检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Shin, Juyeb Jeong, Hyeonjun Rameau, Francois Kum, Dongsuk Robotics Program Korea Advanced Institute of Science and Technology Daejeon34051 Korea Republic of Graduate School of Mobility Korea Advanced Institute of Science and Technology Daejeon34051 Korea Republic of Computer Science department State University of New York - Korea Songdo21985 Korea Republic of

For scalable autonomous driving, a robust map-based localization system, independent of GPS, is fundamental. To achieve such map-based localization, online high-definition (HD) map construction plays a significant role in accurate estimation of the pose. Although recent advancements in online HD map construction have predominantly investigated on vectorized representation due to its effectiveness, they suffer from computational cost and fixed parametric model, which limit scalability. To alleviate these limitations, we propose a novel HD map learning framework that leverages graph modeling. This framework is designed to learn the construction of diverse geometric shapes, thereby enhancing the scalability of HD map construction. Our approach involves representing the map elements as an instance-level graph by decomposing them into vertices and edges to facilitate accurate and efficient end-to-end vectorized HD map learning. Furthermore, we introduce an association strategy using a Graph Neural Network to efficiently handle the complex geometry of various map elements, while maintaining scalability. Comprehensive experiments on public open dataset show that our proposed network outperforms state-of-the-art model by 1.6 mAP. We further showcase the superior scalability of our approach compared to state-of-the-art methods, achieving a 4.8 mAP improvement in long range configuration. Our code is available at https://***/juyebshin/InstaGraM. Copyright © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Multiplier analysis of Lurye systems with power signals

Multiplier analysis of Lurye systems with power signals

引用

IEEE Conference on Decision and Control

作者： William P. Heath Joaquin Carrasco School of Computer Science and Engineering Bangor University Dean St LL57 1UT UK Department of Electrical and Electronic Engineering Control Systems and Robotics Group Nancy Rothwell Building University of Manchester M13 9PL UK

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

Multipliers can be used to guarantee both the Lyapunov stability and input-output stability of Lurye systems with time-invariant memoryless slope-restricted nonlinearities. If a dynamic multiplier is used there is no guarantee the closedloop system has finite incremental gain. It has been suggested in the literature that without this guarantee such a system may be critically sensitive to time-varying exogenous signals including noise. We show that multipliers guarantee the power gain of the system to be bounded and quantifiable. Furthermore power may be measured about an appropriate steady state bias term, provided the multiplier does not require the nonlinearity to be odd. Hence dynamic multipliers can be used to guarantee Lurye systems have low sensitivity to noise, provided other exogenous systems have constant steady state. We illustrate the analysis with an example where the exogenous signal is a power signal with non-zero mean.

关键词： Sensitivity Power measurement Noise Stability analysis Steady-state Time-varying systems Lyapunov methods

来源：评论

学校读者我要写书评

暂无评论

Behavior Replication of Cascaded Dynamic Systems Using Machine Learning

Behavior Replication of Cascaded Dynamic Systems Using Machi...

引用

International Workshop on Robot Sensing (ROSE)

作者： Mohammed Abouheaf Wail Gueaieb Mohammad Mayyas Robotics Engineering Bowling Green State University Bowling Green OH 43403 USA School of Electrical Engineering and Computer Science Ottawa University Ottawa Ontario K1N 6N5 Canada

