检索结果-内蒙古大学图书馆

Visual Place Recognition via a Multitask Learning Method With Attentive Feature Aggregation

IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL systems 2023年第3期15卷 1263-1278页

作者： Guan, Peiyu Cao, Zhiqiang Yu, Junzhi Tan, Min Wang, Shuo Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Peking Univ Coll Engn Dept Adv Mfg & Robot State Key Lab Turbulence & Complex Syst Beijing 100871 Peoples R China

Visual place recognition has gained popularity in recent years. Mainstream convolutional neural network-based methods formulate it as a ranking task and optimize it in the paradigm of deep metric learning, however, the ranking-motivated losses concern only the ranking relationship for each query image and the compactness of intraplace feature distribution is seldom considered. It is still challenging due to varying viewpoints, illuminations, and even dynamic objects. In this article, a novel multitask learning framework is proposed, which combines the existing triplet ranking task and our designed binary classification task to jointly optimize the network for better generalization capability. Specifically, a binary classification network with the corresponding binary cross-entropy loss is designed in the classification task. In this way, the intraplace feature compactness and interplace feature separability are reinforced. At the testing stage, this classification network is discarded without increasing the computation cost. Furthermore, an attention module is presented to promote the network to concentrate on the salient regions by assigning different importance to each spatial position. Our method achieves the top-10 recalls of 97.27%, 94.6%, and 96.93% on Pitts250k-test, Tokyo 24/7, and TokyoTM-val data sets, respectively. Extensive experiments prove that the proposed network can learn discriminative global features with better robustness to viewpoints and environmental variations.

关键词： Attentive feature aggregation multitask learning visual place recognition

来源：评论

学校读者我要写书评

暂无评论

Scenarios Engineering: Enabling Trustworthy and Effective AI for Autonomous Vehicles

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES

引用

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 2023年第5期8卷 3205-3210页

作者： Li, Xuan Wang, Fei-Yue Peng Cheng Lab Dept Math & Theories Shenzhen 518055 Peoples R China Chinese Acad Sci Inst Automation State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

The first journal impact factor (IF) of IEEE TIV is 5.009 with a CiteScore = 10.9 in 2022, signifying a promising start for our periodical. By April 2023, our real-time IF stands at 7.03 according to Web of Science, and CiteScore from Elsevier is 11.6. These numbers indicate that IEEE TIV is among the top-tier publications in the related fields.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Autonomous Services: The Evolution of Services Through Intelligent Vehicles

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES

引用

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 2023年第11期8卷 4468-4473页

作者： Jing, Zheng Li, Lefei Lyu, Yudan Wang, Ridong Wang, Yutong Wang, Ding Wang, Fei-Yue Tsinghua Univ Dept Ind Engn Beijing 100084 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Shanghai Artificial Intelligence Lab Urban Comp Lab Shanghai 200235 Peoples R China Chinese Acad Sci State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Macau Univ Sci & Technol Macao Inst Syst Engn Taipa 999078 Macao Peoples R China

The emergence of intelligent vehicles brings unique opportunities for the service industry. This study introduces the concept of autonomous services, a new service paradigm, and autonomous services systems, in which intelligent vehicles are vital enabling technology. Specifically, autonomous services aim to minimize unnecessary human participation and effort in the service process by leveraging intelligence for service delivery, rather than relying on simple stimulus-response or rule-based program behavior. This letter reports on the first Decentralized and Hybrid Workshop (DHW) on autonomous services, aiming to reduce the cost of human labor and improve the quality and efficiency of service while tackling the challenges posed by a shrinking workforce. The introduction of intelligent vehicles enhances the capability of the service systems, while also significantly increasing complexity. To address the challenges associated with complexity, the systems Engineering (SE) approach is indispensable. The Requirements-Functional-Logical-Physical (RFLP) framework can implement Model-Based System Engineering (MBSE) and help researchers and managers to understand the autonomous services system more comprehensively, so as to better operate and manage it. We substitute "Implementation" for "Physical" in this research to define and elaborate on the autonomous services system. Finally, we outline the potential research opportunities within the autonomous services system.

