检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Hu, Xuemin Li, Shen Huang, Tingyu Tang, Bo Huai, Rouxing Chen, Long The School of Artificial Intelligence Hubei University Hubei Wuhan430062 China The Department of Electrical and Computer Engineering Worcester Polytechnic Institute WorcesterMA01609 United States Beijing Huairou Academy of Parallel Sensing Beijing101499 China The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100864 China The Waytous Inc. Beijing100083 China

Safety and cost are two important concerns for the development of autonomous driving technologies. From the academic research to commercial applications of autonomous driving vehicles, sufficient simulation and real world testing are required. In general, a large scale of testing in simulation environment is conducted and then the learned driving knowledge is transferred to the real world, so how to adapt driving knowledge learned in simulation to reality becomes a critical issue. However, the virtual simulation world differs from the real world in many aspects such as lighting, textures, vehicle dynamics, and agents' behaviors, etc., which makes it difficult to bridge the gap between the virtual and real worlds. This gap is commonly referred to as the reality gap (RG). In recent years, researchers have explored various approaches to address the reality gap issue, which can be broadly classified into three categories: transferring knowledge from simulation to reality (sim2real), learning in digital twins (DTs), and learning by parallel intelligence (PI) technologies. In this paper, we consider the solutions through the sim2real, DTs, and PI technologies, and review important applications and innovations in the field of autonomous driving. Meanwhile, we show the state-of-the-arts from the views of algorithms, models, and simulators, and elaborate the development process from sim2real to DTs and PI. The presentation also illustrates the far-reaching effects and challenges in the development of sim2real, DTs, and PI in autonomous driving. Copyright © 2023, The Authors. All rights reserved.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

AI Graphical Programming Learning Platform for Children

AI Graphical Programming Learning Platform for Children

引用

2021 China automation Congress, CAC 2021

作者： Zhao, Hongxia Liu, Xiwei Gong, Xiaoyan Li, Qiang Jing, Sifeng Xue, Yaofeng The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Institute of Smart Education Systems Qingdao Academy of Intelligent Industries Qingdao China University of Chinese Academy of Sciences Beijing China Shanghai Engineering Research Center of Digital Education Equipment Department of Education Information Technology East China Normal University Shanghai China

ISBN: (纸本)9781665426473

In this era of rapid development of artificial intelligence, the truth of competition in the future is the talent. Countries all over the world attach great importance to the programming and artificial intelligence education of children. In the future, the theoretical development and practical application of this emerging field will usher in a period of rapid development. This paper presents an artificial intelligence graphical programming learning platform based on Jetson Nano, which combines artificial intelligence education with modular software programming, provides students with a more open, intelligent, and interesting programming environment through the cross-platform development mode of "cloud service + intelligent hardware", and adopts visual programming to reduce the difficulty of artificial intelligence programming. The platform can fully tap learning resources, reduce education costs, and make artificial intelligence education more intuitive and humanized. © 2021 IEEE

关键词： Computer graphics

来源：评论

学校读者我要写书评

暂无评论

Event-triggered Observability: A Set-membership Perspective

arXiv

引用

arXiv 2022年

作者： Zheng, Kaikai Shi, Dawei Chen, Tongwen State Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing100081 China Department of Electrical and Computer Engineering University of Alberta EdmontonABT6G 1H9 Canada

This work attempts to discuss the observability of linear time-invariant systems with event-triggered measurements. A new notion of observability, namely, ǫ-observability is defined with parameter ǫ, which relates to the worst-case performance of inferring the initial state based on not only the received measurement but also the implicit information in the event-triggering conditions at no-event instants. A criterion is developed to test the proposed ǫ-observability of discrete-time linear systems, based on which an iterative event-triggered set-membership observer is designed to evaluate a set containing all possible values of the state. The proposed set-membership observer is designed as the outer approximation of the ellipsoids predicted based on previous state estimates and the ellipsoids inferred by fusing the received measurement and communication conditions, which is optimal in the sense of trace at each step and is proved to be asymptotically bounded. The efficiency of the proposed event-triggered set-membership state observer is verified by numerical experiments. © 2022, CC BY.

