检索结果-内蒙古大学图书馆

22nd World Congress of the International Federation of Automatic control (IFAC)

作者： Mohiuddin, Mohammed B. Haddad, Abdel Gafoor Boiko, Igor Zweiri, Yahya Khalifa Univ Ctr Autonomous Robot Syst Abu Dhabi U Arab Emirates Khalifa Univ Dept Elect Engn & Comp Sci Abu Dhabi U Arab Emirates Khalifa Univ Dept Aerosp Engn Abu Dhabi U Arab Emirates Khalifa Univ Adv Res & Innovat Ctr Abu Dhabi U Arab Emirates

ISBN: (纸本)9781713872344

control of nonlinear systems is a challenging task that often requires linearization, which limits the operating envelope. Moreover, designing a controller for such nonlinear systems requires complex tuning rules and expert system knowledge. deep reinforcement learning (DRL) has been used as a controller for nonlinear systems. However, its applicability is hindered by the Sim2Real gap, an issue where the DRL agent trained in simulation does not transfer to reality. In this work, we propose using DRL for the control of nonlinear systems across the Sim2Real gap by utilizing a detailed dynamic model of the nonlinear system. To demonstrate the proposed methodology, we use a tower crane as the nonlinear system of interest. The control policy of the DRL agent is learned rather than explicitly programmed. To highlight the effectiveness of the proposed DRL-based controller, the results are compared with the PI controller. The experimental results presented demonstrate the successful Sim2Real transfer and effectiveness of the proposed approach. Copyright (c) 2023 The Authors. This is an open access article under the CC BY-NC- ND license (https://***/licenses/by-nc-nd/4.0/)

关键词： reinforcement learning and deep learning in control Mechatronic systems control of constrained systems Simulation to reality transfer.

来源：评论

学校读者我要写书评

暂无评论

Stability in reinforcement learning Process control for Additive Manufacturing 22

Stability in Reinforcement Learning Process Control for Addi...

引用

22nd World Congress of the International Federation of Automatic control (IFAC)

作者： Vagenas, Stylianos Panoutsos, George Univ Sheffield Dept Automat Control & Syst Engn Sheffield S Yorkshire England

ISBN: (纸本)9781713872344

reinforcement learning (RL), as a machine learning paradigm, receives increasing attention in both academia and industry, in particular for process control. Its trial-and-error concept, along with its data-driven nature, make RL suitable for process control in complex tasks, where the control task and framework can be formulated flexibly. However, there are still challenges that need to be addressed in order for RL to be introduced into the control mainstream, in particular for critical processes. A major challenge in RL is that there is no guarantee for robust, stable RL process control. This is a key impediment to RL implementation on tasks for which stability is an important requirement. Additive Manufacturing (AM) is an example of such process control task, since the very high complexity of the manufacturing process makes it suitable for RL process control, while stable performance is a necessity. However, one has to firstly understand performance and stability as a key requirement. In this paper, we reflect on stability approaches in RL and we investigate the stability requirements for AM. Our AM case study provides intuition and encourages further research for stable RL that would unlock potential for adoption and implementation of RL in AM applications. Research in the proposed direction would also have the potential for impacts to other process control sectors, in critical applications, where appropriate utilisation of stable RL control could bring significant advantages. Copyright (c) 2023 The Authors.

关键词： reinforcement learning and deep learning in control Robust control Lyapunov methods Additive manufacturing

来源：评论

学校读者我要写书评

暂无评论

Risk-based Convolutional Perception Models for Collision Avoidance in Autonomous Marine Surface Vessels using deep reinforcement learning 22

Risk-based Convolutional Perception Models for Collision Avo...

引用

22nd World Congress of the International Federation of Automatic control (IFAC)

作者： Larsen, Thomas Nakken Hansen, Hannah Rasheed, Adil Norwegian Univ Sci & Technol Dept Engn Cybernet OS Bragstads Plass 2 NO-7034 Trondheim Norway

ISBN: (纸本)9781713872344

In this work, we propose a novel policy network architecture for model-free reinforcement learning (RL)-based path-following and collision avoidance in marine surface vessels. By applying convolutional neural networks (CNNs) for mapping LiDAR-like distance measurements to Collision Risk Indices (CRIs), we evaluate the utility of risk-based pretraining of CNN feature extractors prior to RL. Where previous works required hand-crafted preprocessing of highresolution distance measurements to train an autonomous RL agent successfully, the proposed approach achieves this goal in a data-driven fashion. Ultimately, we propose future directions to improve CNN-based perception models for collision avoidance in range sensing applications. Copyright (c) 2023 The Authors. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0/)

