检索结果-内蒙古大学图书馆

IEEE/RSJ International Conference on Intelligent Robots and systems (IROS)

作者： Yuting Xie Xianda Guo Cong Wang Kunhua Liu Long Chen School of Computer Science and Engineering Sun Yat-Sen University School of Computer Science Wuhan University State Key Laboratory for Management and Control of Complex Systems at the Institute of Automation Chinese Academy of Sciences School of Mechanical and Automotive Engineering Qingdao University of Technology

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Safety-critical scenarios are infrequent in natural driving environments but hold significant importance for the training and testing of autonomous driving systems. The prevailing approach involves generating safety-critical scenarios automatically in simulation by introducing adversarial adjustments to natural environments. These adjustments are often tailored to specific tested systems, thereby disregarding their transferability across different systems. In this paper, we propose AdvDiffuser, an adversarial framework for generating safety-critical driving scenarios through guided diffusion. By incorporating a diffusion model to capture plausible collective behaviors of background vehicles and a lightweight guide model to effectively handle adversarial scenarios, AdvDiffuser facilitates transferability. Experimental results on the nuScenes dataset demonstrate that AdvDiffuser, trained on offline driving logs, can be applied to various tested systems with minimal warm-up episode data and outperform other existing methods in terms of realism, diversity, and adversarial performance.

关键词： Training Diffusion models Intelligent robots Autonomous vehicles Testing

来源：评论

学校读者我要写书评

暂无评论

A novel underwater image synthesis method based on a pixel-level self-supervised training strategy

A novel underwater image synthesis method based on a pixel-l...

引用

2021 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2021

作者： Wu, Zhiheng Wu, Zhengxing Lu, Yue Wang, Jian Yu, Junzhi Institute of Automation Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China State Key Laboratory for Turbulence and Complex Systems Department of Advanced Manufacturing and Robotics BIC-ESAT College of Engineering Peking University Beijing100871 China

ISBN: (纸本)9781665436786

With the rapid development of deep neural networks, underwater vision plays an increasingly important role in the underwater robotic operation. However, the scarce underwater datasets greatly limit the performance of deep learning on underwater visual tasks, further hindering the applications of underwater operation. To solve this problem, we propose an underwater image synthesis method, which can directly convert the natural light image into the synthetic underwater image end-to-end. Particularly, a pixel-level self-supervised training strategy is designed to maximize the structural similarity between the synthesized and real images, through training the real underwater images. Finally, extensive experiments are carried out, and the obtained results demonstrate the effectiveness and superiority of our methods by quantitative and qualitative comparisons. The proposed underwater image synthesis method offers a valuable sight for underwater vision and manipulating control. © 2021 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Manifestations of 9754 gout patients in a Chinese clinical center: A 10-year observational study

引用

Revue du Rhumatisme (Edition Francaise) 2022年第1期89卷 65-71页

作者： Gao, Qianhui Cheng, Xiaoyu Merriman, Tony R. Wang, Can Cui, Lingling Zhang, Hui Sun, Wenyan Wang, Jing Wang, Feiyue Li, Changgui Lu, Jie Shandong Provincial Key Laboratory of Metabolic Diseases and Qingdao Key Laboratory of Gout Department of Endocrinology and Metabolism the Affiliated Hospital of Qingdao University Qingdao 266003 China Institute of Metabolic Diseases Qingdao University Qingdao 266003 China Department of Biochemistry University of Otago Dunedin New Zealand Division of Clinical Immunology and Rheumatology University of Alabama Birmingham Alabama United States Institute of Smart Healthcare Systems Qingdao Academy of Intelligent Industries Qingdao 266109 China The State Key Laboratory for Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China

