检索结果-内蒙古大学图书馆

9th International Symposium on Artificial Intelligence and robotics, ISAIR 2024

作者： Tang, Chang Chen, Shitao Tian, Zhiqiang Lan, Xuguang School of Software Engineering Xi’an Jiaotong University Xi’an China National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an China

ISBN: (纸本)9789819629107

Multi-Agent Path Finding (MAPF) is vital for large-scale Multi-Agent Systems (MAS), where agents must plan collision-free paths to reach their goals. While Reinforcement Learning (RL) methods aim to enhance real-time performance and scalability over search-based approaches, their success on complex maps is limited. This is due to the use of independent RL algorithms, which fail to address the non-stationarity of the environment, and inappropriate reward functions that cause the agent’s policy to worsen with greater distance to the goal. To tackle these issues, we propose a MAPF algorithm based on a new variant of the Value Decomposition Network (VDN), a multi-agent RL algorithm, and introduce a novel reward function. This VDN variant trains the network using agents within a specific agent’s field of view, addressing non-stationarity and training challenges in large-scale MAS, unlike naive VDN, which considers all agents. We introduce a novel reward function using potential-based reward shaping, rendering the agent’s policy independent of the map size. Additionally, we enhance the reward to alleviate congestion by preventing agents from stopping next to each other and by penalizing the following conflicts. Experiments show our planner has a notably higher success rate than other RL-based planners and slightly lower than the latest state-of-the-art search-based planner, LaCAM*, on complex maps. For instance, on a 160 × 160 map with 30% obstacle density and 1024 agents, our planner achieves an 88% success rate, while other RL-based planners achieve virtually 0%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

JVPR: Bilateral Information Interaction by Joint Training for Sequence-Based Visual Place Recognition

JVPR: Bilateral Information Interaction by Joint Training fo...

引用

International Conference on Intelligent Transportation

作者： Jincheng Li Yanqing Shen Jingmin Xin Nanning Zheng National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University

Visual Place Recognition (VPR) focuses on retrieving the most similar imagery from database given a query, and it usually takes a video stream as input. Facing omnipresent sequential information in robotics and autonomous systems, neither image descriptor-based sequence match methods nor sequential descriptor aggregation techniques consider correlation between image descriptors and sequential descriptors. Instead, they are processed independently as two separate information flows. In this work, we propose a novel joint-training visual place recognition (JVPR) to enhance the consistency and robustness between two kinds of descriptors, thereby coupling former two independent pipelines and maintaining the robustness of both image and sequential descriptors. We also pre-process recently released Mapillary Street-Level Sequences dataset so that more choices in sequence-based VPR researches are afterwards available to the community, and we benchmark our JVPR as well as SeqNet on several representative cities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SMIRK: 3D Facial Expressions through Analysis-by-Neural-Synthesis

arXiv

引用

arXiv 2024年

作者： Retsinas, George Filntisis, Panagiotis P. Daněček, Radek Abrevaya, Victoria F. Roussos, Anastasios Bolkart, Timo Maragos, Petros Institute of Robotics Athena Research Center Maroussi15125 Greece School of Electrical & Computer Engineering National Technical University of Athens Greece MPI for Intelligent Systems Tübingen Germany Greece

While existing methods for 3D face reconstruction from in-the-wild images excel at recovering the overall face shape, they commonly miss subtle, extreme, asymmetric, or rarely observed expressions. We improve upon these methods with SMIRK (Spatial Modeling for Image-based Reconstruction of Kinesics), which faithfully reconstructs expressive 3D faces from images. We identify two key limitations in existing methods: shortcomings in their self-supervised training formulation, and a lack of expression diversity in the training images. For training, most methods employ differentiable rendering to compare a predicted face mesh with the input image, along with a plethora of additional loss functions. This differentiable rendering loss not only has to provide supervision to optimize for 3D face geometry, camera, albedo, and lighting, which is an ill-posed optimization problem, but the domain gap between rendering and input image further hinders the learning process. Instead, SMIRK replaces the differentiable rendering with a neural rendering module that, given the rendered predicted mesh geometry, and sparsely sampled pixels of the input image, generates a face image. As the neural rendering gets color information from sampled image pixels, supervising with neural rendering-based reconstruction loss can focus solely on the geometry. Further, it enables us to generate images of the input identity with varying expressions while training. These are then utilized as input to the reconstruction model and used as supervision with ground truth geometry. This effectively augments the training data and enhances the generalization for diverse expressions. Our qualitative, quantitative and particularly our perceptual evaluations demonstrate that SMIRK achieves the new state-of-the art performance on accurate expression reconstruction. For our method’s source code, demo video and more, please visit our project webpage: https://***/smirk/. © 2024, CC BY.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Moment Quantization for Video Temporal Grounding

