检索结果-内蒙古大学图书馆

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

作者： Hui Chen Yanbin Liu Yongqiang Ma Nanning Zheng Xin Yu National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center of Visual Information and Applications and Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Auckland University of Technology The University of Queensland

ISBN: (纸本)9798331314385

Pre-trained vision-language models (VLMs) such as CLIP have shown excellent performance for zero-shot classification. Based on CLIP, recent methods design various learnable prompts to evaluate the zero-shot generalization capability on a base-to-novel setting. This setting assumes test samples are already divided into either base or novel classes, limiting its application to realistic scenarios. In this paper, we focus on a more challenging and practical setting: generalized zero-shot learning (GZSL), i.e., testing with no information about the base/novel division. To address this challenging zero-shot problem, we introduce two unique designs that enable us to classify an image without the need of knowing whether it comes from seen or unseen classes. Firstly, most existing methods only adopt a single latent space to align visual and linguistic features, which has a limited ability to represent complex visual-linguistic patterns, especially for fine-grained tasks. Instead, we propose a dual-space feature alignment module that effectively augments the latent space with a novel attribute space induced by a well-devised attribute reservoir. In particular, the attribute reservoir consists of a static vocabulary and learnable tokens complementing each other for flexible control over feature granularity. Secondly, finetuning CLIP models (e.g., prompt learning) on seen base classes usually sacrifices the model's original generalization capability on unseen novel classes. To mitigate this issue, we present a new topology-preserving objective that can enforce feature topology structures of the combined base and novel classes to resemble the topology of CLIP. In this manner, our model will inherit the generalization ability of CLIP through maintaining the pairwise class angles in the attribute space. Extensive experiments on twelve object recognition datasets demonstrate that our model, termed Topology-Preserving Reservoir (TPR), outperforms strong baselines including both pro

关键词：

来源：评论

学校读者我要写书评

暂无评论

Anti-Disturbance Path Following of Unmanned Surface Vehicles Based on Fuzzy Active Disturbance Rejection Control 5

Anti-Disturbance Path Following of Unmanned Surface Vehicles...

引用

5th International Conference on Intelligent Autonomous Systems, ICoIAS 2022

作者： Ma, Chuang Wang, Wei Er, Meng Joo Gong, Huibin Institute of Artificial Intelligence and Marine Robotics College of Marine Electrical Engineering Dalian Maritime University Dalian China College of Intelligent Systems Science Engineering Harbin Engineering University Harbin China

ISBN: (数字)9781665498388

ISBN: (纸本)9781665498388

With the view of achieving path following of unmanned surface vehicles (USVs) in a complex marine environment, a novel path following algorithm based on fuzzy active disturbance rejection control (FADRC) is proposed. Firstly, an improved LOS (IMLOS) guidance law is designed deal with influences of sideslip angle on path following so as to improve robustness of the guidance system. Secondly, to circumvent the problem that the traditional ADRC method cannot automatically adjust system parameters, a FADRC controller which can realize disturbance compensation without accurate model parameters is designed. FADRC can estimate and eliminate internal and external disturbances. The IMLOS and FADRC are integrated to form a composite path following controller. The simulation results demonstrate that the proposed FADRC. © 2022 IEEE.

关键词： Unmanned surface vehicles

来源：评论

学校读者我要写书评

暂无评论

Online Triangular Constraint Calibration for LiDAR and Cameras in Open-Pit Mines

IEEE Transactions on Field Robotics

引用

IEEE Transactions on Field robotics 2024年 2卷 131-146页

作者： Yuchen Li Luxi Li Siyu Teng Zhenshan Bing Alois Christian Knoll Zhe Xuanyuan Long Chen Guangdong Provincial/Zhuhai Key Laboratory of IRADS BNU-HKBU United International College Zhuhai China Faculty of Science Hong Kong Baptist University Hong Kong SAR China Research and Development Center WAYTOUS Inc. Beijing China Department of Information Technische Universität München Munich Germany State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an China Department of Artificial Intelligence Guangdong Laboratory of Artificial Intelligence and Digital Economy Shenzhen China