关键词： reinforcement learning and deep learning in control Autonomous surface vehicles Neural networks Collision Risk Indices

来源：评论

学校读者我要写书评

暂无评论

Stability in reinforcement learning Process control for Additive Manufacturing

引用

IFAC-PapersOnLine 2023年第2期56卷 4719-4724页

作者： Stylianos Vagenas George Panoutsos

关键词： reinforcement learning and deep learning in control Robust control Lyapunov methods Additive manufacturing

来源：评论

学校读者我要写书评

暂无评论

Risk-based Convolutional Perception Models for Collision Avoidance in Autonomous Marine Surface Vessels using deep reinforcement learning

引用

IFAC-PapersOnLine 2023年第2期56卷 10033-10038页

作者： Thomas Nakken Larsen Hannah Hansen Adil Rasheed Department of Engineering Cybernetics Norwegian University of Science and Technology O. S. Bragstads plass 2 Trondheim NO-7034 Norway

In this work, we propose a novel policy network architecture for model-free reinforcement learning (RL)-based path-following and collision avoidance in marine surface vessels. By applying convolutional neural networks (CNNs) for mapping LiDAR-like distance measurements to Collision Risk Indices (CRIs), we evaluate the utility of risk-based pretraining of CNN feature extractors prior to RL. Where previous works required hand-crafted preprocessing of high-resolution distance measurements to train an autonomous RL agent successfully, the proposed approach achieves this goal in a data-driven fashion. Ultimately, we propose future directions to improve CNN-based perception models for collision avoidance in range sensing applications.

关键词： reinforcement learning and deep learning in control Autonomous surface vehicles Neural networks Collision Risk Indices

来源：评论

学校读者我要写书评

暂无评论

Zero-Shot Sim2Real Transfer of deep reinforcement learning controller for Tower Crane System

引用

IFAC-PapersOnLine 2023年第2期56卷 10016-10020页

作者： Mohammed B. Mohiuddin Abdel Gafoor Haddad Igor Boiko Yahya Zweiri Center for Autonomous Robotic Systems Khalifa University Abu Dhabi UAE Department of Electrical Engineering and Computer Science Khalifa University Abu Dhabi UAE Department of Aerospace Engineering and Director of Advanced Research and Innovation Center Khalifa University Abu Dhabi UAE

关键词： reinforcement learning and deep learning in control Mechatronic systems control of constrained systems Simulation to reality transfer

来源：评论

学校读者我要写书评

暂无评论

Real-Time Counterfactual Explanations For Robotic Systems With Multiple Continuous Outputs 22

Real-Time Counterfactual Explanations For Robotic Systems Wi...

引用

22nd World Congress of the International Federation of Automatic control (IFAC)

作者： Gjaerum, Vilde B. Strumke, Inga Lekkas, Anastasios M. Miller, Timothy Norwegian Univ Sci & Technol Dept Engn Cybernet Trondheim Norway Norwegian Univ Sci & Technol Dept Comp Sci Trondheim Norway Univ Melbourne Sch Comp & Informat Syst Melbourne Australia

ISBN: (纸本)9781713872344

Although many machine learning methods, especially from the field of deep learning, have been instrumental in addressing challenges within robotic applications, we cannot take full advantage of such methods before these can provide performance and safety guarantees. The lack of trust that impedes the use of these methods mainly stems from a lack of human understanding of what exactly machine learning models have learned, and how robust their behaviour is. This is the problem the field of explainable artificial intelligence aims to solve. Based on insights from the social sciences, we know that humans prefer contrastive explanations, i.e. explanations answering the hypothetical question "what if?". In this paper, we show that linear model trees are capable of producing answers to such questions, so-called counterfactual explanations, for robotic systems, including in the case of multiple, continuous inputs and outputs. We demonstrate the use of this method to produce counterfactual explanations for two robotic applications. Additionally, we explore the issue of infeasibility, which is of particular interest in systems governed by the laws of physics. Copyright (c) 2023 The Authors. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0/)

关键词： Explicability and transparency in Cyber-physical and human systems reinforcement learning and deep learning in control data-driven control autonomous robotic systems explainable artificial intelligence for robotics counterfactual explanations for robotic systems

来源：评论

学校读者我要写书评

暂无评论

reinforcement learning in an Adaptable Chess Environment for Detecting Human-understandable Concepts 22

Reinforcement Learning in an Adaptable Chess Environment for...