Objectif: La prévalence de la goutte augmente, mais les études analysant ses caractéristiques cliniques dans de grands échantillons sont insuffisantes. Cette étude s'attache à clarifier les changements dans les manifestations cliniques de la goutte en Chine au cours des dix dernières années et à analyser les caractéristiques cliniques et les facteurs de risque de la goutte précoce. Méthodes: Les manifestations cliniques de la goutte ont été comparées chez 9754 patients reçus pour la première fois dans notre établissement entre 2008 et 2012 (premier groupe) ou entre 2013 et 2018 (dernier groupe). La goutte apparue ≤ 30 ans a été définie comme goutte précoce et > 30 ans, comme goutte tardive. Les caractéristiques cliniques et les facteurs de risque ont été comparés entre les groupes. Résultats: La goutte est apparue 4,14 ans plus tôt dans le dernier groupe (2013-2018, 5979 patients) et le pourcentage de goutte précoce (3827 patients) y était plus élevé. La durée de la maladie était significativement plus courte (5,72 ± 0,09 contre 6,01 ± 0,11, p < 0,05) et la proportion de patients présentant des tophi était plus faible dans le dernier groupe (20,0% contre 22,0%, p<0,05). Le dernier groupe comptait davantage de patients obèses (37,7% contre 32,6%, p < 0,001) et l'uricémie y était significativement plus élevée (485,5 ± 1,5 Μmol/l contre 465,0 ± 1,9 Μmol/l). Comme la goutte survenait à un âge plus jeune, nous avons appliqué une régression logistique multivariée et déterminé que des antécédents familiaux positifs, le sexe masculin, l'obésité, une uricémie élevée et la consommation de sodas sucrés étaient des facteurs prédictifs indépendants de goutte précoce. Conclusion: Les manifestations de la goutte en Chine ont évolué au cours des dix dernières années, avec notamment une tendance à une apparition plus précoce. © 2021

关键词： Apparition précoce Drop Early onset Facteurs de risque Goutte Risk factors

来源：评论

学校读者我要写书评

暂无评论

Anti-sway control of Crane Based on Equivalent-Input-Disturbance Method and Feedback Linearization

Anti-sway Control of Crane Based on Equivalent-Input-Disturb...

引用

第42届中国控制会议

作者： Shuhan He Gang Yu Yongbo Li Fengyu Zhang Wangyong He School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation Complex Systems Huaxin Cement Technology Management (Wuhan) Co. Ltd

The anti-sway issue with crane systems is discussed in this essay. Because cranes are undriveable and nonlinear,implementing anti-sway controllers becomes much more challenging. This work suggests a crane anti-sway controller that uses feedback linearization(FL) in conjunction with the Equivalent-Input-Disturbance(EID) technique to address the issues. to reduce the problem that the feedback linearization largely relies on the model's *** crane system is first treated as a linear system, after which the unmodeled disturbances, nonlinear components, and external disturbances of the system are treated as the total disturbances of the system, and the effects of these disturbances are then compensated for using disturbance estimation. Finally, simulation experiments confirm that the maximum steady-state fluctuations of the position and angle of the anti-sway controller based on the equivalent input disturbance method and the feedback linearization method are 14 and 6.85percent, respectively, of those estimated without *** demonstrates the potency of this approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning Transferable Negative Prompts for Out-of-Distribution Detection

Learning Transferable Negative Prompts for Out-of-Distributi...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Tianqi Li Guansong Pang Xiao Bai Wenjun Miao Jin Zheng State Key Laboratory of Complex & Critical Software Environment School of Computer Science and Engineering Jiangxi Research Institute Beihang University China School of Computing and Information Systems Singapore Management University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Existing prompt learning methods have shown certain capabilities in Out-of-Distribution (OOD) detection, but the lack of OOD images in the target dataset in their training can lead to mismatches between OOD images and In-Distribution (ID) categories, resulting in a high false positive rate. To address this issue, we introduce a novel OOD detection method, named ‘NegPrompt’, to learn a set of negative prompts, each representing a negative connotation of a given class label, for delineating the boundaries between ID and OOD images. It learns such negative prompts with ID data only, without any reliance on external out-lier data. Further, current methods assume the availability of samples of all ID classes, rendering them ineffective in open-vocabulary learning scenarios where the inference stage can contain novel ID classes not present during training. In contrast, our learned negative prompts are transferable to novel class labels. Experiments on various ImageNet benchmarks show that NegPrompt surpasses state-of-the-art prompt-learning-based OOD detection methods and maintains a consistent lead in hard OOD detection in closed- and open-vocabulary classification scenarios. Code is available at https://***/mala-lab/negprompt.

