检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Mina, Tamzidul Jo, Wonse Kannan, Shyam S. Min, Byung-Cheol The SMART Lab Department of Computer and Information Technology Purdue University West LafayetteIN47907 United States The School of Mechanical Engineering Purdue University West LafayetteIN47907 United States

Autonomous shape and structure formation is an important problem in the domain of large-scale multiagent systems. In this paper, we propose a 3D structure representation method and a distributed structure formation strategy where settled agents guide free moving agents to a prescribed location to settle in the structure. Agents at the structure formation frontier looking for neighbors to settle act as beacons, generating a surface gradient throughout the formed structure propagated by settled agents. Free-moving agents follow the surface gradient along the formed structure surface to the formation frontier, where they eventually reach the closest beacon and settle to continue the structure formation following a local bidding process. Agent behavior is governed by a finite state machine implementation, along with potential field-based motion control laws. We also discuss appropriate rules for recovering from stagnation points. Simulation experiments are presented to show planar and 3D structure formations with continuous and discontinuous boundary/surfaces, which validate the proposed strategy, followed by a scalability analysis. Copyright © 2023, The Authors. All rights reserved.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Type-2 Fuzzy Control for Driving State and Behavioral Decisions of Unmanned Vehicle

引用

IEEE/CAA Journal of Automatica Sinica 2020年第1期7卷 178-186页

作者： Xuanming Zhao Hong Mo Kefu Yan Lingxi Li College of Electric and Information Engineering Changsha University of Science and TechnologyChangsha 410114China Department of Electrical and Computer Engineering Purdue School of Engineering and TechnologyIndiana University-Purdue University IndianapolisIndiana 46202-5132 USA

In this paper, interval type-2 fuzzy sets, fuzzy comprehensive evaluation and the fuzzy control rules are synthesized to realize the control of unmanned vehicle in driving state and behavioral decisions. Compared to the type-1 fuzzy set, type-2 fuzzy sets have more advantages in handling the model based on uncertainties, linguistic information because the membership functions are fuzzy sets. Different membership functions are established for each factor when the unmanned vehicle is driving at different speed intervals. In addition, a new evaluation method is developed to analyze unmanned vehicle’s driving state. Finally, a set of dynamic fuzzy rules are sorted out, which can be applied to the unmanned vehicle’s behavioral decision-making and provide a new idea to related research.

关键词： Fuzzy comprehensive evaluation fuzzy control interval type-2 fuzzy sets unmanned vehicle

来源：评论

学校读者我要写书评

暂无评论

DistilDIRE: A Small, Fast, Cheap and Lightweight Diffusion Synthesized Deepfake Detection

arXiv

引用

arXiv 2024年

作者： Lim, Yewon Lee, Changyeon Kim, Aerin Etzioni, Oren Department of Computer Science and Engineering Yonsei University Seoul Korea Republic of Computer and Information Technology Purdue University West LafayetteIN United States Miraflow KirklandWA United States *** SeattleWA United States

A dramatic influx of diffusion-generated images has marked recent years, posing unique challenges to current detection technologies. While the task of identifying these images falls under binary classification, a seemingly straightforward category, the computational load is significant when employing the "reconstruction then compare" technique. This approach, known as DIRE (Diffusion Reconstruction Error), not only identifies diffusion-generated images but also detects those produced by GANs, highlighting the technique's broad applicability. To address the computational challenges and improve efficiency, we propose distilling the knowledge embedded in diffusion models to develop rapid deepfake detection models. Our approach, aimed at creating a small, fast, cheap, and lightweight diffusion synthesized deepfake detector, maintains robust performance while significantly reducing operational demands. Maintaining performance, our experimental results indicate an inference speed 3.2 times faster than the existing DIRE framework. This advance not only enhances the practicality of deploying these systems in real-world settings but also paves the way for future research endeavors that seek to leverage diffusion model knowledge. The code and weights for our framework are available at https://***/miraflow/DistilDIRE. © 2024, CC BY.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

NaviSTAR: Socially Aware Robot Navigation with Hybrid Spatio-Temporal Graph Transformer and Preference Learning

NaviSTAR: Socially Aware Robot Navigation with Hybrid Spatio...

引用

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

作者： Weizheng Wang Ruiqi Wang Le Mao Byung-Cheol Min Department of Computer and Information Technology SMART Laboratory Purdue University West Lafayette IN USA College of Mechanical and Electrical Engineering Beijing University of Chemical Technology Beijing China

Developing robotic technologies for use in human society requires ensuring the safety of robots' navigation behaviors while adhering to pedestrians' expectations and social norms. However, understanding complex human-robot interactions (HRI) to infer potential cooperation and response among robots and pedestrians for cooperative collision avoid-ance is challenging. To address these challenges, we propose a novel socially-aware navigation benchmark called NaviS Tar, which utilizes a hybrid Spatio- Temporal grAph tRansformer to understand interactions in human-rich environments fusing crowd multi-modal dynamic features. We leverage an off-policy reinforcement learning algorithm with preference learning to train a policy and a reward function network with supervi-sor guidance. Additionally, we design a social score function to evaluate the overall performance of social navigation. To compare, we train and test our algorithm with other state-of-the-art methods in both simulator and real-world scenarios independently. Our results show that NaviSTAR outperforms previous methods with outstanding performance 1 1 The source code and experiment videos of this work are available at: https://***/view/san-navistar

关键词：

来源：评论

学校读者我要写书评

暂无评论

Initial Task Allocation for Multi-Human Multi-Robot Teams with Attention-Based Deep Reinforcement Learning

Initial Task Allocation for Multi-Human Multi-Robot Teams wi...

