检索结果-内蒙古大学图书馆

Real time embedded system for object detection using deep learning

AIP Conference Proceedings 2022年第1期2415卷

作者： Bashra Kadhim Oleiwi Mais R. Kadhim Control and Systems Engineering Department University of Technology Baghdad Iraq

Blind people face difficulty in practicing their daily life safely because they cannot know the objects surrounding them and this exposes them to many dangers. Given that the number of blind people around the world is a significant number, this research deals to build an intelligent system that helps the blind people to know the objects surrounding them in an internal environment where it is formed. The system consists of two parts, the first part is the software, which depends on the use of one of the deep learning algorithms and its name is YOLO (You Only Look Once). This algorithm was chosen because of its high speed and accuracy, and this is what this group of people needs, which the research aims to help them as much as possible. The algorithm was trained on a ready-made dataset called COCO (Common Objects in COntex) Dataset which It is used for the purposes of discovering objects and detecting faces … etc. The other part of the system is the part of the hardware, which mainly depends on a fast and lightweight microprocessor, which is Raspberry Pi B3, in addition to the headphone and Raspberry Pi camera. After the images is taken by the Raspberry Pi Camera, these images are send to the Raspberry pi and the YOLO algorithm detect the objects in each image, and after the object is detected, it sends the output that is converted into sound via the head Phone to the person and thus can avoid the things surrounding them.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Parallel Planning:A New Motion Planning Framework for Autonomous Driving

引用

IEEE/CAA Journal of Automatica Sinica 2019年第1期6卷 236-246页

作者： Long Chen Xuemin Hu Wei Tian Hong Wang Dongpu Cao Fei-Yue Wang IEEE School of Data and Computer Science Sun Yat-sen University the School of Computer Science and Information Engineering Hubei University Institute of Measurement and Control Systems Karlsruhe Institute of Technology Department of Mechanical and Mechatronics Engineering University of Waterloo the State Key Laboratory of Management and Control for Complex Systems.Institute of Automation Chinese Academy of Sciences the Research Center for Military Computational Experiments and Parallel Systems Technology National University of Defense Technology

Motion planning is one of the most significant technologies for autonomous driving. To make motion planning models able to learn from the environment and to deal with emergency situations, a new motion planning framework called as"parallel planning" is proposed in this paper. In order to generate sufficient and various training samples, artificial traffic scenes are firstly constructed based on the knowledge from the reality.A deep planning model which combines a convolutional neural network(CNN) with the Long Short-Term Memory module(LSTM) is developed to make planning decisions in an end-toend mode. This model can learn from both real and artificial traffic scenes and imitate the driving style of human ***, a parallel deep reinforcement learning approach is also presented to improve the robustness of planning model and reduce the error rate. To handle emergency situations, a hybrid generative model including a variational auto-encoder(VAE) and a generative adversarial network(GAN) is utilized to learn from virtual emergencies generated in artificial traffic scenes. While an autonomous vehicle is moving, the hybrid generative model generates multiple video clips in parallel, which correspond to different potential emergency scenarios. Simultaneously, the deep planning model makes planning decisions for both virtual and current real scenes. The final planning decision is determined by analysis of real observations. Leveraging the parallel planning approach, the planner is able to make rational decisions without heavy calculation burden when an emergency occurs.

关键词： Autonomous driving artificial traffic scene deep learning emergencies motion planning parallel planning

来源：评论

学校读者我要写书评

暂无评论

Design of optimal sliding mode controllers for electrical servo drive system under disturbance

引用

AIP Conference Proceedings 2022年第1期2415卷

作者： Mohammed K. Hamzah Luay Thamir Rasheed Control and Systems Engineering Department University of Technology Baghdad Iraq

This paper presents the design of three types of optimal sliding mode controllers (SMCs); the classical sliding mode controller (CSMC), the modified sliding mode controller (MSMC), and the integral sliding mode controller (ISMC), for position control of the electrical servo drive system under disturbance. The sliding mode control methodology is considered one of the best approaches for the robust controller design and the chattering phenomenon in the control effort of the CSMC is attenuated by using the boundary layer method. The Fruit Fly optimization (FFO) algorithm has been utilized to get and tune the gain variable of the proposed sliding mode controllers and the thickness of the boundary layer function in order to find the best current action for the system. The numerical simulation results obtained by using MATLAB package reveal that all controllers can give excellent performance; however, in terms of minimizing the settling time, hitting time, and the amplitude of chattering phenomenon in the control effort, the performance of the optimal ISMC is better than those of the optimal CSMC and optimal MSMC. Moreover, the fitness evaluation value is reduced.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of Linear Battery Model for Path Planning with Mixed Integer Linear Programming: Simulated and Experimental Validation

arXiv

引用

arXiv 2022年

作者： Scott, Drew Manyam, Satyanarayana G. Casbeer, David W. Kumar, Manish Weintraub, Isaac E. Rothenberger, Michael J. Department of Mechanical and Materials Engineering University of Cincinnati United States Infoscitex Corp. A DCS Company DaytonOH45431 United States Cooperative & Intelligent Control Control Science Center Air Force Research Laboratory WPAFB OH45433 United States Control Science Center Air Force Research Laboratory WPAFB OH45433 United States Flight Systems Integration Branch Air Force Research Laboratory WPAFB OH45433 United States

