检索结果-内蒙古大学图书馆

Deep reinforcement learning with a stage incentive mechanism of dense reward for robotic trajectory planning

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Peng, Gang Yang, Jin Khyam, Mohammad Omar Key Laboratory of Image Processing and Intelligent Control Ministry of EducationB School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China School of Automation South East University Nanjing China School of Engineering and Technology Central Queensland University Melbourne Australia

To improve the efficiency of deep reinforcement learning (DRL)-based methods for robot manipulator trajectory planning in random working environments, we present three dense reward functions. These rewards differ from the traditional sparse reward. First, a posture reward function is proposed to speed up the learning process with a more reasonable trajectory by modeling the distance and direction constraints, which can reduce the blindness of exploration. Second, a stride reward function is proposed to improve the stability of the learning process by modeling the distance and movement distance of joint constraints. Finally, in order to further improve learning efficiency, we are inspired by the cognitive process of human behavior and propose a stage incentive mechanism, including a hard stage incentive reward function and a soft stage incentive reward function. Extensive experiments show that the soft stage incentive reward function is able to improve the convergence rate by up to 46.9% with the state-of-the-art DRL methods. The percentage increase in the convergence mean reward was 4.4-15.5% and the percentage decreases with respect to standard deviation were 21.9-63.2%. In the evaluation experiments, the success rate of trajectory planning for a robot manipulator reached 99.6%. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep learning

Forget less,count better:a domain-incremental self-distillation learning benchmark for lifelong crowd counting

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic Engineering 2023年第2期24卷 187-202页

作者： Jiaqi GAO Jingqi LI Hongming SHAN Yanyun QU James ZWANG Fei-Yue WANG Junping ZHANG Shanghai Key Laboratory of Intelligent Information Processing School of Computer ScienceFudan UniversityShanghai 200433China Institute of Science and Technology for Brain-inspired Intelligence Fudan UniversityShanghai 200433China Shanghai Center for Brain Science and Brain-inspired Technology Shanghai 201210China School of Information Science and Technology Xiamen UniversityXiamen 361005China College of Information Sciences and Technology the Pennsylvania State UniversityUniversity ParkPA 16802USA State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China

Crowd counting has important applications in public safety and pandemic control.A robust and practical crowd counting system has to be capable of continuously learning with the newly incoming domain data in real-world scenarios instead of fitting one domain ***-the-shelf methods have some drawbacks when handling multiple domains:(1)the models will achieve limited performance(even drop dramatically)among old domains after training images from new domains due to the discrepancies in intrinsic data distributions from various domains,which is called catastrophic forgetting;(2)the well-trained model in a specific domain achieves imperfect performance among other unseen domains because of domain shift;(3)it leads to linearly increasing storage overhead,either mixing all the data for training or simply training dozens of separate models for different domains when new ones are *** overcome these issues,we investigate a new crowd counting task in incremental domain training setting called lifelong crowd *** goal is to alleviate catastrophic forgetting and improve the generalization ability using a single model updated by the incremental ***,we propose a self-distillation learning framework as a benchmark(forget less,count better,or FLCB)for lifelong crowd counting,which helps the model leverage previous meaningful knowledge in a sustainable manner for better crowd counting to mitigate the forgetting when new data arrive.A new quantitative metric,normalized Backward Transfer(nBwT),is developed to evaluate the forgetting degree of the model in the lifelong learning *** experimental results demonstrate the superiority of our proposed benchmark in achieving a low catastrophic forgetting degree and strong generalization ability.

关键词： Crowd counting Knowledge distillation Lifelong learning

Integration of nonlinear disturbance observer within proxy-based sliding mode control for pneumatic muscle actuators

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Cao, Yu Huang, Jian Wu, Dongrui Zhang, Mengshi Xiong, Caihua Li, Zhijun Key Laboratory for Image Processing and Intelligent Control of Education Ministry of China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China School of Mechanical Science Engineering State Key Laboratory of Digital Manufacturing Equipment and Technology Huazhong University of Science and Technology Wuhan430074 China College of Automation Science and Engineering South China University of Technology Guangzhou510641 China

This paper presents an integration of nonlinear disturbance observer within proxy-based sliding mode control (IDO-PSMC) approach for Pneumatic Muscle Actuators (PMAs). Due to the nonlinearities, uncertainties, hysteresis, and timevarying characteristics of the PMA, the model parameters are difficult to be identified accurately, which results in unmeasurable uncertainties and disturbances of the system. To solve this problem, a novel design of proxy-based sliding mode controller (PSMC) combined with a nonlinear disturbance observer (DO) is used for the tracking control of the PMA. Our approach combines both the merits of the PSMC and the DO so that it is effective in both reducing the "chattering" phenomeno n and improving the system robustness. A constrained Firefly Algorithm is used to search for the optimal control parameters. Based on the Lyapunov theorem, the states of the PMA are shown to be globally uniformly ultimately bounded. Extensive experiments were conducted to verify the superior performance of our approach, in multiple tracking scenarios. Copyright © 2019, The Authors. All rights reserved.

