检索结果-内蒙古大学图书馆

ProtoGCD: Unified and Unbiased Prototype Learning for Generalized Category Discovery

IEEE Transactions on Pattern Analysis and Machine intelligence 2025年 PP卷 PP页

作者： Ma, Shijie Zhu, Fei Zhang, Xu-Yao Liu, Cheng-Lin Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Beijing100190 China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100049 China Chinese Academy of Sciences Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science and Innovation Hong Kong999077 Hong Kong

Generalized category discovery (GCD) is a pragmatic but underexplored problem, which requires models to automatically cluster and discover novel categories by leveraging the labeled samples from old classes. The challenge is that unlabeled data contain both old and new classes. Early works leveraging pseudo-labeling with parametric classifiers handle old and new classes separately, which brings about imbalanced accuracy between them. Recent methods employing contrastive learning neglect potential positives and are decoupled from the clustering objective, leading to biased representations and sub-optimal results. To address these issues, we introduce a unified and unbiased prototype learning framework, namely ProtoGCD, wherein old and new classes are modeled with joint prototypes and unified learning objectives, enabling unified modeling between old and new classes. Specifically, we propose a dual-level adaptive pseudo-labeling mechanism to mitigate confirmation bias, together with two regularization terms to collectively help learn more suitable representations for GCD. Moreover, for practical considerations, we devise a criterion to estimate the number of new classes. Furthermore, we extend ProtoGCD to detect unseen outliers, achieving task-level unification. Comprehensive experiments show that ProtoGCD achieves state-of-the-art performance on both generic and fine-grained datasets. ©1979-2012 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Three-Dimensional Trajectory Planning for Quadrotor UAV Based on Simplified PSO Algorithm 3rd

Three-Dimensional Trajectory Planning for Quadrotor UAV Base...

引用

3rd International Conference on Machine Learning, Cloud Computing and Intelligent Mining, MLCCIM 2024

作者： Yin, Ruhui Jiang, Han Shu, Zilin Ren, Ziang Lin, Qinghao Huang, Zixin School of Electrical and Information Engineering Wuhan Institute of Technology Wuhan430205 China Hubei Key Laboratory of Digital Textile Equipment Wuhan Textile University Wuhan430200 China Institute of Robotics and Automatic Information Systems College of Artificial Intelligence Nankai University Tianjin300350 China

ISBN: (纸本)9789819624676

Aiming to address the requirements of Quadrotor Unmanned Aerial Vehicle (QUAV) for conducting mission cruises in three-dimensional complex environments, this paper introduces an optimization algorithm for trajectory planning. By analyzing the motion of the QUAV, the dynamics model is established, along with the constraint model for its flight trajectory. Based on the basic Particle Swarm Optimization (PSO) algorithm, simplified Particle Swarm Optimization (sPSO) removes the particle velocity term from the evolution equation. This adjustment helps prevent slower convergence and lower accuracy in the later stages, which can occur due to the dispersion of particles caused by the particle velocity term. The trajectory is smoothed by using the Minimum Snap principle to ensure that it meets the flight constraints of the QUAV. The simulation results demonstrate that the sPSO algorithm is effective and feasible for application in QUAV three-dimensional trajectory planning. In comparison to the PSO algorithm, the trajectory is more optimal, and the convergence accuracy is higher. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Adversarial Mixup-Based Contrast Learning for Data-Driven Predictive Maintenance in Long-Tailed Recognition

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Peng, Ru Chen, Xingyu Lan, Xuguang National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Application Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University China

