检索结果-内蒙古大学图书馆

IEEE Conference on Decision and Control

作者： Jun Wang Tongsheng Shen Dexin Zhao Feitian Zhang Department of Advanced Manufacturing and Robotics College of Engineering Peking University Beijing China National Innovation Institute of Defense Technology Beijing China Department of Advanced Manufacturing and Robotics State Key Laboratory of Turbulence and Complex Systems College of Engineering Peking University Beijing China

An artificial lateral line (ALL) is a sensing system that imitates the distributed perception organs of fish and plays a major role in enhancing the flow estimation capability of underwater robots. Whereas various ALLs have been designed and developed, it is still an open question how to better place ALL sensors on underwater robots, especially for those with complex shapes and working in dynamic flow and robot operating conditions. Aiming to answer this question, this paper presents a novel data-driven sensor placement method for ALLs of underwater robots. This method adopts distributed pressure sensors to measure the flow field along the profile or the outermost boundary of an underwater robot, and quantifies the dynamic information embedded within these measurements using multi-resolution dynamic mode decomposition (mrDMD). The sensors are then positioned by optimizing the dynamic flow information to enhance the perception. Compared with existing sensor placement methods, such as observability maximization and exhaustive experimental search, the proposed method focuses on the modes of dynamics variability at various spatio-temporal scales, thus leading to improved sensing ability especially in complex and dynamic flows. In addition, comprehensively considering the sensor placement under different flow and robot operating conditions, the proposed method is expected to provide an optimal solution for the overall sensing performance of the ALL system. To demonstrate the effectiveness of the proposed method, a case study of background flow speed estimation of oscillating underwater robots of different shapes in a uniform flow is presented.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Object Detection Methods for a Robot Soccer

Object Detection Methods for a Robot Soccer

引用

Information, Control, and Communication Technologies (ICCT), International Conference on

作者： Ramir Sultanov Roman Lavrenov Shifa Sulaiman Yang Bai Mikhail Svinin Evgeni Magid Laboratory of Intelligent Robotics Systems (LIRS) Institute of Information Technology and Intelligent Systems Kazan Federal University Kazan Russia Information Science and Engineering Department Ritsumeikan University Biwako-Kusatsu Campus Shiga Japan

Soccer tournaments between robot teams are being held around the world to encourage robotic research. An accurate detection and tracking of a ball position, an identification of robots and objects during a game are crucial for robot teams. In this paper, object detection methods for identifying robots and a ball during a robot soccer game are presented. Standard OpenCV library functions were adjusted for a ball and robots' detection. Simulation studies were carried out in Gazebo environment to compare a performance of various methods discussed in this paper.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MCTS-Judge: Test-Time Scaling in LLM-as-a-Judge for Code Correctness Evaluation

arXiv

引用

arXiv 2025年

作者： Wang, Yutong Ji, Pengliang Yang, Chaoqun Li, Kaixin Hu, Ming Li, Jiaoyang Sartoretti, Guillaume Department of Mechanical Engineering National University of Singapore Singapore Robotics Institute Carnegie Mellon University United States School of Computing National University of Singapore Singapore Department of Electrical and Computer Systems Monash University Australia

The LLM-as-a-Judge paradigm shows promise for evaluating generative content but lacks reliability in reasoning-intensive scenarios, such as programming. Inspired by recent advances in reasoning models and shifts in scaling laws, we pioneer bringing test-time computation into LLM-as-a-Judge, proposing MCTS-Judge, a resource-efficient, System-2 thinking framework for code correctness evaluation. MCTS-Judge leverages Monte Carlo Tree Search (MCTS) to decompose problems into simpler, multi-perspective evaluations. Through a node-selection strategy that combines self-assessment based on historical actions in the current trajectory and the Upper Confidence Bound for Trees based on prior rollouts, MCTS-Judge balances global optimization and refinement of the current trajectory. We further designed a high-precision, unit-test-level reward mechanism to encourage the Large Language Model (LLM) to perform line-by-line analysis. Extensive experiments on three benchmarks and five LLMs demonstrate the effectiveness of MCTS-Judge, which improves the base model’s accuracy from 41.0% to 80.0%, surpassing the o1-series models with 3× fewer tokens. Further evaluations validate the superiority of its reasoning trajectory in logic, analytics, thoroughness, and overall quality, while revealing the test-time scaling law of the LLM-as-a-Judge paradigm. Copyright © 2025, The Authors. All rights reserved.