关键词： Sliding mode control

Implicit Ray-Transformers for Multi-view Remote Sensing image Segmentation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Qi, Zipeng Chen, Hao Liu, Chenyang Shi, Zhenwei Zou, Zhengxia The Image Processing Center School of Astronautics The Beijing Key Laboratory of Digital Media The State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China The Shanghai Artificial Intelligence Laboratory Shanghai200232 China The Department of Guidance Navigation and Control School of Astronautics Beihang University Beijing100191 China

The mainstream CNN-based remote sensing (RS) image semantic segmentation approaches typically rely on massive labeled training data. Such a paradigm struggles with the problem of RS multi-view scene segmentation with limited labeled views due to the lack of considering 3D information within the scene. In this paper, we propose "Implicit Ray-Transformer (IRT)" based on Implicit Neural Representation (INR), for RS scene semantic segmentation with sparse labels (such as 4-6 labels per 100 images). We explore a new way of introducing multi-view 3D structure priors to the task for accurate and view-consistent semantic segmentation. The proposed method includes a two-stage learning process. In the first stage, we optimize a neural field to encode the color and 3D structure of the remote sensing scene based on multi-view images. In the second stage, we design a Ray Transformer to leverage the relations between the neural field 3D features and 2D texture features for learning better semantic representations. Different from previous methods that only consider 3D prior or 2D features, we incorporate additional 2D texture information and 3D prior by broadcasting CNN features to different point features along the sampled ray. To verify the effectiveness of the proposed method, we construct a challenging dataset containing six synthetic sub-datasets collected from the Carla platform and three real sub-datasets from Google Maps. Experiments show that the proposed method outperforms the CNN-based methods and the state-of-the-art INR-based segmentation methods in quantitative and qualitative metrics. Ablation study shows that under limited label conditions, the combination of the 3D structure prior and 2D texture can significantly improve the performance and effectively complete missing semantic information in novel views. Experiments also demonstrate the proposed method could yield geometry-consistent segmentation results against illumination changes and viewpoint changes. Our dat

关键词： Remote sensing

A Network-Based VPN Architecture Using Virtual Routing

学校读者我要写书评

暂无评论

Wuhan University Journal of Natural Sciences 2005年第1期10卷 161-164页

作者： ZHANG Bao-liang 1,2,HU Han-ping 1,2,WU Xiao-gang 1,2, KONG Tao 31.state Education Ministry key laboratory of image Information and intelligent control, Wuhan 430074, Hubei, China 2.Institute of Pattem Recognition and Artificial Intelligonce, Huazhong University of Science and Technology, Wuhan 430074, Hubei, China 3.709th Research Institute of China Shipbuilding Engineering Society, Wuhan 430074, Hubei, China State Education Ministry Key Laboratory of Image Information and Intelligent Control Wuhan China Huazhong University of Science and Technology Institute of Pattern Recognition and Artificial Intelligonce Wuhan China (GRID:grid.33199.31) (ISNI:***) State Education Ministry Key Laboratory of Image Information and Intelligent Control Wuhan China (GRID:grid.33199.31) Huazhong University of Science and Technology Institute of Pattern Recognition and Artificial Intelligonce Wuhan China (GRID:grid.33199.31) (ISNI:***) 709th Research Institute of China Shipbuilding Engineering Society Wuhan China (GRID:grid.33199.31)

A network-based Virtual Private Network (VPN) architecture by using fundamental routing mechanism is proposed. This network is a virtual overlay network based on the relay of IP-in-IP tunneling of virtual routing modules. The packet format employs the encapsulation of IPSec ESP(Encapsulating Security Payload), an impact path code and an extended DS(Differentiated Services) code to support multi-path routing and QoS. Comparing with other models of VPN, this network system can be deployed in the current network with little investment, and it is easy to implement. The simulation result shows its performance is better than the traditional VPN system of black box mode.

关键词： virtual routing network-based VPN proactive defense

Isoform Function Prediction Based on Heterogeneous Graph Attention Networks

学校读者我要写书评

暂无评论

Isoform Function Prediction Based on Heterogeneous Graph Att...

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Kuo Guo Yifan Li Hao Chen Hong-Bin Shen Yang Yang Department of Computer Science and Engineering Shanghai Jiao Tong University and Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University and Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China Computational Biology Department School of Computer Science Carnegie Mellon University Pittsburgh PA USA

Isoforms refer to different mRNA molecules transcribed from the same gene, which can be translated into proteins with varying structures and functions. Predicting the functions of isoforms is an essential topic in bioinformatics as it can provide valuable insights into the intricate mechanisms of gene regulation and biological processes. Conventionally, gene function labels are standardized in Gene Ontology (GO) terms. However, traditional methods for predicting isoform function are largely limited by the absence of isoform-specific labels, sparse annotations, and the vast number of GO terms. To address these issues, we propose HANIso, a deep learning-based method for isoform function prediction. HANIso leverages a pretrained protein language model to extract features from protein sequences. It also integrates heterogeneous information, such as isoform sequence features, GO annotations, and isoform interaction data, using a Heterogeneous Graph Attention Network (HAN). This allows the model to learn the importance of different sources of information and their semantic relationships through the attention mechanism. Our method can predict function labels at both the gene level and isoform level. We conduct experiments on two species datasets, and the results demonstrate that our method outperforms existing methods on both AUROC and AUPRC. HANIso has the potential to overcome the limitations of traditional methods and provide a more accurate and comprehensive understanding of isoform function.