Deep neural networks have achieved remarkable success in various computer vision tasks. However, in real-world applications, such as the Internet of Things (IoT), these models often struggle due to the long-tailed data distributions. For instance, in scenarios such as Holographic Counterpart Integration in IoT-based predictive maintenance for home systems or smart repair services, common operational states are prevalent in the dataset. In contrast, rare failures, such as hardware malfunctions or system breakdowns, are represented by only a few samples. This imbalance severely impacts models, making it difficult to accurately predict rare failures, leading to costly downtime or unanticipated equipment failure. Current contrastive learning-based methods are effective at optimizing feature distributions but often overlook inter-class relationships and are highly sensitive to class imbalance, which limits their generalization ability. To address these challenges, we propose the Adversarial Mixup-based supervised contrast learning (AMCL) framework, which integrates Mixup-based data augmentation with contrastive learning and incorporates an adversarial-inspired sample policy generator. AMCL generates boundary samples via a dynamically optimized Mixup strategy to enhance inter-class relationship modeling and improve predictions on ambiguous boundaries. Furthermore, we introduce a new MixCo loss function to account for the non-one-hot distribution of Mixup-generated targets, ensuring better alignment with augmented data and improving optimization efficiency. AMCL is easy to implement and achieves a performance superior to recent approaches for long-tailed recognition across various datasets such as ImageNet-LT, iNaturalist18, CIFAR-10-LT, and CIFAR-100-LT. © 1975-2011 IEEE.

关键词： Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

Epipolar Attention Field Transformers for Bird's Eye View Semantic Segmentation

Epipolar Attention Field Transformers for Bird's Eye View Se...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Christian Witte Jens Behley Cyrill Stachniss Marvin Raaijmakers CARIAD SE Germany Center for Robotics University of Bonn Germany Lamarr Institute for Machine Learning and Artificial Intelligence Germany

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Spatial understanding of the semantics of the surroundings is a key capability needed by autonomous cars to enable safe driving decisions. Recently, purely vision-based solutions have gained increasing research interest. In particular, approaches extracting a bird's eye view (BEV) from multiple cameras have demonstrated great performance for spatial understanding. This paper addresses the dependency on learned positional encodings to correlate image and BEV feature map elements for transformer-based methods. We propose leveraging epipolar geometric constraints to model the relationship between cameras and the BEV by Epipolar Attention Fields. They are incorporated into the attention mechanism as a novel attribution term, serving as an alternative to learned positional encodings. Experiments show that our method EAFormer outperforms previous BEV approaches by 2% mIoU for map semantic segmentation and exhibits superior generalization capabilities compared to implicitly learning the camera configuration.

关键词： Computer vision Image coding Attention mechanisms Semantic segmentation Semantics Cameras Transformers Feature extraction Encoding Automobiles

来源：评论

学校读者我要写书评

暂无评论

SICNav-Diffusion: Safe and Interactive Crowd Navigation with Diffusion Trajectory Predictions

arXiv

引用

arXiv 2025年

作者： Samavi, Sepehr Lem, Anthony Sato, Fumiaki Chen, Sirui Gu, Qiao Yano, Keijiro Schoellig, Angela P. Shkurti, Florian University of Toronto Robotics Institute Vector Institute for Artificial Intelligence Toronto Canada Munich Germany Konica Minolta Inc. Japan

To navigate crowds without collisions, robots must interact with humans by forecasting their future motion and reacting accordingly. While learning-based prediction models have shown success in generating likely human trajectory predictions, integrating these stochastic models into a robot controller presents several challenges. The controller needs to account for interactive coupling between planned robot motion and human predictions while ensuring both predictions and robot actions are safe (i.e. collision-free). To address these challenges, we present a receding horizon crowd navigation method for single-robot multi-human environments. We first propose a diffusion model to generate joint trajectory predictions for all humans in the scene. We then incorporate these multi-modal predictions into a SICNav Bilevel MPC problem that simultaneously solves for a robot plan (upper-level) and acts as a safety filter to refine the predictions for non-collision (lower-level). Combining planning and prediction refinement into one bilevel problem ensures that the robot plan and human predictions are coupled. We validate the open-loop trajectory prediction performance of our diffusion model on the commonly used ETH/UCY benchmark and evaluate the closed-loop performance of our robot navigation method in simulation and extensive real-robot experiments demonstrating safe, efficient, and reactive robot motion. Copyright © 2025, The Authors. All rights reserved.

