检索结果-内蒙古大学图书馆

6th International Conference on Intelligent Computing and Signal Processing (ICSP)

作者： Pingfang Tian Deting Liu Department of Computer Science and Technology Wuhan University of Science and Technology Wuhan China The Key Laboratory of the Rich Media Knowledge Organisation and Service of Digital Publishing Content Institute of Scientific and Technical Information of China Beijing China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China Big Data Science and Engineering Research Institute Wuhan University of Science and Technology Wuhan China

ISBN: (数字)9798350376548

ISBN: (纸本)9798350376555

Topic shift detection aims to identify whether there is a change in the current topic of conversation or if a change is needed. The study found previous work did not evaluate the performance of large language models like ChatGPT on the task of topic shift. Therefore, this paper's main task and innovation lie in analyzing ChatGPT's performance on topic shift detection. To provide a more comprehensive evaluation, we conducted topic shift detection tasks on ChatGPT from three aspects: single utterances, adjacent utterances, and contextual levels. Additionally, to gauge the performance of large language models, we conducted experiments on multiple small-scale models and compared the results of the two models. Experimental results on the publicly available English TIAGE dataset showed that small-scale models exhibited lower recall in all three aspects, while ChatGPT performed better in the recall. This suggests that compared to small-scale models, large models are more capable of accurately detecting topic shifts. However, large models also exhibited lower precision, indicating that while ChatGPT can recognize content differences in utterances, its judgment on whether these different contents belong to the same topic is poor.

关键词： Technological innovation Large language models Oral communication Signal processing Chatbots Context modeling

来源：评论

学校读者我要写书评

暂无评论

Accurate Prior-centric Monocular Positioning with Offline LiDAR Fusion

Accurate Prior-centric Monocular Positioning with Offline Li...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Jinhao He Huaiyang Huang Shuyang Zhang Jianhao Jiao Chengju Liu Ming Liu Thrust of Robotics and Autonomous Systems The Hong Kong University of Science and Technology (Guangzhou) Guangzhou China Baidu Autonomous Driving Technology Department (ADT) Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Clear Water Bay Kowloon Hong Kong Department of Computer Science University College London London UK School of Electronics and Information Engineering Tongji University Shanghai China HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute Shenzhen China

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Unmanned vehicles usually rely on Global Positioning System (GPS) and Light Detection and Ranging (LiDAR) sensors to achieve high-precision localization results for navigation purpose. However, this combination with their associated costs and infrastructure demands, poses challenges for widespread adoption in mass-market applications. In this paper, we aim to use only a monocular camera to achieve comparable onboard localization performance by tracking deep-learning visual features on a LiDAR-enhanced visual prior map. Experiments show that the proposed algorithm can provide centimeter-level global positioning results with scale, which is effortlessly integrated and favorable for low-cost robot system deployment in real-world applications.

关键词： Location awareness Visualization Laser radar Robot vision systems Cameras Sensor systems Robustness

来源：评论

学校读者我要写书评

暂无评论

Deep Image Clustering by Spiking Neural Networks

Deep Image Clustering by Spiking Neural Networks

引用

Applied Imagery Pattern Recognition Workshop (AIPR)

作者： Arash Mahyari Hadi AliAkbarpour Florida Institute For Human and Machine Cognition (IHMC) Pensacola FL USA Department of Intelligent Systems and Robotics University of West Florida Pensacola FL USA Department of Computer Science Saint Louis University St. Louis MO USA

Neuromorphic cameras, or event cameras, are biologically-inspired sensors that detect changes in illumination at a pixel level, different from traditional cameras where each pixel independently and asynchronously outputs when it senses illumination changes. The neuromorphic cameras exhibit high-temporal resolution and dynamic range, useful in various applications. Spiking Neural Networks (SNNs), mimicking biological neurons, are efficient in processing neuromorphic images due to their event-driven, low-power nature. However, training SNNs is challenging because of the non-differentiability of neuron models which require different optimization techniques. Inspired by recent works on unsupervised deep clustering in conventional deep learning, we introduce a novel deep clustering algorithm that employs SNNs to extract and group visual features from neuromorphic images into clusters. It utilizes an SNN feature extractor for neuromorphic images, grouping the extracted features using K-means clustering. This algorithm, which doesn’t require pre-trained SNN weights, alternates between cluster updates and SNN weight adjustments. The extracted feature vectors in SNN are clustered and used as pseudo-labels for supervised training of the SNN extractor. The performance of the proposed algorithm is evaluated on two datasets of MNIST and NMNIST, and its effectiveness is assessed using the Normalized Mutual Information (NMI) metric. The performance of our SNN system with neuromorphic images, while marginally below its counterparts of ANNs with traditional images, demonstrates considerable potential.