Extrinsic calibration between a LiDAR and a camera is a crucial task for intelligent vehicles and mobile robots. However, most of the current extrinsic calibration methods are offline and target-based, making it hard to achieve real-time calibration depending on the characteristics of the environments. Although a few online calibration strategies can solve the above drawbacks, they still rely on a large amount of labeled data and struggle to achieve satisfactory performance in extrinsic calibration in unstructured scenarios where valid targets are scarce. In this work, we propose an effective online calibration strategy for mining scenarios, one of the typical unstructured scenarios. Based on the analysis of mining area data, we adopt an approach that integrates image and point cloud segmentation to accomplish the entire calibration process. An initialization method supporting a single rigid target is proposed, effectively addressing the initialization failure caused by the scarcity of targets in mining areas. Incorporating the segmentation results from the right camera to establish a left-right camera-LiDAR triangular constraint effectively reduces translation errors. Temporal data with confidence scores are then used to update and optimize the extrinsic parameters. Our online extrinsic calibration method has been validated on mining scenarios data and has achieved less than 0.2 m in data collected from an SUV and 0.3 m from trucks in translation errors within 10 frames. Besides, we provide a detailed discussion on the challenges of calibration in mining areas and the limitations of the proposed method.

关键词： Calibration Image segmentation Cameras Sensors Point cloud compression Laser radar Translation Image edge detection Accuracy Mining industry

来源：评论

学校读者我要写书评

暂无评论

DG-NBV: A Cognitive Framework for Direct Generation of Next Best View in Continuous View Space

引用

IEEE Transactions on Cognitive and Developmental Systems 2024年

作者： Liu, Zhicheng Cao, Zhiqiang Li, Jianjie Guan, Peiyu Yu, Junzhi 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 Peking University Department of Advanced Manufacturing and Robotics BIC-ESAT College of Engineering Beijing100871 China

The next best view (NBV) plays an important role in the three-dimensional object reconstruction. Existing NBV methods mainly adopt the generate-and-test strategy to select the best view in the discrete view space. This affects the adaptation to diverse objects. To solve this problem, a new NBV paradigm to directly generate the next best view in the continuous view space according to the input point cloud is proposed. Specifically, a point cloud feature extraction module with learnable view and position tokens is presented. These tokens are added upon the neighborhood and the position features of the point cloud to fully mine global contextual information, enhancing the feature representation. The predicted view from the proposed network is linked to a pre-trained view evaluation network. By duplicating this prediction view and then concatenating the duplication result with the extracted point cloud feature, the evaluation network is endowed with the ability to evaluate arbitrary views. Take the evaluation score of the evaluation network corresponding to the predicted view as the supervision signal, the network is trained. In this way, an effective solution of the next best view selection in the continuous view space is obtained. Accordingly, the adaptability to different objects is reinforced. Experimental results on the ShapeNet and MIT CSAIL datasets demonstrate the effectiveness of the proposed method. © 2024 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Grounded Answers for Multi-agent Decision-making Problem through Generative World Model

arXiv

引用

arXiv 2024年

作者： Liu, Zeyang Yang, Xinrui Sun, Shiguang Qian, Long Wan, Lipeng 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 Xi’an710049 China

Recent progress in generative models has stimulated significant innovations in many fields, such as image generation and chatbots. Despite their success, these models often produce sketchy and misleading solutions for complex multi-agent decision-making problems because they miss the trial-and-error experience and reasoning as humans. To address this limitation, we explore a paradigm that integrates a language-guided simulator into the multi-agent reinforcement learning pipeline to enhance the generated answer. The simulator is a world model that separately learns dynamics and reward, where the dynamics model comprises an image tokenizer as well as a causal transformer to generate interaction transitions autoregressively, and the reward model is a bidirectional transformer learned by maximizing the likelihood of trajectories in the expert demonstrations under language guidance. Given an image of the current state and the task description, we use the world model to train the joint policy and produce the image sequence as the answer by running the converged policy on the dynamics model. The empirical results demonstrate that this framework can improve the answers for multi-agent decision-making problems by showing superior performance on the training and unseen tasks of the StarCraft Multi-Agent Challenge benchmark. In particular, it can generate consistent interaction sequences and explainable reward functions at interaction states, opening the path for training generative models of the future. © 2024, CC BY.