关键词： Training Learning systems Computer vision Codes Computational modeling Semantics Lead

来源：评论

学校读者我要写书评

暂无评论

Pedestrian Trajectory Prediction by Modeling the Interactions using Social LSTM Extensions

Pedestrian Trajectory Prediction by Modeling the Interaction...

引用

Chinese Automation Congress (CAC)

作者： Zeze Si Hongxia Zhao Haina Tang Fenghua Zhu Yisheng Lv Hao Lu State Key Laboratory for Management and Control of Complex Systems Institute of Autamation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academic of Sciences Beijing China Qingdao Academy of Intelligent Industries Qingdao China

In many driving situations, human mobility is an important topic in trajectory prediction. Considering the pedestrian trajectory as a sequence generative task, a prediction algorithm based on Social Long Short-Term Memory (Social LSTM) is implemented. In order to simulate the social interaction between pedestrians, Social Pooling (S-Pooling) is used to aggregate the hidden state of pedestrians, while the attention mechanism is utilized to aggregate information differently according to the importance of surrounding pedestrians. Furthermore, Convolutional Neural Networks (CNN) is introduced into Social LSTM model to consider both the interaction between people and the characteristic of scene scale in the prediction process. Experiments are carried out against baseline methods, and the results demonstrated that combining Social LSTM with attention mechanism or CNN can improve the performance of pedestrian trajectory prediction.

关键词： Automation Aggregates Predictive models Prediction algorithms Trajectory Convolutional neural networks Task analysis

来源：评论

学校读者我要写书评

暂无评论

A comprehensive review of electrochemical hybrid power supply systems and intelligent energy managements for unmanned aerial vehicles in public services

引用

Energy and AI 2022年第3期9卷 148-171页

作者： Caizhi Zhang Yuqi Qiu Jiawei Chen Yuehua Li Zhitao Liu Yang Liu Jiujun Zhang Chan Siew Hwa College of Mechanical and Vehicle Engineering The State Key Laboratory of Mechanical TransmissionsChongqing Automotive Collaborative Innovation CentreChongqing UniversityChongqing400044China College of Automation Chongqing UniversityKey Laboratory of Complex System Safety and ControlMinistry of EducationChongqing UniversityChongqing400044China School of Mechanical Engineering University of Science and Technology BeijingBeijing100083China State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and ControlZhejiang UniversityHangzhou310027China Institute for Sustainable Energy/College of Sciences Shanghai UniversityShanghai 200444China School of Mechanical and Aerospace Engineering Nanyang Technological University50 Nanyang Avenue639798Singapore Sichuan Energy Internet Research Institute Tsinghua UniversityChengdu 610213Sichuan ProvinceChina

The electric unmanned aerial vehicles (UAVs) are rapidly growing due to their abilities to perform some difficult or dangerous tasks as well as many public services including real-time monitoring, wireless coverage, search and rescue, wildlife surveys, and precision agriculture. However, the electrochemical power supply system of UAV is a critical issue in terms of its energy/power densities and lifetime for service endurance. In this paper, the current power supply systems used in UAVs are comprehensively reviewed and analyzed on the existing power configurations and the energy management systems. It is identified that a single type of electrochemical power source is not enough to support a UAV to achieve a long-haul flight;hence, a hybrid power system architecture is necessary. To make use of the advantages of each type of power source to increase the endurance and achieve good performance of the UAVs, the hybrid systems containing two or three types of power sources (fuel cell,battery, solar cell, and supercapacitor,) have to be developed. In this regard, the selection of an appropriate hybrid power structure with the optimized energy management system is critical for the efficient operation of a UAV. It is found that the data-driven models with artificial intelligence (AI) are promising in intelligent energy management. This paper can provide insights and guidelines for future research and development into the design and fabrication of the advanced UAV power systems.

关键词： Unmanned aerial vehicles(UAVs) Power supply system Fuel cell system Artificial intelligence(AI) Energy management systems

来源：评论

学校读者我要写书评

暂无评论

ReCUS: Reconvolution and Upsampling Network for Object Detection 7

ReCUS: Reconvolution and Upsampling Network for Object Detec...

