检索结果-内蒙古大学图书馆

第三十九届中国控制会议

作者： Feng Liu Chang Chen Zhihua Li Zhi-Hong Guan Hua O Wang School of Automation China University of Geosciences Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems College of Automation Huazhong University of Science and Technology Department of Mechanical Engineering Boston University

In this paper, to avoid the problem of local optimization and slow convergence in complex environment, a reinforcement learning algorithm is proposed to solve the problem. A robot path planning model is built and its feasibility is verified by simulation. In addition, this paper proposes a deep environment to neural network for robot camera to establish a deep reinforcement learning path planning model, and establishes a deep recursive Q-network（DRQN） and Deep Dueling Q-network（DDQN）respectively. In the comparison of the final simulation results, DRQN needs to consume more computation time, but can achieve better results with higher accuracy.

关键词： Reinforcement learning path planning robots deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Improved potential field method path planning based on genetic algorithm

Improved potential field method path planning based on genet...

引用

第三十九届中国控制会议

作者： Feng Liu Hualing He Zhihua Li Zhi-Hong Guan Hua O Wang School of Automation China University of Geosciences Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems College of Automation Huazhong University of Science and Technology Department of Mechanical Engineering Boston University

In order to overcome the problem of path planning failure in traditional potential field method, an improved potential field path planning method based on genetic algorithm is proposed in this paper. Firstly, for the problem of inaccessibility of the target, a factor method is added to the traditional gravity function to solve it;then the local minimum point problem of the traditional artificial potential field method is solved to ensure that the robot can reach the target point. At the same time, in order to get the optimal path, genetic algorithm is used to optimize the combined potential field function of gravity and repulsion, to find the lowest point of potential energy directly, so as to determine the step size and moving direction of the robot. Simulation is carried out to verify the effectiveness of the method.

关键词： Path planning artificial potential field gravitation function genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Development of GPU Enhanced AI Education Platforms for K-12 Schools

Development of GPU Enhanced AI Education Platforms for K-12 ...

引用

2021 China automation Congress, CAC 2021

作者： Gong, Xiaoyan Wen, Yifan Liu, Xiwei Zhao, Hongxia Jing, Sifeng Li, Qiang Gao, Kai Luo, Jilong The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Institute of Smart Education Systems Qingdao Academy of Intelligent Industries Qingdao 266000 China The 21st Century International School Beijing100142 China Beijing NO. 2 Middle School Beijing100087 China Beijing University of Chemical Technology Beijing100029 China

ISBN: (纸本)9781665426473

Recently, with continuous implementation of education reform, AI (Artificial Intelligence) has been included in K-12 (Kindergarten to 12th grade) curricula and AI education is in full swing in China. However, standard, cost-efficient AI education platforms for K-12 schools are still not available. So in this paper, based on Jetson Nano, we developed a GPU-enhanced AI teaching platform including AI learning computers for students to develop Al-related algorithms and applications, AI computer clusters for whole classes, and modular auto-driving cars to run and test algorithms and applications. © 2021 IEEE

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

A Novel Multi-objective Evolutionary Algorithm Based on Space Partitioning 11th

A Novel Multi-objective Evolutionary Algorithm Based on Spac...

引用

11th International Symposium on Intelligence Computation and Applications, ISICA 2019

作者： Wu, Xiaofang Li, Changhe Zeng, Sanyou Yang, Shengxiang School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China School of Mechanical Engineering and Electronic Information China University of Geosciences Wuhan430074 China School of Computer Science and Informatics De Montfort University LeicesterLE1 9BH United Kingdom

ISBN: (纸本)9789811555763

To design an effective multi-objective optimization evolutionary algorithms (MOEA), we need to address the following issues: 1) the sensitivity to the shape of true Pareto front (PF) on decomposition-based MOEAs;2) the loss of diversity due to paying so much attention to the convergence on domination-based MOEAs;3) the curse of dimensionality for many-objective optimization problems on grid-based MOEAs. This paper proposes an MOEA based on space partitioning (MOEA-SP) to address the above issues. In MOEA-SP, subspaces, partitioned by a k-dimensional tree (kd-tree), are sorted according to a bi-indicator criterion defined in this paper. Subspace-oriented and Max-Min selection methods are introduced to increase selection pressure and maintain diversity, respectively. Experimental studies show that MOEA-SP outperforms several compared algorithms on a set of benchmarks. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Toward parallel intelligence: an interdisciplinary solution for complex systems