关键词： Chatbots

来源：评论

学校读者我要写书评

暂无评论

Optimizing Medication Compliance through Machine Learning and IoT for Personalized Health Management 9

Optimizing Medication Compliance through Machine Learning an...

引用

9th International Conference on Communication and Electronics Systems, ICCES 2024

作者： Balaji, P. Mohitha, I.K. Prashanthini, K. Sivaprakash, K. Rithick, P. Kasthuri, S. Sri Ramakrishna Engineering College Department of Electronics and Instrumentation Engineering Coimbatore India KGiSL Institute of Technology Department of Electronics and Communication Engineering Coimbatore India Sri Ramakrishna Engineering College Department of Robotics and Automation Engineering Coimbatore India Sns College of Engineering Department of Artificial Intelligence and Data Science Coimbatore India

ISBN: (纸本)9798350377972

Machine learning (ML) and Internet of Things (IoT) technologies have revolutionized the healthcare industry, particularly in the field of medication administration. Inadequate adherence to medication is a serious worldwide issue that can result in poor health and higher medical expenses. Through continuous monitoring and analysis of patient-specific parameters, such as vital signs, medication history, and lifestyle factors, the system dynamically adjusts medication schedules and dosages to optimize therapeutic efficacy while minimizing adverse effects. The system tracks medicine usage, vital signs, and ambient variables using data gathered from Internet of Things (IoT) devices like wearable devices and smart pill bottles. An ML model, trained to anticipate potential adherence problems, is then provided with this preprocessed data. Personalized interventions, like medicine reminders, educational content, and progress reports, are delivered by the Intelligent Medication Compliance System (IMAC) based on these predictions. The integration of IoT-enabled smart sensors and connectivity allows for smooth communication between patients, healthcare professionals, and medicine dispensers, permitting prompt interventions, prescription reminders, and remote monitoring. Additionally, the system makes it easier for patients and medical professionals to communicate, allowing for prompt modifications to treatment programs. Serving as an anticipatory system, the IMAC provides personalized interventions. Predicting possible adherence problems, such as missing doses or inadvertent drug interactions, is done by the model through data analysis. The proposed IMAS seeks to empower patients, personalized medication management, and eventually improve medication adherence by fusing real-time IoT data with ML-driven insights. © 2024 IEEE.

关键词： Personalized medicine

来源：评论

学校读者我要写书评

暂无评论

Behavior Management Method of Social Service Robot based on Needs and Actuator Weight

Behavior Management Method of Social Service Robot based on ...

引用

第34届中国控制与决策会议

作者： Zhongyu Wang Wei Wang Jiadong Zhang Diansheng Chen Xiaochuan Zhang School of Artificial Intelligence Chongqing University of Technology Robotics Institute Beihang University

Aim at present service robots are difficult to deal with the interaction intention of multiple interaction objects,with low efficiency and lack of flexibility,and their behaviors cannot be recovered after being interrupted,a robot behavior management model is designed to schedule multiple candidate behaviors,to ensure that the most needed behaviors are performed effectively,and the suspended behaviors can be continued to be completed,so as to solve the problems of concurrency and conflict of multi-interaction objects' social *** two simulation experiments are designed to validate the *** results show that the method can be used to insert and concurrent reasonable behaviors of the social service robot.

关键词： Social service robot Behavior management Behavior insertion Behavior concurrency ROS

来源：评论

学校读者我要写书评

暂无评论

Development of a Miniaturized Bedside Robotic Wrist with Multifunctional Movement Capabilities: An Analysis Based on a Simulation Environment

Development of a Miniaturized Bedside Robotic Wrist with Mul...

