检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Peng, Zengqi Wang, Yubin Han, Xu Zheng, Lei Ma, Jun Robotics and Autonomous Systems Thrust The Hong Kong University of Science and Technology Guangzhou China Data Science and Analytics Thrust The Hong Kong University of Science and Technology Guangzhou China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology China

Recent advancements in reinforcement learning (RL) demonstrate the significant potential in autonomous driving. Despite this promise, challenges such as the manual design of reward functions and low sample efficiency in complex environments continue to impede the development of safe and effective driving policies. To tackle these issues, we introduce LearningFlow, an innovative automated policy learning workflow tailored to urban driving. This framework leverages the collaboration of multiple large language model (LLM) agents throughout the RL training process. LearningFlow includes a curriculum sequence generation process and a reward generation process, which work in tandem to guide the RL policy by generating tailored training curricula and reward functions. Particularly, each process is supported by an analysis agent that evaluates training progress and provides critical insights to the generation agent. Through the collaborative efforts of these LLM agents, LearningFlow automates policy learning across a series of complex driving tasks, and it significantly reduces the reliance on manual reward function design while enhancing sample efficiency. Comprehensive experiments are conducted in the high-fidelity CARLA simulator, along with comparisons with other existing methods, to demonstrate the efficacy of our proposed approach. The results demonstrate that LearningFlow excels in generating rewards and curricula. It also achieves superior performance and robust generalization across various driving tasks, as well as commendable adaptation to different RL algorithms. Copyright © 2025, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Design and testing of Hybrid Slime Mold Algorithm for Real-Time Adaptive Mobile Robot Path Planning in Dynamic Environments

Design and testing of Hybrid Slime Mold Algorithm for Real-T...

引用

Advancement in Computation & computer Technologies (InCACCT), International Conference on

作者： Sachin Gupta Shivali Gupta Shaik Mohammed Raith Anand Kumar Salil Bharany Vishnu Kant Ch.Sandeep Department of Robotics and Control Engineering School of Electronics and Control Engineering Lovely Professional University Phagwara India Department of Chemistry School of Chemical Engineering and Physical Sciences Lovely Professional University Phagwara India Department of Computer Science and Engineering Lovely Professional University Phagwara Punjab India Chitkara University Institute of Engineering and Technology Chitkara University Rajpura India School of Computer Science and Artificial Intelligence SR University Warangal Telangana

ISBN: (数字)9798331543891

ISBN: (纸本)9798331543907

Dynamic path planning and collision prevention is one of the key tasks for autonomous vehicles in relation to dynamic movement of obstacles. In this paper, a novel hybrid approach based on integration of Slime Mold Algorithm (SMA), Triangle Inequality Principle (TIP), and Partition Method Strategy (PMS) for solution of this problem statement. The SMA algorithm is very flexible and adaptive by nature due to its biological working mechanism which is associated with TIP and PMS strategies in relation to their optimization and efficient path planning capabilities and robust solutions. This integrated module is tested in virtual environment and the results are compared with other updated algorithms such as A*, Genetic Algorithm (GA), and Particle Swarm Optimization (PSO) for the same static and dynamic environment. It has been observed from the results that this hybrid strategy significantly improves the path planning task several times than other algorithms in terms of multiple aspects. Under testing conditions, the path length was reduced to 25% than other algorithms in a dynamic environment. During this calculation, the computational efficiency of the system has been improved to 60% than conventional methods. The chances of collision have been improved to 34.23% especially in environment where the obstacles are moving. The capability of SMA has been improved due to the synergy between TIP and PMS. The dynamic and adaptive nature of this algorithm is suitable for various applications such as search-and-rescue operations, manufacturing units’ automation and other hazardous environment exploration.

关键词： Navigation Heuristic algorithms Virtual environments Path planning Partitioning algorithms Safety Mobile robots Vehicle dynamics Testing Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Analysis of IoT and IoT Security Attacks: Understanding the Threat Landscape

A Comprehensive Analysis of IoT and IoT Security Attacks: Un...

引用

Computational Intelligence, Communication Technology and Networking (CICTN), International Conference on

作者： Himanshi Dhayal Vikas Siwach Harkesh Sehrawat Renu Dalai Department of Computer Science and Engineering UIET Maharshi Dayanand University Rohtak Haryana India University School of Automation and Robotics (USAR) GGSIPU Guru Gobind Singh Indraprastha University Delhi India

ISBN: (数字)9798331530389

ISBN: (纸本)9798331530396

IoT has remarkably changed the internet landscape since its introduction. Today, even an isolated physical device is provided with the internet, which allows it to exchange information with other devices. As much flexibility as these devices offer, they also have numerous security issues, causing threats to its users. Adversaries increasingly exploit the vulnerabilities in Internet of Things devices to execute attacks that can inflict significant harm on individuals, communities, and organizations. Consequently, prioritizing the detection, prevention and mitigation of the attacks is imperative to ensure safety and security. The paper provides an in-depth examination of internet of things (IoT) taxonomy, highlighting the associated challenges and security attacks within the IoT ecosystem, which subsequently gives insights into the vulnerabilities of the IoT ecosystem. Additionally, it includes a comparative analysis of various security attacks along with their impacts.