关键词： Stochastic models

来源：评论

学校读者我要写书评

暂无评论

Invariance and Contraction in Geometrically Periodic Systems with Differential Inclusions

引用

IEEE Transactions on Automatic Control 2025年

作者： Qian, Chen Fang, Yongchun Research Center for Intelligent Robotics Zhejiang Lab Research Institute of Interdisciplinary Innovation Hangzhou311100 China College of Artificial Intelligence Institute of Robotics and Automatic Information Systems China Nankai University Tianjin Key Laboratory of Intelligent Robotics Tianjin300353 China

The objective of this paper is to derive the essential invariance and contraction properties for the geometric periodic systems, which can be formulated as a category of differential inclusions, and primarily rendered in the phase coordinate, or the cycle coordinate. First, we introduce the geometric averaging method for this category of systems, and also analyze the accuracy of its averaging approximation. Specifically, we delve into the details of the geometrically periodic system through the tunnel of considering the convergence between the system and its geometrically averaging approximation. Under different corresponding conditions, the approximation on infinite time intervals can achieve certain accuracies, such that one can use the stability result of either the original system or the averaging system to deduce the stability of the other. After that, we employ the graphical stability to investigate the "pattern stability"with respect to the phase-based system. Finally, by virtue of the contraction analysis on the Finsler manifold, the idea of accentuating the periodic pattern incremental stability and convergence is nurtured in the phase-based differential inclusion system, and comes to its preliminary fruition in application to biomimetic mechanic robot control problem. © 1963-2012 IEEE.

关键词： System stability

来源：评论

学校读者我要写书评

暂无评论

A Socially Mediating Robot to Assist Non-Verbal Children in an Inclusive Daycare Context 25

A Socially Mediating Robot to Assist Non-Verbal Children in ...

引用

ACM/IEEE International Conference on Human-Robot Interaction (HRI)

作者： Jan Ole Rixen Rafik Abdalla Victoria Coralie Kuch Nadja Scherer Barbara Bruno Kathrin Gerling HCI and Accessibility Karlsruhe Institute of Technology Karlsruhe Germany Socially Assistive Robotics with Artificial Intelligence Karlsruhe Institute of Technology Karlsruhe Germany

ISBN: (数字)9798350378931

ISBN: (纸本)9798350378948

Non-verbal children are often provided with non-verbal communication cards (NVCCs) to share their needs. However, in busy spaces that prioritize verbal communication, for example, a daycare, this may place them at a disadvantage in comparison with verbal peers. In this work, we introduce the concept of a Socially Mediating Robot (SMR), acting as a communicational intermediary that verbalizes NVCC input. Thereby, we want to explore whether non-verbal children can be empowered by giving them an additional way of expressing themselves in a dynamic, buzzing environment. In an exploratory interview study with six participants professionally working with children, we then provide first insights on the feasibility of our concept from the perspective of caregiving staff. Thereby, we lay the groundwork for evaluating the concept in an ongoing field study in an inclusive daycare context.

关键词： Human-robot interaction Assistive robots Interviews Robots

来源：评论

学校读者我要写书评

暂无评论

Fabrication of Sensorsless Automated Guided Vehicle for Small Warehouse Rack Management

Fabrication of Sensorsless Automated Guided Vehicle for Smal...

引用

2025 IEEE International Conference on Computational, Communication and Information Technology, ICCCIT 2025

作者： Sahu, Neelesh Kumar Chaturvedi, Piyush Gupta, Vaishali Patel, Ruchi Verma, Ashok Shrivastava, Megha Gyan Ganga Institute of Technology and Sciences Artificial Intelligence and Robotics MP Jabalpur India IPS Academy Institute of Engineering & Science Department of Computer Sc. & Engg. MP Indore India Gyan Ganga Institute of Technology and Sciences MP Jabalpur India Medicaps University Department of Mathematics MP Indore India

ISBN: (纸本)9798331512965

Automated guided vehicles (AGVs) are an essential part of today's logistics networks because they save time, reduce wear and maintenance expenses, and maximize efficiency in route *** creation of AGVthat is capable of effectively managing warehouse racks without the utilization of sensors is the primary emphasis of this project. In order to travel and carry out duties, the AGVruns on predetermined pathways and makes use of a button-based interface. For the purpose of offering an efficient and costeffective solution for the automation of small warehouses, it is outfitted with a lever mechanism that is operated by a servo motor and features the ability to connect and move racks. © 2025 IEEE.

