检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Song, Yaoxian Sun, Penglei Liu, Haoyu Li, Zhixu Song, Wei Xiao, Yanghua Zhou, Xiaofang Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China Research Center for Intelligent Robotics Zhejiang Lab China The Hong Kong University of Science and Technology Hong Kong

Embodied AI is one of the most popular studies in artificial intelligence and robotics, which can effectively improve the intelligence of real-world agents (i.e. robots) serving human beings. Scene knowledge is important for an agent to understand the surroundings and make correct decisions in the varied open world. Currently, knowledge base for embodied tasks is missing and most existing work use general knowledge base or pre-trained models to enhance the intelligence of an agent. For conventional knowledge base, it is sparse, insufficient in capacity and cost in data collection. For pre-trained models, they face the uncertainty of knowledge and hard maintenance. To overcome the challenges of scene knowledge, we propose a scene-driven multimodal knowledge graph (Scene-MMKG) construction method combining conventional knowledge engineering and large language models. A unified scene knowledge injection framework is introduced for knowledge representation. To evaluate the advantages of our proposed method, we instantiate Scene-MMKG considering typical indoor robotic functionalities (Manipulation and Mobility), named ManipMob-MMKG. Comparisons in characteristics indicate our instantiated ManipMob-MMKG has broad superiority on data-collection efficiency and knowledge quality. Experimental results on typical embodied tasks show that knowledge-enhanced methods using our instantiated ManipMob-MMKG can improve the performance obviously without re-designing model structures complexly. Our project can be found on https://***/view/manipmob-mmkg © 2023, CC BY-NC-SA.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Adaptive position tracking control of the lower limb exoskeleton robot with an uncertain dynamic model 18

Adaptive position tracking control of the lower limb exoskel...

引用

18th IEEE Conference on Industrial Electronics and Applications, ICIEA 2023

作者： Yuan, Ting Zhang, Chi Yi, Feng Lv, Pingping Li, Shupei Zhang, Meitong Ningbo University Ningbo Instituteof Materials Technology and Engineering Chinese Academy of Sciences Faculty of Electrical Engineering and Computer Science Ningbo315201 China Chinese Academy of Sciences Zhejiang Key Laboratory of Robotics and Intelligent Manufacturing Equipment Technology Ningbo Institute of Materials Technology and Engineering Ningbo315201 China University of Chinese Academy of Sciences Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences College of Materials Science and Opto-Electronic Technology Ningbo315201 China Hebei University of Science and Technology Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences School of Electrical Engineering Ningbo315201 China

ISBN: (纸本)9798350312201

In this paper, an adaptive position control method combining proportional-derivative (PD) control, RBF neural network-based sliding mode (SM) control, and feedforward (FF) control, i.e., PD-FF-SM control, is proposed to deal with the dynamic uncertainties, disturbances, and slow response in lower limb exoskeleton robot system. The Lagrange method is utilized to establish dynamic models that ignore the uncertainties and disturbances in the swing phase and supporting phase. Then, the PD feedback controller is designed with a sliding surface function, to keep the system stable. The FF controller is adopted to improve the response by using dynamic models. And the RBF neural network-based SM controller is designed to compensate for the uncertainties and disturbances. The system's stability is verified by Lyapunov's theorem. The simulation results show that the proposed control method can effectively reduce the error of position tracking and response time with inaccurate dynamic modeling. © 2023 IEEE.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Remote Sensing Scene Classification with Spectral-Spatial Convolutional Network

Hyperspectral Remote Sensing Scene Classification with Spect...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Jialin Zheng Zhen Li Puhong Duan Xudong Kang Wei Fu College of Electrical and Information Engineering Hunan University China College of Computer Science and Technology (CCST) Zhejiang University China Institute of Remote Sensing Satellite China Academy of Space Technology (CAST) China School of Robotics Hunan University China College of Computer Science and Electronic Engineering Hunan University China

