检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Hu, Xuemin Li, Shen Huang, Tingyu Tang, Bo Huai, Rouxing Chen, Long The School of Artificial Intelligence Hubei University Hubei Wuhan430062 China The Department of Electrical and Computer Engineering Worcester Polytechnic Institute WorcesterMA01609 United States Beijing Huairou Academy of Parallel Sensing Beijing101499 China The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100864 China The Waytous Inc. Beijing100083 China

Safety and cost are two important concerns for the development of autonomous driving technologies. From the academic research to commercial applications of autonomous driving vehicles, sufficient simulation and real world testing are required. In general, a large scale of testing in simulation environment is conducted and then the learned driving knowledge is transferred to the real world, so how to adapt driving knowledge learned in simulation to reality becomes a critical issue. However, the virtual simulation world differs from the real world in many aspects such as lighting, textures, vehicle dynamics, and agents' behaviors, etc., which makes it difficult to bridge the gap between the virtual and real worlds. This gap is commonly referred to as the reality gap (RG). In recent years, researchers have explored various approaches to address the reality gap issue, which can be broadly classified into three categories: transferring knowledge from simulation to reality (sim2real), learning in digital twins (DTs), and learning by parallel intelligence (PI) technologies. In this paper, we consider the solutions through the sim2real, DTs, and PI technologies, and review important applications and innovations in the field of autonomous driving. Meanwhile, we show the state-of-the-arts from the views of algorithms, models, and simulators, and elaborate the development process from sim2real to DTs and PI. The presentation also illustrates the far-reaching effects and challenges in the development of sim2real, DTs, and PI in autonomous driving. Copyright © 2023, The Authors. All rights reserved.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

A Unified Weight Initialization Paradigm for Tensorial Convolutional Neural Networks

arXiv

引用

arXiv 2022年

作者： Pan, Yu Su, Zeyong Liu, Ao Wang, Jingquan Li, Nannan Xu, Zenglin Harbin Institute of Technology Shenzhen Shenzhen China University of Electronic Science and Technology of China Chengdu China Tokyo Institute of Technology Tokyo Japan State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Pengcheng Laboratory Shenzhen China

Tensorial Convolutional Neural Networks (TCNNs) have attracted much research attention for their power in reducing model parameters or enhancing the generalization ability. However, exploration of TCNNs is hindered even from weight initialization methods. To be specific, general initialization methods, such as Xavier or Kaiming initialization, usually fail to generate appropriate weights for TCNNs. Meanwhile, although there are ad-hoc approaches for specific architectures (e.g., Tensor Ring Nets), they are not applicable to TCNNs with other tensor decomposition methods (e.g., CP or Tucker decomposition). To address this problem, we propose a universal weight initialization paradigm, which generalizes Xavier and Kaiming methods and can be widely applicable to arbitrary TCNNs. Specifically, we first present the Reproducing Transformation to convert the backward process in TCNNs to an equivalent convolution process. Then, based on the convolution operators in the forward and backward processes, we build a unified paradigm to control the variance of features and gradients in TCNNs. Thus, we can derive fan-in and fan-out initialization for various TCNNs. We demonstrate that our paradigm can stabilize the training of TCNNs, leading to faster convergence and better results. Copyright © 2022, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

The Emerging Intelligent Vehicles and Intelligent Vehicle Carriers Collaborative systems

The Emerging Intelligent Vehicles and Intelligent Vehicle Ca...

引用

IEEE Symposium on Intelligent Vehicle

作者： Zhipeng Shen Chao Huang Hailong Huang Yutong Wang Fei-Yue Wang Abbas Jamalipour Duc Truong Pham Ljubo Vlacic Andrey V. Savkin Department of Aeronautical and Aviation Engineering the Hong Kong Polytechnic University Hong Kong Department of Industrial and Systems Engineering the Hong Kong Polytechnic University Hong Kong State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Institute of Engineering Macau University of Science and Technology Macau China School of Electrical and Information Engineering University of Sydney Sydney Australia Department of Mechanical Engineering University of Birmingham Birmingham UK Institute of Intelligent & Integrated Systems and the School of Engineering and Built Environment Griffith University Brisbane Australia School of Electrical Engineering and Telecommunications University of New South Wales Sydney Australia

ISBN: (数字)9798350348811

ISBN: (纸本)9798350348828

In this paper, we propose the innovative use of Intelligent Vehicle Carriers (IVCs) as a key solution to address the energy constraints of small-scale unmanned Intelligent Vehicles (IVs). IVCs function as both transporters and charging stations, significantly boosting the operational range and efficiency of IVs. Our research delves into the IV-IVC collaborative framework, highlighting the existing challenges, exploring potential solutions, and examining a range of applications. This study offers a visionary approach to revolutionizing intelligent transportation systems by leveraging the synergistic relationship between IVs and IVCs.