引用

7th IEEE International Conference on Cloud Computing and Intelligence systems, CCIS 2021

作者： Li, Fudong Gao, Dongyang Yang, Yuequan Cao, Zhiqiang Wang, Wei Yangzhou225000 China Institute of Automation Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems Beijing100190 China Affiliated Hospital of Yangzhou University Yangzhou225012 China

ISBN: (纸本)9781665441490

Most of the mainstream object detection models such as RetinaNet, SSD, YOLO, and Faster RCNN hardly achieve a good balance between detection accuracy and speed. A major reason is rich deep feature semantic information of images is not fully exploited. To solve this problem, a novel deep convolutional network structure termed as reconvolution and upsampling network (ReCUS) is proposed. In the ReCUS, a modified path aggregation network(mPAN) is added after the backbone, which is beneficial to strengthen the foreground salient feature information and weaken background information. Moreover, two new spatial pyramid pooling (SPP) modules are embedded before output heads for multi-scale fusion of local and global features. The experiments show that the effectiveness of our proposed ReCUS. Furthermore, the better detectability of the ReCUS network is demonstrated for both small scale objects and large scale objects. © 2021 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A Predictive Tracking control Algorithm for Initial Angle of Brushless DC Motor Based on Reinforcement Learning

A Predictive Tracking Control Algorithm for Initial Angle of...

引用

Asian control Conference

作者： Yu Zhu Haodong Chen Xihong Fei Kang Wang Jing Wang School of Electrical and Information Engineering Anhui University of Technology Ma'anshan China Key Laboratory of Multidisciplinary Management and Control of Complex Systems of Anhui Higher Education Institutes Anhui University of Technology Ma’anshan China

ISBN: (数字)9789887581598

ISBN: (纸本)9798331540845

The initial angle detection and tracking control of brushless direct current motor (BLDC) is widely used in military, aviation, industrial, automotive, civil control systems, and household appliances. The motor is a nonlinear system, which is easily affected by external factors, so it is difficult to maintain the stability of the system with fixed control parameters. Therefore, this paper proposes a control method for initial angle tracking of BLDC based on reinforcement learning (RL). In order to determine the initial angle of the surface-mounted direct current (DC) motor, in the traditional Field-Oriented control (FOC) algorithm, the pulsating high-frequency injection algorithm is introduced and combined with the RL theory. According to the given PI parameters, the appropriate rewards are obtained through the RL controller. Then the proportional integral (PI) parameters are dynamically adjusted to make the estimated angle closer to the true angle value. This method avoids the error of angle estimation caused by fixed PI parameters in different situations, and obtains the best results by dynamically adjusting the parameters. Finally, the simulation experiment is carried out to prove the feasibility of the proposed scheme.

关键词： Home appliances Brushless DC motors Heuristic algorithms Estimation Reinforcement learning Prediction algorithms control systems

来源：评论

学校读者我要写书评

暂无评论

Moving Target Shooting control Policy Based on Deep Reinforcement Learning

Moving Target Shooting Control Policy Based on Deep Reinforc...

引用

2021 International Conference on Information, Cybernetics, and Computational Social systems, ICCSS 2021

作者： Li, Boyu Jin, Tao Zhu, Yuanheng Li, Haoran Wu, Yingnian Zhao, Dongbin Institute of Automation Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems Beijing100190 China Beijing Information Science and Technology University School of Automation Beijing100192 China

ISBN: (纸本)9781665402453

Robots are playing a more and more important role in people's production and life, recently. However, robot control in dynamic environment is still a difficulty. With the great breakthrough of deep reinforcement learning in the field of video games, this method is also extended to the field of robots. Due to the gap between the simulation environment and the real environment, the deep reinforcement learning algorithm trained in the simulation environment is difficult to be applied to the real environment. Aiming at the gimbal control with two degrees of freedom (DOF), a pipline combining system identification and deep reinforcement learning is proposed. On the one hand, the shooting accuracy of the gimbal to moving objects is improved through deep reinforcement learning algorithm. On the other hand, the gap between simulation and reality is reduced through system identification. The method is verified in the RoboMaster University AI Challenge (RMUA) shooting system. The results show that the shooting accuracy is better than the classical control method. © 2021 IEEE.

关键词： Deep learning

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：