policy Gradient approach. The developed multi-agent deep reinforcement learning algorithm creates a dynamic and non-stationary scenario, mirroring real-world traffic complexities and making trained agents more robust. The algorithm's reward function is strategically and uniquely formulated to cover multiple vehicle control tasks, including maintaining desired speeds, overtaking, collision avoidance, and merging and diverging maneuvers. Moreover, additional considerations for both lateral and longitudinal passenger comfort and safety criteria are taken into account. We employed inter-vehicle forces, known as nudging and repulsive forces, to manage the maneuvers of CAVs in a lane-free traffic environment. The proposed driving algorithm is trained and evaluated on lane-free roads using the Simulation of Urban Mobility platform. Experimental results demonstrate the algorithm's efficacy in achieving various defined objectives. These include laterally sorting vehicles based on their desired speeds with minimal deviation from those speeds. Additionally, the jerk and acceleration values remain within acceptable ranges. Overall, these promising results highlight the potential of the proposed approach to enhance safety and efficiency in autonomous driving within lane-free traffic environments. © 2025 The Authors

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Flatness-Based Identification of Nonlinear Dynamics

Flatness-Based Identification of Nonlinear Dynamics

引用

Mediterranean Conference on control and Automation (MED)

作者： Alexander M. Kopp Lisa Fuchs Christoph Ament Chair of Control Engineering at the Faculty of Applied Computer Science University of Augsburg Augsburg Germany

ISBN: (数字)9798350395440

ISBN: (纸本)9798350395457

The identification of a nonlinear system model given only measurement data is a frequently encountered task. Uncovering the structure of differential equations as system model alongside with the determination of the optimal parameters is still problem under investigation. Assuming a differentially flat system under investigation, an algorithm for single input single output systems is proposed that faces this identification task. To find a proper state space model, an iterative strategy is presented expanding an initial solution in every step. Harnessing only the measurement data and not their time derivatives a criterion is proposed to select promising extensions to the model avoiding extensive simulation studies on possible model structures. Applying a subset selection reduces the complexity of the resulting models and avoids overfitting. To show the capability of the presented approach to identify a nonlinear state space model from data, a simulation example is presented.

关键词： Training Neural networks Differential equations Solids Polynomials Mathematical models Data models

来源：评论

学校读者我要写书评

暂无评论

Adaptive Stochastic Predictive control from Noisy Data: A Sampling-based Approach

Adaptive Stochastic Predictive Control from Noisy Data: A Sa...

引用

IEEE Conference on Decision and control

作者： Johannes Teutsch Christopher Narr Sebastian Kerz Dirk Wollherr Marion Leibold Department of Computer Engineering Chair of Automatic Control Engineering (LSR) Technical University of Munich Theresienstr. 90 Munich Germany

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

In this work, an adaptive predictive control scheme for linear systems with unknown parameters and bounded additive disturbances is proposed. In contrast to related adaptive control approaches that robustly consider the parametric uncertainty, the proposed method handles all uncertainties stochastically by employing an online adaptive sampling-based approximation of chance constraints. The approach requires initial data in the form of a short input-output trajectory and distributional knowledge of the disturbances. This prior knowledge is used to construct an initial set of dataconsistent system parameters and a distribution that allows for sample generation. As new data stream in online, the set of consistent system parameters is adapted by exploiting set membership identification. Consequently, chance constraints are deterministically approximated using a probabilistic scaling approach by sampling from the set of system parameters. In combination with a robust constraint on the first predicted step, recursive feasibility of the proposed predictive controller and closed-loop constraint satisfaction are guaranteed. A numerical example demonstrates the efficacy of the proposed method.