关键词： Intelligent vehicles Collaboration Charging stations Boosting

来源：评论

学校读者我要写书评

暂无评论

A Study on Decentralized Autonomous Organizations Based Intelligent Transportation System enabled by Blockchain and Smart Contract

A Study on Decentralized Autonomous Organizations Based Inte...

引用

Chinese Automation Congress (CAC)

作者： JiaChen Hou WenWen Ding Xiaolong Liang FengHua Zhu Yong Yuan FeiYue Wang Institute of Systems Engineering Macau University of Science and Technology Macau China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Mathematics Renmin University of China Beijing China

ISBN: (纸本)9781665426480

With the rapid development of the transportation industry, Intelligent Transportation System (ITS) tries to adapt to industry changes through constructing new organizational forms, management methods, and incentive mechanisms. However, many new governance issues have arisen due to the transportation system’s complexity, diversity, and uncertainty. DAO(Decentralized autonomous organization) enabled by blockchain and smart contracts are regarded as effective methods to solve the organizational governance problems for complex systems. Therefore, this article analyzes the main issues currently faced by ITS. Then, this paper proposed a 6-layer DAO structure framework for ITS and discussed its key research issues. Finally, a case study for the Macau transportation system is carried out, and further research directions are proposed. The DAO-based transportation system will represent the future trend of ITS development. This paper aims to motivate more discussion for this new direction and provide helpful guidance and reference for future research work.

关键词： Visualization Uncertainty Decentralized autonomous organization Transportation industry Smart contracts Transportation Market research

来源：评论

学校读者我要写书评

暂无评论

A learning-based control approach for blind quadrupedal locomotion with guided-DRL and hierarchical-DRL

A learning-based control approach for blind quadrupedal loco...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Liang Ren Chunlei Wang Ya Yang Zhiqiang Cao 21st Research Institute of China Electronics Technology Group Corporation Shanghai China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781665405362

control parameters play an important role on the locomotion performance of quadruped robot system. In this paper, a learning-based control method is proposed, where the parameters of controller are learned by deep reinforcement learning (DRL). The proposed control system consists of a hierarchical controller and an agent, in which the agent learns the parameters in the upper layer of the controller. In the learning process, the guided-DRL and the hierarchical-DRL were used to solve the exploration problem and reward sparse problem, respectively. The former learns good expert trajectories with controller, which can realize the transition from supervised learning to self-learning, whereas the latter divides the task into a series of sub-goals to ensure that the difficulty of each subtask matches the decision-making ability of the agent in the learning stage. Finally, the controller with the trained policy is deployed to a real robot without manual tuning, and experimental results prove the effectiveness of the proposed method.

关键词： Energy consumption Supervised learning Reinforcement learning Manuals Interference Robustness Trajectory

来源：评论

学校读者我要写书评

暂无评论

AirVista-II: An Agentic System for Embodied UAVs Toward Dynamic Scene Semantic Understanding

arXiv

引用

arXiv 2025年

作者： Lin, Fei Tian, Yonglin Zhang, Tengchao Huang, Jun Guan, Sangtian Wang, Fei-Yue Department of Engineering Science Faculty of Innovation Engineering Macau University of Science and Technology 999078 China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

Unmanned Aerial Vehicles (UAVs) are increasingly important in dynamic environments such as logistics transportation and disaster response. However, current tasks often rely on human operators to monitor aerial videos and make operational decisions. This mode of human-machine collaboration suffers from significant limitations in efficiency and adaptability. In this paper, we present AirVista-II—an end-to-end agentic system for embodied UAVs, designed to enable general-purpose semantic understanding and reasoning in dynamic scenes. The system integrates agent-based task identification and scheduling, multimodal perception mechanisms, and differentiated keyframe extraction strategies tailored for various temporal scenarios, enabling the efficient capture of critical scene information. Experimental results demonstrate that the proposed system achieves high-quality semantic understanding across diverse UAV-based dynamic scenarios under a zero-shot setting. Copyright © 2025, The Authors. All rights reserved.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Society 5.0: Metaverse Facilitated Human-centric “5H” Services Across Cyber-Physical-Social Spaces

引用

IFAC-PapersOnLine 2024年第3期58卷 159-164页

作者： Xiao Wang Jun Huang QingHua Ni Zhe Wan HuaDan Xue Larry Stapleton Fei-Yue Wang Engineering Research Center of Autonomous Unmanned System Technology Ministry of Education Anhui University Hefei 230601 China Macau University of Science and Technology Macau 999078 China Beijing Normal University Beijing 100875 China Department of Radiology Peking Union Medical College Hospital Shuaifuyuan Beijing 100730 Dongcheng District China Brownsbarn Thomastown Co. Kilkenny Ireland R95D8P2 Qingdao Academy of Intelligent Industries Qingdao 266109 China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China

Cyber-Physical-Social systems bridge the gap between social resource organization and distribution, and give birth to Society 5.0, which represents a transformative vision aimed at realizing the human-centric paradigm for more efficient and effective sustainable development. In this paper, we discuss the decentralized paradigm in fostering human needs-driven smart services, in line with Maslow’s hierarchy of needs theory. Societies 5.0 is committed to optimizing the use of natural, artificial, and social resources by enhancing democratic participation and ensuring that decision-making processes are more transparent, reliable, and aligned with the needs of the populace in sustainable ways. Moreover, our discussion extends to how Society 5.0’s principles correlate with the United Nations Sustainable Development Goals (SDGs), providing a framework that supports health, education, and poverty reduction, among other targets. This approach also aligns with the Human Development Index (HDI), reinforcing the notion that technological progress in Society 5.0 does not overshadow but rather complements and enhances human values, paving a synergistic path towards sustainable development that is both advanced and fundamentally human-centric.