关键词： State estimation

来源：评论

学校读者我要写书评

暂无评论

Distributed Momentum-based Frank-Wolfe Algorithm for Stochastic Optimization

arXiv

引用

arXiv 2022年

作者： Hou, Jie Zeng, Xianlin Wang, Gang Sun, Jian Chen, Jie The Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing100081 China Beijing Institute of Technology Chongqing Innovation Center Chongqing401120 China The School of Electronic and Information Engineering Tongji University Shanghai200082 China

—This paper considers distributed stochastic optimization, in which a number of agents cooperate to optimize a global objective function through local computations and information exchanges with neighbors over a network. Stochastic optimization problems are usually tackled by variants of projected stochastic gradient descent. However, projecting a point onto a feasible set is often expensive. The Frank-Wolfe (FW) method has well-documented merits in handling convex constraints, but existing stochastic FW algorithms are basically developed for centralized settings. In this context, the present work puts forth a distributed stochastic Frank-Wolfe solver, by judiciously combining Nesterov’s momentum and gradient tracking techniques for stochastic convex and nonconvex optimization over networks. It is shown that the convergence rate 1 of the proposed algorithm is O(k− 2) for convex optimization, and O(1/log2(k)) for nonconvex optimization. The efficacy of the algorithm is demonstrated by numerical simulations against a number of competing alternatives. Copyright © 2022, The Authors. All rights reserved.

关键词： Momentum

来源：评论

学校读者我要写书评

暂无评论

Weak-value technique for detecting weak magnetic field based on Faraday magneto-optic effect

arXiv

引用

arXiv 2021年

作者： Huang, Jing-Hui Duan, Xue-Ying Wang, Guang-Jun Hu, Xiang-Yun School of Institute of Geophysics and Geomatics China University of Geosciences Wuhan430074 China School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

We study the amplification of weak magnetic field with Weak-value technique based on Faraday magneto-optic effect. By using a different scheme to perform the Sagnac interferometer with the probe in momentum space, we have demonstrated the new weak measure protocol to detect the small weak magnetic field by amplifying the phase shift of Faraday magneto-optic effect. At the given the maximum incident intensity of the initial spectrum, the detection limit of the intensity of the spectrometer and the accuracy of detecting weak magnetic field, we can theoretically give the appropriate pre-selection, post-selection and others optical structure before experiment. Our numerical results show our scheme with Weak-value technique is effective and feasible to detect weak magnetic field with magnetic field intensity lower than 10−10 T. © 2021, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Influence of Temperature and Noise on Subthreshold Signal Propagation in Feedforward Neural Network

Research Square

引用

Research Square 2021年

作者： Yi, Ming Dai, Shiqi Lu, Lulu Wei, Zhouchao Zhu, Yuan School of Mathematics and Physics China University of Geosciences Hubei Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems School of Automation China University of Geosciences Hubei Wuhan430074 China Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence Ministry of Education Fudan University Shanghai200433 China

Temperature is an important environmental factor that all creatures depend on. Under the appropriate temperature, the neural system shows good biological performance. Based on an improved Hodgkin-Huxley (HH) neuron model considering temperature and noise, the ten-layers pure excitatory feedforward neural network and the ten-layers excitatory-inhibitory (EI) neural network are constructed to study the subthreshold signal propagation. It’s found that increasing temperature can restrain the signal propagation, and raise the noises intensity threshold where the failed signal propagation can transform into succeed signal propagation. Under the large noise, the signal propagation in network in different temperatures exhibits different anti-noise capabilities. There exists the saturation value of interlayer connection probability, that is, the signal propagation maintains constant when interlayer connection probability beyond a certain value. Moreover, in EI network with large noise, the network’s intrinsic oscillation activity will completely cover subthreshold signal, and block the signal propagation. The jumping phenomenon in the value of fidelity, which measures the similarity between input signal and output signal, appears in both pure excitatory network and EI network. This paper provides potential value for understanding the regulation of both temperature and noise in information propagation in neural network. © 2021, CC BY.

关键词： Backpropagation

来源：评论

学校读者我要写书评

暂无评论

Design of a novel flexible assistive hand exoskeleton

Design of a novel flexible assistive hand exoskeleton

引用

Youth Academic Annual Conference of Chinese Association of automation (YAC)

作者： Guotao Li Long Cheng Zhengrun Gao Jilong Lu Yanjiang Zhao State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China The National Clinical Research Center for Aging and Medicine Fudan University Shanghai China Key Laboratory of Advanced Manufacturing and Intelligent Technology Ministry of Education Harbin University of Science and Technology Harbin China Intelligent Machine Institute Harbin University of Science and Technology Harbin China

ISBN: (纸本)9781665465373

Hand paralysis caused by stroke, spinal cord injury, or neurological trauma has a significant impact on the independence and quality of life of the patients. The hand exoskeleton can provide hand assistance and improve the patient’s grasp. In this article, a novel wearable flexible hand exoskeleton is proposed to assist users in activities of daily life. To create a simple and lightweight assistive hand exoskeleton, 3D printing is used to manufacture most of the components, and a remote drive system is designed to reduce the weight of the hand exoskeleton. A ball pair device and a slider device are used to ensure the freedom of the thumb and the adaptability of the hand exoskeleton to different hand sizes. Finally, the experiments are conducted to verify that the hand exoskeleton can achieve motion assistance.