Mixed Integer Linear Programs (MILPs) are often used in the path planning of both ground and aerial vehicles. Such a formulation of the path planning problem requires a linear objective function and constraints, limiting the fidelity of the the tracking of vehicle states. One such parameter is the state of charge of the battery used to power the vehicle. Accurate battery state estimation requires nonlinear differential equations to be solved. This state estimation is important in path planning to ensure flyable paths, however when using MILPs to formulate the path planning problem these nonlinear equations cannot be implemented. Poor accuracy in battery estimation during the path planning runs the risk of the planned path being feasible by the estimation model but in reality will deplete the battery to a critical level. To the end of higher accuracy battery estimation within a MILP, we present here a simple linear battery model which predicts the change in state-of-charge (SOC) of a battery given a power draw and duration. This model accounts for changes in battery voltage due to applied electrical load and changes in battery SOC. The battery model is presented and then tested against alternate battery models in numerical and in experimental tests. Further, the effect the proposed linear model has over a simpler SOC estimation on the time-to-solve a resource constrained shortest path problem is also evaluated, implemented in two different algorithms. It is seen that the linear model performs well in battery state estimation while remaining implementable in a Linear Program or MILP, with little affect on the time-to-solve. © 2022, CC BY-SA.

关键词： Nonlinear equations

来源：评论

学校读者我要写书评

暂无评论

Characterising linear spatio-temporal dynamical systems in the frequency domain

arXiv

引用

arXiv 2021年

作者： Wei, Hua-Liang Billings, Stephen A. Department of Automatic Control and Systems Engineering The University of Sheffield Mappin Street SheffieldS1 3JD United Kingdom

A new concept, called the spatio-temporal transfer function (STTF), is introduced to characterise a class of linear time-invariant (LTI) spatio-temporal dynamical systems. The spatio-temporal transfer function is a natural extension of the ordinary transfer function for classical linear time-invariant control systems. As in the case of the classical transfer function, the spatio-temporal transfer function can be used to characterise, in the frequency domain, the inherent dynamics of linear time-invariant spatio-temporal systems. The introduction of the spatio-temporal transfer function should also facilitate the analysis of the dynamical stability of discrete-time spatio-temporal systems. © 2021, CC BY-NC-ND.

关键词： Integral equations

来源：评论

学校读者我要写书评

暂无评论

Safety and Optimality in Learning-Based control At Low Computational Cost

引用

IEEE Transactions on Automatic control 2025年

作者： Baumann, Dominik Kowalczyk, Krzysztof Rojas, Cristian R. Tiels, Koen Wachel, Pawel Aalto University Cyber-physical Systems Group Espoo Finland Uppsala University Department of Information Technology Uppsala Sweden Wroc Law University of Science and Technology Department of Control Systems and Mechatronics Wroclaw Poland Kth Royal Institute of Technology Division of Decision and Control Systems Stockholm Sweden Eindhoven University of Technology Department of Mechanical Engineering Eindhoven Netherlands

Applying machine learning methods to physical systems that are supposed to act in the real world requires providing safety guarantees. However, methods that include such guarantees often come at a high computational cost, making them inapplicable to large datasets and embedded devices with low computational power. In this paper, we propose Colsafe, a computationally lightweight safe learning algorithm whose computational complexity grows sublinearly with the number of data points. We derive both safety and optimality guarantees and showcase the effectiveness of our algorithm on a seven-degrees-of-freedom robot arm. © 1963-2012 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Stochastic subgradient projection methods for composite optimization with functional constraints

arXiv

引用

arXiv 2022年

作者： Necoara, Ion Singh, Nitesh Kumar Automatic Control and Systems Engineering Department University Politehnica Bucharest Spl. Independentei 313 Bucharest060042 Romania Gheorghe Mihoc-Caius Iacob Institute of Mathematical Statistics and Applied Mathematics The Romanian Academy Bucharest050711 Romania

In this paper we consider convex optimization problems with stochastic composite objective function subject to (possibly) infinite intersection of constraints. The objective function is expressed in terms of expectation operator over a sum of two terms satisfying a stochastic bounded gradient condition, with or without strong convexity type properties. In contrast to the classical approach, where the constraints are usually represented as intersection of simple sets, in this paper we consider that each constraint set is given as the level set of a convex but not necessarily differentiable function. Based on the flexibility offered by our general optimization model we consider a stochastic subgradient method with random feasibility updates. At each iteration, our algorithm takes a stochastic proximal (sub)gradient step aimed at minimizing the objective function and then a subsequent subgradient step minimizing the feasibility violation of the observed random constraint. We analyze the convergence behavior of the proposed algorithm for diminishing stepsizes and for the case when the objective function is convex or strongly convex, unifying the nonsmooth and smooth cases. We prove sublinear convergence rates for this stochastic subgradient algorithm, which are known to be optimal for subgradient methods on this class of problems. When the objective function has a linear least-square form and the constraints are polyhedral, it is shown that the algorithm converges linearly. Numerical evidence supports the effectiveness of our method in real problems. © 2022, CC BY.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Urban trip generation forecasting based on gradient boosting algorithm 1

Urban trip generation forecasting based on gradient boosting...

