检索结果-内蒙古大学图书馆

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

作者： Qianxin Qu Yijin Xiong Guipeng Zhang Xin Wu Xiaohan Gao Xin Gao Hanyu Li Shichun Guo Guoying Zhang School of Artificial Intelligence China University of Mining and Technology -Beijing Beijing China State Key Laboratory of Automotive Safety and Energy and School of Vehicle and Mobility Tsinghua University Beijing China Computer Science and Technology in Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Cooperative LiDAR systems integrating vehicles and road infrastructure, termed V2I calibration, exhibit substantial potential, yet their deployment encounters numerous challenges. A pivotal aspect of ensuring data accuracy and consistency across such systems involves the calibration of LiDAR units across heterogeneous vehicular and infrastructural endpoints. This necessitates the development of calibration methods that are both real-time and robust, particularly those that can ensure robust performance in urban canyon scenarios without relying on initial positioning values. Accordingly, this paper introduces a novel approach to V2I calibration, leveraging spatial association information among perceived objects. Central to this method is the innovative Overall Intersection over Union (oIoU) metric, which quantifies the correlation between targets identified by vehicle and infrastructure systems, thereby facilitating the real-time monitoring of calibration results. Our approach involves identifying common targets within the perception results of vehicle and infrastructure LiDAR systems through the construction of an affinity matrix. These common targets then form the basis for the calculation and optimization of extrinsic parameters. Comparative and ablation studies conducted using the DAIR-V2X dataset substantiate the superiority of our approach. For further insights and resources, our project repository is accessible at https://***/MassimoQu/v2i-calib.

关键词： Point cloud compression Laser radar Accuracy Roads Stability criteria Real-time systems Calibration Safety Synchronization Reliability

来源：评论

学校读者我要写书评

暂无评论

Damage Identification in Bridge Structures Based on a Novel Whale-Sand Cat Swarm optimization Algorithm and an Improved Objective Function

引用

Structural Control and Health Monitoring 2025年第1期2025卷

作者： Chen, Zhen Wang, Yikai Wang, Hui Liu, Shiming Chan, Tommy H. T. School of Civil Engineering and Communication North China University of Water Resources and Electric Power Zhengzhou450045 China Brisbane4000 Australia Key Laboratory of Geotechnical Mechanics and Engineering of the Ministry of Water Resources Changjiang River Scientific Research Institute Wuhan430010 China

Structural damage identification (SDI) serves as an indirect approach that has the potential to meet real-time monitoring of structures. However, the identification accuracy and efficiency of some methods need to be improved, especially when there are some uncertain interfering factors or noise. This paper presents a new optimization algorithm and an improved objective function for inverse problems of SDI, offering an effective solution for bridge damage identification under uncertain noise interference and incomplete modal data. In this study, by hybridizing the whale optimization algorithm and the sand cat swarm optimization, a novel whale-sand cat swarm optimization (W-SCSO) method is proposed for SDI. The cubic chaotic mapping is introduced for initialization of the W-SCSO method, and then the lens opposition-based learning and the stochastic differential mutation are employed to enhance the search capability and convergence accuracy of the proposed algorithm. Besides, the mode shape curvature, the frequency change ratio, and the L1/2 sparse regularization are used to improve the objective function. Four other existing state-of-the-art methods are used to verify the performance of the proposed W-SCSO method by the CEC2017 benchmark functions and a simply supported beam finite model. The comparative analysis highlights the feasibility and effectiveness of the proposed method in the considered cases. Moreover, an aluminum alloy simply supported beam was conducted for the SDI experiment to further prove the effectiveness of the improved method in practice. Simulation and experimental results show that the proposed method effectively locates and quantifies stiffness reduction in bridge structures, which maintains high accuracy in damage identification despite potential modal incompleteness and uncertain measurement noise interference. Copyright © 2025 Zhen Chen et al. Structural Control and Health Monitoring published by John Wiley & Sons Ltd.

