检索结果-内蒙古大学图书馆

The Journal of Machine Learning Research 2023年第1期24卷 8447-8521页

作者： Wenhao Li Bo Jin Xiangfeng Wang Junchi Yan Hongyuan Zha School of Data Science The Chinese University of Hong Kong Shenzhen Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China School of Software Engineering Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai China School of Computer Science and Technology Key Laboratory of Mathematics and Engineering Applications Ministry of Education East China Normal University Shanghai China Department of Computer Science and Engineering Key Laboratory of Artificial Intelligence Ministry of Education Shanghai Jiao Tong University Shanghai China

Traditional centralized multi-agent reinforcement learning (MARL) algorithms are sometimes unpractical in complicated applications due to non-interactivity between agents, the curse of dimensionality, and computation complexity. Hence, several decentralized MARL algorithms are motivated. However, existing decentralized methods only handle the fully cooperative setting where massive information needs to be transmitted in training. The block coordinate gradient descent scheme they used for successive independent actor and critic steps can simplify the calculation, but it causes serious bias. This paper proposes a exible fully decentralized actor-critic MARL framework, which can combine most of the actor-critic methods and handle large-scale general cooperative multi-agent settings. A primal-dual hybrid gradient descent type algorithm framework is designed to learn individual agents separately for decentralization. From the perspective of each agent, policy improvement and value evaluation are jointly optimized, which can stabilize multi-agent policy learning. Furthermore, the proposed framework can achieve scalability and stability for the large-scale environment. This framework also reduces information transmission by the parameter sharing mechanism and novel modeling-other-agents methods based on theory-of-mind and online supervised learning. Sufficient experiments in cooperative Multi-agent Particle Environment and StarCraft II show that the proposed decentralized MARL instantiation algorithms perform competitively against conventional centralized and decentralized methods.

关键词： cooperative MARL decentralized actor-critic primal-dual method

来源：评论

学校读者我要写书评

暂无评论

6DoF-ICTC: A Deep Image Feature Extraction Network Combining Transformers and CNNs for 6DoF Pose Estimation 12

6DoF-ICTC: A Deep Image Feature Extraction Network Combining...

引用

12th International Conference on CYBER Technology in Automation, Control, and Intelligent systems, CYBER 2022

作者： Zhang, Liming Zhou, Xin Zhu, Baixian Wang, Can Wu, Xinyu Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Cas Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology China University of Science and Technology of China China Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Hong Kong

ISBN: (数字)9781665472678

ISBN: (纸本)9781665472678

In this work, we propose a new image feature extraction network for 6D pose estimation tasks. The majority of existing 6D pose estimation networks are based on the RGBD input, which is the fusion of images and point clouds. They are mainly working on keypoint extraction, point cloud feature extraction, and other tasks, however, image features, on the other hand, mainly rely on CNN networks that are currently advanced. With the development of Vision Transformer in the field of computer vision, the results on ImageNet demonstrate its benefit of extracting global features, and we see new directions that the Transformers can bring to the area of image feature extraction. ICTC is a Transformer paired with a CNN network that fuses the retrieved global features into each pixel and then does local feature extraction. This provides greater robustness to 6D pose estimation In complex situations such as shifting lighting conditions and object occlusion. Our method achieves 96% accuracy using the average ADD metric on the LineMOD dataset, demonstrating our method's effectiveness. © 2022 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Robot-aided fN∙m torque sensing within an ultrawide dynamic range

引用

Microsystems & Nanoengineering 2021年第1期7卷 51-61页

作者： Shudong Wang Xueyong Wei Haojian Lu Ziming Ren Zhuangde Jiang Juan Ren Zhan Yang Lining Sun Wanfeng Shang Xinyu Wu Yajing Shen State Key Laboratory for Manufacturing Systems Engineering Xi’an Jiaotong UniversityXi’an 710049China Mechanical and Biomedical Engineering Department City University of Hong KongHong Kong SAR 999077China Department of Mechatronics Chang’an UniversityXi’an 710054China Robotics and Microsystems Center Soochow UniversitySuzhou 215021China Shenzhen Institutes of Advanced Technology Chinese Academy of SciencesShenzhen 518055China Shenzhen Research Institute City University of Hong KongShenzhen 440305China

