检索结果-内蒙古大学图书馆

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

Data-based Stabilization of Unknown Discrete-time 2-D Roesser systems

Data-based Stabilization of Unknown Discrete-time 2-D Roesse...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Runmin Yang Rongni Yang Renjie Ma Yanzheng Zhu Peng Shi School of Control Science and Engineering Shandong University Jinan China State Key Laboratory of Robotics and Systems Harbin Institute of Technology Harbin China College of Electrical Engineering and Automation Shandong University of Science and Technology Qingdao China School of Electrical and Mechanical Engineering University of Adelaide Adelaide SA Australia

ISBN: (数字)9798331528041

ISBN: (纸本)9798331528058

This paper studies the stabilization problem of discrete-time two-dimensional (2-D) systems represented by Roesser based on available data. First of all, based on the pre-collected input-state data, the original system is transformed into a data-based form. Then a set is established to represent all systems capable of generating the given data, thereby indirectly stabilizing the original system by stabilizing all systems within this set. Next, by utilizing the S-procedure, sufficient conditions are established for the resultant closed-loop systems that incorporate a state feedback controller based on collected data. Finally, an example is given to demonstrate the effectiveness of the proposed approach.

关键词： Sufficient conditions State feedback Two-dimensional displays Transforms Machine learning Stability analysis Data models Numerical models Closed loop systems Numerical stability

来源：评论

学校读者我要写书评

暂无评论

Model-Free Predictive Control for Harmonic Suppression of PMSMs Based on Adaptive Resonant Controller

引用

IEEE Transactions on Energy Conversion 2025年

作者： Li, Teng Sun, Xiaodong Su, Zonghao Zha, Xuhao Dianov, Anton Prakht, Vladimir Demidova, Galina Ma, Jinlin Jiangsu University Automotive Engineering Research Institute Zhenjiang212013 China Wenzhou University Pingyang Institute of Intelligent Manufacturing Wenzhou325035 China Ural Federal University Department of Electrical Engineering Ekaterinburg620062 Russia ITMO University Faculty of Control Systems and Robotics Petersburg197101 Russia Jiangsu University School of Automotive and Traffic Engineering Zhenjiang212013 China

To simultaneously suppress the periodic and aperiodic disturbances experienced by permanent magnet synchronous motors in model predictive control, a model-free predictive current control with adaptive resonance control based on an ultra-local model is proposed. Firstly, the ultra-local models of the speed loop and the current loop are established respectively, and the unmodeled and uncertain unknown part F in the ultra-local model is estimated by using a high-order fast terminal sliding mode observer, and its stability is analyzed. Then, an adaptive resonant controller (ARC) is designed to suppress the periodic disturbance caused by the dead zone effect. The ARC and the model-free control based on the ultra-local model are combined to compensate for their respective shortcomings, achieving the suppression of periodic and aperiodic disturbances in the system. Finally, by comparing with the traditional duty cycle model predictive control and the model-free model predictive control without ARC, the proposed scheme is proved to be robust to periodic and aperiodic disturbances. © 2025 IEEE. All rights reserved.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

Neural-iLQR: A Learning-Aided Shooting Method for Trajectory Optimization

Neural-iLQR: A Learning-Aided Shooting Method for Trajectory...

引用

2023 IEEE International Conference on robotics and Biomimetics, ROBIO 2023

作者： Cheng, Zilong Li, Yulin Chen, Kai Duan, Jianghua Ma, Jun Lee, Tong Heng National University of Singapore Department of Electrical and Computer Engineering Singapore The Hong Kong University of Science and Technology Department of Mechanical and Aerospace Engineering Hong Kong The Hong Kong University of Science and Technology Division of Emerging Interdisciplinary Areas Hong Kong Robotics and Autonomous Systems Thrust Guangzhou China Hkust Shenzhen-Hong Kong Collaborative Innovation Research Institute Shenzhen China

ISBN: (纸本)9798350325706

Iterative linear quadratic regulator (iLQR) has gained wide popularity in addressing trajectory optimization problems with nonlinear system models. However, as a model-based shooting method, it relies heavily on an accurate system model to update the optimal control actions and the trajectory determined with forward integration, thus becoming vulnerable to inevitable model inaccuracies. Recently, substantial research efforts in learning-based methods for optimal control problems have been progressing significantly in addressing unknown system models, particularly when the system has complex interactions with the environment. Yet an incremental machine learning method or a deep neural network is normally required to fit a substantial scale of sampling motion data. Existing works mainly focus on capturing the whole picture of the motion pattern from trial data (which is essentially noisy and hard to identify with any simple predefined structures) for complex robot systems. Instead, we present Neural-iLQR, a learning-aided shooting method over the unconstrained control space, in which a neural network with a simple structure is used to drive the optimization process towards optimal direction. Through comprehensive evaluations on two illustrative control tasks using three different kinds of lightweight network structures, the proposed method is shown to outperform the conventional iLQR significantly with fast and continuous cost convergence in the presence of inaccuracies in system models, which demonstrates the generalizability and robustness of the proposed learning-aided method. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