关键词： Intelligent vehicles autonomous services cyber-physical-social systems(CPSSs) parallel intelligence requirement-functional-logical-physical(RFLP) framework

来源：评论

学校读者我要写书评

暂无评论

Distilling Siamese Trackers with Attention Mask 41

Distilling Siamese Trackers with Attention Mask

引用

第41届中国控制会议

作者： Han Sun Yongqiang Bai Wenbo Zhang State Key Lab of Intelligent Control and Decision of Complex Systems and School of Automation Beijing Institute of Technology

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In recent years,the introduction of Siamese network has brought new vitality to the object tracking ***,high-performance Siamese trackers cannot run at a real-time speed on mobile devices due to their complex and huge *** distillation is a common and effective model compression method,but it is difficult to be applied to the challenging task like object *** find out the fundamental cause is that the imbalance between the foreground and background in the object tracking task,which aggravates the problem of insufficient feature extraction ability of small ***,we propose the attention mask distillation(AMD) to help the student tracker focus on the foreground area faster and more *** attention mask can be easily obtained from the feature maps and brings fine-granularity to the traditional binary *** experimental results on OTB100 and VOT2018 show that our method enables the student tracker perform as well as the teacher *** the same time,it's able to run on the CPU at a hyper-real-time of 66 fps and achieves nearly 9 times model compression *** low computational and storage costs make it possible to deploy high-performance trackers on resource-constrained platforms.

关键词： Object Tracking Siamese Network Knowledge Distillation Attention Mask

来源：评论

学校读者我要写书评

暂无评论

Mobility 5.0: Smart Logistics and Transportation Services in Cyber-Physical-Social systems

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES

引用

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 2023年第6期8卷 3527-3532页

作者： Lin, Yilun Na, Xiaoxiang Wang, Ding Dai, Xingyuan Wang, Fei-Yue Shanghai Artificial Intelligence Lab Urban Comp Lab Shanghai 200235 Peoples R China Univ Cambridge Dept Engn Cambridge CB2 1PZ England Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100090 Peoples R China Chinese Acad Sci State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Macau Univ Sci & Technol Macao Inst Syst Engn Taipa 999078 Macao Peoples R China

The logistics and transportation industry has made significant progress in improving sustainability, efficiency, and accessibility, primarily due to the continuous development of technologies, including clean energy, advanced algorithms, unmanned vehicles, and privacy-enhancing techniques. Along with these advancements, the Mobility 5.0 paradigm has been proposed in the ITSS Intelligent Vehicle 5.0 project meeting. This letter discusses the changes in the supply and demand of mobility resources and looks at the basic components on which the implementation of the Mobility 5.0 relies on. By integrating emerging technologies into Cyber-Physical-Social systems (CPSS), we believe that Mobility 5.0 has tremendous potential in shaping a new era of intelligent logistics and transportation services and will bring significant benefits to individuals, businesses, the government, and the entire society.

关键词： Mobility logistics transportation cyber-physical-social systems

来源：评论

学校读者我要写书评

暂无评论

Robot-Guided Crowd Evacuation in a Railway Hub Station in Case of Emergencies

引用

JOURNAL OF INTELLIGENT & ROBOTIC systems 2022年第4期104卷 1-14页

作者： Zhou, Min Dong, Hairong Ge, Shichao Wang, Xiao Wang, Fei-Yue Beijing Jiaotong Univ State Key Lab Rail Traff Control & Safety Beijing 100044 Peoples R China Chinese Acad Sci CASIA Inst Automat State Key Lab Management & Control Complex Syst S Beijing 100190 Peoples R China

The rapid and orderly evacuation of passengers at the railway hub station in case of emergencies is an important issue for railway safety and efficiency. In this paper, a robot-guided passenger evacuation method is proposed to help passengers search evacuation paths and avoid potential risks. The number and initial positions of robots are determined by using a k-means clustering approach. The exit assignment and evacuation paths of robots are calculated by using a hybrid bi-level optimization approach taking into account the cooperative mechanism between robots. Then, a robot-guided crowd evacuation dynamical model is built based on a modified social force model, in which a navigation force is introduced to influence the speed and direction of evacuees. A case study of a typical railway hub station is used to demonstrate the effectiveness of the proposed approach. The scenarios of the mall and platform are designed to verify the evacuation efficiency under different robot distribution schemes. The experimental results prove that setting up robots can effectively reduce evacuation time, and the utilization of exits is more balanced. The proposed optimal scheme shows the best performance in evacuation efficiency, including evacuation time and exit utilization rate, compared to the uniform distribution scheme and no robot scheme.

关键词： Robot guided crowd evacuation Modified social force model Railway hub station Robot distribution Cooperative mechanism Emergencies

来源：评论

学校读者我要写书评

暂无评论

Finite-time filtering of T-S fuzzy semi-Markov jump systems with asynchronous mode-dependent delays

引用

JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS 2023年第16期360卷 12707-12728页

作者： Ma, Chao Fu, Hang Wu, Wei Univ Sci & Technol Beijing Sch Mech Engn Beijing 100083 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

