检索结果-内蒙古大学图书馆

Mixed Motivation Driven Social Multi-Agent Reinforcement Learning for Autonomous Driving

IEEE/CAA Journal of Automatica Sinica 2025年第6期12卷 1272-1282页

作者： Long Chen Peng Deng Lingxi Li Xuemin Hu State Key Laboratory of Multimodal Artificial Intelligence Systems and the State Key Laboratory of Management and Control for Complex Systems Chinese Academy of Sciences Beijing WAYTOUS Inc. Beijing Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) Shenzhen Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China School of Computer Science and Information Engineering Hubei University Wuhan China Purdue School of Engineering and Technology Indiana University-Purdue University Indianapolis Indianapolis IN USA School of Artificial Intelligence Hubei University Wuhan Key Laboratory of Intelligent Sensing System and Security (Hubei University) Ministry of Education Wuhan China

Despite great achievement has been made in autonomous driving technologies, autonomous vehicles (AVs) still exhibit limitations in intelligence and lack social coordination, which is primarily attributed to their reliance on single-agent technologies, neglecting inter-AV interactions. Current research on multi-agent autonomous driving (MAAD) predominantly focuses on either distributed individual learning or centralized cooperative learning, ignoring the mixed-motive nature of MAAD systems, where each agent is not only self-interested in reaching its own destination but also needs to coordinate with other traffic participants to enhance efficiency and safety. Inspired by the mixed motivation of human driving behavior and their learning process, we propose a novel mixed motivation driven social multi-agent reinforcement learning method for autonomous driving. In our method, a multi-agent reinforcement learning (MARL) algorithm, called Social Learning Policy Optimization (SoLPO), which takes advantage of both the individual and social learning paradigms, is proposed to empower agents to rapidly acquire self-interested policies and effectively learn socially coordinated behavior. Based on the proposed SoLPO, we further develop a mixed-motive MARL method for autonomous driving combined with a social reward integration module that can model the mixed-motive nature of MAAD systems by integrating individual and neighbor rewards into a social learning objective for improved learning speed and effectiveness. Experiments conducted on the MetaDrive simulator show that our proposed method outperforms existing state-of-the-art MARL approaches in metrics including the success rate, safety, and efficiency. More-over, the AVs trained by our method form coordinated social norms and exhibit human-like driving behavior, demonstrating a high degree of social coordination.

关键词： Measurement Reinforcement learning Safety Driver behavior Autonomous vehicles Optimization

来源：评论

学校读者我要写书评

暂无评论

Modified Hough Transform Based Registration Method for Heavy-haul Railway Rail Profile with Intensive Environmental Noise

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： An, Yuntong Cao, Yuan Sun, Yongkui Su, Shuai Wang, Feng Beijing Jiaotong University National Engineering Research Center of Rail Transportation Operation Control System School of Automation and Intelligent Beijing100044 China Beijing Jiaotong University Frontiers Science Center for Smart High-speed Railway System Beijing100044 China Beijing Jiaotong University State Key Laboratory of Advanced Rail Autonomous Operation Beijing100044 China

In heavy-haul railway inspections, accurate rail profile registration is essential for assessing wear and deformation of tracks. In this process, identifying the rail waist arc as key segments and determining the center of the arc as feature points are crucial steps for rough rail profile registration, often affected by noise from sensors, surface contaminants, and environmental factors. To address these challenges, a profile registration method is proposed, with the Modified Hough Transform (MHT) as a core component. The method first segments key profile sections using curvature thresholds to identify arc segments. For each point in these segments, MHT constructs circles with fixed radius and calculates their intersection points. A distance matrix based on Euclidean distances between intersection points is generated. By sorting and normalizing these distances, the method identifies local density variations and calculates density coefficients to find the circle center, without manual thresholding. Comparative experiments on simulated and field data show that the proposed method achieves high accuracy and robustness in noisy environments. The dual validation confirms its reliability, making this method effective for rail profile registration in heavy-haul railway inspections. © 1963-2012 IEEE.