引用

Digital Twins and Parallel intelligence (DTPI), IEEE International Conference on

作者： Pengcheng Zhang Zhaokun Deng Xilong Hou Shuangyi Wang State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences Hong Kong China

Bedside robots equipped with medical devices can be effective in assisting physicians to perform specific medical tasks on mobile medical vehicles via remote operation. However, the major challenges are to make the robot small and dexterous enough to meet the clinical requirements and fit into the small space of the mobile medical vehicle. In this paper, we propose a miniaturized bedside robotic wrist based on a 6-RSU parallel mechanism with multifunctional motion capabilities. The robotic wrist can be equipped with various medical instruments, including but not limited to ultrasound probes, biopsy needles and endoscopes. To meet different clinical needs, the motion mode of the robotic wrist can be switched between decoupled and remote center of motion. To verify the effectiveness of the design, the kinematic model of the robotic wrist for two motion modes was established and different simulation studies were performed. The experimental results show that the robotic wrist has a favorable working performance to be deployed onto mobile medical vehicles, demonstrating its promising application prospects.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Transforming Classification with Federated Learning on Blockchain: A Unique Model Integration Approach

Transforming Classification with Federated Learning on Block...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zhihao Hao Bob Zhang Haisheng Li School of Computer Science and Artificial Intelligence Beijing Technology and Business University Beijing China Dept. of Computer and Information Science Faculty of Science and Technology University of Macau Taipa Macau Centre for Artificial Intelligence and Robotics Institute of Collaborative Innovation University of Macau Taipa Macau

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The need for robust machine learning models is particularly evident in the realm of biological pattern recognition. Traditional centralized methods often struggle, as they frequently depend on large datasets that are challenging to gather due to stringent data privacy regulations. To address these limitations while maintaining classification accuracy, we propose an innovative approach that unifies models with diverse architectures within a federated learning framework built on a blockchain network. This decentralized and trustworthy system fosters effective collaboration among various models. Furthermore, we have implemented a weight distribution mechanism designed to maximize the individual strengths of each model. By leveraging blockchains inherent transparency and auditability, this approach also ensures secure and traceable data exchanges among participants. Additionally, the adaptability of the framework allows it to be extended to other domains where privacy-preserving data sharing is critical. Our experimental results showcase that the proposed methodology significantly enhances performance in classification tasks compared to existing alternatives.

关键词： Training Adaptation models Federated learning Biological system modeling Collaboration Signal processing Regulation Blockchains Security Speech processing

来源：评论

学校读者我要写书评

暂无评论

Tailored Low-Rank Matrix Factorization for Similarity Matrix Completion

arXiv

引用

arXiv 2024年

作者： Ma, Changyi Chen, Xiao Yu, Runsheng Zhang, Youzhi Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation CAS Hong Kong The Hong Kong Polytechnic University Hong Kong SAR China

Similarity matrix serves as a fundamental tool at the core of numerous downstream machine-learning tasks. However, missing data is inevitable and often results in an inaccurate similarity matrix. To address this issue, Similarity Matrix Completion (SMC) methods have been proposed, but they suffer from high computation complexity due to the Singular Value Decomposition (SVD) operation. To reduce the computation complexity, Matrix Factorization (MF) techniques are more explicit and frequently applied to provide a low-rank solution, but the exact low-rank optimal solution can not be guaranteed since it suffers from a non-convex structure. In this paper, we introduce a novel SMC framework that offers a more reliable and efficient solution. Specifically, beyond simply utilizing the unique Positive Semi-definiteness (PSD) property to guide the completion process, our approach further complements a carefully designed rank-minimization regularizer, aiming to achieve an optimal and low-rank solution. Based on the key insights that the underlying PSD property and Low-Rank property improve the SMC performance, we present two novel, scalable, and effective algorithms, SMCNN and SMCNmF, which investigate the PSD property to guide the estimation process and incorporate nonconvex low-rank regularizer to ensure the low-rank solution. Theoretical analysis ensures better estimation performance and convergence speed. Empirical results on real-world datasets demonstrate the superiority and efficiency of our proposed methods compared to various baseline methods. © 2024, CC BY.

关键词： Matrix factorization

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：