检索结果-内蒙古大学图书馆

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 2024年第2期9卷 3360-3371页

作者： Tian, Yonglin Zhang, Xianjing Wang, Xiao Xu, Jintao Wang, Jiangong Ai, Rui Gu, Weihao Ding, Weiping Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Haomo Technol Co Ltd AI Ctr Beijing 100192 Peoples R China Anhui Univ Sch Artificial Intelligence Hefei 230031 Peoples R China Haomo Technol Co Ltd Beijing 100192 Peoples R China Nantong Univ Sch Informat Sci & Technol Nantong 226019 Peoples R China

The recognition and utilization of complementary information arising from modality-intrinsic properties play crucial roles in multimodal 3D detection. However, most of the current approaches for fusion-based 3D detection follow symmetrical fusion paradigms and adopt early fusion, middle fusion as well as late fusion styles, which ignore the unequal status of data with different modalities. In this paper, according to the timing of fusion, we adopt an asymmetric cascade fusion network to exploit both the structural information from point clouds and the complementary semantic information from images. A multi-stage cascade design of 3D object detection is proposed to iteratively refine predictions and several late image features (comprised of detection clues, segmentation clues, and deep features from encoders) are incorporated into different stages of the LiDAR branch to maintain the integrity of image features and enable deep multimodal interactions. Besides, to mitigate the effects of the down-sampling of voxelized features and possible mismatching of multimodal data, we propose proxy-based cross-modality sampling to utilize the high-density point clouds coordinates and develop an image degeneration process to simulate the noise in cross-modality matching for robust training. Extensive experiments are conducted on KITTI and Waymo Open Dataset, which validate the effectiveness of the proposed method.

关键词： Three-dimensional displays Feature extraction Point cloud compression Laser radar Object detection Timing Fuses 3D detection autonomous driving asymmetric fusion cascade fusion multimodal fusion

来源：评论

学校读者我要写书评

暂无评论

Ground-Based Cloud Detection Using Multiscale Attention Convolutional Neural Network

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2022年 19卷 1页

作者： Zhang, Zhong Yang, Shuzhen Liu, Shuang Xiao, Baihua Cao, Xiaozhong Tianjin Normal Univ Tianjin Key Lab Wireless Mobile Commun & Power Tr Tianjin 300387 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China China Meteorol Adm Meteorol Observat Ctr Beijing 100081 Peoples R China

Cloud detection plays a significant role in ground-based remote sensing observation, and it is quite challenging due to the variations in illumination and cloud form, and the vague boundaries between cloud and sky. In this letter, we propose a novel deep model named multiscale attention convolutional neural network (MACNN) for ground-based cloud detection, which possesses a symmetric encoder-decoder structure. For accurate cloud detection, we design the multiscale module in MACNN to obtain different receptive fields by using different hole rates for the filters, and meanwhile, we propose the attention module in MACNN to learn the attention coefficients in order to reflect different importance of pixels. Furthermore, we release the Tianjin Normal University (TJNU) cloud detection database (TCDD) to provide a comparative study for different methods, and to the best of our knowledge, it is the largest cloud detection database. We conduct a series of experiments on the TCDD, and the experimental results demonstrate that the proposed MACNN outperforms state-of-the-art methods in five quantitative evaluation criteria.

关键词： Clouds Databases Decoding Cloud computing Convolutional neural networks Computer architecture Training Attention module cloud detection multiscale module Tianjin Normal University (TJNU) cloud detection database (TCDD)

来源：评论

学校读者我要写书评

暂无评论

A Doubly Graduated Method for Inference in Markov Random Field\ast

引用

SIAM JOURNAL ON IMAGING SCIENCES 2021年第3期14卷 1354-1373页

作者： Yang, Xu Liu, Zhi-Yong Chinese Acad Sci State Key Lab Management & Control Complex Syst Inst Automat Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China

Maximum a posteriori (MAP) inference in Markov random field (MRF) lays the foundation for many computer vision tasks, which can be formulated by a binary quadratic programming (BQP) problem. Compared with the discrete methods, the continuous relaxation scheme becomes popular due to its generality and efficiency. However, existing continuous relaxation based MAP algorithms are still limited by two problems, i.e., the highly nonconvex original objective function and the gap between the original BQP problem and the relaxed continuous optimization problem. Targeting the two problems, this paper presents a doubly graduated continuous relaxation algorithm for MAP inference in MRF, which are, respectively, the Gaussian smoothing based graduated nonconvexity process and conditional gradient ascent based graduated projection. Experiments on both synthetic data and real-world images illustrate the algorithm's state-of-the-art performance in objective function optimization and typical computer vision tasks.