关键词： Scaling laws

来源：评论

学校读者我要写书评

暂无评论

Generalized Net Model of Coyote Optimization Algorithm

引用

International Journal Bioautomation 2022年第4期26卷 353-360页

作者： Roeva, Olympia Zoteva, Dafina Vassilev, Peter Institute of Biophysics and Biomedical Engineering Bulgarian Academy of Sciences Acad. G. Bonchev Str.Bl. 105 Sofia1113 Bulgaria Department of Mehatronic Bio/Technological Systems Institute of Robotics Bulgarian Academy of Sciences Sofia1113 Bulgaria Faculty of Mathematics and Informatics Sofia University "St. Kliment Ohridski" 5 James Bourchier Blvd. Sofia1164 Bulgaria

In the presented paper, the functioning of the coyote optimization algorithm (COA) is described using the apparatus of generalized nets (GNs). The COA is a population-based metaheuristic for optimization inspired by the Canis latrans species. Based on a Universal GN-model of population-based metaheuristics, а GN-model of COA is constructed by setting different characteristic functions of the GN-tokens. The presented GN-model successfully describes the considered metaheuristic algorithm, conducting basic steps and performing an optimal search © 2022 by the authors. Licensee institute of Biophysics and Biomedical engineering, Bulgarian Academy of Sciences. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://***/licenses/by/4.0/)

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Towards Fast Face Image Quality Assessment via Latent Diffusion Model 18th

Towards Fast Face Image Quality Assessment via Latent Diffu...

引用

18th Chinese Conference on Biometric Recognition, CCBR 2024

作者： Yan, Zheyu Zhao, Weisong Zhu, Xiangyu Gao, Li Zhang, Xiao-Yu Lei, Zhen State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China China Mobile Financial Technology Co. Ltd. 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 and Innovation Chinese Academy of Sciences Hong Kong Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9789819610679

Face recognition technology has gradually come into wide application in real life. However, in real-life unconstrained scenarios, low-quality images could be matched to unpredictable individuals, thereby affecting the stability of recognition and even causing security problems. Conducting quality assessment on face images before facial recognition can help alleviate these problems by rejecting low-quality samples. In this paper, we propose a Fast Diffusion-model-based Face Image Quality Assessment method (FDif-FIQA). It uses a diffusion model to perturb face images and measures image quality based on the similarity of features before and after the perturbation. The denoising process is transferred from the pixel space to the latent space, thereby reducing the computational cost. We evaluated the performance of this method with multiple mainstream face recognition models on various public datasets. Compared to state-of-the-art methods, our approach demonstrates highly competitive performance and significant improvements in computational efficiency. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Resilient distributed optimization under mobile malicious attacks

引用

IFAC-PapersOnLine 2023年第2期56卷 997-1002页

作者： Yuan Wang Changxin Liu Hideaki Ishii Karl Henrik Johansson Department of Robotics Hunan University Changsha China Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology and Digital Futures Stockholm Sweden Department of Computer Science Tokyo Institute of Technology Yokohama Japan

This article addresses the distributed optimization problem in the presence of malicious adversaries that can move within the network and induce faulty behaviors in the attacked nodes. We first investigate the vulnerabilities of a consensus-based secure distributed optimization protocol under mobile adversaries. Then, a modified resilient distributed optimization algorithm is proposed. We develop conditions on the network structure for both complete and non-complete directed graph cases, under which the proposed algorithm guarantees that the estimates by regular nodes converge to the convex combination of the minimizers of their local functions. Simulations are carried out to verify the effectiveness of our approach.

关键词： Fault-tolerant distributed optimization multi-agent systems network security mobile adversary agents

来源：评论

学校读者我要写书评

暂无评论

MEM: Multi-Modal Elevation Mapping for robotics and Learning

MEM: Multi-Modal Elevation Mapping for Robotics and Learning

引用

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

作者： Gian Erni Jonas Frey Takahiro Miki Matias Mattamala Marco Hutter Department of Mechanical and Process Engineering ETH Zürich Zürich Switzerland Max Planck Institute for Intelligent Systems Tübingen Germany Oxford Robotics Institute at the University of Oxford UK

Elevation maps are commonly used to represent the environment of mobile robots and are instrumental for locomotion and navigation tasks. However, pure geometric information is insufficient for many field applications that require appearance or semantic information, which limits their applicability to other platforms or domains. In this work, we extend a 2.5D robot-centric elevation mapping framework by fusing multi-modal information from multiple sources into a popular map representation. The framework allows inputting data contained in point clouds or images in a unified manner. To manage the different nature of the data, we also present a set of fusion algorithms that can be selected based on the information type and user requirements. Our system is designed to run on the GPU, making it real-time capable for various robotic and learning tasks. We demonstrate the capabilities of our framework by deploying it on multiple robots with varying sensor configurations and showcasing a range of applications that utilize multi-modal layers, including line detection, human detection, and colorization.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deterministic Framework based Structured Learning for Quadrotors

Deterministic Framework based Structured Learning for Quadro...