In situ scanning electron microscope(SEM)characterization have enabled the stretching,compression,and bending of micro/nanomaterials and have greatly expanded our understanding of small-scale ***,as one of the fundamental approaches for material analytics,torsion tests at a small scale remain a major challenge due to the lack of an ultrahigh precise torque sensor and the delicate sample assembly ***,we present a microelectromechanical resonant torque sensor with an ultrahigh resolution of up to 4.78 fN∙m within an ultrawide dynamic range of 123 ***,we propose a nanorobotic system to realize the precise assembly of microscale specimens with nanoscale positioning accuracy and to conduct repeatable in situ pure torsion tests for the first *** a demonstration,we characterized the mechanical properties of Si microbeams through torsion tests and found that these microbeams were five-fold stronger than their bulk *** proposed torsion characterization system pushes the limit of mechanical torsion tests,overcomes the deficiencies in current in situ characterization techniques,and expands our knowledge regarding the behavior of micro/nanomaterials at various loads,which is expected to have significant implications for the eventual development and implementation of materials science.

关键词： torsion precise dynamic

来源：评论

学校读者我要写书评

暂无评论

An Improved Method for Small Target Recognition Based on Faster RCNN 17th

An Improved Method for Small Target Recognition Based on Fas...

引用

17th Chinese Intelligent systems Conference, CISC 2021

作者： Liu, Qun-po Wang, Qi-jing Hanajima, Naohiko Su, Bo Department of Robotics Engineering Henan Polytechnic University 2001 Century Avenue Jiaozuo Henan454003 China Henan International Joint Laboratory of Direct Drive and Control of Intelligent Equipment 2001 Century Avenue Jiaozuo Henan454003 China College of Information and Systems Muroran Institute of Technology 27-1 Mizumoto-cho Muroran-shi Hokkaido050-8585 Japan

ISBN: (纸本)9789811663239

As one of the most challenging tasks in the field of deep learning, target detection has achieved remarkable results. The existing algorithms have achieved excellent results in the detection of large and medium-sized targets, but the detection accuracy of small targets is not ideal because of their small size and weak features. A small target recognition method based on improved Faster_Rcnn that aims at the problem of low accuracy in small target detection is proposed in this paper. Since the ROI Pooling method in Faster Rcnn might cause quantization errors in the operation process, resulting in inaccurate positioning and other problems during detection, an improved ROI Align method is adopted to eliminate the quantization errors. The cell public data set is used for the experiment, the results show that the average recognition accuracy of the recognition model with improved algorithm is 92.11%, which is an increase of 7%. The method also obtains good effect on NWPU VHR-10 data set, which indicates that it has good universality. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Electrolyte Effect on Photoetching of Gallium Nitride

引用

Nanomanufacturing and Metrology 2024年第1期7卷 61-74页

作者： Huiqiang Liang Zhenghao Wei Jiongchong Fang Yanming Li Changli Li Zhirun Xie Yun Hau Ng Guosong Zeng Shenzhen Key Laboratory of Intelligent Robotics and Flexible Manufacturing Systems Southern University of Science and TechnologyShenzhen 518055People’s Republic of China Department of Mechanical and Energy Engineering Southern University of Science and TechnologyShenzhen 518055People’s Republic of China School of Materials Sun Yat-Sen UniversityGuangzhou 510275People’s Republic of China School of Energy and Environment City University of Hong KongKowloon 999077Hong Kong SARPeople’s Republic of China City University of Hong Kong Shenzhen Research Institute Shenzhen Hi-Tech Industrial ParkNanshan DistrictShenzhen 518000People’s Republic of China SUSTech Energy Institute for Carbon Neutrality Southern University of Science and TechnologyShenzhen 518055People’s Republic of China