关键词： Modal analysis

来源：评论

学校读者我要写书评

暂无评论

Evolution of Thought: Diverse and High-Quality Reasoning via Multi-Objective optimization

arXiv

引用

arXiv 2024年

作者： Qi, Biqing Qian, Zhouyi Luo, Yiang Gao, Junqi Li, Dong Zhang, Kaiyan Zhou, Bowen Shanghai Artificial Intelligence Laboratory China School of Mathematics Harbin Institute of Technology China Department of Control Science and Engineering Harbin Institute of Technology China Department of Electronic Engineering Tsinghua University China

As multi-modal large language models (MLLMs) are increasingly applied to complex reasoning tasks, the diversity and quality of reasoning paths become crucial factors affecting their performance. Although current methods aim to enhance reasoning quality through path expansion, they often neglect the diversity of reasoning paths and effective information sharing, leading to local optima and inefficiency. To address these challenges, we propose Evolution of Thought (EoT), a multi-objective framework designed to improve reasoning by fostering both high-quality and diverse reasoning paths. Specifically, we introduce the Non-dominated Sorting Genetic Algorithm II for multi-objective optimization, utilizing crossover and mutation operators to promote greater diversity in reasoning solutions. Additionally, we propose a Condensation-Aggregation mechanism to cluster and eliminate redundant paths, facilitate improved information sharing among parent nodes, and ultimately enhance both the efficiency and quality of the reasoning process. Validation experiments on various vision-language and language reasoning tasks demonstrate that EoT achieves superior reasoning performance and efficiency compared to other competitive baselines. Our study provides a novel perspective on the design of heuristic reasoning frameworks for MLLMs. © 2024, CC BY-SA.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

To Cooperate or Not: Multi-Agent Reinforcement Learning-Based On-Ramp Merging Strategies for Autonomous Vehicles

To Cooperate or Not: Multi-Agent Reinforcement Learning-Base...

引用

IEEE International Conference on Automation Science and Engineering (CASE)

作者： Dan Wang Gangyan Xu Zhizhou Wu Department of Aeronautical and Aviation Engineering The Hong Kong Polytechnic University Hong Kong SAR The Key Laboratory of Road and Traffic Engineering Ministry of Education Tongji University Shanghai China

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

On-ramp merging for Autonomous Vehicles (AVs) is a challenging task that involves complex interactions of multiple vehicles and should consider both the safety and efficiency. Extensive works have been conducted on merging decisions using various control and learning-based methods. Although these methods are proved effective in different scenarios, debate still exist whether AVs should cooperate or not during the processes, or whether such cooperation should be considered in the method design. To answer these questions, this paper formulates the problem of on-ramp merging for AVs as a Partially Observable Markov Decision Process (POMDP), and develops several cooperative and non-cooperative Multi-Agent Reinforcement Learning (MARL) algorithms based on state-of-the-art models, i.e., Independent DQN, Bi-level Actor-Critic, and MADDPG. Experimental case studies are conducted to compare the performance of these algorithms, in terms of training efficiency, merge rate, average speed, and safety metrics (such as collision rates and acceleration). Surprisingly, results reveal that it is not always good to cooperate in merging process and the non-cooperation method performs better in many cases. The findings also emphasize the importance of strategy selection based on specific traffic scenarios and objectives. Besides, by understanding the interplay between cooperation and independent optimization, our work provides insights for safer and more efficient traffic management.

关键词： Training Measurement Heuristic algorithms Merging Decision making Reinforcement learning Stability analysis Safety Vehicle dynamics Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Projection-free variance reduction methods for stochastic constrained multi-level compositional optimization 24

Projection-free variance reduction methods for stochastic co...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Wei Jiang Sifan Yang Wenhao Yang Yibo Wang Yuanyu Wan Lijun Zhang National Key Laboratory for Novel Software Technology Nanjing University Nanjing China National Key Laboratory for Novel Software Technology and School of Artificial Intelligence Nanjing University Nanjing China School of Software Technology Zhejiang University Ningbo China and and National Key Laboratory for Novel Software Technology Nanjing University Nanjing China