关键词：

来源：评论

学校读者我要写书评

暂无评论

At school with a robot: Italian students’ perception of robotics during an educational program.

At school with a robot: Italian students’ perception of rob...

引用

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： Francesca Cocchella Giulia Pusceddu Giulia Belgiovine Michela Bogliolo Linda Lastrico Maura Casadio Francesco Rea Alessandra Sciutti CONTACT unit Italian Institute of Technology Genoa Italy Department of Computer Science Bioengineering Robotics and Systems Engineering (DIBRIS) University of Genova Genova Italy RBCS unit Italian Institute of Technology Genoa Italy Scuola di Robotica Genoa Italy

Social robots are expected to become more and more used in the education field. However, in the interaction between children and social robots, how robots are perceived in social contexts is still under investigation. In this exploratory study, we aimed to investigate how children’s expectations and demographical characteristics (N= 53, 9-14 years old) influence their perception of robot NAO during an education training program in schools. MANCOVA analysis conducted over questionnaire data indicates a positive correlation between the acceptance of the robot and the enjoyment of interacting with it. We found evidence that the more students accepted the robot, the more they perceived the group environment positively. Through a Correspondence Analysis, we investigate which are the preferred features of a robot according to the age of participants. The study suggests that a better opinion of robotics is a factor that can improve the learning environment in this specific context. Our exploratory study encourages conducting studies in-the-wild using self-reported measures to understand the implication of Child-Robot Interaction better.

关键词：

来源：评论

学校读者我要写书评

暂无评论

iMTSP: Solving Min-Max Multiple Traveling Salesman Problem with Imperative Learning

arXiv

引用

arXiv 2024年

作者： Guo, Yifan Ren, Zhongqiang Wang, Chen The Flight Dynamics & Control/Hybrid Systems Lab Purdue University West LafayetteIN47907 United States Robotics Institute Carnegie Mellon University PittsburghPA15213 United States Lab Department of Computer Science and Engineering University at Buffalo NY14260 United States

This paper considers a Min-Max Multiple Traveling Salesman Problem (MTSP), where the goal is to find a set of tours, one for each agent, to collectively visit all the cities while minimizing the length of the longest tour. Though MTSP has been widely studied, obtaining near-optimal solutions for large-scale problems is still challenging due to its NP-hardness. Recent efforts in data-driven methods face challenges of the need for hard-to-obtain supervision and issues with high variance in gradient estimations, leading to slow convergence and highly sub-optimal solutions. We address these issues by reformulating MTSP as a bilevel optimization problem, using the concept of imperative learning (IL). This involves introducing an allocation network that decomposes the MTSP into multiple single-agent traveling salesman problems (TSPs). The longest tour from these TSP solutions is then used to self-supervise the allocation network, resulting in a new self-supervised, bilevel, end-to-end learning framework, which we refer to as imperative MTSP (iMTSP). Additionally, to tackle the high-variance gradient issues during the optimization, we introduce a control variate-based gradient estimation algorithm. Our experiments showed that these innovative designs enable our gradient estimator to converge 20× faster than the advanced reinforcement learning baseline, and find up to 80% shorter tour length compared with Google OR-Tools MTSP solver, especially in large-scale problems (e.g. 1000 cities and 15 agents). © 2024, CC BY.

关键词： Traveling salesman problem

来源：评论

学校读者我要写书评

暂无评论

AR/VR Digital Twin for Simulation and Data Collection of Robotic Environments

AR/VR Digital Twin for Simulation and Data Collection of Rob...

引用

IEEE International Conference on Autonomous Robot systems and Competitions (ICARSC)

作者： João G. Martins Karle Nutonen Paulo Costa Vladimir Kuts Tauno Otto Armando Sousa Marcelo R. Petry CRIIS - Centre for Robotics in Industry and Intelligent Systems INESC TEC - Institute for Systems and Computer Engineering Technology and Science Porto Portugal Faculty of Engineering University of Porto (FEUP) Porto Portugal ViruTech - Virumaa innovation center of digitalization and green technologies Taltech Virumaa College Kohtla-Jarve Estonia Department of Mechanical and Indusrial Taltech Tallinn Estonia

