检索结果-内蒙古大学图书馆

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

作者： Johnson, Seth Escamilla, Laura Lehman, Hannah Valasek, John Vehicle Systems and Control Laboratory Aerospace Engineering Department Texas AandM University College StationTX77843 United States

ISBN: (数字)9781624107238

ISBN: (纸本)9781624107238

Reinforcement learning has been used to train autonomous single-agent and multi-agent systems to solve complex problems in the aerospace domain. This type of machine learning is a long process, often requiring training to run millions of time steps to achieve practical solutions. Training environments are often simplified to expedite training, such as using reduced vehicle dynamics and environmental abstractions to remove dependency on visual-based graphics. However, these complexities may be favorable when realism and accuracy are prioritized over run-time during full autonomous system validation. This paper introduces and develops an architecture that facilitates the transition from a reduced training environment to more realistic simulations. Modularity is emphasized to reduce implementation time and scalability to support large multi-agent systems. The proposed system leverages Unreal Engine 5 for high-fidelity graphics, optimized performance, and developer-oriented workflow to create a simulation for demonstrating and validating multi-agent systems for real-world deployment. The integration of Software-in-the-Loop (SITL) and Hardware-in-the-Loop (HITL) further validate the simulation framework, allowing for detailed testing and adjustment phases. Results presented in the paper investigate case studies on the validation for deployment of a single-agent autonomous tracking UAS and extend the proposed framework to an auction-based multi-agent coordination scenario. © 2025, American Institute of Aeronautics and Astronautics Inc, AIAA. 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 Implementation of an 80-160 kV High Voltage Power Supply

Design and Implementation of an 80-160 kV High Voltage Power...

引用

2024 Energy Conversion Congress and Expo Europe, ECCE Europe 2024

作者： Bilicioglu, Muhammed Faruk Bodur, Haci Aselsan Inc. Department of Power and Control Systems Design Engineering Ankara Turkey Yildiz Technical University Department of Electrical Engineering Istanbul Turkey

ISBN: (纸本)9798350364446

In this study, an 80-160 kV, 200 W high voltage power supply is designed and implemented. To overcome the insulation restrictions of the transformer used in the high voltage power supply, a resonant converter and a voltage multiplier circuit were used consecutively for the voltage boosting process. To utilize the parasitic capacitor of transformer becoming dominant due to the high turn ratio, an LCC type series-parallel resonant converter is used as the resonant converter. An optimization algorithm that optimizes efficiency and power density is developed to determine the resonant tank parameters. Bipolar Cockcroft-Walton Voltage Multiplier as the voltage multiplier is preferred due to the advantages of less secondary winding and lower voltage drop. The high voltage power supply design is verified with simulations and experimental results. © 2024 IEEE.

关键词： Resonant converters

来源：评论

学校读者我要写书评

暂无评论

A Contact-Aided Model for Soft Continuum Robots Moving in Unstructured Environment

A Contact-Aided Model for Soft Continuum Robots Moving in Un...

引用

2024 China Automation Congress, CAC 2024

作者： Jingyu, Zhang Qin, Fang Mingjian, Sun Rong, Xiong Wang, Yue Haojian, Lu School of Information Science and Engineering Harbin Institute of Technology Weihai China Institute of Cyber-Systems and Control Zhejiang University Hangzhou China Department of Control Science and Engineering Harbin Institute of Technology Heilongjiang China

ISBN: (纸本)9798350368604

Due to their inherent flexibility and high human-computer interaction potential, soft continuum robots have been developed and popularized in industrial and medical scenarios. However, when moving in an unstructured environment, the contact with environment will change the configuration parameters of the robot, which brings problems to the control. Aiming at improving the control performance of soft continuum robots in an unstructured environment, a contact-aided model is proposed to estimate the varying configurations of the robot. Besides, a model-based controller is proposed to control the robot in an unstructured environment. To verify the performance of the proposed method, a small-scale soft continuum robot is designed and fabricated. Through the characterization experiment, the robot shows a large workspace by changing the contact position, and the kinematic model is verified. Through the trajectory tracking experiment, the robot showed good accuracy, with an average error of 1.2mm. Through an exploration experiment in the unstructured environment, the robot showed good control effect, with an average error of 1.9mm. This work enhances the application capability of the soft continuum robots in unstructured environments. © 2024 IEEE.