This paper investigates projection-free algorithms for stochastic constrained multi-level optimization. In this context, the objective function is a nested composition of several smooth functions, and the decision set is closed and convex. Existing projection-free algorithms for solving this problem suffer from two limitations: 1) they solely focus on the gradient mapping criterion and fail to match the optimal sample complexities in unconstrained settings; 2) their analysis is exclusively applicable to non-convex functions, without considering convex and strongly convex objectives. To address these issues, we introduce novel projection-free variance reduction algorithms and analyze their complexities under different criteria. For gradient mapping, our complexities improve existing results and match the optimal rates for unconstrained problems. For the widely-used Frank-Wolfe gap criterion, we provide theoretical guarantees that align with those for single-level problems. Additionally, by using a stagewise adaptation, we further obtain complexities for convex and strongly convex functions. Finally, numerical experiments on different tasks demonstrate the effectiveness of our methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

REFLECTOOL: Towards Reflection-Aware Tool-Augmented Clinical Agents

arXiv

引用

arXiv 2024年

作者： Liao, Yusheng Jiang, Shuyang Wang, Yanfeng Wang, Yu Shanghai Jiao Tong University China Fudan University China Shanghai Artificial Intelligence Laboratory China

Large Language Models (LLMs) have shown promising potential in the medical domain, assisting with tasks like clinical note generation and patient communication. However, current LLMs are limited to text-based communication, hindering their ability to interact with diverse forms of information in clinical environments. Despite clinical agents succeeding in diverse signal interaction, they are oriented to a single clinical scenario and hence fail for broader applications. To evaluate clinical agents holistically, we propose ClinicalAgent Bench (CAB), a comprehensive medical agent benchmark consisting of 18 tasks across five key realistic clinical dimensions. Building on this, we introduce REFLECTOOL, a novel framework that excels at utilizing domain-specific tools within two stages. The first optimization stage progressively enlarges a long-term memory by saving successful solving processes and tool-wise experience of agents in a tiny pre-defined training set. In the following inference stage, REFLECTOOL can search for supportive successful demonstrations from already built long-term memory to guide the tool selection strategy, and a verifier improves the tool usage according to the tool-wise experience with two verification methods–iterative refinement and candidate selection. Extensive experiments on CAB demonstrate that REFLECTOOL surpasses the pure LLMs with more than 10 points and the well-established agent-based methods with 3 points, highlighting its adaptability and effectiveness in solving complex clinical tasks. Our code and datasets are available at https://***/BlueZeros/ReflecTool. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

A new approach for non-Gaussian vibration analysis of hyperbolic tangent package with a critical component

A new approach for non-Gaussian vibration analysis of hyperb...

引用

作者： Yang, Song-Ping Su, Ri-Qing Wang, Zhi-Wei Chen, Yu Packaging Engineering Institute College of Packaging Engineering Jinan University Zhuhai China MOE Key Laboratory of Disaster Forecast and Control in Engineering School of Mechanics and Construction Engineering Jinan University Guangzhou China Key Laboratory of Product Packaging and Logistics of Guangdong Higher Education Institutes Jinan University Zhuhai China International Energy College/Energy and Electricity Research Center Jinan University Zhuhai China

A new approach is proposed to analyze the non-Gaussian random vibration of hyperbolic tangent package. Firstly, the non-Gaussian vibration noise of specified mean, variance, skewness, and kurtosis is developed by Hermite polynomial and verified by Gaussian mixture model theory. Secondly, next to analyzing an analytical and numerical response of the two degrees of freedom linear package, the acceleration response of the two degrees of freedom hyperbolic tangent package system under non-Gaussian vibration excitation is obtained though the Hermite polynomial and Runge–Kutta method, and the effects of the external excitation and system parameters are investigated. Finally, on the basis of the first-passage probability of the acceleration response, the reliability analysis method is introduced. The analysis provides a guidance to the vibration reliability analysis and packaging optimization design. © 2022 John Wiley & Sons Ltd.