The limited material removal rate of conventional chemical mechanical polishing(CMP)significantly hinders the fabrica-tion efficiency and surface quality,thereby preventing the development of gallium nitride(GaN)-based ***,the incorporation of photoelectrochemistry in CMP has garnered increasing attention because of its potential to enhance the quality and efficiency of the GaN ***,a considerable gap still exists in the comprehensive understanding of the specific photoelectrochemical(PEC)behavior of ***,we report the influence of the electrolyte on the PEC etching of *** acids and bases were tested,with their pH being carefully *** concentrations of the cations and anions were also *** results showed that photocorrosion/photoetching was more pronounced in sulfuric acid,phosphoric acid,and nitric acid environments than in alkaline environments,but it was less pronounced in hydrochloric ***,the effects of pH and anion concentration on photoetching were investigated,and the results revealed that pho-toetching in acidic environments weakened with increasing pH levels and diminished with increasing sulfate *** underlying reasons contributing to this observation were *** findings provide ideas for improving the pho-toetching efficiency of GaN,thereby enriching the photoelectrochemical mechanical polishing(PECMP)technology of GaN.

关键词： GaN Photoelectrochemistry Photoetching pH

来源：评论

学校读者我要写书评

暂无评论

CPL-CLIP: Compound Prompt Learning for Flexible-Modal Face Anti-Spoofing

CPL-CLIP: Compound Prompt Learning for Flexible-Modal Face A...

引用

IEEE International Joint Conference on Biometrics (IJCB)

作者： Ying Zhang Xiangyu Zhu Ajian Liu Xun Lin Jun Wan Jing Zhang Zhen Lei State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences School of Computer Science and Engineering Beihang University School of Computer Science and Engineering Macau University of Science and Technology Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences

ISBN: (数字)9798350364132

ISBN: (纸本)9798350364149

Face anti-spoofing (FAS) is pivotal in safeguarding the integrity of face recognition systems. Flexible-modal FAS utilizes multi-modal data and trains a unified model adaptable to any single-modal testing scenario. This innovation addresses the shortcomings of conventional multi-modal FAS approaches, which typically demand separate model training and deployment for each modality. However, existing flexible-modal FAS approaches activate specific network branches based on the modality of the tested sample. This not only increases the model’s parameters but also necessitates the provision of the image’s modality for testing, thereby constraining deployment flexibility. To address the issue, we present Compound Prompt Learning CLIP (CPL-CLIP), a novel method for flexible-modal FAS. This approach capitalizes on a learned textual prompt that is nearly independent of modality, thus bolstering class-based classification across arbitrary modalities. Specifically, our CPL-CLIP introduces a Dual-Branch Prompt (DBP), consisting of class and modal prompts that describe and guide classification, where each prompt is composed of learnable vectors and fixed templates. To further render the class prompt as modality-agnostic as possible, a Cosine Similarity Loss (CSL) is proposed to facilitate the maximal separation of the class prompt from the modality prompt. With only the class prompt utilized during testing, CPL-CLIP enables deployment in diverse modal testing scenarios without the necessity of the test image’s modality to be known. Extensive experiments demonstrate CPL-CLIP’s superiority over existing methods on several flexible-modal FAS benchmarks.

关键词： Training Adaptation models Technological innovation Accuracy Face recognition Benchmark testing Vectors Robustness Data models Compounds

来源：评论

学校读者我要写书评

暂无评论

A Tendon-Driven Actuator with Cantilever Initiated Variable Stiffness Used for Robotic Fingers

SSRN

引用

SSRN 2024年

作者： Li, Chenning Yang, Shangkui Branson, David T. Song, Zhibin Sun, Tao Dai, Jiansheng Kang, Rongjie Key Laboratory of Mechanism Theory and Equipment Design of Ministry of Education School of Mechanical Engineering Tianjin University Tianjin300072 China Advanced Manufacturing Technology Research Group Faculty of Engineering University of Nottingham NottinghamNG7 2RD United Kingdom Beijing Institute of Technology China Shenzhen Key Laboratory of Intelligent Robotics and Flexible Manufacturing Systems Southern University of Science and Technology Shenzhen518055 China

