检索结果-内蒙古大学图书馆

2024 China Automation Congress, CAC 2024

作者： Luo, Xiangyong Dang, Lujuan Yang, Meng Chen, Badong 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 Xi’an710049 China

ISBN: (纸本)9798350368604

Accurate state of charge (SOC) estimation of lithium-ion battery in battery management system (BMS) is important for the safety and reliability of electronic devices and electric vehicles. This paper proposes a LSTM-extended Kalman filter based on AhI-model (LSTM-EA), which constrains SOC result from LSTM with an AhI-model based Kalman filter. AhI-model is based on Ampere-hour integration method and requires simpler structure to obtain estimated SOC with higher accuracy and robustness. In the experiments, the public datasets from the Center for Advanced Life Cycle Engineering (CALCE) are used to validate the SOC estimation performance. The mean absolute error (MAE) and maximum error of the proposed method are less than 2.51% and 8.82% respectively. © 2024 IEEE.

关键词： State of charge

来源：评论

学校读者我要写书评

暂无评论

Pedestrian Attribute Recognition Using Hierarchical Transformers 27th

Pedestrian Attribute Recognition Using Hierarchical Transfor...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Lohani, Lalit Thakare, Kamalakar Vijay Nayak, Kamakshya Prasad Dogra, Debi Prosad Choi, Heeseung Jung, Hyungjoo Kim, Ig-Jae Bhubaneswar752050 India Artificial Intelligence and Robotics Institute Korea Institute of Science and Technology Seoul02792 Korea Republic of Yonsei-KIST Convergence Research Institute Yonsei University Seoul03722 Korea Republic of

ISBN: (纸本)9783031784439

The goal of pedestrian attribute recognition (PAR) is to detect and classify a wide range of pedestrian attributes, such as gender, carrying objects, clothing styles, body postures, age groups, and more. It plays a vital role in computer vision, specifically in crucial applications such as behaviour analysis, public safety monitoring, and video surveillance. However, existing PAR approaches are unable to achieve substantial performance due to multiple factors. First, multiple appearances of the same attribute confuse the models. Second, adverse weather and lighting conditions restrict model generalization capability. To mitigate these challenges, this paper proposes a new evaluation baseline that uses Vision Transformer (ViT) blocks for hierarchical feature modelling. The approach categorizes attributes into different spatial granularity levels and employs diverse patch formations to extract discriminative features. Furthermore, we introduce an enhanced loss function for stable training in the re-formulated granularity scenario, where a novel attribute-aware granularity factor influences the loss. The proposed baseline has been extensively evaluated on the three popular PAR datasets, namely RAP, PA100K and PETA. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Pedestrian safety

来源：评论

学校读者我要写书评

暂无评论

General Planning Method for Humanoid Collaborative Robots using Large Language Models

General Planning Method for Humanoid Collaborative Robots us...

引用

2024 China Automation Congress, CAC 2024

作者： Gao, Runqin Shi, Jiamin Tian, Shu Chen, Shitao 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 Xi’an710049 China

ISBN: (纸本)9798350368604

Humanoid robots, capable of simulating human behavior and decision-making, have garnered extensive attention due to their anthropomorphic structures and versatile functional designs. Traditionally, actions and high-level decision-making in robots have been manually achieved by developers, requiring modifications and adaptations for different task requirements, thus lacking autonomous decision-making capabilities. With the rapid advancement of deep learning technologies, large language models trained on internet data have provided new solutions for robot intelligence, demonstrating effective applications in high-level task planning for robots. Based on this, we propose a general high-level task planning method using large language models, implemented on a mobile single-arm humanoid robot as the platform. This method consists of two core components: high-level decision planning and low-level action execution, coupled through the robot’s atomic action interface. The robot autonomously completes sequential action planning by receiving natural language task instructions and executes long-term, complex, general indoor collaborative tasks. By deploying on a real robot, we conducted sub-module tests and overall system performance tests, successfully achieving the process of sorting and organizing tasks in an indoor experimental environment. © 2024 IEEE.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

Multi-grained Correspondence Learning of Audio-language Models for Few-shot Audio Recognition 24

Multi-grained Correspondence Learning of Audio-language Mode...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Zhao, Shengwei Xu, Linhai Liu, Yuying Du, Shaoyi 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 Shaanxi Xi'an China