关键词： maximum a posteriori Markov random field Gaussian smoothing continuous relaxation

来源：评论

学校读者我要写书评

暂无评论

Microfabrication of Li4SiO4 pebbles with complex pore structure via digital light processing: Accuracy control and properties optimizing

引用

INTERNATIONAL JOURNAL OF HYDROGEN ENERGY 2024年 54卷 1410-1421页

作者： Cai, Liang Tao, Sirong Shen, Zhen Wan, Li Liu, Ziao He, Xilin Zhang, Yingchun Univ Sci & Technol Beijing Sch Mat Sci & Engn 30 Xueyuan Rd Beijing 100083 Peoples R China Chinese Acad Sci Inst Automat Beijing Engn Res Ctr Intelligent Syst & Technol State Key Lab Management & Control Complex Syst 95 Zhongguancun E Rd Beijing 100190 Peoples R China Ten Dimens Guangdong Technol Co Ltd 33 Informat Rd Foshan 528225 Peoples R China

Li4SiO4 ceramic pebble is deemed as the most attractive tritium breeder for fusion reactor blanket. In this work, we fabricated a novel Li4SiO4 pebble with micrometer-scale pore structure by digital light processing to verify the feasibility of complex pore structure manufacturing for future breeders. The effects of processing parameters on printing accuracy, microstructure and mechanical properties of Li4SiO4 pebbles were investigated. For synthesizing the pure Li4SiO4 phase, the optimal stoichiometric ratio of Li2SiO3 to Li2CO3 was 1:1.09 in the premixed powder. The photosensitivity of dual-phase ceramic suspension was investigated according to an attenuation model, and the overgrowth was reduced to similar to 50 mu m by using the dimension formula. After optimizing the post-processing, the radial pore structure Li4SiO4 pebbles with excellent crush load (50.3 N, standard deviation = 4.4 N) and suitable open porosity (18.3 %) can be yielded. This work provides a fresh solution to control the pore structure of tritium breeding pebbles in an unprecedented micrometer scale.

关键词： Additive manufacturing Digital light processing Tritium breeder material Ceramic pebble Lithium orthosilicate

来源：评论

学校读者我要写书评

暂无评论

Attitude tracking control of spacecraft with preset-time preset-bounded convergence

引用

INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR control 2022年第18期32卷 10162-10179页

作者： Zou, An-Min Liu, Yangyang Shantou Univ Coll Engn Dept Elect & Informat Engn Shantou 515063 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing Peoples R China Guangdong Prov Key Lab Digital Signal & Image Pro Shantou Peoples R China Shantou Univ Key Lab Intelligent Mfg Technol Minist Educ Shantou Peoples R China

This article addresses the issue of attitude tracking control of rigid spacecraft in the existence of bounded external disturbances. By introducing a smooth time-varying scaling function, a preset-time sliding mode surface is designed. Then, a nonsingular and continuous preset-time preset-bounded attitude tracking control scheme is developed. The distinctive feature of the present control law is that the size of the convergence region and the settling time can be prescribed a priori. In addition, the proposed control scheme exhibits superiority in reducing the magnitude of the applied control torques and saving energy. At last the feasibility of the derived control protocol is illustrated by numerical simulations including a comparative example.

关键词： attitude control preset-time preset-bounded stability rigid spacecraft sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Missile guidance with assisted deep reinforcement learning for head-on interception of maneuvering target

引用

complex & INTELLIGENT systemS 2022年第2期8卷 1205-1216页

作者： Li, Weifan Zhu, Yuanheng Zhao, Dongbin Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst 95 Zhongguancun East Rd Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 101408 Peoples R China