引用

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

作者： Ruiqi Wang Dezhong Zhao Byung-Cheol Min Department of Computer and Information Technology SMART Laboratory Purdue University West Lafayette IN USA College of Mechanical and Electrical Engineering Beijing University of Chemical Technology Beijing China

Multi-human multi-robot teams have great potential for complex and large-scale tasks through the collaboration of humans and robots with diverse capabilities and expertise. To efficiently operate such highly heterogeneous teams and maximize team performance timely, sophisticated initial task allocation strategies that consider individual differences across team members and tasks are required. While existing works have shown promising results in reallocating tasks based on agent state and performance, the neglect of the inherent heterogeneity of the team hinders their effectiveness in realistic scenarios. In this paper, we present a novel formulation of the initial task allocation problem in multi-human multi-robot teams as a contextual multi-attribute decision-make process and propose an attention-based deep reinforcement learning approach. We introduce a cross-attribute attention module to encode the latent and complex dependencies of multiple attributes in the state representation. We conduct a case study in a massive threat surveillance scenario and demonstrate the strengths of our model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robots on the road - Investigating potentials of eHMI-concepts for HRI to tackle critical situations in public spaces

Robots on the road - Investigating potentials of eHMI-concep...

引用

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： Lea Turriziani Johannes Kraus Stephanie Ruess Zhe Zeng Shyam Sundar Kannan Human Factors Department Ulm University Germany Department of General Experimental Psychology Johannes-Gutenberg University of Mainz Germany Department of Computer and Information Technology SMART Lab Purdue University IN USA

ISBN: (数字)9798350375022

ISBN: (纸本)9798350375039

Robots in public spaces need to communicate with lay persons who are not directly involved in the robot task to coordinate their movements and resolve critical situations. Hereby, this communication aims at salience and clarity and at the same time needs to be unobtrusive. While in automated cars, communication with uninvolved road members has been investigated with the label external human-machine interface (eHMI) in human-robot interaction (HRI) this has not been systematically discussed. This study investigates some of the mainly discussed eHMI concepts (blinker lights, beep, and speech) for solving critical situations in HRI. Six critical situations were presented together with five communication strategies (presented as videos) in an online study with N = 175 participants. Mainly, criticality and trust were measured as dependent variables. Overall, situations including visually or hearing-impaired persons were perceived as most critical. For all situations, criticality was reduced with added interaction modalities. The combination of blinker lights and voice was ranked as the most preferred strategy for five situations and led to a reduction in criticality of all situations and higher trust in the robot. The relation between perceived criticality and trust was partially mediated by predictability and transparency. Design recommendations for solving critical situations through robots’ communication strategies in the public are discussed.

关键词： Atmospheric measurements Robot kinematics Roads Human-machine systems Human-robot interaction Particle measurements Automobiles Videos

来源：评论

学校读者我要写书评

暂无评论

Hands-Free VR

arXiv

引用

arXiv 2024年

作者： Fernandez, Jorge Askur Vazquez Lee, Jae Joong Vacca, Santiago Andres Serrano Magana, Alejandra Pesa, Radim Benes, Bedrich Popescu, Voicu Department of Computer Science Purdue University West Lafayette United States School of Engineering and Science Tecnologico de Monterrey Monterrey Mexico Department of Computer and Information Technology Purdue University West Lafayette United States Department of Informatics and Computers Ostravska Universita Ostrava Czech Republic

We introduce Hands-Free VR, a voice-based natural-language interface for VR that allows interaction without additional hardware just using voice. The user voice command is converted into text using a fine-tuned speech-to-text deep-learning model. Then, the text is mapped to an executable VR command using an LLM, which is robust to natural language diversity. Hands-Free VR was evaluated in a within-subjects study (N = 22) where participants arranged objects using either a conventional VR interface or Hands-Free VR. The results confirm that Hands-Free VR is: (1) significantly more efficient than conventional VR interfaces in task completion time and user motion metrics;(2) highly rated for ease of use, intuitiveness, ergonomics, reliability, and desirability;(3) robust to English accents (20 participants were non-native speakers) and phonetic similarity, accurately transcribing 96.7% of voice commands, and (3) robust to natural language diversity, mapping 97.83% of transcriptions to executable commands. © 2024, CC BY.