关键词： Prevention and mitigation Ecosystems Taxonomy Organizations Communications technology Safety Security Internet of Things Computational intelligence

来源：评论

学校读者我要写书评

暂无评论

Cutting Skill Assessment by Motion Analysis Using Deep Learning and Spatial Marker Tracking

引用

IEEE Transactions on Biomedical engineering 2025年第6期72卷 1963-1972页

作者： Su, Bai-Quan Ma, Xu-Dong Li, Weihan Kuang, Zi-Ao Gong, Yi Wang, Gang Zhang, Qingqian Liu, Wenyong Li, Changsheng Gao, Li Wang, Junchen Beijing University of Posts and Telecommunications Medical Robotics Laboratory School of Automation Beijing100876 China University of Tokyo School of Mechanical Engineering Tokyo113-0033 Japan Beijing University of Posts and Telecommunications School of Computer Science Beijing100876 China Peking University General Surgery Department Beijing100191 China Beihang University Key Laboratory for Biomechanics and Mechanobiology of Chinese Education Ministry Beijing Advanced Innovation Centre for Biomedical Engineering School of Biological Science and Medical Engineering Beijing100083 China Beijing Institute of Technology School of Mechatronical Engineering Beijing100081 China Beijing Institute of Technology Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing100081 China Peking University Department of Periodontology National Stomatological Center School and Hospital of Stomatology National Clinical Research Center for Oral Diseases National Engineering Research Center of Oral Biomaterials and Digital Medical Devices Beijing100081 China Beihang University School of Mechanical Engineering and Automation Beijing100083 China

The assessment of surgical skill is crucial for indicating a surgeon's proficiency. While motion analysis of surgical tools is widely used in endoscopic surgery, it is not commonly applied to open surgery. Instead, open surgery skill assessment relies on observing the trajectory of surgical tools on tissue. This observation-based method often lacks clear standards, leading to inaccurate assessments. This paper presents a method for evaluating cutting skill in open surgery through scalpel motion analysis. A 3D multiple-facet ArUco code cube is designed, and a dataset of tip coordinate system poses for various scalpels in the ArUco code coordinate system (ACS) is established using the pivot calibration method. The YOLOv8 model and an image dataset of different scalpels are used to identify the scalpel type and select its tip position. The tip position is then transformed from ACS to a binocular camera coordinate system (BCS), representing the incision curve made by the scalpel. Five assessment metrics are proposed to quantify the surgeon's cutting skill: average incision curvature deviation, incision length difference, incision endpoint deviation, average incision deviation, and average cutting jerk. Experiments involving twenty expert and novice surgeons performing four common incisions (straight line, polyline, semicircle, and cross line) demonstrate the metrics' effectiveness. The metrics provide a clear, objective display of individual cutting skills, and a combined ranking reveals comparative skill levels. This study offers a precise method for evaluating surgeons' cutting skills with a scalpel in open surgery. © 1964-2012 IEEE.

关键词： Surgery

来源：评论

学校读者我要写书评

暂无评论

Visual Sensor-Based Trajectory Multimodality Prediction via Anchor-Free Query Attention Network

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Wang, Ruiping Cheng, Jun Yu, Junzhi Nanyang Technological University School of Computer Science and Engineering Jurong West Singapore639798 Singapore Peking University College of Engineering Beijing100871 China Peking University State Key Laboratory for Turbulence and Complex Systems Department of Advanced Manufacturing and Robotics College of Engineering Beijing100871 China

As a core component of intelligent surveillance and autonomous driving systems, visual sensor-based trajectory multimodality prediction can significantly improve their perception and decision-making capabilities. Numerous existing trajectory prediction methods are dedicated to enhance prediction performance. However, they still fail to effectively model the complex spatiotemporal interactions among pedestrians and trajectory multimodality. To address the above challenges, this article presents one new trajectory multimodality prediction method via anchor-free query-based attention network, which can more effectively capture spatiotemporal interactions and model trajectory multimodality. First, the initial trajectory proposal module employs target-centered query-based attention to capture complex spatiotemporal interactions and generate multiple trajectory proposals corresponding to the multiple modes of the future trajectory, which allows the model to use different interaction information when decoding trajectory points at different time steps. Second, the novel trajectory refinement module utilizes the learnable trajectory proposals to construct proposal-level interaction mechanisms to refine future trajectories. Experimental results conducted on ETH and UCY datasets demonstrate that the proposed model can provide the state-of-the-art prediction performance. © 1963-2012 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