In missile guidance, pursuit performance is seriously degraded due to the uncertainty and randomness in target maneuverability, detection delay, and environmental noise. In many methods, accurately estimating the acceleration of the target or the time-to-go is needed to intercept the maneuvering target, which is hard in an environment with uncertainty. In this paper, we propose an assisted deep reinforcement learning (ARL) algorithm to optimize the neural network-based missile guidance controller for head-on interception. Based on the relative velocity, distance, and angle, ARL can control the missile to intercept the maneuvering target and achieve large terminal intercept angle. To reduce the influence of environmental uncertainty, ARL predicts the target's acceleration as an auxiliary supervised task. The supervised learning task improves the ability of the agent to extract information from observations. To exploit the agent's good trajectories, ARL presents the Gaussian self-imitation learning to make the mean of action distribution approach the agent's good actions. Compared with vanilla self-imitation learning, Gaussian self-imitation learning improves the exploration in continuous control. Simulation results validate that ARL outperforms traditional methods and proximal policy optimization algorithm with higher hit rate and larger terminal intercept angle in the simulation environment with noise, delay, and maneuverable target.

关键词： Reinforcement learning Missile guidance Auxiliary learning Self-imitation learning

来源：评论

学校读者我要写书评

暂无评论

Towards Automated Segmentation of Human Abdominal Aorta and Its Branches Using a Hybrid Feature Extraction Module with LSTM 29th

Towards Automated Segmentation of Human Abdominal Aorta and ...

引用

29th International Conference on Neural Information Processing

作者： Zhang, Bo Liu, Shiqi Xie, Xiaoliang Zhou, Xiaohu Hou, Zengguang Song, Meng Ma, Xiyao Zhang, Linsen Univ Sci & Technol Beijing Beijing 100083 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China

ISBN: (纸本)9789819916474;9789819916481

Abdominal aortic aneurysm (AAA) is a disease with high rates of morbidity and mortality. For AAA treatment, appropriately covered stents are placed to prevent blood from entering the aneurysm. Before the interventional procedure, the morphology of the abdominal arteries (the aorta and its branches) is of the utmost importance to formulate surgical plans and prepare surgical instruments. Due to accurate vessel measurements, in particular, custom-made fenestrated stent grafts and chimney stent grafts are widely used for complicated AAAs. Therefore, rapid and accurate reconstruction of the vascular from CTA images is necessary. In this study, we proposed a novel network for automated segmentation of the human abdominal aorta and its branches. The hybrid feature extraction module, which combines convolution and transformer, represents intra-frame vessel feature information well. And the inter-frame vessel structure information is extracted by a special attention mechanism that includes the LSTM module. The results of 38 patients' CTA image sequences show that the proposed network achieves state-of-the-art performance. The proposed method can assist physicians with preoperative diagnosis.

关键词： Abdominal Aortic Aneurysm Segmentation Computed Tomography Angiography

来源：评论

学校读者我要写书评

暂无评论

VistaGPT: Generative Parallel Transformers for Vehicles With Intelligent systems for Transport Automation

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES

引用

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 2023年第9期8卷 4198-4207页

作者： Tian, Yonglin Li, Xuan Zhang, Hui Zhao, Chen Li, Bai Wang, Xiao Wang, Xiao Wang, Fei-Yue Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Peng Cheng Lab Shenzhen 518000 Peoples R China Beijing Jiaotong Univ Sch Comp & Informat Technol Beijing 100044 Peoples R China Hunan Univ Coll Mech & Vehicle Engn State Key Lab Adv Design & Mfg Vehicle Body Changsha 410082 Peoples R China Purdue Univ Dept Comp Sci W Lafayette IN 47906 USA Anhui Univ Hefei 266114 Peoples R China

Diverse transport demands have resulted in the wide existence of heterogeneous vehicle automation systems. While these systems have demonstrated effectiveness, they also pose challenges in terms of the share of technological advancements among different organizations and lead to poor generalization ability of individual systems. This article proposes a Transformer-based unified framework, VistaGPT, to address these challenges. VistaGPT, composed of Modular Federations of Vehicular Transformers (M-FoV) and Automated Composing of Autonomous Driving systems (AutoAuto), aims to overcome the information barriers due to system-level and module-level heterogeneity. M-FoV collects and organizes Transformer-based models in a modular fashion to facilitate system integration by providing diversity and versatility. AutoAuto utilizes large language models (LLMs) to automatically compose end-to-end autonomous driving systems with a "Dividing and Recombining" strategy. Besides, we deploy Scenario Engineering systems to evaluate the composed systems and provide systematic feedback for the optimization of AutoAuto, and Federated intelligence to contribute to diverse training samples and applications. With its capacity, scalability, and diversity, VistaGPT provides a new paradigm of LLM-aided system development for transport automation, which promotes virtual-real interactive parallel driving and advances progress toward "6S" objectives.