引用

1st IEEE International Conference on Digital Twins and Parallel Intelligence, DTPI 2021

作者： Li, Zhishuai Xiong, Gang Zhang, Yu Zheng, Meng Dong, Xisong Lv, Yisheng Institute of Automation Chinese Academy of Sciences State Key Laboratory for Management and Control of Complex Systems Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan China Beijing Municipal Institute of City Planning and Design Traffic Planning Department Beijing China

ISBN: (纸本)9781665433372

The four-step transportation model plays an important role in urban planning. The quality of the first phase, i.e. trip generation, determines the performance of the global course. The majority of trip generation forecasting models highly rely on mathematical derivation and have many predictor variables during the prediction, which leads to low accuracy of results and requires laboriously hand-crafted design of input vectors. This paper is the first to introduce the gradient boosting decision tree (GBDT) algorithm for trip generation prediction, and harmonizes such a powerful machine learning method with traditional urban planning requirements to achieve better prediction performance. Unlike the commonly used linear regression method, GBDT can automatically perform feature selection and model the non-linear relationships between input and output variables. Experimental results on real-world residential travel census in Beijing prove that the GBDT model significantly outperforms the baseline and can forecast the trip generation more accurately. © 2021 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Geometry Problem Solving Based on Counter-Factual Evolutionary Reasoning

Geometry Problem Solving Based on Counter-Factual Evolutiona...

引用

IEEE International Conference on Automation Science and engineering (CASE)

作者： Bing Song Gang Xiong Zhen Shen Fenghua Zhu Yisheng Lv Peijun Ye The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China The Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences China The Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing The Cloud Computing Center Chinese Academy of Sciences Dongguan China Intelligent Manufacturing Center Qingdao Academy of Intelligent Industries Qingdao China

As a representative topic in natural language processing and automated theorem proving, geometry problem solving requires an abstract problem understanding and symbolic reasoning. A major challenge here is to find a feasible reasoning sequence that is consistent with given axioms and the theorems already proved. Most recent methods have exploited neural network-based techniques to automatically discover eligible solving steps. Such a kind of methods, however, is greatly impacted by the expert solutions for training. To improve the accuracy, this paper proposes a new method called counterfactual evolutionary reasoning, which uses a generative adversarial network to generate initial reasoning sequences and then introduces counterfactual reasoning to explore potential solutions. By directly exploring theorem candidates rather than the neural network selection, the new method can sufficiently extend the searching space to get a more appropriate reasoning step. Through comparative experiments on the recent proposed Geometry3k, the largest geometry problem solving dataset, our method generally achieves a higher accuracy than most previous methods, bringing an overall improvement about 4.4% compared with the transformer models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Study of the Influence of Rolling Modes on the Operation of Interconnected Electric Drives of a Rolling Mill

Study of the Influence of Rolling Modes on the Operation of ...

引用

Advanced Technology (KhPIWeek), IEEE KhPI Week on

作者： Valerii Tytiuk Alexey Kalinin Valeriy Druzhinin Victor Busher Oleksii Chornyi Dmytro Halushko Department of Electromechanics Kryvyi Rih National University Kryvyi Rih Ukraine Department of Informative computer systems Abylkas Saginov Karaganda Technical University NPJSC Karaganda The Republic of Kazakhstan Department of Power Engineering Karaganda Industrial University NPJSC Temirtau The Republic of Kazakhstan Dept. of Electrical Engineering and Electronics National University “Odessa Maritime Academy” Odessa Ukraine Institute of Electromechanics Energy Saving and Automatic Control Systems Kremenchuk Mykhailo Ostrogradskyi National University Kremenchuk Ukraine Dept. of Electrical Engineering Ukrainian State University of Science and Technologies Dnipro Ukraine

The paper is devoted to study of the influence of rolling modes on the performance of powerful interconnected electric drives of a hot rolling mill under the action of an electromagnetic coupling circuit between the electric drives of the roughing and finishing groups. The action of the electromagnetic coupling circuit manifests itself in the form of the influence of impact loads of synchronous electric drives on the angular velocity of direct current electric drives of the finishing group of the mill. The parameters of the electromagnetic coupling circuit are determined by the power supply scheme and equipment parameters. Values of impact loads applied to a synchronous motor depend on the rolling process parameters, in particular, the chemical composition of the rolled steel and the temperature of the ingot. The paper presents the results of calculating the rolling power for various rolling mode parameters. Using mathematical modeling in Simulink, numerical estimates of the influence of rolling modes on the magnitude of the voltage drop in the power supply unit and the drop in the angular velocity of the electric drive of the finishing group were obtained on the example of a wide-strip hot rolling mill 1700 of ArcelorMittal Temirtau JSC.

关键词：

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：