arXiv

引用

arXiv 2025年

作者： Sun, Xiaolong Wang, Le Zhou, Sanping Shi, Liushuai Xia, Kun Liu, Mengnan Wang, Yabing Hua, Gang National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University China Multimodal Experiences Research Lab Dolby Laboratories

Video temporal grounding is a critical video understanding task, which aims to localize moments relevant to a language description. The challenge of this task lies in distinguishing relevant and irrelevant moments. Previous methods focused on learning continuous features exhibit weak differentiation between foreground and background features. In this paper, we propose a novel Moment-Quantization based Video Temporal Grounding method (MQVTG), which quantizes the input video into various discrete vectors to enhance the discrimination between relevant and irrelevant moments. Specifically, MQVTG maintains a learnable moment codebook, where each video moment matches a codeword. Considering the visual diversity, i.e., various visual expressions for the same moment, MQVTG treats moment-codeword matching as a clustering process without using discrete vectors, avoiding the loss of useful information from direct hard quantization. Additionally, we employ effective prior-initialization and joint-projection strategies to enhance the maintained moment codebook. With its simple implementation, the proposed method can be integrated into existing temporal grounding models as a plug-and-play component. Extensive experiments on six popular benchmarks demonstrate the effectiveness and generalizability of MQVTG, significantly outperforming state-of-the-art methods. Further qualitative analysis shows that our method effectively groups relevant features and separates irrelevant ones, aligning with our goal of enhancing discrimination. © 2025, CC BY.

关键词： Electric grounding

来源：评论

学校读者我要写书评

暂无评论

SCIGS: 3D Gaussians Splatting from a Snapshot Compressive Image

arXiv

引用

arXiv 2024年

作者： Wang, Zixu Yang, Hao Guo, Yu Wang, Fei National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications School of Software Engineering Xi’an Jiaotong University China Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University China

Snapshot Compressive Imaging (SCI) offers a possibility for capturing information in high-speed dynamic scenes, requiring efficient reconstruction method to recover scene information. Despite promising results, current deep learning-based and NeRF-based reconstruction methods face challenges: 1) deep learning-based reconstruction methods struggle to maintain 3D structural consistency within scenes, and 2) NeRF-based reconstruction methods still face limitations in handling dynamic scenes. To address these challenges, we propose SCIGS, a variant of 3DGS, and develop a primitive-level transformation network that utilizes camera pose stamps and Gaussian primitive coordinates as embedding vectors. This approach resolves the necessity of camera pose in vanilla 3DGS and enhances multi-view 3D structural consistency in dynamic scenes by utilizing transformed primitives. Additionally, a high-frequency filter is introduced to eliminate the artifacts generated during the transformation. The proposed SCIGS is the first to reconstruct a 3D explicit scene from a single compressed image, extending its application to dynamic 3D scenes. Experiments on both static and dynamic scenes demonstrate that SCIGS not only enhances SCI decoding but also outperforms current state-of-the-art methods in reconstructing dynamic 3D scenes from a single compressed image. The code will be made available upon publication. Copyright © 2024, The Authors. All rights reserved.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

Exploring Humanoid Robot Face Preference Using Brain Functional Connectivity and Graph Neural Network 12

Exploring Humanoid Robot Face Preference Using Brain Functio...