arXiv

引用

arXiv 2023年

作者： Zhao, Yong Zhu, Zhengqiu Chen, Bin Qiu, Sihang Huang, Jincai Lu, Xin Yang, Weiyi Ai, Chuan Huang, Kuihua He, Cheng Jin, Yucheng Liu, Zhong Wang, Fei-Yue College of Systems Engineering National University of Defense Technology Changsha410073 China Hunan Institute of Advanced Technology Changsha410073 China Shanghai Institute of Infectious Disease and Biosecurity Shanghai200032 China Neuherberg Germany Department of Computer Science Hong Kong Baptist University 999077 Hong Kong State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

The growing complexity of real-world systems necessitates interdisciplinary solutions to confront myriad challenges in modeling, analysis, management, and control. To meet these demands, the parallel systems method rooted in Artificial systems, Computational experiments, and Parallel execution (ACP) approach has been developed. The method cultivates a cycle, termed parallel intelligence, which iteratively creates data, acquires knowledge, and refines the actual system. Over the past two decades, the parallel systems method has continuously woven advanced knowledge and technologies from various disciplines, offering versatile interdisciplinary solutions for complex systems across diverse fields. This review explores the origins and fundamental concepts of the parallel systems method, showcasing its accomplishments as a diverse array of parallel technologies and applications, while also prognosticating potential challenges. We posit that this method will considerably augment sustainable development while enhancing interdisciplinary communication and cooperation. © 2023, CC BY-NC-ND.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Fusionplanner: A Multi-Task Motion Planner for Mining Trucks Using Multisensor Fusion Method

SSRN

引用

SSRN 2023年

作者： Teng, Siyu Chen, Long Li, Luxi Li, Yuchen Hu, Xuein Li, Lingxi Ai, Yunfeng Department of Computer Science Hong Kong Baptist University Hong Kong The School of Artificial Intelligence Hubei University Wuhan China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences China Waytous Inc. Haidian Distinct Beijing China Indianapolis United States School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

In recent years, significant achievements have been made in motion planning for intelligent vehicles. However, as a typical unstructured environment, open-pit mining attracts limited attention due to its complex operational conditions and adverse environmental factors. A comprehensive paradigm for unmanned transportation in open-pit mines is proposed in this research, including a simulation platform, a testing benchmark, and a trustworthy and robust motion planner. Firstly, we introduce the Parallel Mining Simulator (PMS), a high-fidelity simulator specifically designed for open-pit mining scenarios. PMS enables to management and control of open-pit mine transportation from both the single-truck control and multi-truck scheduling perspectives. Then, we develop a novel benchmark called MiningNav, which offers three validation approaches suitable for transportation roads. The purpose of MiningNav is to evaluate the trustworthiness and robustness of algorithms in open-pit mines. Finally, we propose the first multi-task motion planning algorithm, called FusionPlanner, for the mining truck by the multisensor fusion method to adapt both lateral and longitudinal control tasks for unmanned transportation. We validate the performance of our planner using MiningNav in PMS, and empirical results demonstrate a significant reduction in the number of collisions and takeovers of FusionPlanner, thereby improving overall trustworthiness and robustness. © 2023, The Authors. All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Consensus in multi-agent systems with multiple disturbances and time delay via proportional-integral control

Consensus in multi-agent systems with multiple disturbances ...

引用

第40届中国控制会议

作者： Fenglan Sun Yunhao Shen Key Laboratory of Intelligent Analysis and Decision on Complex Systems School of ScienceChongqing University of Posts and Telecommunications Key Laboratory of Intelligent Air-Ground Cooperative Control for Universities in Chongqing College of AutomationChongqing University of Posts and Telecommunications Potsdam Institute for Climate Impact Research

This paper studies the consensus in multi-agent systems with multiple disturbances and time delay over fixed and switching topology via proportional-integral control. The controller that includes proportional and integral actions is *** adopting matrix theory, algebraic graph theory and Lyapunov stability theory, sufficient conditions for consensus are obtained. Several numerical simulations are given to verify the effectiveness of the algorithms.