This paper introduces an innovative data-driven approach for replicating behaviors in interconnected and heterogeneous dynamic systems. The core concept involves real-time control of dynamic systems to closely mimic reference-model trajectories using model-free techniques. Within this coupled framework, one component possesses complete information about reference-trajectories, although not necessarily their dynamics. In contrast, follower systems, with limited connectivity to reference-model trajectories, exclusively replicate the behavior of the primary process, which retains insight into model-reference dynamics. The adopted strategies are causal, integrating higher-order error dynamics to ensure precise tracking of reference-trajectories. Furthermore, these strategies incorporate variations in reference-model dynamics via a pseudo partial derivative, akin to sensitivity derivatives in model-reference adaptive strategies. To optimize the dynamic behavior of the follower process, the solution employs a reinforcement learning mechanism through adaptive critics. This mechanism approximates the optimal strategy and the associated value function. The actor and critic weights of the adaptive critic structure are tuned using a projection technique to ensure convergence of the adapted strategy. The validation of this solution is demonstrated on a dynamic system with delays, simulating an underwater vehicle scenario. The developed methodology is rigorously compared with another high-order model-free adaptive control approach. The presented approach showcases its capability to effectively replicate behaviors, resulting in improved tracking accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimal Energy Storage Operation under Demand Uncertainty: A Prospect Theory Analysis

Optimal Energy Storage Operation under Demand Uncertainty: A...

引用

IEEE International Conference on Smart Grid Communications (SmartGridComm)

作者： Qisheng Huang Jin Xu Peng Sun Bo Liu Costas Courcoubetis School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen Shenzhen China School of Management Huazhong University of Science and Technology Wuhan China College of Computer Science and Electronic Engineering Hunan University Changsha China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China School of Data Science The Chinese University of Hong Kong Shenzhen Shenzhen China

In this paper, we study the consumer’s optimal energy storage operation problem under demand uncertainty. Each consumer can purchase energy storage service from an independent energy storage aggregator to shift demand from peak periods to off-peak periods under time-of-use (ToU) pricing. Previous studies on energy storage operation and investment mainly focused on the expected cost-minimization problem of a risk-neutral consumer based on the expected utility theory (EUT). We propose a prospect theory (PT) model from behavioral economics to understand the consumer’s realistic energy storage operation behaviors considering their risk preferences. Although it is challenging to solve the PT-based non-convex optimization problem, we are able to characterize the optimal solution by exploiting the unimodal structure of the objective function. Theoretical and numerical results show that the consumer’s risk preferences have a significant impact on his decisions: 1) a PT-consumer with a low reference point is more willing to use energy storage to reduce risk compared with the EUT benchmark; and 2) a PT consumer is more willing to use the energy storage when the probability of high demand is small, due to the probability distortion.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Training Human-Robot Teams by Improving Transparency Through a Virtual Spectator Interface

arXiv

引用

arXiv 2025年

作者： Dallas, Sean Qiang, Hongjiao AbuHijleh, Motaz Jo, Wonse Riegner, Kayla Smereka, Jon Robert, Lionel Louie, Wing-Yue Tilbury, Dawn M. Robotics Department University of Michigan Ann ArborMI48105 United States Department of Electrical and Computer Engineering Oakland University RochesterMI48309 United States Department of Mechanical Engineering Department of Electrical Engineering and Computer Science University of Michigan Ann ArborMI48105 United States School of Information University of Michigan Ann ArborMI48105 United States United States

After-action reviews (AARs) are professional discussions that help operators and teams enhance their task performance by analyzing completed missions with peers and professionals. Previous studies comparing different formats of AARs have focused mainly on human teams. However, the inclusion of robotic teammates brings along new challenges in understanding teammate intent and communication. Traditional AAR between human teammates may not be satisfactory for human-robot teams. To address this limitation, we propose a new training review (TR) tool, called the Virtual Spectator Interface (VSI), to enhance human-robot team performance and situational awareness (SA) in a simulated search mission. The proposed VSI primarily utilizes visual feedback to review subjects’ behavior. To examine the effectiveness of VSI, we took elements from AAR to conduct our own TR, and designed a 1 × 3 between-subjects experiment with experimental conditions: TR with (1) VSI, (2) screen recording, and (3) non-technology (only verbal descriptions). The results of our experiments demonstrated that the VSI did not result in significantly better team performance than other conditions. However, the TR with VSI led to more improvement in the subjects’ SA over the other conditions. Copyright © 2025, The Authors. All rights reserved.