Variable stiffness actuators (VSAs) have emerged as a key actuation technology known for their bionic performance and task adaptability. However, current VSAs often exhibit relatively large sizes, making them possible for use in robotic arms and legs but less convenient for integrations into robotic hands. This paper introduces a compact design of a tendon-driven variable stiffness actuator (TVSA) based on an adjustable cantilever mechanism, which can be embedded into a robotic finger. This implementation endows the robotic finger with the decoupled regulation of joint position and stiffness. A concise and computationally efficient stiffness mapping model from the TVSA to the finger joints is then established, providing a theoretical foundation for the stiffness regulation of the tendon-driven fingers. A prototype of a robotic hand equipped with the presented TVSA demonstrates safe interactions with various objects with diverse shapes, weights and stiffness. © 2024, The Authors. All rights reserved.

关键词： Stiffness

来源：评论

学校读者我要写书评

暂无评论

Intention-Aware Planner for Robust and Safe Aerial Tracking

arXiv

引用

arXiv 2023年

作者： Ren, Qiuyu Yu, Huan Dai, Jiajun Zheng, Zhi Meng, Jun Xu, Li Xu, Chao Gao, Fei Cao, Yanjun The State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou310027 China Huzhou Institute Zhejiang University Huzhou313000 China Huzhou Laboratory of Autonomous Intelligent Systems Huzhou313000 China The Robotics Institute Zhejiang University Yuyao315400 China College of Electrical Engineering Zhejiang University Hangzhou310027 China

Autonomous target tracking with quadrotors has wide applications in many scenarios, such as cinematographic follow-up shooting or suspect chasing. Target motion prediction is necessary when designing the tracking planner. However, the widely used constant velocity or constant rotation assumption can not fully capture the dynamics of the target. The tracker may fail when the target happens to move aggressively, such as sudden turn or deceleration. In this paper, we propose an intention-aware planner by additionally considering the intention of the target to enhance safety and robustness in aerial tracking applications. Firstly, a designated intention prediction method is proposed, which combines a user-defined potential assessment function and a state observation function. A reachable region is generated to specifically evaluate the turning intentions. Then we design an intention-driven hybrid A* method to predict the future possible positions for the target. Finally, an intention-aware optimization approach is designed to generate a spatial-temporal optimal trajectory, allowing the tracker to perceive unexpected situations from the target. Benchmark comparisons and real-world experiments are conducted to validate the performance of our method. Copyright © 2023, The Authors. All rights reserved.

关键词： Aircraft detection

来源：评论

学校读者我要写书评

暂无评论

CA-SpaceNet: Counterfactual Analysis for 6D Pose Estimation in Space

arXiv

引用

arXiv 2022年

作者： Wang, Shunli Wang, Shuaibing Jiao, Bo Yang, Dingkang Su, Liuzhen Zhai, Peng Chen, Chixiao Zhang, Lihua Academy for Engineering & Technology Fudan University China Engineering Research Center of AI and Robotics Ministry of Education China Jilin Provincial Key Laboratory of Intelligence Science & Engineering China Artifical Intelligence and Unmanned Systems Engineering Research Center of Jilin Province China

Reliable and stable 6D pose estimation of uncooperative space objects plays an essential role in on-orbit servicing and debris removal missions. Considering that the pose estimator is sensitive to background interference, this paper proposes a counterfactual analysis framework named CA-SpaceNet to complete robust 6D pose estimation of the space-borne targets under complicated background. Specifically, conventional methods are adopted to extract the features of the whole image in the factual case. In the counterfactual case, a non-existent image without the target but only the background is imagined. Side effect caused by background interference is reduced by counterfactual analysis, which leads to unbiased prediction in final results. In addition, we also carry out low-bit-width quantization for CA-SpaceNet and deploy part of the framework to a Processing-In-Memory (PIM) accelerator on FPGA. Qualitative and quantitative results demonstrate the effectiveness and efficiency of our proposed method. To our best knowledge, this paper applies causal inference and network quantization to the 6D pose estimation of space-borne targets for the first time. The code is available at https://***/Shunli-Wang/CA-SpaceNet. Copyright © 2022, The Authors. All rights reserved.

关键词： Space debris

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

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：