关键词：

ROAD CENTRAL CONTOUR EXTRACTION FROM HIGH RESOLUTION SATELLITE image USING TENSOR VOTING FRAMEWORK

学校读者我要写书评

暂无评论

ROAD CENTRAL CONTOUR EXTRACTION FROM HIGH RESOLUTION SATELLI...

2006 International Conference on Machine Learning and Cybernetics(IEEE第五届机器学习与控制论坛)

作者： SHENG ZHENG JIAN LIU WEN-ZHONG SHI GUANG-XI ZHU Electronic & Information Engineering Dept. Huazhong University of Science and Technology Wuhan 430 State Education Commission Key Laboratory for Image Processing and Intelligent Control Inst.for Pat Advanced Research Center for Spatial Information Technology Department of Land Surveying and Geo-In Chinese Key lab of optic & electronics Huazhong University of Science and Technology Wuhan 430074

In this paper, a unique road contour extraction approach from high resolution satellite image is proposed, in which the road contour was extracted in two steps. Firstly, support vector machines (SVM) was employed merely to classify the image into two groups of categories: a road group and a non-road group. The identified road group images are the discrete and irregularly distributed sampled points, and they are an uncompleted data set for the road. Secondly, the road contour was extracted from the road group images using the tensor voting framework, since the tensor voting technique is superior to the traditional methods in extracting the geometrical structure from the uncompleted data set. The experimental results on the high resolution satellite image demonstrate that the proposed approach worked well with images comprised by both rural and urban area features.

关键词： Tensor voting framework Road central line extraction High-resolution satellite image

A delay system method to design of event-triggered control of networked control systems

学校读者我要写书评

暂无评论

A delay system method to design of event-triggered control o...

IEEE Conference on Decision and control

作者： Dong Yue Engang Tian Qing-Long Han Department of Control Science and Engineering and the Key Laboratory of Ministry of Education for Image Processing and Intelligent Control Huazhong University of Science and Technology Hubei 430074 China School of Electrical and Automation Engineering Nanjing Normal University 78 Bancang Street Nanjing 210042 China Center for Intelligent and Networked Systems and the School of Information and Communication Technology Central Queensland University Rockhampton Qld 4702 Australia

ISBN: (纸本)9781612848006

The event-triggered H_(infinity) control design is investigated for networked control systems with uncertainties and transmission delays. A novel event-triggering scheme is proposed, which has some advantages over traditional ones with a continuous detector. Considering the effect of the transmission delay, a delay system model for the analysis is firstly constructed. Then, based on the model and Lyapunov functional method, criteria for the stability with an H_(infinity) norm bound and criteria for the co-design of both the feedback gain and the trigger parameters are derived. In order to solve the feedback gain and the trigger parameters, the linear matrix inequality technique is employed. From the simulation example, it can be concluded that the proposed event-triggering scheme is superior to some other event-triggering schemes in some existing literature.

关键词： feedback gain Networked control systems Event trigger Delay systems Scheme Co-design control systems design control

Topology-Aware 3D Gaussian Splatting: Leveraging Persistent Homology for Optimized Structural Integrity

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Shen, Tianqi Liu, Shaohua Feng, Jiaqi Ma, Ziye An, Ning Department of Computer Science City University of Hong Kong Hong Kong Image Processing Center Beihang University China Shen Yuan Honors College Beihang University China Research Institute of Mine Artificial Intelligence China Coal Research Institute China State Key Laboratory of Intelligent Coal Mining and Strata Control China

Gaussian Splatting (GS) has emerged as a crucial technique for representing discrete volumetric radiance fields. It leverages unique parametrization to mitigate computational demands in scene optimization. This work introduces Topology-Aware 3D Gaussian Splatting (Topology-GS), which addresses two key limitations in current approaches: compromised pixel-level structural integrity due to incomplete initial geometric coverage, and inadequate feature-level integrity from insufficient topological constraints during optimization. To overcome these limitations, Topology-GS incorporates a novel interpolation strategy, Local Persistent Voronoi Interpolation (LPVI), and a topology-focused regularization term based on persistent barcodes, named PersLoss. LPVI utilizes persistent homology to guide adaptive interpolation, enhancing point coverage in low-curvature areas while preserving topological structure. PersLoss aligns the visual perceptual similarity of rendered images with ground truth by constraining distances between their topological features. Comprehensive experiments on three novel-view synthesis benchmarks demonstrate that Topology-GS outperforms existing methods in terms of PSNR, SSIM, and LPIPS metrics, while maintaining efficient memory usage. This study pioneers the integration of topology with 3D-GS, laying the groundwork for future research in this area. Copyright © 2024, The Authors. All rights reserved.

关键词： Interpolation