关键词： Ergonomics

来源：评论

学校读者我要写书评

暂无评论

Hybrid Algorithm Selection and Hyperparameter Tuning on Distributed Machine Learning Resources: A Hierarchical Agent-based Approach

arXiv

引用

arXiv 2023年

作者： Esmaeili, Ahmad Rayz, Julia T. Matson, Eric T. Department of Computer and Information Technology Purdue University 401 N. Grant St. West LafayetteIN47907 United States

Algorithm selection and hyperparameter tuning are critical steps in both academic and applied machine learning. On the other hand, these steps are becoming ever increasingly delicate due to the extensive rise in the number, diversity, and distributedness of machine learning resources. Multi-agent systems, when applied to the design of machine learning platforms, bring about several distinctive characteristics such as scalability, flexibility, and robustness, just to name a few. This paper proposes a fully automatic and collaborative agent-based mechanism for selecting distributedly organized machine learning algorithms and simultaneously tuning their hyperparameters. Our method builds upon an existing agent-based hierarchical machine-learning platform and augments its query structure to support the aforementioned functionalities without being limited to specific learning, selection, and tuning mechanisms. We have conducted theoretical assessments, formal verification, and analytical study to demonstrate the correctness, resource utilization, and computational efficiency of our technique. According to the results, our solution is totally correct and exhibits linear time and space complexity in relation to the size of available resources. To provide concrete examples of how the proposed methodologies can effectively adapt and perform across a range of algorithmic options and datasets, we have also conducted a series of experiments using a system comprised of 24 algorithms and 9 datasets. © 2023, CC BY.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Safe Route Recommendation based on Crime Risk Prediction with Urban and Crime Data

Safe Route Recommendation based on Crime Risk Prediction wit...

引用

IEEE International Conference on Big Data Computing Service and Applications (BigDataService)

作者： Daye Kim Juwon Baek Jihu Yang Hyun Roh Heewon Jeong Bryanna Ruiz Minji Lee Eric T. Matson Software Convergence Kyung Hee University Yongin Republic of Korea Computer Science and Electrical Engineering Handong Global University Pohang Republic of Korea Computer Engineering Chungbuk National University Cheongju Republic of Korea Computer and Information Technology Purdue University West Lafayette IN USA Technology Purdue University West Lafayette IN USA

Public safety is an escalating concern in the United States, given the rising crime rates. However, existing research paper on recommending safe routes often overlooks crucial factors essential for assessing road risk. In contrast to prior studies, this study introduces an innovative approach that recommends safe routes based on road risk prediction. By employing Gaussian Kernel Density Estimation, the study estimates the densities of crime and urban data for each coordinate in Chicago while considering the severity of crimes. These estimated densities are then utilized to predict future crime density using a machine learning model. The predicted crime density is assigned to each node and edge of the Chicago graph map, serving as an indicator of road risk. Four types of weighted graphs are generated by combining road risk and road length in different ratios, which are subsequently applied in the Dijkstra shortest path algorithm. The proposed application of this study is expected to decrease the likelihood of crime incidents, thereby fostering a safer environment. Furthermore, the results analyzed in this paper can serve as valuable reference material for community safety initiatives.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EL2W: Extended Layer 2 Services for Bare-Metal Provisioning Over WAN

EL2W: Extended Layer 2 Services for Bare-Metal Provisioning ...

引用

IEEE Cloud Summit

作者： Thomas J. Hacker Deepika Kaushal Zhiwei Chu Dept. of Computer and Information Technology Purdue University West Lafayette Indiana USA *** LLC Software Engineer Kirkland Washington USA

Researchers are embracing deep learning in various interdisciplinary research domains, recognizing undeniable benefits offered by deep neural networks. However, in order to meet the substantial computational demands for processing deep learning models, researchers extensively rely on cloud servers. Nevertheless, the shared nature of cloud servers encourages research labs and facilities to establish private clouds, ensuring exclusive access to computational resources and safeguarding data privacy. Creating a private cloud from bare metal presents challenges with existing provisioning solutions. These solutions not only come with a set of complex installation and configuration steps but are also limited to a constrained local Ethernet broadcast domain for network loading, which may pose unforeseen difficulties and risks for researchers who do not specialize in computing. To address these issues, this paper introduces EL2W, Extended Layer 2 services to Wide area networks (WAN), a novel approach we developed following Infrastructure-as-Code (IaC) principles. EL2W aims to help automate the system installation procedure by reducing the repetitive configurations and setups using Infrastructure-as-Code based scripts and codes. In addition, EL2W can securely expand an Ethernet network’s logical and functional extent beyond the current physical limitations of Ethernet layer 2 networks. We describe the implementation and architecture of a remote bare metal provisioning system built upon secure extended layer 2 networks. Experimental results demonstrate the capability of EL2W for establishing a secure layer 2 connection to provide essential bare metal provisioning services, as well as the effectiveness of a local proxy cache server to reduce the operating system loading time.

关键词：

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：