关键词： Reliability analysis

来源：评论

学校读者我要写书评

暂无评论

State Estimation of Moving Target Using Sequential Range and Doppler Measurements with Swarm of UAV-borne Radars

引用

IEEE Transactions on Aerospace and Electronic systems 2025年

作者： Li, JIng Wen, Liwu Yu, Zehua Ding, Jinshan Xidian University National Key Laboratory of Radar Signal Processing Xi'an710071 China Xidian University School of Electronic Engineering Xi'an710071 China

Estimation of moving target states is always needed in area situational awareness. This work presents a three-stage weighted least squares (3S-WLS) approach that improves the reliability of the estimation of location, velocity and acceleration of moving targets using sequential range and Doppler measurements obtained from swarm UAV-borne radars. First, the sequential locations of the target are accurately estimated using an improved plane approximation algorithm, which avoids second-order measurement errors. Second, the initial velocity and acceleration are estimated through weighted least squares (WLS), with relaxed constraints to resolve Doppler measurement ambiguities. Finally, a joint optimization of target states is performed using a first-order Taylor approximation, further refining estimation accuracy. The Cramér-Rao lower bound (CRLB) of state estimation using spatiotemporal measurements is reformulated, demonstrating the theoretical benefits of the proposed method in improving state estimation performance. Simulation experiments show that the proposed approach provides superior target state estimates compared to other reported methods. © 1965-2011 IEEE.

关键词： Direction of arrival

来源：评论

学校读者我要写书评

暂无评论

Walking-by-Logic: Signal Temporal Logic-Guided Model Predictive Control for Bipedal Locomotion Resilient to External Perturbations

Walking-by-Logic: Signal Temporal Logic-Guided Model Predict...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Zhaoyuan Gu Rongming Guo William Yates Yipu Chen Yuntian Zhao Ye Zhao Laboratory for Intelligent Decision and Autonomous Robots Woodruff School of Mechanical Engineering Georgia Institute of Technology

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

This study proposes a novel planning framework based on a model predictive control formulation that incorporates signal temporal logic (STL) specifications for task completion guarantees and robustness quantification. This marks the first-ever study to apply STL-guided trajectory optimization for bipedal locomotion push recovery, where the robot experiences unexpected disturbances. Existing recovery strategies often struggle with complex task logic reasoning and locomotion robustness evaluation, making them susceptible to failures due to inappropriate recovery strategies or insufficient robustness. To address this issue, the STL-guided framework generates optimal and safe recovery trajectories that simultaneously satisfy the task specification and maximize the locomotion robustness. Our framework outperforms a state-of-the-art locomotion controller in a high-fidelity dynamic simulation, especially in scenarios involving crossed-leg maneuvers. Furthermore, it demonstrates versatility in tasks such as locomotion on stepping stones, where the robot must select from a set of disjointed footholds to maneuver successfully.

关键词： Legged locomotion Perturbation methods Predictive models Robustness Planning Logic Task analysis

来源：评论

学校读者我要写书评

暂无评论

Continual Reinforcement Learning for Autonomous Driving with Application on Velocity Control under Various Environment

Continual Reinforcement Learning for Autonomous Driving with...

引用

Conference on Vehicle Control and Intelligence (CVCI)

作者： Dengwei Wei Jiaming Xing Shuo Yang Yukun Lu Yanjun Huang School of Automotive Studies Tongji University Shanghai China Mechatronic Vehicle Systems Laboratory University of Waterloo Waterloo Canada

Reinforcement learning based methods are extensively studied in autonomous driving. However, most existing methods, suffering from catastrophic forgetting, only work properly under certain scenarios. Therefore, this paper proposes a continual reinforcement learning approach to improve the control adaptability of autonomous driving systems. Specifically, the framework is based on a Soft Actor-Critic algorithm, which includes a shared feature extractor with regularization loss to learn task-specific output mapping. A linear multi-policy heads structure is designed to continuously learn different tasks without interference. Velocity control under various environment is taken as a case study, and three velocity control tasks with a high degree of overlap in the observation spaces are designed. In addition, multi-modal optimization objectives considering safety, efficiency and comfort for the three tasks are designed to evaluate the effectiveness of the proposed approach. The simulation studies are conducted in CARLA, which demonstrates the efficiency of the proposed method in terms of improving the continual learning capability of the model. Overall, the proposed continual reinforcement learning framework contributes to the development of adaptive autonomous driving systems to a large extent.

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：