关键词： Exoskeletons Thumb Metals Stroke (medical condition) Three-dimensional printing Motion capture Paralysis

来源：评论

学校读者我要写书评

暂无评论

Interval prediction model of blast furnace gas utilization rate based on multi-time-scale

Interval prediction model of blast furnace gas utilization r...

引用

第三十九届中国控制会议

作者： Feng Yin Jianqi An Xiaoling Shen Takao Terano School of Automation China University of Geosciences Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Chiba University of Commerce

Gas utilization rate（GUR） is an important indicator that reflects the state of a blast furnace（BF）. However, most researches only predict the point values of GUR, it is difficult for the operator to make corresponding operations. This paper presents an interval prediction model based on multi-time-scale to predict the GUR. First, this paper analyzes the impact of the burden distribution and the hot-blast supply on multi-time-scale of the blast furnace. Then, we build a multi-time-scale point prediction model based on support vector regression（SVR）. Next, an interval prediction model of multi-objective optimization based on interval prediction indicators and the point prediction model was proposed. Finally, some experiment results base on actual run data shows that the method predicts the GUR more effectively than the point prediction model based on single time scale.

关键词： Blast furnace Gas utilization rate Interval prediction Multi-time-scale Multi-objective optimization

来源：评论

学校读者我要写书评

暂无评论

A Deep Reinforcement Learning Method with Action Switching for Autonomous Navigation

A Deep Reinforcement Learning Method with Action Switching f...

引用

第40届中国控制会议

作者： Zuowei Wang Xiaozhong Liao Fengdi Zhang Min Xu Yanmin Liu Xiangdong Liu Xi Zhang Rui wei Dong Zhen Li School of Automation and Key Laboratory for Intelligent Control & Decision on Complex Systems Beijing Institute of Technology Beijing Aerospace Automatic Control Institute National Key Laboratory of Science and Technology on Aerospace Intelligence Control Capital Aerospace Machinery Co. Ltd.

Stochastic policy-based deep reinforcement learning（DRL） has successfully gained the widespread application but demands plenty of stochastic exploration to learn the environment at the initial training *** the agent is exposed to more complex environment,not only is the methodology inefficient,but its performance may also suffer from the issue of high *** paper develops a framework to accelerate the training procedure and reduce the variance by introducing a stochastic switching network,which specifically allows the agent to choose between heuristic actions and actions output by proximal policy optimization（PPO） *** of starting from the random actions,the agent can be effectively guided by the heuristic actions so that the navigation capability of the agent can be rapidly *** vanilla policy gradient（VPG） algorithm is further utilized to train the switching network,which can be jointly trained with the baseline *** the experimental comparison with the baseline PPO in the customized maze environment with openAI Gym toolkit,our method greatly contributes to the more efficient execution of navigation task by means of the heuristic actions for guidance.

关键词： Robot navigation proximal policy optimization（PPO） deep reinforcement learning（DRL） Vanilla policy gradient（VPG） action switching

来源：评论

学校读者我要写书评

暂无评论

A comparative study on evolutionary algorithms for the agent routing problem in multi-point dynamic task

A comparative study on evolutionary algorithms for the agent...

引用

作者： Lu, Sai Xin, Bin Dou, Lihua Wang, Ling School of Automation Beijing Institute of Technology Beijing China Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology Beijing China Department of Automation Tsinghua University Beijing China

The agent routing problem in multi-point dynamic task (ARP-MPDT) proposed recently is a novel permutation optimisation problem. In ARP-MPDT, a number of task points are located at different places and their states change over time. The agent must go to the task points in turn to execute the tasks, and the execution time of each task depends on the task state. The optimisation objective is to minimise the time for the agent to complete all the tasks. In this paper, five evolutionary algorithms are redesigned and tried to solve this problem, including a permutation genetic algorithm (GA), a variant of the particle swarm optimisation (PSO) and three variants of the estimation of distribution algorithm (EDA). In particular, a dual-model EDA (DM-EDA) employing two probability models was proposed. Finally, comparative tests confirm that the DM-EDA has a stronger adaptability than the other algorithms though GA performs better for the large-scale instances. Copyright © 2020 Inderscience Enterprises Ltd.

关键词： Genetic algorithms

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：