关键词： Transformers Task analysis Autonomous vehicles Planning Biological system modeling Navigation Automation Generative parallel transformers end-to-end driving transport automation large-language models federation of vehicular transformers scenario engineering

来源：评论

学校读者我要写书评

暂无评论

Constructing Constraint Force Field in Musculoskeletal Robot by Co-optimizing Muscle Arrangements and Constant Activations

Constructing Constraint Force Field in Musculoskeletal Robot...

引用

IEEE International Conference on Fuzzy systems (FUZZ-IEEE) / IEEE World Congress on Computational Intelligence (IEEE WCCI) / International Joint Conference on Neural Networks (IJCNN) / IEEE Congress on Evolutionary Computation (IEEE CEC)

作者： Zhong, Shanlin Zhou, Junjie Wu, Wei Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China

ISBN: (数字)9781728186719

ISBN: (纸本)9781728186719

Robots with high-precision motion and operation ability are of great application significance. By referring to the biomechanical structure and neural control mechanism of human motion system, the research of musculoskeletal robot system with rigid-flexible coupling characteristics is one of the important ways to improve the operation flexibility and control robustness of robot. Inspired by the equilibrium point hypothesis proposed in neuroscience, this paper proposes a co-optimization algorithm of muscle arrangement and activation to construct constraint force field in the workspace of musculoskeletal robot. When the muscle arrangement is rough due to the insufficient precision of the mechanical structure, the musculoskeletal robot can maintain accurate motion with the help of constraint force field by adopting the optimized constant activation. Experiments are carried out on a musculoskeletal robot model with human-mimetic muscle to demonstrate the effectiveness of the proposed algorithm in movement accuracy, noise robustness and generalization. This work may be of great significance for the further introduction of constraint force field into hardware system of musculoskeletal robot.

关键词： Musculoskeletal robot Constraint Force Field High precision control Schemes of robot

来源：评论

学校读者我要写书评

暂无评论

A Framework and Operational Procedures for Metaverses-Based Industrial Foundation Models

引用

IEEE TRANSACTIONS ON systemS MAN CYBERNETICS-systemS 2023年第4期53卷 2037-2046页

作者： Wang, Jiangong Tian, Yonglin Wang, Yutong Yang, Jing Wang, Xingxia Wang, Sanjin Kwan, Oliver 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 Qingdao Acad Intelligent Ind Qingdao 266109 Peoples R China China North Ind North Automatic Control Technol Re North Automat Control Technol Inst Taiyuan 030006 Peoples R China Mot G Inc Shenzhen 518071 Peoples R China

Industrial processes are typical cyber-physical-social systems (CPSSs), where the effective management of employees and the efficient control of machines play important roles. Traditional industries heavily rely on human labor and neglect the development of collection-utilization-transmission integrated information loops, thereby leading to high costs and low efficiency in operational procedures. To facilitate the natural interactions and smart operations for humans and machines, industrial foundation models (IFMs) based on metaverses are proposed in this article, serving as the operating systems of industrial parallel machines that provide sustainable data resources and scenarios for management and control experiments. On this basis, IFM comprised of vision foundation models, language foundation models, as well as operational foundation models, are constructed to manage resources in industrial parallel machines and provides comprehensive services for industrial procedures. On the one hand, IFM can efficiently manage various resources including computing power, digital assets, enterprise resources, and platform I/O via the proposed CPSS-based competing, sharing, scheduling, monitoring, allocating, and recovering mechanisms. On the other hand, imaginative intelligence, linguistic intelligence, and algorithmic intelligence can be achieved through vivid visualization of vision foundation models, natural conversations of language foundation models, and smart manipulation of operational foundation models. With the proposed IFM, cyber-physical-social intelligence (CPSI) can be achieved to enhance the efficient management and control of industrial processes.

关键词： Cyber-physical-social intelligence (CPSI) cyber-physical-social systems (CPSSs) industrial foundation models (IFMs) intelligent enterprises metaverses operational processes parallel intelligence

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：