How to turn your camera into a perfect pinhole model

arXiv

引用

arXiv 2023年

作者： De Boi, Ivan Pathak, Stuti Oliveira, Marina Penne, Rudi InViLab University of Antwerp Groenenborgerlaan 171 Antwerp2020 Belgium Institute of Systems and Robotics Department of Electrical and Computer Engineering University of Coimbra Coimbra3004-531 Portugal

Camera calibration is a first and fundamental step in various computer vision applications. Despite being an active field of research, Zhang's method remains widely used for camera calibration due to its implementation in popular toolboxes like MATLAB and OpenCV. However, this method initially assumes a pinhole model with oversimplified distortion models. In this work, we propose a novel approach that involves a pre-processing step to remove distortions from images by means of Gaussian processes. Our method does not need to assume any distortion model and can be applied to severely warped images, even in the case of multiple distortion sources, e.g., a fisheye image of a curved mirror reflection. The Gaussian processes capture all distortions and camera imperfections, resulting in virtual images as though taken by an ideal pinhole camera with square pixels. Furthermore, this ideal GP-camera only needs one image of a square grid calibration pattern. This model allows for a serious upgrade of many algorithms and applications that are designed in a pure projective geometry setting but with a performance that is very sensitive to nonlinear lens distortions. We demonstrate the effectiveness of our method by simplifying Zhang's calibration method, reducing the number of parameters and getting rid of the distortion parameters and iterative optimization. We validate by means of synthetic data and real world images. The contributions of this work include the construction of a virtual ideal pinhole camera using Gaussian processes, a simplified calibration method and lens distortion removal. Copyright © 2023, The Authors. All rights reserved.

关键词： Pinhole cameras

来源：评论

学校读者我要写书评

暂无评论

Adaptive Fuzzy Generalized Predictive Control of pH in Tubular Photobioreactors on Microalgae Plant

Adaptive Fuzzy Generalized Predictive Control of pH in Tubul...

引用

On-Line Conference (ONCON), Industrial Electronics Society Annual

作者： Mafalda Amaro Jérôme Mendes Tiago Matias Rui Araújo Department of Electrical and Computer Engineering Institute of Systems and Robotics University of Coimbra Coimbra Portugal Department of Mechanical Engineering CEMMPRE ARISE University of Coimbra Coimbra Portugal Oncontrol Technologies Coimbra Portugal

Culture conditions in a photobioreactor on a microalgae plant are essential for production rates, and the pH value is one of the critical variables for a harmonizing process. However, the biological nature of microalgae growth represents a complex reaction that is arduous to model and control. This work proposes an approach of the application of adaptive identification and predictive control to regulate the pH in a photobioreactor in a microalgae production system. The proposed approach is composed of two main stages: identification and control. The identification is performed by a Takagi-Sugeno (T-S) fuzzy model, which will be learned with an offline strategy, by Fuzzy c-means, for the antecedent part, and by the Least Squares Method (LSM), for the consequent part. Then, the model is updated with an online method, the Recursive Least Squares with Adaptive Directional Forgetting (RLS-ADF) factor algorithm. The control scheme is based on a Generalized Predictive Control approach, which is a Model Predictive Controller (MPC), with the adaptive T-S fuzzy model designed in the identification stage. In this way, the model parameters from GPC are online adapted by RLS-ADF. To validate the control structure, the proposed approach was tested by using an estimated model from real data of a microalgae production process.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Biodegradable Gliding Paper Flyers Fabricated Through Inkjet Printing

Biodegradable Gliding Paper Flyers Fabricated Through Inkjet...

引用

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

作者： Luca Girardi Rui Wu Yuki Fukatsu Hiroki Shigemune Stefano Mintchev Department of Environmental Systems Science Environmental Robotics Laboratory ETH Zurich Zurich Switzerland Swiss Federal Institute for Forest Snow and Landscape Research (WSL) Birmensdorf Switzerland Department of Electrical Engineering Shibaura Institute of Technology Tokyo Japan

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Seed-inspired minimalist microflyers are showing potential as dispersal platforms for sensor networks and seeds. Their function relies on the sheer number of low-cost flyers, inevitably raising concerns about the post-operation environmental impact. We propose a biodegradable paper glider platform fabricated through origami inkjet printing. This method can fold origami along printing patterns on different paper varieties. We created a printing pattern that allows 2D paper sheets to self-fold into a 3D flying wing glider with designable wing geometry and center of gravity (CG). The design allows stable and repeatable gliding behavior, proven in our gliding tests. It successfully achieves the dispersal of multiple gliders from a hovering drone, covering an average horizontal distance larger than the release height. We also tested the biodegradation of different paper types compatible with the printing method, showing near-complete degradation after 15 weeks in moist soil. Our study presents a novel, potentially scalable approach for fabricating environmentally friendly microflyers, offering new avenues for remote environmental sensing and automated forest restoration programs.