关键词： Social robots

来源：评论

学校读者我要写书评

暂无评论

Act as you wish: fine-grained control of motion diffusion model with hierarchical semantic graphs 23

Act as you wish: fine-grained control of motion diffusion mo...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Peng Jin Yang Wu Yanbo Fan Zhongqian Sun Yang Wei Li Yuan School of Electronic and Computer Engineering Peking University Shenzhen China and AI for Science (AI4S)-Preferred Program Peking University Shenzhen Graduate School China Tencent AI Lab China School of Electronic and Computer Engineering Peking University Shenzhen China and Peng Cheng Laboratory Shenzhen China and AI for Science (AI4S)-Preferred Program Peking University Shenzhen Graduate School China

Most text-driven human motion generation methods employ sequential modeling approaches, e.g., transformer, to extract sentence-level text representations automatically and implicitly for human motion synthesis. However, these compact text representations may overemphasize the action names at the expense of other important properties and lack fine-grained details to guide the synthesis of subtly distinct motion. In this paper, we propose hierarchical semantic graphs for fine-grained control over motion generation. Specifically, we disentangle motion descriptions into hierarchical semantic graphs including three levels of motions, actions, and specifics. Such global-to-local structures facilitate a comprehensive understanding of motion description and fine-grained control of motion generation. Correspondingly, to leverage the coarse-to-fine topology of hierarchical semantic graphs, we decompose the text-to-motion diffusion process into three semantic levels, which correspond to capturing the overall motion, local actions, and action specifics. Extensive experiments on two benchmark human motion datasets, including HumanML3D and KIT, with superior performances, justify the efficacy of our method. More encouragingly, by modifying the edge weights of hierarchical semantic graphs, our method can continuously refine the generated motion, which may have a far-reaching impact on the community. Code and pre-trained weights are available at https://***/jpthu17/GraphMotion.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robot Trust and Self-Confidence Based Role Arbitration Method for Physical Human-Robot Collaboration

Robot Trust and Self-Confidence Based Role Arbitration Metho...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Qiao Wang Dikai Liu Marc G. Carmichael Chin-Teng Lin Faculty of Engineering and Information Technology Robotics Institute University of Technology Sydney Ultimo NSW Australia Faculty of Engineering and Information Technology Australian Artificial Intelligence Institute School of Computer Science University of Technology Sydney Ultimo NSW Australia

Role arbitration in human-robot collaboration (HRC) is a dynamically changing process that is affected by many factors such as physical workload, environmental changes and trust. In order to address this dynamic process, a trust-based role arbitration method is studied in this research. A computational model of robot trust and self-confidence (TSC) in physical human-robot collaboration (pHRC) is proposed. The TSC model is defined as a function of objective robot and human co-worker performance. A role arbitration method is then proposed based on the TSC model presented. The human-in-the-loop experiments with a collaborative robot are conducted to verify the TSC-based role arbitration method. The results show that the proposed method could achieve superior human-robot combined performance, reduce human co-workers' workload, and improve subjective preference.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Finite Difference Method for a Normalized Time-Fractional Black–Scholes Equation

引用

International Journal of Applied and Computational Mathematics 2025年第3期11卷 1-17页

作者： Nam, Yunjae Wang, Jian Lee, Chaeyoung Choi, Yongho Bang, Minjoon Li, Zhengang Kim, Junseok Program in Actuarial Science and Financial Engineering Korea University Seoul 02841 South Korea School of Mathematics and Statistics Nanjing University of Information Science and Technology Nanjing 210044 China Department of Mathematics Kyonggi University Suwon 16227 South Korea Computer and Information Engineering Daegu University Gyeongsan 38453 South Korea Department of Mathematics Korea University Seoul 02841 South Korea