ISBN: (纸本)9798400706868

Large-scale pre-trained audio-language models excel in general multi-modal representation, facilitating their adaptation to downstream audio recognition tasks in a data-efficient manner. However, existing few-shot audio recognition methods based on audio-language models primarily focus on learning coarse-grained correlations, which are not sufficient to capture the intricate matching patterns between the multi-level information of audio and the diverse characteristics of category concepts. To address this gap, we propose multi-grained correspondence learning for bootstrapping audio-language models to improve audio recognition with few training samples. This approach leverages generative models to enrich multi-modal representation learning, mining the multi-level information of audio alongside the diverse characteristics of category concepts. Multi-grained matching patterns are then established through multi-grained key-value cache and multi-grained cross-modal contrast, enhancing the alignment between audio and category concepts. Additionally, we incorporate optimal transport to tackle temporal misalignment and semantic intersection issues in fine-grained correspondence learning, enabling flexible fine-grained matching. Our method achieves state-of-the-art results on multiple benchmark datasets for few-shot audio recognition, with comprehensive ablation experiments validating its effectiveness. © 2024 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Population-based Multi-agent Evaluation for Large-scale Voltage Control

Population-based Multi-agent Evaluation for Large-scale Volt...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Jin, Cheng Zhang, Senlin Liu, Meiqin Zheng, Ronghao Dong, Shanling College of Electrical Engineering Zhejiang University Hangzhou China Institute of Artificial Intelligence and Robotics Xi 'An Jiaotong University Xi'an China

ISBN: (纸本)9798350337020

Under the purpose of achieving the optimal voltage control strategy in power grid system, multi-agent evaluation algorithms like a-rank are widely used. However, in large-scale systems with massive agents and strategies, these methods are not time feasible. Therefore, a two-stage population-based multi-agent evaluation algorithm is proposed to solve voltage control problem in large-scale power grid systems. For stage one, a population is first established for each agent. And then, individuals in the populations randomly combined to form joint strategies. Base on the max and mean reward from the interaction between joint strategies and the environment, populations evolve to a near-optimal joint strategy. Stage two takes the above near-optimal joint strategy as the starting point, and uses a strategy search algorithm with maximum transfer possibility to find the Markov-Conley chain in the system. Finally, the above two-stage method is simulated in 10 and 32-agent power grid systems to verify the effectiveness. © 2023 IEEE.

关键词： a-rank Markov-Conley chain multi-agent evaluation population evolution voltage control

来源：评论

学校读者我要写书评

暂无评论

KernelDNA: Dynamic Kernel Sharing via Decoupled Naive Adapters

arXiv

引用

arXiv 2025年

作者： Huang, Haiduo Zhang, Yadong Ren, Pengju Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University China

Dynamic convolution enhances model capacity by adaptively combining multiple kernels, yet faces critical tradeoffs: prior works either (1) incur significant parameter overhead by scaling kernel numbers linearly, (2) compromise inference speed through complex kernel interactions, or (3) struggle to jointly optimize dynamic attention and static kernels. We also observe that pre-trained Convolutional Neural Networks (CNNs) exhibit inter-layer redundancy akin to that in Large Language Models (LLMs). Specifically, dense convolutional layers can be efficiently replaced by derived "child" layers generated from a shared "parent" convolutional kernel through an adapter. To address these limitations and implement the weight-sharing mechanism, we propose a lightweight convolution kernel plug-in, named KernelDNA. It decouples kernel adaptation into input-dependent dynamic routing and pre-trained static modulation, ensuring both parameter efficiency and hardware-friendly inference. Unlike existing dynamic convolutions that expand parameters via multikernel ensembles, our method leverages cross-layer weight sharing and adapter-based modulation, enabling dynamic kernel specialization without altering the standard convolution structure. This design preserves the native computational efficiency of standard convolutions while enhancing representation power through input-adaptive kernel adjustments. Experiments on image classification and dense prediction tasks demonstrate that KernelDNA achieves state-ofthe-art accuracy-efficiency balance among dynamic convolution variants. Our codes are available at https://***/haiduo/KernelDNA 1 Copyright © 2025, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

REGNav: Room Expert Guided Image-Goal Navigation

arXiv

引用

arXiv 2025年

作者： Li, Pengna Wu, Kangyi Fu, Jingwen Zhou, Sanping Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University China