关键词： Cyber-Physical-Social systems Society 5.0 Human-Centric Services Socio-technical synergistic sustainable development

来源：评论

学校读者我要写书评

暂无评论

Geometry Problem Solving Based on Counter-Factual Evolutionary Reasoning

Geometry Problem Solving Based on Counter-Factual Evolutiona...

引用

IEEE International Conference on Automation Science and Engineering (CASE)

作者： Bing Song Gang Xiong Zhen Shen Fenghua Zhu Yisheng Lv Peijun Ye The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China The Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences China The Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing The Cloud Computing Center Chinese Academy of Sciences Dongguan China Intelligent Manufacturing Center Qingdao Academy of Intelligent Industries Qingdao China

As a representative topic in natural language processing and automated theorem proving, geometry problem solving requires an abstract problem understanding and symbolic reasoning. A major challenge here is to find a feasible reasoning sequence that is consistent with given axioms and the theorems already proved. Most recent methods have exploited neural network-based techniques to automatically discover eligible solving steps. Such a kind of methods, however, is greatly impacted by the expert solutions for training. To improve the accuracy, this paper proposes a new method called counterfactual evolutionary reasoning, which uses a generative adversarial network to generate initial reasoning sequences and then introduces counterfactual reasoning to explore potential solutions. By directly exploring theorem candidates rather than the neural network selection, the new method can sufficiently extend the searching space to get a more appropriate reasoning step. Through comparative experiments on the recent proposed Geometry3k, the largest geometry problem solving dataset, our method generally achieves a higher accuracy than most previous methods, bringing an overall improvement about 4.4% compared with the transformer models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Accurate and Robust Eye Center Localization via Fully Convolutional Networks

引用

IEEE/CAA Journal of Automatica Sinica 2019年第5期6卷 1127-1138页

作者： Yifan Xia Hui Yu Fei-Yue Wang the School of Creative Technologies University of PortsmouthPortsmouthPO1 2DJUK the State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China

Eye center localization is one of the most crucial and basic requirements for some human-computer interaction applications such as eye gaze estimation and eye tracking. There is a large body of works on this topic in recent years, but the accuracy still needs to be improved due to challenges in appearance such as the high variability of shapes, lighting conditions, viewing angles and possible occlusions. To address these problems and limitations, we propose a novel approach in this paper for the eye center localization with a fully convolutional network(FCN),which is an end-to-end and pixels-to-pixels network and can locate the eye center accurately. The key idea is to apply the FCN from the object semantic segmentation task to the eye center localization task since the problem of eye center localization can be regarded as a special semantic segmentation problem. We adapt contemporary FCN into a shallow structure with a large kernel convolutional block and transfer their performance from semantic segmentation to the eye center localization task by *** experiments show that the proposed method outperforms the state-of-the-art methods in both accuracy and reliability of eye center localization. The proposed method has achieved a large performance improvement on the most challenging database and it thus provides a promising solution to some challenging applications.

关键词： Deep learning eye center localization eye gaze estimation eye tracking fully convolutional network (FCN) humancomputer interaction

来源：评论

学校读者我要写书评

暂无评论

Learning to Manipulate Tools Using Deep Reinforcement Learning and Anchor Information

Learning to Manipulate Tools Using Deep Reinforcement Learni...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Junhang Wei Shaowei Cui Peng Hao Shuo Wang School of Future Technology University of Chinese Academy of Sciences Beijing China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai China

ISBN: (纸本)9781665481106

Endowing robots with tool manipulation skills helps them accomplish challenging tasks. While robots manipulate tools to achieve goals, the alignment of tools and targets is a noise-sensitive and contact-rich task. However, it is difficult to access the accurate pose of the tool and the target. When there is unknown noise in the observations, reinforcement learning can't be sure to perform well. In this paper, we define the easier-to-obtain accurate task-related information as anchor information and introduce a tool manipulation method based on reinforcement learning and anchor information, which can perform well when the observations include unknown noise. To evaluate the method, we build a simulated environment ToolGym, which includes four different kinds of tools and different noise sampling functions for each tool. Finally, we compare our method with baseline methods to show the effectiveness of the proposed method.

关键词： Deep learning Biomimetics Reinforcement learning Grasping Fasteners End effectors Task analysis

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：