关键词： Hough transforms

来源：评论

学校读者我要写书评

暂无评论

A Model-Predictive-Enabled Equivalent-Input-Disturbance Approach for Disturbance Rejection

A Model-Predictive-Enabled Equivalent-Input-Disturbance Appr...

引用

Industrial Cyber-Physical systems (ICPS)

作者： Yujian Zhou Jinhua She Feng Wang Makoto Iwasaki School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China School of Engineering Tokyo University of Technology Tokyo Japan Department of Electrical and Mechanical Engineering Nagoya Institute of Technology Nagoya Japan

This paper presents a model-predictive-enabled equivalent-input-disturbance (MPEID) method for disturbance rejection. An EID estimator with a state observer estimates the effect of disturbances in a system. The disturbance estimation will not be directly added to the input channel for disturbance rejection. A cost function that considers the disturbance estimation is designed. An MPC controller calculates an optimal control input by minimizing the cost function. The stability condition of the closed-loop system is analyzed based on the Lyapunov stability theory. Simulation results show that our method has better disturbance-rejection performance than an MPC method when the control input is similar.

关键词： Simulation Estimation Optimal control Predictive models Observers Cyber-physical systems Cost function

来源：评论

学校读者我要写书评

暂无评论

No-Reference Image Quality Assessment using Meta-SGD

No-Reference Image Quality Assessment using Meta-SGD

引用

2021 China automation Congress, CAC 2021

作者： Van, Qmgqmg Dong, Bei Li, Xin Xiang, Yiwen Luo, Dapeng Wei, Longsheng School of Automation China University of Geosciences Wuhan China Key Laboratory of Geological Survey and Evaluation of Ministry of Education Wuhan China Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Intelligent Technology co. Ltd of Chinese Construction Third Engineering Bureau Wuhan China School of Electronic Information and Mechanics China University of Geosciences Wuhan China

ISBN: (纸本)9781665426473

Deep learning-based no-reference image quality assessment (NR-IQA) algorithm requires massive training data and labels, but data scarcity usually exists in practical applications. Most of the previous metrics used pre-trained networks to solve this problem by fine-tuning on the target tasks. Unfortunately, the network trained on other tasks cannot be directly applied to IQA tasks and failed when encountering complex distortions. To reduce dependence on labeled data and improve generalization ability of unknown distortion types, a NR-IQA metric based on Meta-SGD is proposed, which can learn the quick adaptability of humans and obtain general meta-knowledge for distortion evaluation. Specifically, we collected a great many NR-IQA tasks with different distortion types to pre-train the model;then a meta-learning metric based on optimization, Meta-SGD, is proposed to acquire the meta-knowledge when evaluating images quality with various known distortions;finally, the obtained pre-trained meta-model can be directly applied to the new NR-IQA tasks only by fine-tuning a few images. Experiments on the TID2013 database demonstrate that the model after meta-learning obviously outperforms than some existing methods, and the average SRCC value for all types of distortion performance tests can reach 0.91. © 2021 IEEE

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

SC-NeRF: Self-Correcting Neural Radiance Field with Sparse Views

arXiv

引用

arXiv 2023年

作者： Song, Liang Wang, Guangming Liu, Jiuming Fu, Zhenyang Miao, Yanzi Wang, Hesheng Engineering Research Center of Intelligent Control for Underground Space Ministry of Education School of Information and Control Engineering Advanced Robotics Research Center China University of Mining and Technology Xuzhou221116 China Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai200240 China