ISBN: (数字)9798331538606

ISBN: (纸本)9798331538613

Digital twins enable real-time modeling, simulation, and monitoring of complex systems, driving advancements in automation, robotics, and industrial applications. This study presents a large-scale digital twin-testing facility for evaluating mobile robots and pilot robotic systems in a research laboratory environment. The platform integrates high-fidelity physical and environmental models, providing a controlled yet dynamic setting for analyzing robotic behavior. A key feature of the system is its comprehensive data collection framework, capturing critical parameters such as position, orientation, and velocity, which can be leveraged for machine learning, performance optimization, and decision-making. The facility also supports the simulation of discrete operational systems, using predictive modeling to bridge informational gaps when real-time data updates are unavailable. The digital twin was validated through a matrix manufacturing system simulation, with an Augmented reality (AR) interface on the HoloLens 2 to overlay digital information onto mobile platform controllers, enhancing situational awareness. The main contributions include a digital twin framework for deploying data-driven robotic systems and three key AR/VR integration optimization methods. Demonstrated in a laboratory setting, the system is a versatile tool for research and industrial applications, fostering insights into robotic automation and digital twin scalability while reducing costs and risks associated with real-world testing.

关键词： Service robots Navigation Metaverse Databases Scalability Digital representation real-time systems Digital twins Mobile robots Robots

来源：评论

学校读者我要写书评

暂无评论

From localized to propagating surface plasmon resonances in Au nanoparticle-coated optical fiber sensors and its implications in biosensing

引用

Photonics Research 2024年第10期12卷 2166-2177页

作者： PAULO S.S.DOS SANTOS JOÃO P.MENDES JORGE PÉREZ-JUSTE I.PASTORIZA-SANTOS JOSÉM.M.M.DE ALMEIDA LUÍS C.C.COELHO INESC TEC–Institute of Systems and Computer Engineering Technology and Scienceand Department of PhysicsFaculty of SciencesUniversity of PortoRua do Campo Alegre4169-007 PortoPortugal Faculty of Engineering University of PortoRua Dr.Roberto Frias4200-465 PortoPortugal CINBIO Universidade de VigoCampus Universitario LagoasMarcosende36310 VigoSpain SERGAS-UVIGO Galicia Sur Health Research Institute(IIS Galicia Sur)36312 VigoSpain Department of Physics School of Science and TechnologyUniversity of Trás-os-Montes e Alto Douro5001-801 Vila RealPortugal

Nanoparticle-based plasmonic optical fiber sensors can exhibit high sensing performance,in terms of refractive index sensitivities(RISs).However,a comprehensive understanding of the factors governing the RIS in this type of sensor remains limited,with existing reports often overlooking the presence of surface plasmon resonance(SPR)phenomena in nanoparticle(NP)assemblies and attributing high RIS to plasmonic coupling or waveguiding ***,using plasmonic optical fiber sensors based on spherical Au nanoparticles,we investigate the basis of their enhanced RIS,both experimentally and *** bulk behavior of assembled Au NPs on the optical fiber was investigated using an effective medium approximation(EMA),specifically the gradient effective medium approximation(GEMA).Our findings demonstrate that the Au-coated optical fibers can support the localized surface plasmon resonance(LSPR)as well as SPR in particular ***,we found that the nanoparticle sizes and surface coverage dictate which effect takes precedence in determining the RIS of the *** data,in line with numerical simulations,revealed that increasing the Au NP diameter from 20 to 90 nm(15%surface coverage)led to an RIS increase from 135 to 6998 nm/RIU due to a transition from LSPR to SPR ***,increasing the surface coverage of the fiber from 9%to 15%with 90 nm Au nanoparticles resulted in anincrease in RIS from 1297(LSPR)to 6998 nm/RIU(SPR).Hence,we ascribe the exceptional performance of these plasmonic optical fibers primary to SPR effects,as evidenced by the nonlinear RIS *** outstanding RIS of these plasmonic optical fibers was further demonstrated in the detection of thrombin protein,achieving very low limits of *** findings support broader applications of high-performance NP-based plasmonic optical fiber sensors in areas such as biomedical diagnostics,environmental monitoring,and chemical analysis.

关键词： fiber surface fibers

来源：评论

学校读者我要写书评

暂无评论

Embodied Runtime Monitoring of Learning-enabled Robot Perception Components

Embodied Runtime Monitoring of Learning-enabled Robot Percep...