This paper studies the finite-time filter design of semi-Markov jump system by Takagi-Sugeno (T-S) fuzzy rules. Asynchronous mode-dependent delays are concerned to describe more practical random features, which implies that the semi-Markov process of system state is different from another semiMarkov process of mode-dependent time-varying delays. With the help of model transformation as well as mode-dependent Lyapunov-Krasovskii function method, sufficient criteria are first established for maintaining finite-time passivity performance of filtering errors. Then, the matrix technique is employed to synthesize the filter gain design. In the end, the applicableness and effectiveness of our developed results are confirmed by an illustrative example. (c) 2021 The Franklin Institute. Published by Elsevier Ltd. All rights reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Online Model Predictive control of Robot Manipulator With Structured Deep Koopman Model

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2023年第5期8卷 3102-3109页

作者： Zhang, Jinxin Wang, Hongze Chinese Acad Sci Inst Automation State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China

The model predictive control (MPC) can provide the benefit of optimality (sub-optimality, exactly speaking) and explicitly treat hard constraints in both states and inputs, which makes it an attractive approach in the fields of robotics. However, the performance of this approach heavily depends on the system model and it is computationally intensive, which hinders its application in the real-time control of robotic systems with fast dynamics, such as the robotic manipulators. Data-driven modeling approaches based on the Koopman operator have the potential to remove the barriers to adopting the MPC in robotics, through learning a globally linear model. In this letter, we propose a novel Koopman model-the structured deep Koopman model, which can improve the accuracy of the learned linear model and reduce the number of states in the lifted space, through exploiting the deep Lipschitz neural network and making the lifted dynamics structured. We also prove the rationality of the presented method and provide a new perspective on Koopman operator-based models, which brings the local and global linearization methods under the same umbrella. The effectiveness of the presented method has been verified by simulations and a real-world robotic experiment.

关键词： Deep learning in robotics and automation model learning for control Koopman operator model predictive control Lipschitz neural network

来源：评论

学校读者我要写书评

暂无评论

Reconstruction-Based Hand-Eye Calibration Using Arbitrary Objects

引用

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2023年第5期19卷 6545-6555页

作者： Xing, Shiyu Jing, Fengshui Tan, Min Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

This article introduces a flexible hand-eye calibration technique for a 3-D sensor from a reconstruction perspective, with no need for a specialized and accurate calibration rig. Our intention is to find the hand-eye relation that simultaneously aligns multiview point clouds of a common scene into the robot base frame, namely simultaneous calibration and reconstruction. To achieve this goal, a novel variant of iterative closest point (ICP) algorithm based on the Gauss-Newton method and Lie algebra is proposed, which iteratively transforms multiview point clouds into the robot base frame, estimates point-to-point correspondences between point clouds then refines the hand-eye relation to minimize the Euclidean distance between corresponding points. In addition to the calibration result, it returns a preliminary reconstruction as a byproduct. Cases of degeneracy and applicable conditions are given and proved. Using arbitrary daily objects with no prior information and a real robotic eye-in-hand system, we verify our method feasible and effective.

关键词： Robot sensing systems Calibration Robots Point cloud compression Three-dimensional displays Service robots Robot motion 3-D reconstruction arbitrary objects computer vision and its industrial application hand-eye calibration iterative closest point (ICP) variant

来源：评论

学校读者我要写书评

暂无评论

OS-DS tracker: Orientation-variant Siamese 3D tracking with Detection based Sampling

引用

PATTERN RECOGNITION LETTERS 2023年第1期174卷 57-63页

作者： Zhang, Qiuyu Wang, Lipeng Li, Wanyi Meng, Hao Zhang, Wen Zhang, Zhi Wang, Peng Harbin Engn Univ Coll Intelligent Syst Sci & Engn Harbin 150001 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing Peoples R China

LIDAR point clouds are less affected by the weather and possess more depth of field than 2D images. However, sparsity and disorder of point clouds bring challenges for 3D object tracking due to the difficulty in detecting and encoding. In addition, ineffective candidate proposals increase the phenomenon of the loss of target tracking or wrong target tracking. In this paper, we propose an Orientation-variant Siamese 3D object tracking network that utilizes a Detection based Sampling module to generate candidate proposals (OS-DS tracker). The Detection based Sampling module is used to cut the excessive and useless proposals. And the multivariate Gaussian sampling generates the candidate proposals when the objects are not detected. Concretely, we first pre-train PointRCNN Network to globally detect objects from LIDAR point clouds. Then the 3D detected objects are refined by Candidate Regions Sampling to generate candidate proposals. Meanwhile, to make the feature vectors more discriminative, we design an Orientation-variant Siamese Auto-encoder, i.e., tracking loss regress to the intersection over union (IOU) of the template box and the candidate region boxes. Our method is tested on the KITTI dataset and the SHIP Tracking dataset. Compared with the previous state-of-the-arts, the proposed method outperforms in vessel tracking with 5.2%/2.1% improvement in Success and Precision.

关键词： LIDAR point clouds Object tracking Gaussian sampling Candidate regions Auto-encoder

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：