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Remote sensing scene classification has garnered significant interest. However, few studies are dedicated to the classifi-cation of hyperspectral remote sensing scenes. Furthermore, current approaches that are designed for multispectral or visible images are not suitable for hyperspectral remote sensing scene classification. To solve these issues, a spectral-spatial convolutional network is proposed for hyperspectral remote sensing scene classification. First, a multiscale regional growth search method is developed to extract object region of the input data. Then, a three-branch network is designed to extract local spatial, global spatial, and spectral features. Finally, the obtained features are fed into fully connected layer to obtain class scores followed by a decision fusion rule to yield the final classification result. To evaluate the effect of hyperspectral remote sensing scene classification, a hyper-spectral remote sensing scene classification dataset (HRSS-C) is constructed, which consists of 1445 hyperspectral images with 11 different classes. Experiments on the HRSS-C reveal that our method gains superior classification performance with respect to other advanced approaches.

关键词： Training Scene classification Databases Feature extraction Search problems Convolutional neural networks Data mining

来源：评论

学校读者我要写书评

暂无评论

Happy: a debiased learning framework for continual generalized category discovery 24

Happy: a debiased learning framework for continual generaliz...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Shijie Ma Fei Zhu Zhun Zhong Wenzhuo Liu Xu-Yao Zhang Cheng-Lin Liu MAIS Institute of Automation Chinese Academy of Sciences China and School of Artificial Intelligence University of Chinese Academy of Sciences China Centre for Artificial Intelligence and Robotics HKISI-CAS China School of Computer Science and Information Engineering Hefei University of Technology China and School of Computer Science University of Nottingham NG8 1BB Nottingham UK

ISBN: (纸本)9798331314385

Constantly discovering novel concepts is crucial in evolving environments. This paper explores the underexplored task of Continual Generalized Category Discovery (C-GCD), which aims to incrementally discover new classes from unlabeled data while maintaining the ability to recognize previously learned classes. Although several settings are proposed to study the C-GCD task, they have limitations that do not reflect real-world scenarios. We thus study a more practical C-GCD setting, which includes more new classes to be discovered over a longer period, without storing samples of past classes. In C-GCD, the model is initially trained on labeled data of known classes, followed by multiple incremental stages where the model is fed with unlabeled data containing both old and new classes. The core challenge involves two conflicting objectives: discover new classes and prevent forgetting old ones. We delve into the conflicts and identify that models are susceptible to prediction bias and hardness bias. To address these issues, we introduce a debiased learning framework, namely Happy, characterized by Hardness-aware prototype sampling and soft entropy regularization. For the prediction bias, we first introduce clustering-guided initialization to provide robust features. In addition, we propose soft entropy regularization to assign appropriate probabilities to new classes, which can significantly enhance the clustering performance of new classes. For the harness bias, we present the hardness-aware prototype sampling, which can effectively reduce the forgetting issue for previously seen classes, especially for difficult classes. Experimental results demonstrate our method proficiently manages the conflicts of C-GCD and achieves remarkable performance across various datasets, e.g., 7.5% overall gains on ImageNet-100. Our code is publicly available at https://***/mashijie1028/Happy-CGCD.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semantic Traffic Element Removal by Learning to Follow Linguistic Instructions

Semantic Traffic Element Removal by Learning to Follow Lingu...

引用

IEEE International Conference on Unmanned Systems (ICUS)

作者： Xiaodan Feng Yuanqi Su Yuehu Liu Chi Zhang School of Computer Science and Technology Xi'an Jiaotong University Xi'an Shaanxi China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an Shaanxi China

We propose a novel task of semantic object removal in traffic scenes through human-guided image editing. Unlike traditional methods, our model does not require image masks; instead, it effectively removes semantic elements from a traffic scene image based solely on an input image and linguistic instruction. To achieve this objective, we use large-scale pre-trained models to construct a traffic scene image dataset suitable for human-guided image editing. We train a text-guided image translation model on this dataset. During inference, our model quickly generalizes to photorealistic traffic scene images and user-written instructions, obviating the need for fine-tuning and enabling rapid removal of semantic object elements from images within seconds. Experimental results demonstrate that our model achieves satisfying removal performance in the traffic scene semantic object removal task, showing the potential advantages of text guidance in image processing tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TagOOD: A Novel Approach to Out-of-Distribution Detection via Vision-Language Representations and Class Center Learning

arXiv

引用

arXiv 2024年

作者： Li, Jinglun Zhou, Xinyu Jiang, Kaixun Hong, Lingyi Guo, Pinxue Chen, Zhaoyu Ge, Weifeng Zhang, Wenqiang Shanghai Engineering Research Center of AI & Robotics Academy for Engineering & Technology Fudan University Shanghai China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China