引用

IEEE International Conference on Automation science and Engineering (CASE)

作者： Deebul Nair Sathwik Panchangam Miguel A. Olivares-Mendez Nico Hochgeschwender Institute for Artificial Intelligence and Autonomous Systems Bonn-Rhein-Sieg University of Applied Sciences Sankt Augustin Germany Space Robotics Research Group (SpaceR) Interdisciplinary Centre for Security Reliability and Trust (SnT) University of Luxembourg Luxembourg Department of Mathematics and Computer Science University of Bremen Germany

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

Monitoring during runtime, the estimated uncertainty from learning-enabled robot perception components, is a vital tool for assuring and evaluating model correctness. By utilizing different uncertainty estimation methods, monitors exploit the perceived sensor data and predictions generated by the perception model to make informed decisions, such as in safety-critical situations. In robotics, informed decisions should be aligned with embodied information regarding space and time. We argue and show that runtime monitors of learning-enabled components can be made more robust by including the embodiment information of the robot. However, it remains challenging to build uncertainty-based runtime monitors with embodiment information using only real-world datasets, which are tedious to collect. To this end, we propose a solution that leverages simulation-based datasets to characterize expected uncertainty estimates with robot embodiment. By constructing a nominal runtime monitor model based on simulated datasets, we establish a reference for the expected uncertainty along with the embodiment information that can be subsequently used to monitor real-world deployed perception components. We demonstrate the zero-shot sim-to-real transfer of our approach on a Kinova Gen3 manipulator picking task, for which the runtime monitor reliability model was trained using simulation-based data containing embodiment information of distance from the object being selected.

关键词： Runtime Uncertainty Computational modeling Estimation Predictive models Robot sensing systems Manipulators Reliability engineering Data models Monitoring

来源：评论

学校读者我要写书评

暂无评论

F2A2: flexible fully-decentralized approximate actor-critic for cooperative multi-agent reinforcement learning

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2023年第1期24卷 8447-8521页

作者： Wenhao Li Bo Jin Xiangfeng Wang Junchi Yan Hongyuan Zha School of Data Science The Chinese University of Hong Kong Shenzhen Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China School of Software Engineering Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai China School of Computer Science and Technology Key Laboratory of Mathematics and Engineering Applications Ministry of Education East China Normal University Shanghai China Department of Computer Science and Engineering Key Laboratory of Artificial Intelligence Ministry of Education Shanghai Jiao Tong University Shanghai China

Traditional centralized multi-agent reinforcement learning (MARL) algorithms are sometimes unpractical in complicated applications due to non-interactivity between agents, the curse of dimensionality, and computation complexity. Hence, several decentralized MARL algorithms are motivated. However, existing decentralized methods only handle the fully cooperative setting where massive information needs to be transmitted in training. The block coordinate gradient descent scheme they used for successive independent actor and critic steps can simplify the calculation, but it causes serious bias. This paper proposes a exible fully decentralized actor-critic MARL framework, which can combine most of the actor-critic methods and handle large-scale general cooperative multi-agent settings. A primal-dual hybrid gradient descent type algorithm framework is designed to learn individual agents separately for decentralization. From the perspective of each agent, policy improvement and value evaluation are jointly optimized, which can stabilize multi-agent policy learning. Furthermore, the proposed framework can achieve scalability and stability for the large-scale environment. This framework also reduces information transmission by the parameter sharing mechanism and novel modeling-other-agents methods based on theory-of-mind and online supervised learning. Sufficient experiments in cooperative Multi-agent Particle Environment and StarCraft II show that the proposed decentralized MARL instantiation algorithms perform competitively against conventional centralized and decentralized methods.

关键词： cooperative MARL decentralized actor-critic primal-dual method

来源：评论

学校读者我要写书评

暂无评论

Segmentation of Foetus Brain MRI Based on K-nn Algorithm, A Case Study 12th

Segmentation of Foetus Brain MRI Based on K-nn Algorithm, A ...

引用

12th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2020 and 16th International Conference on Information Assurance and Security, IAS 2020

作者： Salgado, Paulo Azevedo Perdicoúlis, Teresa-Paula CITAB-Dep. de Engenharias ECT UTAD Quinta de Prados Vila Real5000-801 Portugal Institute of Systems and Robotics Department of Electrical and Computer Engineering University of Coimbra Rua Silvio Lima-Polo II Coimbra3030-290 Portugal

ISBN: (纸本)9783030736880

The segmentation of magnetic resonance images of the fetal brain has been emerging as a clinical tool to detect abnormalities during the development of the foetus. Since the brain is still in development, a mixture of regions of white matter, grey matter and transition structures that are related to brain growth are still associated with it. In this work, two versions of the K-nearest neighbour algorithm are proposed as the core method for the recognition of different regions of an image;the first one is a refinement of the standard algorithm since some statistics are associated with the pixel, and the second a reinforcing iterative version of the same method. Both versions are used to identify 3 apriori selected regions—the brain, the intracranial region and the remaining part of the foetus. The effectiveness of the method has been demonstrated in a magnetic resonance image segmentation that was first pre-processed with digital filters for feature extraction. The present study illustrates the capabilities of this type of method to support obstetricians and general practitioners to assess the foetus and, in particular, its brain. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Image segmentation

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：