关键词： Robust control Linear systems Uncertainty Shape Probabilistic logic Trajectory Noise measurement Synthetic aperture sonar Predictive control Convergence

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Lane-Free Driving Strategy for Connected and Automated Vehicles: A Multi-Agent Deep Reinforcement Learning Approach

arXiv

引用

arXiv 2024年

作者： Berahman, Mehran Rostami-Shahrbabaki, Majid Bogenberger, Klaus Department of Electrical and Computer Engineering Shiraz University Shiraz Iran Chair of Traffic Engineering and Control Technical University of Munich Munich Germany

Deep reinforcement learning has shown promise in various engineering applications, including vehicular traffic control. The non-stationary nature of traffic, especially in the lane-free environment with more degrees of freedom in vehicle behaviors, poses challenges for decision-making since a wrong action might lead to a catastrophic failure. In this paper, we propose a novel driving strategy for Connected and Automated Vehicles (CAVs) based on a competitive Multi-Agent Deep Deterministic Policy Gradient approach. The developed multi-agent deep reinforcement learning algorithm creates a dynamic and non-stationary scenario, mirroring real-world traffic complexities and making trained agents more robust. The algorithm’s reward function is strategically and uniquely formulated to cover multiple vehicle control tasks, including maintaining desired speeds, overtaking, collision avoidance, and merging and diverging maneuvers. Moreover, additional considerations for both lateral and longitudinal passenger comfort and safety criteria are taken into account. We employed inter-vehicle forces, known as nudging and repulsive forces, to manage the maneuvers of CAVs in a lane-free traffic environment. The proposed driving algorithm is trained and evaluated on lane-free roads using the Simulation of Urban Mobility platform. Experimental results demonstrate the algorithm’s efficacy in handling different objectives, highlighting its potential to enhance safety and efficiency in autonomous driving within lane-free traffic environments. © 2024, CC BY-NC-SA.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Learning-based control for PMSM Using Distributed Gaussian Processes with Optimal Aggregation Strategy 49

Learning-based Control for PMSM Using Distributed Gaussian P...

引用

49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023

作者： Yin, Zhenxiao Dai, Xiaobing Yang, Zewen Shen, Yang Hattab, Georges Zhao, Hang Robotics and Autonomous Systems Thrust Guangzhou China Technical University of Munich Chair of Information-oriented Control Munich Germany Berlin Germany Freie Universität Berlin Department of Mathematics and Computer Science Berlin Germany The Hong Kong University of Science and Technology Department of Electronic & Computer Engineering Hong Kong

ISBN: (纸本)9798350331820

The growing demand for accurate control in varying and unknown environments has sparked a corresponding increase in the requirements for power supply components, including permanent magnet synchronous motors (PMSMs). To infer the unknown part of the system, machine learning techniques are widely employed, especially Gaussian process regression (GPR) due to its flexibility of continuous system modeling and its guaranteed performance. For practical implementation, distributed GPR is adopted to alleviate the high computational complexity. However, the study of distributed GPR from a control perspective remains an open problem. In this paper, a control-aware optimal aggregation strategy of distributed GPR for PMSMs is proposed based on the Lyapunov stability theory. This strategy exclusively leverages the posterior mean, thereby obviating the need for computationally intensive calculations associated with posterior variance in alternative approaches. Moreover, the straightforward calculation process of our proposed strategy lends itself to seamless implementation in high-frequency PMSM control. The effectiveness of the proposed strategy is demonstrated in the simulations. © 2023 IEEE.

关键词： Synchronous motors

来源：评论

学校读者我要写书评

暂无评论

Driving Strategy for Vehicles in Lane-Free Traffic Environment Based on Deep Deterministic Policy Gradient and Artificial Forces

引用

IFAC-PapersOnLine 2022年第14期55卷 14-21页

作者： Mehran Berahman Majid Rostmai-Shahrbabaki Klaus Bogenberger Department of Electrical and Computer Engineering Shiraz University Shiraz Iran Chair of Traffic Engineering and Control Technical University of Munich Munich Germany

This paper proposes a novel driving strategy for Connected and Automated Vehicles (CAVs) in a lane-free traffic environment. To this end, a combination of artificial forces and a reinforcement learning approach are used. To ensure the safe driving behavior of vehicles, an artificial ellipsoid border is assumed around each vehicle by which the lateral and longitudinal forces are obtained and applied. Furthermore, a longitudinal repulsive force based on a Deep Deterministic Policy Gradient (DDPG) network is exerted on the vehicles to avoid longitudinal collisions. Using this approach, the reaction of vehicles is improved, and vehicles may experience closer longitudinal space gaps allowing higher network throughput. The proposed lane-free driving methodology is implemented in the SUMO traffic simulator to showcase its benefits. Additionally, by implementing typical lane-based scenarios in SUMO with the same road condition and traffic demand as lane-free scenarios, a comparison in terms of average speed and time delay has been drawn between the proposed innovative approach and its conventional counterpart, proving the developed approach's functionality.