引用

12th International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2022

作者： Wang, Pengchao Mu, Wei Zhan, Gege Wang, Aiping Song, Zuoting Fang, Tao Zhang, Xueze Wang, Junkongshuai Niu, Lan Bin, Jianxiong Zhang, Lihua Jia, Jie Kang, Xiaoyang State Key Laboratory of Medical Neurobiology Institute of Ai and Robotics Academy for Engineering and Technology Fudan University Laboratory for Neural Interface and Brain Computer Interface Engineering Research Center of Ai and Robotics Ministry of Education Shanghai Engineering Research Center of Ai and Robotics Moe Frontiers Center for Brain Science Shanghai200433 China Ji Hua Laboratory Guangdong Province Foshan528200 China Huashan Hospital Fudan University Department of Rehabilitation Medicine Shanghai200040 China Yiwu Research Institute of Fudan University Zhejiang Yiwu City322000 China Research Center for Intelligent Sensing Zhejiang Lab Hangzhou311121 China

ISBN: (数字)9781665472678

ISBN: (纸本)9781665472678

Graph neural networks (GNN) have been applied in EEG signal analysis. However, it is not clear how to describe the connection relationships between electrodes, and a reasonable representation of the adjacency matrix cannot be neglected for the study of GNN based on EEG signals. In this paper, we use brain functional connectivity to analyze the face preferences of a humanoid robot and explore the feasibility of using the matrix obtained based on brain functional connectivity measurements as a GNN connectivity matrix. The results show that it is feasible and an average accuracy of 73.47% is achieved. In addition, the results of the brain functional connectivity analysis also show that there is a difference between preferences and non-preferences. © 2022 IEEE.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

StructVPR: Distill Structural Knowledge with Weighting Samples for Visual Place Recognition

StructVPR: Distill Structural Knowledge with Weighting Sampl...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yanqing Shen Sanping Zhou Jingwen Fu Ruotong Wang Shitao Chen Nanning Zheng National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University

Visual place recognition (VPR) is usually considered as a specific image retrieval problem. Limited by existing training frameworks, most deep learning-based works cannot extract sufficiently stable global features from RGB images and rely on a time-consuming re-ranking step to exploit spatial structural information for better performance. In this paper, we propose StructVPR, a novel training architecture for VPR, to enhance structural knowledge in RGB global features and thus improve feature stability in a constantly changing environment. Specifically, StructVPR uses segmentation images as a more definitive source of structural knowledge input into a CNN network and applies knowledge distillation to avoid online segmentation and inference of seg-branch in testing. Considering that not all samples contain high-quality and helpful knowledge, and some even hurt the performance of distillation, we partition samples and weigh each sample's distillation loss to enhance the expected knowledge precisely. Finally, StructVPR achieves impressive performance on several benchmarks using only global retrieval and even outperforms many two-stage approaches by a large margin. After adding additional re-ranking, ours achieves state-of-the-art performance while maintaining a low computational cost.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Feasibility of Pointcloud-based Ultrasound-CT Registration towards Automated, Robot-Assisted Image-Guidance in Spine Surgery*

Feasibility of Pointcloud-based Ultrasound-CT Registration t...

引用

International Symposium on Medical robotics (ISMR)

作者： Xihan Ma Xiao Zhang Yang Wang Christopher Nycz Arno Sungarian Songbai Ji Haichong K. Zhang Department of Robotics Engineering Worcester Polytechnic Institute Worcester MA USA Department of Electrical and Computer Engineering Worcester Polytechnic Institute Worcester MA USA University of Massachusetts Memorial Medical Center Worcester MA USA Department of Biomedical Engineering Worcester Polytechnic Institute Worcester MA USA Department of Biomedical Engineering and the Department of Robotics Engineering Worcester Polytechnic Institute Worcester MA USA

ISBN: (数字)9798350377118

ISBN: (纸本)9798350377125

Image-guidance has been shown to improve spine surgical accuracy and patient outcome. Such image guidance can be achieved by registering low-cost, realtime, and radiation-free intraoperative ultrasound (US) with preoperative computed tomography (CT). Employing robotic US system (RUSS) allows automated acquisition of a wide 3D volume, facilitating efficient and accurate registration with CT. However, the registration between CT and robotic 3D US remains an open problem mainly due to (i) the lack of relevant testbed and dataset, and (ii) the modality discrepancy between CT and US. To address these challenges, we present a custom-built lumbar spine phantom for multimodal imaging with rigidly attached fiducials. The phantom is scanned by CT and in-house RUSS. A novel pointcloud-based registration pipeline is presented to register CT and robotic 3D US data of the spine phantom. Preliminary experiments demonstrate efficient (0.53 ± 0.02 seconds) registration of the lumbar spine with an accuracy of 3.57 mm in terms of fiducial registration error (FRE), which is robust to varying initial alignment of the pointclouds. These results show initial feasibility of adopting the proposed registration pipeline in robotic US guided spine surgery. Future work includes further evaluation of registration performance in ex vivo spine samples with denser US acquisitions to further improve registration accuracy.