引用

22nd World Congress of the International Federation of Automatic control (IFAC)

作者： Hammersborg, Patrik Strumke, Inga Norwegian Univ Sci & Technol Dept Comp Sci Trondheim Norway

ISBN: (纸本)9781713872344

Self-trained autonomous agents developed using machine learning are showing great promise in a variety of control settings, perhaps most remarkably in applications involving autonomous vehicles. The main challenge associated with self-learned agents in the form of deep neural networks, is their black-box nature: it is impossible for humans to interpret deep neural networks. Therefore, humans cannot directly interpret the actions of deep neural network based agents, or foresee their robustness in different scenarios. In this work, we demonstrate a method for probing which concepts self-learning agents internalise in the course of their training. For demonstration, we use a chess playing agent in a fast and light environment developed specifically to be suitable for research groups without access to enormous computational resources or machine learning models. We provide code for the environment and for self-play learning chess agents, as well as for the state-of-the-art explainable AI (XAI) method of concept detection. We present results for different chess board sizes, discussing the concepts learned by our chess agents in light of human domain knowledge.

关键词： reinforcement learning and deep learning in control Machine learning Knowledge-based control Supervision and testing Discrete event modelling and simulation Explainable artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Combining neural networks and control: potentialities, patterns and perspectives 22

Combining neural networks and control: potentialities, patte...

引用

22nd IFAC World Congress

作者： Cerf, Sophie Rutten, Éric Univ. Lille Inria CNRS Centrale Lille UMR 9189 CRIStAL LilleF-59000 France Univ. Grenoble Alpes Inria CNRS LIG GrenobleF-38000 France

ISBN: (纸本)9781713872344

Machine learning tools are widely used for knowledge extraction, modeling, and decision tasks;a range of problems that control Theory also tackles. Their relations have been largely explored by looking at stochastic control and Markov Decision Processes, due to the proximity of their formulations. However, novel links between machine learning and deterministic control are emerging;combining both approaches, e.g. by performing identification with learning, or controlling the training process. The recent flourishing literature is vast: there is a need to identify challenges, trends and opportunities on this interface. This survey contributes i) to the compared analysis of both fields. ii) Based on literature review, a categorization of combinations of learning and control is drawn. In the control framework, learning has been used for modeling, controllers tuning or adaptation, generating a controller or as a controller itself, for translating complex objectives, or checking controlled systems. Conversely, in the learning framework, control is used for tuning hyperparameters, selecting or generating training data, as the training or decision-making algorithm itself or to guarantee learning properties. iii) Finally, discussions on the literature open novel promising combinations to be explored, such as control of neural networks' training process. Copyright © 2023 The Authors. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0/)

关键词： control and automation Data-driven control learning for control Machine learning Machine learning in modelling Neural Networks prediction reinforcement learning and deep learning in control

来源：评论

学校读者我要写书评

暂无评论

Combining neural networks and control: potentialities, patterns and perspectives

引用

IFAC-PapersOnLine 2023年第2期56卷 9036-9049页

作者： Sophie Cerf Éric Rutten Univ. Lille Inria CNRS Centrale Lille UMR 9189 CRIStAL F-59000 Lille France Univ. Grenoble Alpes Inria CNRS LIG Grenoble F-38000 France

Machine learning tools are widely used for knowledge extraction, modeling, and decision tasks; a range of problems that control Theory also tackles. Their relations have been largely explored by looking at stochastic control and Markov Decision Processes, due to the proximity of their formulations. However, novel links between machine learning and deterministic control are emerging; combining both approaches, e.g. by performing identification with learning, or controlling the training process. The recent flourishing literature is vast: there is a need to identify challenges, trends and opportunities on this interface. This survey contributes i) to the compared analysis of both fields. ii) Based on literature review, a categorization of combinations of learning and control is drawn. In the control framework, learning has been used for modeling, controllers tuning or adaptation, generating a controller or as a controller itself, for translating complex objectives, or checking controlled systems. Conversely, in the learning framework, control is used for tuning hyperparameters, selecting or generating training data, as the training or decision-making algorithm itself or to guarantee learning properties. iii) Finally, discussions on the literature open novel promising combinations to be explored, such as control of neural networks’ training process.

关键词： Machine learning Neural Networks learning for control reinforcement learning and deep learning in control Machine learning in modelling prediction control and automation Data-driven control

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：