Multimodal fusion, leveraging data like vision and language, is rapidly gaining traction. This enriched data representation improves performance across various tasks. Existing methods for out-of-distribution (OOD) detection, a critical area where AI models encounter unseen data in real-world scenarios, rely heavily on whole-image features. These image-level features can include irrelevant information that hinders the detection of OOD samples, ultimately limiting overall performance. In this paper, we propose TagOOD, a novel approach for OOD detection that leverages visionlanguage representations to achieve label-free object feature decoupling from whole images. This decomposition enables a more focused analysis of object semantics, enhancing OOD detection performance. Subsequently, TagOOD trains a lightweight network on the extracted object features to learn representative class centers. These centers capture the central tendencies of IND object classes, minimizing the influence of irrelevant image features during OOD detection. Finally, our approach efficiently detects OOD samples by calculating distance-based metrics as OOD scores between learned centers and test samples. We conduct extensive experiments to evaluate TagOOD on several benchmark datasets and demonstrate its superior performance compared to existing OOD detection methods. This work presents a novel perspective for further exploration of multimodal information utilization in OOD detection, with potential applications across various tasks. Code is available at: https://***/Jarvisgivemeasuit/tagood. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

QTER: QoS-Aware Three-Dimensional Efficient and Reliable Routing for LEO Satellite Networks

引用

IEEE Internet of Things Journal 2025年

作者： Zheng, Jinkai Luan, Tom H. Li, Guanjie Zhang, Yanfeng Yuan, Mingfeng Pan, Jianping Dongguan University of Technology School of Electrical Engineering and Intelligentization China Xi’an Jiaotong University China Xidian University School of Cyber Engineering China Singapore University of Technology and Design Information Systems Technology and Design Pillar Singapore University of Toronto Institute for Aerospace Studies University of Toronto Robotics Institute Canada University of Victoria Department of Computer Science Canada

Low Earth Orbit (LEO) satellite networks offer a promising approach for achieving global coverage and high-speed Internet access. However, the existing communication frameworks within these networks may result in low robustness and reliability. This paper introduces QTER, a novel and lightweight routing framework specifically designed for LEO networks, aimed at addressing these challenges. Our contributions are threefold. First, QTER establishes a cost-effective and reliable routing framework that accommodates a variety of applications with distinct Quality of Service (QoS) requirements. By enabling multi-path routing, the framework minimizes costs while ensuring end-to-end reliability, thus enhancing adaptability to diverse service demands. Second, we leverage the unique structural characteristics of LEO satellite networks by modeling the satellite constellation as a three-dimensional network, wherein higher-shell satellites serve as management satellite nodes (MSNs) to coordinate routing strategies among lower-shell satellites. This architecture significantly improves system efficiency and adaptability. Third, we propose a failure recovery mechanism that allows MSNs to relay packets when lower-orbit satellites are rendered unavailable due to environmental factors, thereby enhancing system robustness. Extensive simulations demonstrate that QTER exhibits resilience to node failures and dynamic network conditions, achieving reductions in average cost and delay by 59.4% and 38.9%, respectively, compared to baselines. © 2014 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Distributed Multi-robot Source Seeking in Unknown Environments with Unknown Number of Sources

arXiv

引用

arXiv 2025年

作者： Chen, Lingpeng Kailas, Siva Deolasee, Srujan Luo, Wenhao Sycara, Katia Kim, Woojun Shenzhen Institute of Artificial Intelligence and Robotics for Society Chinese University of Hong Kong Shenzhen China Robotics Institute Carnegie Mellon University United States School of Interactive Computing Georgia Institute of Technology United States Department of Computer Science University of Illinois Chicago United States