REMAC: Self-Reflective and Self-Evolving Multi-Agent Collaboration for Long-Horizon Robot Manipulation

arXiv

引用

arXiv 2025年

作者： Yuan, Puzhen Ma, Angyuan Yao, Yunchao Yao, Huaxiu Tomizuka, Masayoshi Ding, Mingyu Xingjian College Tsinghua University China Robotics Institute Carnegie Mellon University United States Department of Computer Science UNC Chapel Hill United States Department of Mechanical Engineering UC Berkeley United States

Vision-language models (VLMs) have demonstrated remarkable capabilities in robotic planning, particularly for long-horizon tasks that require a holistic understanding of the environment for task decomposition. Existing methods typically rely on prior environmental knowledge or carefully designed task-specific prompts, making them struggle with dynamic scene changes or unexpected task conditions, e.g., a robot attempting to put a carrot in the microwave but finds the door was closed. Such challenges underscore two critical issues: adaptability and efficiency. To address them, in this work, we propose an adaptive multi-agent planning framework, termed REMAC, that enables efficient, scene-agnostic multi-robot long-horizon task planning and execution through continuous reflection and self-evolution. REMAC incorporates two key modules: a self-reflection module performing pre-condition and post-condition checks in the loop to evaluate progress and refine plans, and a self-evolvement module dynamically adapting plans based on scene-specific reasoning. It offers several appealing benefits: 1) Robots can initially explore and reason about the environment without complex prompt design. 2) Robots can keep reflecting on potential planning errors and adapting the plan based on task-specific insights. 3) After iterations, a robot can call another one to coordinate tasks in parallel, maximizing the task execution efficiency. To validate REMAC’s effectiveness, we build a multi-agent environment for long-horizon robot manipulation and navigation based on RoboCasa, featuring 4 task categories with 27 task styles and 50+ different objects. Based on it, we further benchmark state-of-the-art reasoning models, including DeepSeek-R1, o3-mini, QwQ, and Grok3, demonstrating REMAC’s superiority by boosting average success rates by 40% and execution efficiency by 52.7% over the single robot baseline without any task-specific prompting or finetuning. Copyright © 2025, The Authors. All rights r

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

NavG: Risk-Aware Navigation in Crowded Environments Based on Reinforcement Learning with Guidance Points

arXiv

引用

arXiv 2025年

作者： Zhang, Qianyi Luo, Wentao Liu, Boyi Zhang, Ziyang Wang, Yaoyuan Liu, Jingtai Institute of Robotics and Automatic Information System Nankai University Tianjin Key Laboratory of Intelligent Robotics Tianjin China Advanced Computing and Storage Lab Huawei 2012 Lab China Department of Electronic and Computer Engineering The Kong Kong University of Science and Technology Hong Kong

Motion planning in navigation systems is highly susceptible to upstream perceptual errors, particularly in human detection and tracking. To mitigate this issue, the concept of guidance points—a novel directional cue within a reinforcement learning-based framework—is introduced. A structured method for identifying guidance points is developed, consisting of obstacle boundary extraction, potential guidance point detection, and redundancy elimination. To integrate guidance points into the navigation pipeline, a perception-to-planning mapping strategy is proposed, unifying guidance points with other perceptual inputs and enabling the RL agent to effectively leverage the complementary relationships among raw laser data, human detection and tracking, and guidance points. Qualitative and quantitative simulations demonstrate that the proposed approach achieves the highest success rate and near-optimal travel times, greatly improving both safety and efficiency. Furthermore, real-world experiments in dynamic corridors and lobbies validate the robot’s ability to confidently navigate around obstacles and robustly avoid pedestrians. © 2025, CC BY.

关键词： Travel time

来源：评论

学校读者我要写书评

暂无评论

Fabrication of Sensorsless Automated Guided Vehicle for Small Warehouse Rack Management

Fabrication of Sensorsless Automated Guided Vehicle for Smal...