关键词： Accuracy Three-dimensional displays Ultrasonic imaging Medical robotics Computed tomography Spine Pipelines

来源：评论

学校读者我要写书评

暂无评论

Renderable Street View Map-Based Localization: Leveraging 3D Gaussian Splatting for Street-Level Positioning

Renderable Street View Map-Based Localization: Leveraging 3D...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Howoong Jun Hyeonwoo Yu Songhwai Oh Artificial Intelligence (IPAI) Seoul National University and Automation and Systems Research Institute (ASRI) and Sequor Robotics Inc. Seoul Korea Republic of Department of Intelligent Robotics & Mechanical Engineering Sungkyunkwan University (SKKU) Suwon-si Korea Republic of Department of Electrical and Computer Engineering (ECE) & Interdisciplinary Program in Artificial Intelligence (IPAI) Seoul National University and Automation and Systems Research Institute (ASRI) and Sequor Robotics Inc. Seoul Korea Republic of

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

In this paper, we introduce a new method that first utilizes 3D Gaussian splatting in street-level localization problem. Robust localization with street-level real-world images such as street view is a major issue for autonomous vehicle, augmented reality (AR) navigation, and outdoor mobile robots. The objective is to determine the position and orientation of a query image that matches a street view database composed of RGB images. However, given the limited information available in the street view images, accurately determining the location solely based on this data presents a significant challenge. To address this challenge, we propose a novel method called renderable street view map-based localization (RSM-Loc). This approach enhances the localization process by augmenting 2D street view images into a renderable 3D map using 3D Gaussian splatting, to resolve street-level localization problems. Upon receiving a query RGB image without geometry information, the proposed method renders 2D images from a pre-made renderable map and compares image pose similarities between the rendered images and the query image. Through iterations of this process, the proposed method eventually estimates the pose of the given query image. The experimental results demonstrate that RSM-Loc outperforms the baselines with neural-field-based localization. Additionally, we conduct deep analysis on the proposed method to show that our method can serve as a new concept for the street-level localization problem.

关键词： Location awareness Visualization Matched filters Three-dimensional displays Image resolution Navigation Noise measurement Mobile robots Intelligent robots Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

A TB-CSP Motor Imagery EEG Recognition Method for Neural-controlled Manipulator System 12

A TB-CSP Motor Imagery EEG Recognition Method for Neural-con...

引用

12th International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2022

作者： Mu, Wei Wang, Pengchao Wang, Junkongshuai Fang, Tao Wang, Aiping Niu, Lan Bin, Jianxiong Liu, Lusheng Zhang, Jing Jia, Jie Zhang, Lihua Kang, Xiaoyang Laboratory for Neural Interface and Brain Computer Interface Engineering Research Center of Ai and Robotics Ministry of Education Shanghai Engineering Research Center of Ai and Robotics Moe Frontiers Center for Brain Science State Key Laboratory of Medical Neurobiology Institute of Ai and Robotics Academy for Engineering and Technology Fudan University Shanghai200433 China Ji Hua Laboratory Guangdong Province Foshan528200 China Department of Rehabilitation Medicine Huashan Hospital Fudan University Shanghai200040 China Yiwu Research Institute of Fudan University Zhejiang Yiwu City322000 China Research Center for Intelligent Sensing Zhejiang Lab Hangzhou311121 China

ISBN: (数字)9781665472678

ISBN: (纸本)9781665472678

To develop a manipulator system based on spontaneous EEG signal control, this paper proposes a common spatial pattern method combined with the Bhattacharyya distance of time-frequency signal (TB-CSP) for EEG signal feature extraction. Firstly, for different subjects, the original EEG signal is divided by a specific time window and different frequency band;Secondly, the average Bhattacharyya distance of different frequency bands in a specific time window is calculated to select the optimal time-frequency signal and input it to CSP for feature extraction;Finally, the extracted features are input into SVM and LDA to classify and complete the control of the manipulator. The proposed method achieves 82.6% accuracy on the public dataset BCI IVa and 79.48% accuracy on the self-collected dataset. © 2022 IEEE.

关键词： Feature extraction

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：