In this article, we propose a normalized time-fractional Black–Scholes (TFBS) equation. The proposed model uses a normalized time-fractional derivative which has a distinctive feature wherein a weight function possesses the property that its integral with respect to time is always equal to one. This feature ensures a well-balanced integration over time and provides a fair comparison between different fractional orders. An implicit finite difference method is used for the numerical solution of the TFBS equation. We perform several standard numerical tests to examine the effect of the fractional parameter on the option pricing. These experiments are designed to investigate how variations in the fractional parameter influence pricing outcomes and provide valuable insights into the model’s behavior under different conditions. The computational results demonstrate the model’s potential for capturing more intricate market dynamics, which makes the proposed model a promising tool for financial analysis. In the appendix, we provide a computer program that implements the numerical methods discussed in the paper for interested readers. © The Author(s), under exclusive licence to Springer Nature India Private Limited 2025.

关键词： Implicit finite difference method Memory effect Normalized time-fractional Black–Scholes equation

来源：评论

学校读者我要写书评

暂无评论

Imperceptible adversarial attack with entropy feature and segmentation-based constraint 2021

Imperceptible adversarial attack with entropy feature and se...

引用

2021 10th International Conference on Computing and Pattern Recognition

作者： Rongdong Li Qinliang Lin Yinglong Fu Weicheng Xie Linlin Shen School of Computer Science&Software Engineering Shenzhen University China and Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen University China

ISBN: (纸本)9781450390439

Methods of adversarial attack and defense have attracting increasing attention in the fields of security and protection related applications. However, current algorithms carry out perturbations on entire images and mostly consider their imperceptibility to machines, while does not take their human imperceptibility into account. In this work, we propose a constrained adversarial attack algorithm with both machine and human imperceptibility based on image entropy feature and accurate segmentation. The proposed algorithm has three merits. First, image entropy-based feature for quantifying the imperceptibility of a semantic region is introduced, which is simple yet efficient to implement. Second, in terms of the imperceptibility metric, accurate target regions for adversarial perturbation are obtained based on scene-aware segmentation and merging. Third, a general adversarial attack based on segmentation region constraint is proposed to induce both machine and visual imperceptibility. Experimental results in terms of qualitative and quantitative analysis reflect the effectiveness of the proposed algorithm compared with the state of the arts.

关键词： Adversarial attack semantic segmentation robust object classification imperceptibility metric constrained attack algorithm

来源：评论

学校读者我要写书评

暂无评论

Lateralized Learning for Multi-Class Visual Classification Tasks

arXiv

引用

arXiv 2023年

作者： Siddique, Abubakar Browne, Will N. Grimshaw, Gina M. The School of Engineering and Computer Science Victoria University of Wellington PO Box 600 Wellington6140 New Zealand The Faculty of Engineering School of Electrical Engineering & Robotics Queensland University of Technology Brisbane4000 Australia The Cognitive the School of Psychology Victoria University of Wellington PO Box 600 Wellington6140 New Zealand

The majority of computer vision algorithms fail to find higher-order (abstract) patterns in an image so are not robust against adversarial attacks, unlike human lateralized vision. Deep learning considers each input pixel in a homogeneous manner such that different parts of a "locality-sensitive hashing table" are often not connected, meaning higher-order patterns are not discovered. Hence these systems are not robust against noisy, irrelevant, and redundant data, resulting in the wrong prediction being made with high confidence. Conversely, vertebrate brains afford heterogeneous knowledge representation through lateralization, enabling modular learning at different levels of abstraction. This work aims to verify the effectiveness, scalability, and robustness of a lateralized approach to real-world problems that contain noisy, irrelevant, and redundant data. The experimental results of multi-class (200 classes) image classification show that the novel system effectively learns knowledge representation at multiple levels of abstraction making it more robust than other state-of-the-art techniques. Crucially, the novel lateralized system outperformed all the state-of-the-art deep learning-based systems for the classification of normal and adversarial images by 19.05% − 41.02% and 1.36% − 49.22%, respectively. Findings demonstrate the value of heterogeneous and lateralized learning for computer vision applications. Copyright © 2023, The Authors. All rights reserved.

关键词： Image classification

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：