We introduce a novel distributed source seeking framework, DIAS, designed for multi-robot systems in scenarios where the number of sources is unknown and potentially exceeds the number of robots. Traditional robotic source seeking methods typically focused on directing each robot to a specific strong source and may fall short in comprehensively identifying all potential sources. DIAS addresses this gap by introducing a hybrid controller that identifies the presence of sources and then alternates between exploration for data gathering and exploitation for guiding robots to identified sources. It further enhances search efficiency by dividing the environment into Voronoi cells and approximating source density functions based on Gaussian process regression. Additionally, DIAS can be integrated with existing source seeking algorithms. We compare DIAS with existing algorithms, including DoSS and GMES in simulated gas leakage scenarios where the number of sources outnumbers or is equal to the number of robots. The numerical results show that DIAS outperforms the baseline methods in both the efficiency of source identification by the robots and the accuracy of the estimated environmental density function. Copyright © 2025, The Authors. All rights reserved.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

Automated rice counting using canny edge detection technique

Automated rice counting using canny edge detection technique

引用

8th IET Smart Cities Symposium (SCS 2024)

作者： Rahul Goraksha Durgesh Nandan Department of Robotics & Automation Engineering Symbiosis Institute of Technology Symbiosis International (Deemed University) Pune India School of Computer Science & Artificial Intelligence S R University Warangal Telangana 506371 India

ISBN: (数字)9781837243105

In many Asian countries, rice is a staple food of critical importance to local and global markets where rice quality matters. Rice quality has traditionally been appraised by human inspectors, but this approach is labor intensive, time-consuming and subjective. Such samples comprise whole kernels, broken kernels, damaged grains, paddy, stones and other impurities hence their sorting into grades according to the quality required. In this study a machine learning approach as well as image processing techniques for classification and segmentation of rice grain samples based on color texture features are proposed. Automated counting of rice is essential in farming processes such as estimation of yields, management of stores and transport planning. Manual counting is tasking, slow and likely to have errors. Machine vision technology provides an alternative that can be relied upon for automated rice counting systems. This paper gives details on methodology using machine vision for automating rice counting on the field. To identify and count rice grains in images Gaussian blur; thresholding; canny edge detection; contour extraction; are some examples of the image processing methods applied here. High accuracy rate was achieved when tested against a dataset containing several images of rice grains.

关键词：

来源：评论

学校读者我要写书评

暂无评论

VideoPure: Diffusion-based Adversarial Purification for Video Recognition

arXiv

引用

arXiv 2025年

作者： Jiang, Kaixun Chen, Zhaoyu Fu, Jiyuan Hong, Lingyi Li, Jinglun Zhang, Wenqiang Shanghai Engineering Research Center of AI Robotics Academy for Engineering & Technology Fudan University Shanghai China Engineering Research Center of AI & Robotics Ministry of Education Academy for Engineering & Technology Fudan University Shanghai China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China

—Recent work indicates that video recognition models are vulnerable to adversarial examples, posing a serious security risk to downstream applications. However, current research has primarily focused on adversarial attacks, with limited work exploring defense mechanisms. Furthermore, due to the spatial-temporal complexity of videos, existing video defense methods face issues of high cost, overfitting, and limited defense performance. Recently, diffusion-based adversarial purification methods have achieved robust defense performance in the image domain. However, due to the additional temporal dimension in videos, directly applying these diffusion-based adversarial purification methods to the video domain suffers performance and efficiency degradation. To achieve an efficient and effective video adversarial defense method, we propose the first diffusion-based video purification framework to improve video recognition models’ adversarial robustness: VideoPure. Given an adversarial example, we first employ temporal DDIM inversion to transform the input distribution into a temporally consistent and trajectory-defined distribution, covering adversarial noise while preserving more video structure. Then, during DDIM denoising, we leverage intermediate results at each denoising step and conduct guided spatial-temporal optimization, removing adversarial noise while maintaining temporal consistency. Finally, we input the list of optimized intermediate results into the video recognition model for multi-step voting to obtain the predicted class. We investigate the defense performance of our method against state-of-the-art black-box, gray-box, and adaptive attacks on benchmark datasets and models. Compared with other adversarial purification methods, our method overall demonstrates better defense performance against different attacks. Moreover, our method can be applied as a flexible defense plugin for video recognition models. Our code is available at https://***/deep-kaix

关键词： HTTP

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：