关键词： Geometry Atmospheric modeling Forestry Aerodynamics Three-dimensional printing Stability analysis Ink jet printing Seeds (agriculture) Thermal stability Paints

来源：评论

学校读者我要写书评

暂无评论

AN ADDRESSABLE ELECTROWETTING VALVE FOR CENTRIFUGAL MICROFLUIDICS 26

AN ADDRESSABLE ELECTROWETTING VALVE FOR CENTRIFUGAL MICROFLU...

引用

26th International Conference on Miniaturized systems for Chemistry and Life Sciences, MicroTAS 2022

作者： Xia, Yanming Song, Chao Meng, Yingchao Xue, Peng deMello, Andrew J. Gao, Quan Stavrakis, Stavros Ma, Shenglin Cao, Xiaobao Department of Mechanical & Electrical Engineering Xiamen University Xiamen China Institute for Chemical and Bioengineering ETH Zürich Zürich8093 Switzerland Institute of Robotics and Intelligent Systems ETH Zürich Zürich8006 Switzerland Guangzhou Laboratory Guangdong Guangzhou510320 China

ISBN: (纸本)9781733419048

This paper presents and assesses an addressable electrowetting centrifugal (EWC) valve, which can rapidly and selectively open through (remote) control of the applied electric field. The utility of EWC valves is showcased by the implementation of fluid complexly controlling and CD4 cell antigens detection. © 2022 MicroTAS 2022 - 26th International Conference on Miniaturized systems for Chemistry and Life Sciences. All rights reserved.

关键词： Wetting

来源：评论

学校读者我要写书评

暂无评论

Forewarning Crossing Intention of Pedestrians Using Multimodal Deep Learning Approach 7

Forewarning Crossing Intention of Pedestrians Using Multimod...

引用

7th International Conference on Green Technology and Sustainable Development, GTSD 2024

作者： Nguyen, Chi-Tam Duong, Minh-Thien Phan, Thanh-Danh Nguyen, Van-Binh Le, My-Ha Hcmc University of Technology and Education Intelligent System Laboratory Ho Chi Minh City Viet Nam Soongsil University Dept. of Information and Telecommunication Engineering Seoul Korea Republic of Chungbuk National University Dept. of Intelligent Systems and Robotics Cheongju Korea Republic of Institute of Engineering-Technology Thu Dau Mot University Thu Dau Mot City Viet Nam Hcmc University of Technology and Education Faculty of Electrical and Electronics Engineering Ho Chi Minh City Viet Nam

ISBN: (纸本)9798350386073

Nowadays, traffic accidents not only come from public transportation but also from pedestrians. Therefore, designing a solution to protect pedestrian safety is essential. This article proposes a system for forewarning the crossing intentions of pedestrians, comprising the tasks of detection, tracking, and intention prediction. Firstly, our proposed system performs the detection and pose estimation of pedestrians using the YOLOv7-Pose model. Subsequently, the OC-SORT algorithm is employed for the tracking task. Ultimately, an efficient architecture based on the VoVNet backbone and Temporal Shift Module is provided to forewarn whether pedestrians will cross the road or not. The input of the proposed network in multimodality includes RGB image or semantic image map, keypoints, and vehicle speed. In addition, the bag-of-freebies technique is applied to enhance the model's overall performance and address the issue of biased model creation caused by imbalanced data. Comprehensive experiments performed on the JAAD benchmark dataset demonstrate that our proposed method performs better than existing benchmark classification models. © 2024 IEEE.

关键词： Mass transportation

来源：评论

学校读者我要写书评

暂无评论

Unveiling Group-Specific Distributed Concept Drift: A Fairness Imperative in Federated Learning

arXiv

引用

arXiv 2024年

作者： Salazar, Teresa Gama, João Araujo, Helder Abreu, Pedro Henriques The Centre for Informatics and Systems Department of Informatics Engineering University of Coimbra Coimbra3030-790 Portugal INESC TEC The Faculty of Economy University of Porto Porto4200-465 Portugal The Institute of Systems and Robotics Department of Electrical and Computer Engineering University of Coimbra Coimbra3004-531 Portugal

In the evolving field of machine learning, ensuring fairness has become a critical concern, prompting the development of algorithms designed to mitigate bias in decision-making processes. However, achieving fairness in the presence of group-specific concept drift remains an unexplored frontier, and our research represents pioneering efforts in this regard. Group-specific concept drift refers to situations where one group experiences concept drift over time while another does not, leading to a decrease in fairness even if accuracy remains fairly stable. Within the framework of Federated Learning, where clients collaboratively train models, its distributed nature further amplifies these challenges since each client can experience group-specific concept drift independently while still sharing the same underlying concept, creating a complex and dynamic environment for maintaining fairness. The most significant contribution of our research is the formalization and introduction of the problem of group-specific concept drift and its distributed counterpart, shedding light on its critical importance in the realm of fairness. Additionally, leveraging insights from prior research, we adapt an existing distributed concept drift adaptation algorithm to tackle group-specific distributed concept drift which uses a multi-model approach, a local group-specific drift detection mechanism, and continuous clustering of models over time. The findings from our experiments highlight the importance of addressing group-specific concept drift and its distributed counterpart to advance fairness in machine *** Codes 68T01 © 2024, CC BY.

关键词： Machine learning

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：