In recent studies, the generalization of neural radiance fields for novel view synthesis task has been widely explored. However, existing methods are limited to objects and indoor scenes. In this work, we extend the generalization task to outdoor scenes, trained only on object-level datasets. This approach presents two challenges. Firstly, the significant distributional shift between training and testing scenes leads to black artifacts in rendering results. Secondly, viewpoint changes in outdoor scenes cause ghosting or missing regions in rendered images. To address these challenges, we propose a geometric correction module and an appearance correction module based on multi-head attention mechanisms. We normalize rendered depth and combine it with light direction as query in the attention mechanism. Our network effectively corrects varying scene structures and geometric features in outdoor scenes, generalizing well from object-level to unseen outdoor scenes. Additionally, we use appearance correction module to correct appearance features, preventing rendering artifacts like blank borders and ghosting due to viewpoint changes. By combining these modules, our approach successfully tackles the challenges of outdoor scene generalization, producing high-quality rendering results. When evaluated on four datasets (Blender, DTU, LLFF, Spaces), our network outperforms previous methods. Notably, compared to MVSNeRF, our network improves average PSNR from 19.369 to 25.989, SSIM from 0.838 to 0.889, and reduces LPIPS from 0.265 to 0.224 on Spaces outdoor scenes. © 2023, CC BY.

关键词： Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

Learning Pre-Grasp Manipulation of Flat Objects in Cluttered Environments using Sliding Primitives

Learning Pre-Grasp Manipulation of Flat Objects in Cluttered...

引用

IEEE International Conference on Robotics and automation (ICRA)

作者： Jiaxi Wu Haoran Wu Shanlin Zhong Quqin Sun Yinlin Li State Key Laboratory of Turbulence and Complex Systems Intelligent Biomimetic Design Lab College of Engineering Peking University Beijing China Department of Automation University of Science and Technology of China Heifei China State Key Laboratory of Management and Control for Complex System Institute of Automation Chinese Academy of Science Beijing China Science and Technology on Thermal Energy and Power Laboratory Wuhan China

Flat objects with negligible thicknesses like books and disks are challenging to be grasped by the robot because of the width limit of the robot's gripper, especially when they are in cluttered environments. Pre-grasp manipulation is conducive to rearranging objects on the table and moving the flat objects to the table edge, making them graspable. In this paper, we formulate this task as Parameterized Action Markov Decision Process, and a novel method based on deep reinforcement learning is proposed to address this problem by introducing sliding primitives as actions. A weight-sharing policy network is utilized to predict the sliding primitive's parameters for each object, and a Q-network is adopted to select the acted object among all the candidates on the table. Meanwhile, via integrating a curriculum learning scheme, our method can be scaled to cluttered environments with more objects. In both simulation and real-world experiments, our method surpasses the existing methods and achieves pre-grasp manipulation with higher task success rates and fewer action steps. Without fine-tuning, it can be generalized to novel shapes and household objects with more than 85% success rates in the real world. Videos and supplementary materials are available at https://***/view/pre-grasp-sliding.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Overlapped Human Pose Estimation using Non-Maximum Suppression based on Shape Similarity

Overlapped Human Pose Estimation using Non-Maximum Suppressi...

引用

2021 China automation Congress, CAC 2021

作者： Yu, Xuefu Li, Jinsheng Xiao, Fei Liu, Wei Luo, Dapeng Wei, Longsheng School of Automation China University of Geosciences Wuhan China Key Laboratory of Geological Survey and Evaluation of Ministry of Education Wuhan China Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Intelligent Technology co. Ltd Chinese Construction Third Engineering Bureau Wuhan China School of Electronic Information and Mechanics China University of Geosciences Wuhan China

ISBN: (纸本)9781665426473

Deep Convolutional Neural Networks (DNNs) have made significant progress on human pose estimation task in recent years. However, the question of whether we are making the most use of the information we get from DNNs has not been well studied. Top-down approach which first detects person body box then utilizes single person pose estimation by heatmap is a widely used method in multi-person pose estimation. However, information that predicted by DNNs contains more information than we consider. In person box prediction process, when two persons are closed to each other, the Non-Maximum Suppression (NMS) we often use filters out the body boxes with smaller scores. For tackling this problem, we apply NMS based on Shape Similarity to person body boxes detection for tackling the problem that deleting the overlapped body boxes with smaller scores, and then extract keypoint coordinates and tag information for filter noise candidates from heatmap by Trasformer to improve the prediction accuracy. At last we develop an algorithm for refining keypoint coordinate by tag information. In experiment, we got mean Average Precision(mAP) of 76.0% in COCO2017 validation dataset, better than 75.6% with TransPose. © 2021 IEEE

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Multiple Ant Colony system for the Electric Vehicle Routing Problem with Time Windows

A Multiple Ant Colony System for the Electric Vehicle Routin...