Image-goal navigation aims to steer an agent towards the goal location specified by an image. Most prior methods tackle this task by learning a navigation policy, which extracts visual features of goal and observation images, compares their similarity and predicts actions. However, if the agent is in a different room from the goal image, it’s extremely challenging to identify their similarity and infer the likely goal location, which may result in the agent wandering around. Intuitively, when humans carry out this task, they may roughly compare the current observation with the goal image, having an approximate concept of whether they are in the same room before executing the actions. Inspired by this intuition, we try to imitate human behaviour and propose a Room Expert Guided Image-Goal Navigation model (REGNav) to equip the agent with the ability to analyze whether goal and observation images are taken in the same room. Specifically, we first pre-train a room expert with an unsupervised learning technique on the self-collected unlabelled room images. The expert can extract the hidden room style information of goal and observation images and predict their relationship about whether they belong to the same room. In addition, two different fusion approaches are explored to efficiently guide the agent navigation with the room relation knowledge. Extensive experiments show that our REGNav surpasses prior state-of-the-art works on three popular benchmarks. Copyright © 2025, The Authors. All rights reserved.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Railway switch fault diagnosis based on Multi-heads Channel Self Attention,Residual Connection and Deep CNN

引用

Transportation Safety and Environment 2023年第1期5卷 58-65页

作者： Xirui Chen Hui Liu Zhu Duan Institute of Artificial Intelligence&Robotics(IAIR) Key Laboratory of Traffic Safety on Track of Ministry of EducationSchool of Traffic and Transportation EngineeringCentral South UniversityChangsha 410075HunanChina.

A novel switch diagnosis method based on self-attention and residual deep convolutional neural networks(CNNs)is *** of the imbalanced dataset,the K-means synthetic minority oversampling technique(SMOTE)is applied to balancing the dataset at ***,the deep CNN is utilized to extract local features from long power curves,and the residual connection is performed to handle the performance *** the end,the multi-heads channel self attention focuses on those important local *** ablation and comparison experiments are applied to verifying the effectiveness of the proposed *** the residual connection and multi-heads channel self attention,the proposed method has achieved an impressive accuracy of 99.83%.The t-SNE based visualizations for features of the middle layers enhance the trustworthiness.

关键词： fault diagnosis railway switch residual connection channel self-attention deep convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Optimizing Pricing and Charging Strategy for Electric Taxis Considering Credit Mechanism 14

Optimizing Pricing and Charging Strategy for Electric Taxis ...

引用

14th IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids, SmartGridComm 2023

作者： Zhang, Jiwei Sun, Chenxi Tang, Xiaoying The Chinese University of HongKong School of Science and Engineering Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

ISBN: (纸本)9781665455541

With the promotion of low-carbon travel concepts, research in the field of electric vehicles has been continuously emerging in recent years. However, as an important participant in new energy transportation, electric taxis currently lack targeted research. This article proposes an optimization system which determines the optimal price for each charging stations (CS) and help electric taxi (ET) drivers choose the most beneficial charging stations, thereby maximizing overall utility for both CSs and ETs. The system is combined with a credit mechanism to regulate the behavior of both charging stations and drivers. To address the optimization problem, we propose a bi-level approach using particle swarm optimization (PSO). We also provide a detailed description of the credit system, along with supporting reward and punishment mechanisms. In the experimental section, we conduct a comparative experiment to validate the advantages of the pricing optimization system using PSO. Furthermore, we demonstrate the impact of applying the credit mechanism on both CSs and ETs. © 2023 IEEE.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

A Game Approach for EV Brands' Investment Planning of Battery Swapping Stations

A Game Approach for EV Brands' Investment Planning of Batter...

引用

2022 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids, SmartGridComm 2022

作者： Ren, Heyu Sun, Chenxi Tang, Xiaoying Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

ISBN: (数字)9781665432542

ISBN: (纸本)9781665432542

In the current market of energy supply for electric vehicles (EVs), charging stations (CSs) have a definitely high market share, while the battery swapping stations (BSSs) are rapidly developed in recent years due to their potential to save users' waiting time by replacing a depleted battery with a fully-charged one. In order to assess the benefits of battery swapping, an economic model is needed to analyze the market, and different EV brands need to determine the optimal investment plans of BSSs in order to maximize their individual revenues. This paper proposes a Stackelberg game to characterize the interactions between different EV brands, CSs, BSSs, and EV consumers. By analyzing the Nash Equilibrium of the Stackelberg game, a pricing scheme for BSSs is proposed and EV brands' specific profit model from BSSs is formulated to analyze the optimal investment plan of BSSs. Experimental results show that our model and strategy improve EV brands' profits, especially for brands with moderate battery capacity, moderate car price and large sales volume. © 2022 IEEE.

关键词： Game theory

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：