引用

Computational, Communication and Information Technology (ICCCIT), International Conference on

作者： Neelesh Kumar Sahu Piyush Chaturvedi Vaishali Gupta Ruchi Patel Ashok Verma Megha Shrivastava Artificial Intelligence and Robotics Gyan Ganga Institute of Technology and Sciences Jabalpur MP India Department of Computer Sc. & Engg. IPS Academy Institute of Engineering & Science Indore MP India Computer Science and Engineering Gyan Ganga Institute of Technology and Sciences Jabalpur MP India Department of Mathematics Medicaps University Indore MP India

ISBN: (数字)9798331512965

ISBN: (纸本)9798331512972

Automated guided vehicles (AGVs) are an essential part of today's logistics networks because they save time, reduce wear and maintenance expenses, and maximize efficiency in route *** creation of AGVthat is capable of effectively managing warehouse racks without the utilization of sensors is the primary emphasis of this project. In order to travel and carry out duties, the AGVruns on predetermined pathways and makes use of a button-based interface. For the purpose of offering an efficient and costeffective solution for the automation of small warehouses, it is outfitted with a lever mechanism that is operated by a servo motor and features the ability to connect and move racks.

关键词： Fabrication Remotely guided vehicles Automation Solids Sensors Maintenance Information and communication technology Servomotors Logistics

来源：评论

学校读者我要写书评

暂无评论

Cryo-CACTI: Cryogenic-Aware CACTI for Cache Modeling down to 10K in Advanced 7nm FinFETs

引用

IEEE Transactions on computers 2025年

作者： Ravipati, Divya Praneetha van Santen, Victor M. Parihar, Shivendra Singh Chauhan, Yogesh Singh Panda, Preeti Ranjan Amrouch, Hussam Indian Institute of Technology Delhi Department of Computer Science and Engineering New Delhi India Technical University of Munich TUM School of Computation Information and Technology Chair of AI Processor Design Munich Institute of Robotics and Machine Intelligence Germany Kanpur Nanolab Department of Electrical Engineering Uttar Pradesh India

Cryogenic circuits are currently employed in fields such as quantum computing, particle detectors, magnetic resonance imaging, and space applications. While cryogenic circuits are being researched, there is limited work on designing cryogenic caches at temperatures below 77K. Moreover, there is no tool to estimate the delay, power, and area of cryogenic caches at advanced technology nodes. Our research focuses on the development of cryogenic caches tailored for the 7nm technology node, operating at 10K. However, a key challenge is the lack of cryogenic measurement data, especially in recent technologies. Consequently, through conducting our own FinFET transistor measurements, we calibrate cryogenic transistor models at 10K. With the 7nm cryogenic transistor data, we model Cryo-CACTI for cryogenic caches (due to cache’s vital role in improving performance and their considerable share in area and power of the processor). Using Cryo-CACTI, our evaluation reveals considerable improvements in the energy efficiency (up to 99%) of cryogenic caches of larger sizes compared to the caches at room temperature (300K). Additionally, we explore alternative cache configurations at circuit-level to optimize cryogenic operation. Furthermore, we use Cryo-CACTI to explore the performance/energy consumption of cryogenic caches while simulating workloads such as SPEC CPU2017 and machine learning via neural networks. © 1968-2012 IEEE.

关键词： Combinatorial circuits

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Health Monitoring and Maintenance Scheduling for Nuclear Power Systems

Probabilistic Health Monitoring and Maintenance Scheduling f...

引用

AIAA science and Technology Forum and Exposition, AIAA SciTech Forum 2025

作者： Amer, Ahmad Tsilifis, Panagiotis Saxena, Abhinav Baglietto, Emilio Khan, Genghis Probabilistic Design & Material Informatics GE Aerospace Research Niskayuna NY12309 United States Robotics AI & Computer Vision GE Vernova Advanced Research Niskayuna NY12309 United States AI & Computer Vision GE Aerospace Research San RamonCA94583 United States Department of Nuclear Science & Engineering Massachusetts Institute of Technology CambridgeMA02139 United States Sustainable Systems GE Aerospace Research Niskayuna NY12309 United States

ISBN: (数字)9781624107238

ISBN: (纸本)9781624107238

Operations and Maintenance (O&M) cost optimization in the nuclear energy industry is an imperative task for developing sustainable systems and efficient renewable technologies. We present a modular probabilistic framework for addressing maintenance scheduling challenges for small modular nuclear reactors using a Dynamic Bayesian Network (DBN) approach that monitors fatigue and performance in multiple subsystems of the reactors and provides a probabilistic assessment for potential failure events. The DBN framework fuses information from potential digital twins that assimilate real time data from several sensors with different time granularities in order to monitor and update thecurrentstate of knowledge aboutthestatus of several fatigue or performance criteria. Comprised of multi-modal digital twins (empirical, data- and physics-based twins), this DBN serves as a predictive framework forecasting the future state of specific reactor subsystems and enhancing decision-making capabilities associated with preventing system failure and minimizing the time and cost of maintenance events. The work presented in this paper is a holistic approach for monitoring and safeguarding complex, multi-component engineering systems where maintenance scheduling is critical and does not restrict itself to nuclear environments. However, our goal is to illustrate how such a framework can be adjusted to small modular water reactors. © 2025, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Nuclear energy

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：