关键词： Automatic guided vehicles

来源：评论

学校读者我要写书评

暂无评论

PM_(2.5) probabilistic forecasting system based on graph generative network with graph U-nets architecture

引用

Journal of Central South University 2025年第1期32卷 304-318页

作者： LI Yan-fei YANG Rui DUAN Zhu LIU Hui School of Mechatronic Engineering Hunan Agricultural UniversityChangsha 410128China Institute of Artificial Intelligence and Robotics(IAIR) Key Laboratory of Traffic Safety on Track of Ministry of EducationSchool of Traffic and Transportation EngineeringCentral South UniversityChangsha 410075China

Urban air pollution has brought great troubles to physical and mental health,economic development,environmental protection,and other *** the changes and trends of air pollution can provide a scientific basis for governance and prevention *** this paper,we propose an interval prediction method that considers the spatio-temporal characteristic information of PM_(2.5)signals from multiple stations.K-nearest neighbor(KNN)algorithm interpolates the lost signals in the process of collection,transmission,and storage to ensure the continuity of *** generative network(GGN)is used to process time-series meteorological data with complex *** graph U-Nets framework is introduced into the GGN model to enhance its controllability to the graph generation process,which is beneficial to improve the efficiency and robustness of the *** addition,sparse Bayesian regression is incorporated to improve the dimensional disaster defect of traditional kernel density estimation(KDE)interval *** the support of sparse strategy,sparse Bayesian regression kernel density estimation(SBR-KDE)is very efficient in processing high-dimensional large-scale *** PM_(2.5)data of spring,summer,autumn,and winter from 34 air quality monitoring sites in Beijing verified the accuracy,generalization,and superiority of the proposed model in interval prediction.

关键词： PM_(2.5)interval forecasting graph generative network graph U-Nets sparse Bayesian regression kernel density estimation spatial-temporal characteristics

来源：评论

学校读者我要写书评

暂无评论

RINGO: Real-time Navigation with a Guiding Trajectory for Aerial Manipulators in Unknown Environments

arXiv

引用

arXiv 2025年

作者： Zhang, Zhaopeng Wu, Shizhen Guo, Chenfeng Fang, Yongchun Han, Jianda Liang, Xiao Institute of Robotics and Automatic Information System College of Artificial Intelligence Tianjin Key Laboratory of Intelligent Robotics Nankai University Tianjin300350 China Institute of Intelligence Technology and Robotic Systems Shenzhen Research Institute of Nankai University Shenzhen518083 China

Motion planning for aerial manipulators in constrained environments has typically been limited to known environments or simplified to that of multi-rotors, which leads to poor adaptability and overly conservative trajectories. This paper presents RINGO: Real-time Navigation with a Guiding Trajectory, a novel planning framework that enables aerial manipulators to navigate unknown environments in real time. The proposed method simultaneously considers the positions of both the multi-rotor and the end-effector. A pre-obtained multi-rotor trajectory serves as a guiding reference, allowing the end-effector to generate a smooth, collision-free, and workspace-compatible trajectory. Leveraging the convex hull property of B-spline curves, we theoretically guarantee that the trajectory remains within the reachable workspace. To the best of our knowledge, this is the first work that enables real-time navigation of aerial manipulators in unknown environments. The simulation and experimental results show the effectiveness of the proposed method. The proposed method generates less conservative trajectories than approaches that consider only the multi-rotor. © 2025, CC BY.

关键词： Manipulators

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：