关键词： Deep reinforcement learning Deep deterministic policy gradient Connected automated vehicles Lane-free traffic Artificial force

来源：评论

学校读者我要写书评

暂无评论

State Derivative Normalization for Continuous-Time Deep Neural Networks

引用

IFAC-PapersOnLine 2024年第15期58卷 253-258页

作者： Jonas Weigand Gerben I. Beintema Jonas Ulmen Daniel Görges Roland Tóth Maarten Schoukens Martin Ruskowski Chair of Machine Tools and Control Systems RPTU Kaiserslautern and the German Research Center for Artificial Intelligence Kaiserslautern Germany Control Systems (CS) Group at the Department of Electrical Engineering Eindhoven University of Technology Netherlands. R. Tóth is also affiliated to the Systems and Control Laboratory at the Institute for Computer Science and Control Budapest Hungary Institute for Electromobility RPTU Kaiserslautern Germany

The importance of proper data normalization for deep neural networks is well known. However, in continuous-time state-space model estimation, it has been observed that improper normalization of either the hidden state or hidden state derivative of the model estimate, or even of the time interval can lead to numerical and optimization challenges with deep learning based methods. This results in a reduced model quality. In this contribution, we show that these three normalization tasks are inherently coupled. Due to the existence of this coupling, we propose a solution to all three normalization challenges by introducing a normalization constant at the state derivative level. We show that the appropriate choice of the normalization constant is related to the dynamics of the to-be-identified system and we derive multiple methods of obtaining an effective normalization constant. We compare and discuss all the normalization strategies on a benchmark problem based on experimental data from a cascaded tanks system and compare our results with other methods of the identification literature.

关键词： System Identification Continuous-Time Neural Ordinary Differential Equations Nonlinear State-Space

来源：评论

学校读者我要写书评

暂无评论

Comparison of Different Gaussian Process Models and Applications in Model Predictive control

Comparison of Different Gaussian Process Models and Applicat...

引用

International Conference on control, Automation and Systems ( ICCAS)

作者： Florian Diepers Dominik Polke Elmar Ahle Dirk Söftker Faculty of Electrical Engineering and Computer Science University of Applied Sciences Niederrhein Krefeld Germany Chair of Dynamics and Control University of Duisburg-Essen Duisburg Germany

关键词：

来源：评论

学校读者我要写书评

暂无评论

Physically Consistent Learning of Conservative Lagrangian Systems with Gaussian Processes

Physically Consistent Learning of Conservative Lagrangian Sy...

引用

IEEE Conference on Decision and control

作者： Giulio Evangelisti Sandra Hirche Department of Electrical and Computer Engineering Chair of Information-oriented Control Technical University of Munich Munich Germany

ISBN: (数字)9781665467612

ISBN: (纸本)9781665467629

This paper proposes a physically consistent Gaussian Process (GP) enabling the data-driven modelling of uncertain Lagrangian systems. The function space is tailored according to the energy components of the Lagrangian and the differential equation structure, analytically guaranteeing properties such as energy conservation and quadratic form. The novel formulation of Cholesky decomposed matrix kernels allow the probabilistic preservation of positive definiteness. Only differential input-to-output measurements of the function map are required while Gaussian noise is permitted in torques, velocities, and accelerations. We demonstrate the effectiveness of the approach in numerical simulation.

关键词： Uncertainty Gaussian processes Numerical simulation Probabilistic logic Numerical models Velocity measurement Torque measurement

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：