关键词： consensus multiple disturbances switching topology proportional-integral control

来源：评论

学校读者我要写书评

暂无评论

A Low-Cost Enhanced Heterogeneous Barrier Construction Method for Multi-Target Intrusion Monitoring

引用

IEEE Sensors Journal 2025年

作者： Ye, Jing Xiong, Yonghua Dong, Haobin Yu, Anjun She, Jinhua China University of Geosciences School of Automation Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan430074 China Jiangxi Ganyue Expressway Company Ltd Nanchang330200 China Tokyo University of Technology School of Engineering Tokyo192-0982 Japan

In multi-target intrusion monitoring, heterogeneous nodes may overlap due to different sensing ranges. Additionally, excessively long barriers will increase the cost of barriers and reduce the number of barriers. To address these issues, this article proposes a distributed method for constructing weighted heterogeneous barriers using depth-first search and learning automata (WHBDLA). It designs a dynamically weighted coverage graph based on the non-overlap rate and horizontal displacement. The proposed method considers multiple heterogeneous properties. It uses several intrusion targets to identify the boundaries of local sub-regions while avoiding the cost increase and quantity decrease caused by long barriers. WHBDLA combines the advantages of depth-first search and the reinforcement learning mechanism to adaptively construct heterogeneous barriers in sub-regions with unknown faults. The algorithm initially searches for potential barrier path nodes and then activates nodes with sufficient energy and high weights. Finally, it monitors and repairs the barriers. Comparative experiments and analyses indicate that the proposed method increases the number of barriers, reduces node costs, and decreases running time. © 2001-2012 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Online progressive instance-balanced sampling for weakly supervised object detection

arXiv

引用

arXiv 2022年

作者： Chen, Minghao Tian, Yunong Li, Zhishuo Li, En Liang, Zize The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences 95 Zhongguancun East Road Beijing100190 China Yuquan Road Beijing100049 China Engineering Laboratory of Industrial Vision and Intelligent Equipment Technology Chinese Academy of Sciences 95 Zhongguancun East Road Beijing100190 China

Based on multiple instance detection networks (MIDN), plenty of works have contributed tremendous efforts to weakly supervised object detection (WSOD). However, most methods neglect the fact that the overwhelming negative instances exist in each image during the training phase, which would mislead the training and make the network fall into local minima. To tackle this problem, an online progressive instance-balanced sampling (OPIS) algorithm based on hard sampling and soft sampling is proposed in this paper. The algorithm includes two modules: a progressive instance balance (PIB) module and a progressive instance reweighting (PIR) module. The PIB module combining random sampling and IoU-balanced sampling progressively mines hard negative instances while balancing positive instances and negative instances. The PIR module further utilizes classifier scores and IoUs of adjacent refinements to reweight the weights of positive instances for making the network focus on positive instances. Extensive experimental results on the PASCAL VOC 2007 and 2012 datasets demonstrate the proposed method can significantly improve the baseline, which is also comparable to many existing state-of-the-art results. In addition, compared to the baseline, the proposed method requires no extra network parameters and the supplementary training overheads are small, which could be easily integrated into other methods based on the instance classifier refinement paradigm. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A Unified Framework for Finite-/Fixed-Time Synchronization of Memristor Chaotic systems and Its Application in Image Encryption

Research Square

引用

Research Square 2021年

作者： Wang, Leimin Jiang, Shan Ge, Ming-Feng Hu, Junhao China University of Geosciences China School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems China School of Mechanical Engineering and Electronic Information China University of Geosciences Wuhan430074 China College of Mathematics and Statistics South-Central University for Nationalities Wuhan430074 China

This paper proposes a sliding-mode-based unified control framework to solve the synchronization problem of memristor chaotic systems. Both finite- and fixed-time synchronization of the memristor chaotic systems can be obtained in the uniform framework. According to the Lyapunov stability and finite-time stability theories, we demonstrate that the trajectories of error system reach the presented sliding-mode surface and converge to the origin along the surface in a finite/fixed time. Moreover, an image encryption algorithm is developed based on the presented control framework. Finally, the numerical simulations and the statistical performance analyses are discussed to illustrate the correctness of synchronization results, the effectiveness of the proposed encryption algorithm, and its potential applications in the scope of secure communication. © 2021, CC BY.

关键词： Chaotic systems

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：