引用

International Conference on Methods and Models in Automation and robotics (MMAR)

作者： Rupam Singh Jan Steinbrener Stephan Weiss The Faculty of Engineering The Maersk Mc-Kinney Moller Institute SDU Robotics Odense Denmark Control of Networked Systems Institute for Intelligent System Technologies Alpen Adria Universität Klagenfurt Austria

The design of a continuous learning controller for quadrotors often entails some specific implementations that require significant system knowledge and are prone to experience catastrophic forgetting. To address these challenges, a deterministic approach is trained using a quadrotor on a relatively small amount of automatically generated data. The Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm is utilized to develop the policy for learning the maneuvers of a quadrotor and controlling it alongside the low-level controller. The algorithm outlined demonstrates proficiency in handling large state spaces and actions that are continuous. It integrates clipped double Q-learning, target policy smoothing, and delayed policy updates, all of which contribute to its effectiveness in training. The proposed control technique’s efficacy is evaluated through numerical simulations conducted on a quadrotor in both standard and windy conditions. The results identified that learning with TD3 reduced the overestimation bias, improved the convergence accuracy, and achieved efficient maneuver with less tracking error by using the dense reward structure.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Robust Surveillance System for AGV Using Forward-Downward Visual Measurements

A Robust Surveillance System for AGV Using Forward-Downward ...

引用

第35届中国控制与决策会议

作者： Sichao Zhang Wei Liang Xudong Yuan Haibo An Meng Zheng Yinlong Zhang State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of Sciences Key Laboratory of Networked Control Systems Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences University of Chinese Academy of Sciences Science and Technology on Information Systems Engineering Laboratory the 28th Research Institute of CETC

Automatic Guided Vehicle(AGV) has been widely used in the warehouse for transporting the bulky and heavy ***,the AGV may deviate the regular trajectories in presence of incorrect or untimely commands sent form the server due to,e.g.,cyber attacks,unexpected blocks of the wireless *** order to ensure AGV running safely,this paper presents a visual surveillance system by making full use of the measurements from the forward and downward ***,the forward camera estimates the AGV positions and attitudes by tracking the surrounding landmarks detected from the forward image ***,the downward camera is used to detect the QR codes fixed on the floor and estimate the AGV poses in the absolute reference *** from that,the AGV poses from the downward camera could correct scale and poses estimated the forward *** proposed method has been extensively performed on the developed *** results proves the effectiveness in using the complementary forwarddownward visual measurements for AGV security surveillance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparison of Monocular ROS-Based Visual SLAM Methods 1

引用

7th International Conference on Interactive Collaborative robotics, ICR 2022

作者： Safarova, Liaisan Abbyasov, Bulat Tsoy, Tatyana Li, Hongbing Magid, Evgeni Laboratory of Intelligent Robotic Systems Intelligent Robotics Department Institute of Information Technology and Intelligent Systems Kazan Federal University Kremlyovskaya Str. 35 Kazan420111 Russia Department of Instrument Science and Engineering Shanghai Jiao Tong University Shanghai China Tikhonov Moscow Institute of Electronics and Mathematics HSE University Tallinn Str 34 Moscow123592 Russia

ISBN: (数字)9783031236099

ISBN: (纸本)9783031236082

Simultaneous Localization and Mapping (SLAM) is a robot navigation approach used to estimate a movement of a sensor in an unknown environment. SLAM application examples include urban search and rescue operations in high-risk environments, visual surveillance and service robotics. Compared to laser-range finders, visual sensors are more light weight, have less power consumption and provide more vast amount of environmental information. Visual SLAM methods are based on visual information only and employ monocular, stereo or RGD-D cameras as input sensors. Monocular SLAM methods are often preferred for a robotic platform when cost, energy and system weight requirements are limited. Calculation of errors and testing on ready-made datasets allow to check applicability of an algorithm in real-world scenarios with less efforts than experiments with a real robot. Verification of a sensor position and robot trajectory estimation accuracy is achieved by measuring Absolute Trajectory Error (ATE), Relative Pose Error (RPE) and Root Mean Square Error (RMSE). This article presents analysis and comparison of the most widely used Visual SLAM monocular algorithms built for Robot Operating System (ROS): ORB-SLAM2, ORB-SLAM3, DSO and LDSO. The KITTI and Euroc MAV datasets were selected to evaluate the algorithms’ performance. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Robot Operating System

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：