引用

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Michalis Mavrovouniotis Georgios Ellinas Changhe Li Marios Polycarpou Department of Electrical and Computer Engineering KIOS Research and Innovation Center of Excellence University of Cyprus Nicosia Cyprus School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China

ISBN: (纸本)9781665487696

Ant colony optimization (ACO) has been found to be useful on several vehicle routing problem variations. In this work, ACO is applied to the electric vehicle routing problem with time windows (E-VRPTW). The E-VRPTW has a hierarchical multiple objective function, which is to minimize the number of electric vehicles and the total distance traveled. A multiple ACO is applied to E-VRPTW in which two colonies cooperate to minimize the objectives in parallel. A local search is embedded in ACO to improve the quality of the output. The experimental results on a set of benchmark instances show that the multiple ACO is competitive with existing methods.

关键词： Ant colony optimization Vehicle routing Benchmark testing Electric vehicles Routing Search problems Linear programming

来源：评论

学校读者我要写书评

暂无评论

Sound Field control by Using Equivalent Input Disturbance method

Sound Field Control by Using Equivalent Input Disturbance me...

引用

Industrial Cyber-Physical systems (ICPS)

作者： Toshiki Watanabe Jinhua She Zewen Wang Department of Sustainable Engineering Tokyo university of technology Japan School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China Laboratory for Future Interdisciplinary Research of Science and Technology (FIRST) Tokyo Institute of Technology Yokohama Kanagawa Japan

Low-frequency noise, such as road noise from automobiles and interior noise from bullet train cars, is detrimental to passenger comfort. Active noise control provides us with a way of suppressing low-frequency noise. It generates a sound of the same amplitude and opposite phase as noise and uses it to cancel the noise. Conventional active noise control is complicated to apply. Thus, the objective of this study is to establish a sound field control system by using the equivalent-input-disturbance method. system identification was performed to obtain an ideal plant of a duct. The control system is constructed based on the equivalent-input-disturbance approach with a low-order controller. The experimental results showed a suppression effect of about 50% of the sound field.

关键词： Roads Noise reduction Ducts Channel estimation Auditory system Cyber-physical systems control systems

来源：评论

学校读者我要写书评

暂无评论

Accurate Identification and Localization of Transmission Lines Under complex Lighting for Distribution Network Power Supply Operation Robots

Accurate Identification and Localization of Transmission Lin...

引用

Chinese automation Congress (CAC)

作者： Tianhe Liu Xin Chen Chenyu Hu Xu Jian Shengzu Li Gang Wang School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China Equipment Technology Center State Grid Hubei Electric Power Co. Ltd. Electric Power Science Research Institute Wuhan China Distribution Department State Grid Hubei Electric Power Co. Ltd. Wuhan Power Supply Company China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

Accurate identification and position of transmission lines is critical for robots to safely and effectively perform distribution network operations. However, such tasks are often challenged by complex lighting conditions, where depth information can be easily lost. Transmission lines have limited texture features and reflective surfaces, making it difficult to match image feature points. To address these challenges, this paper proposes a visual perception system for weak texture targets under complex lighting, based on an “eye-on-hand” configuration and a depth complementation algorithm. Furthermore, a high-precision identification and localization method for transmission line grasping points is developed, utilizing the fusion of binocular visual color maps and depth maps. The proposed method has been shown to effectively solve the problem of identifying and localizing the grasping points of transmission lines under complex lighting conditions. Experiments demonstrated that the method can improve the localization accuracy to within $\pm 4\text{mm}$ , outperforming other algorithms. The method is characterized as simple and efficient, and it enhances the environmental adaptability of distribution network robots.

关键词： Location awareness Visualization Power transmission lines Accuracy Image color analysis Lighting Distribution networks Grasping Wire Robots

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：