关键词： Microrobots

来源：评论

学校读者我要写书评

暂无评论

A Model-Based Unmatched Disturbance Rejection control Approach for Speed Regulation of a Converter-Driven DC Motor Using Output-Feedback

引用

IEEE/CAA Journal of Automatica Sinica 2022年第2期9卷 365-376页

作者： Lu Zhang Jun Yang Shihua Li School of Automation Southeast UniversityKey Laboratory of Measurement and Control of Complex Systems of EngineeringMinistry of Education IEEE Department of Aeronautical and Automotive Engineering Loughborough University

The speed regulation problem with only speed measurement is investigated in this paper for a permanent magnet direct current(DC)motor driven by a buck *** lumping all unknown matched/unmatched disturbances and uncertainties together,the traditional active disturbance rejection control(ADRC)approach provides an intuitive solution for the problem under ***,for such a higher-order disturbed system,the increase of poles for the extended state observer(ESO)therein will lead to drastically growth of observer gains,which causes severe noise *** paper aims to propose a new model-based disturbance rejection controller for the converter-driven DC motor system using *** of estimating lumped disturbances directly,a new observer is constructed to estimate the desired steady state of control signal as well as errors between the real states and their desired steady-state ***,a controller with only speed measurement is proposed by utilizing the *** performance of the proposed method is tested through experiments on *** is further shown via numerical calculations and experimental results that the poles of the observer within the proposed control approach can be largely increased without significantly increasing magnitude of the observer gains.

关键词： Bandwidth widening converter-driven direct current(DC)motor disturbance observer model-based disturbance rejection speed regulation

来源：评论

学校读者我要写书评

暂无评论

IMPROVING HYDRODYNAMIC PERFORMANCE OF AN ASYMMETRIC TOWFISH USING CFD

IMPROVING HYDRODYNAMIC PERFORMANCE OF AN ASYMMETRIC TOWFISH ...

引用

ASME 2024 International Mechanical engineering Congress and Exposition, IMECE 2024

作者： Bhosale, Yugandhara Sharma, Atul Gupta, Abhishek Vachhani, Leena Department of Mechanical Engineering Indian Institute of Technology Bombay Mumbai India Department of Systems and Control Engineering Indian Institute of Technology Bombay Mumbai India

ISBN: (纸本)9780791888667

A towfish is a passive underwater vehicle that is towed behind a surface vessel. The towfish is often designed to be symmetric from all directions primarily to achieve balanced hydrodynamic behaviour and foreseeable manoeuvrability under water. External attachments or extruded slots can induce asymmetry, which will have an effect on the hydrodynamic behaviour. An asymmetric towfish will experience an uneven distribution of hydrodynamic forces and moments. This will lead to unstable orientation and unpredictable hydrodynamic behaviour. So, the effect of asymmetry on hydrodynamic coefficients like drag coefficients, lift coefficients, pitching moment coefficients and overall stability are investigated in this paper and improved with design modification in towfish. We evaluated these hydrodynamic coefficients of the asymmetric towfish and proposed a redesign strategy. In this work, the significant parts of towfish, like the nose and hull are redesigned to improve hydrodynamic performance. A three-dimensional (3D) simulation is carried out using in Ansys Fluent as a CFD software. To simulate the turbulence, the k-ω shear stress transport (SST) model is employed due to its good prediction capability at a reasonable computational cost. Drag reduction and lift increment are observed with modification and redesigning of the nose and hull to counter the increase in drag due to the asymmetricity of towfish. These results will help to enhance our understanding of the hydrodynamics behavior of the asymmetric nature of towfish. Copyright © 2024 by ASME.

关键词： Computational fluid dynamics

来源：评论

学校读者我要写书评

暂无评论

2411 | Proposing Turning Motion of The Small and Lightweight Push-Rolling Rover with Minimal Configuration 21

2411 | Proposing Turning Motion of The Small and Lightweight...

引用

21st International and 12th Asia-Pacific Regional Conference of the International Society for Terrain-Vehicle systems, ISTVS 2024

作者： Fujiwara, Daisuke Iizuka, Kojiro Suwa University of Science Department of Mechanical Engineering and Electrical Engineering Nagano Japan Shibaura Institute of Technology Department of Machinery and Control Systems Saitama Japan

ISBN: (纸本)9781942112570

Some organizations in Japan have planned planetary explorations using a small rover. However, the rovers with cylindrical wheels have a risk of failing to move in the loose soil area, such as the surface of the lunar/planet. The movement using the supporting force of the locked wheel, for example, a wheeled walking, or push-pull locomotion, can reduce the risk. Previous studies have mainly developed relatively large rovers over a mass of 10 kg. Meanwhile, our group has developed a small and lightweight (under a mass of a few kg) push-rolling rover with minimal configuration, and our previous studies indicated that the rover could climb steep slopes over 30 degrees with low slip. Planetary exploration rovers are required to move in an arbitrary direction;therefore, the developed rover also needs to have a function of a turning motion. This paper proposes the turning motion while inching for the push-rolling rover with minimal configuration and evaluates its performance by the traveling experiments at different conditions (driving conditions, and wheel shapes). The experimental results indicated that the proposed turning motion using high wheel slip and lug's wheel realized turning with low slip on loose surfaces with steep slopes. Additionally, the experimental results also showed that the slip amount of the rotational center is lower than that of a normal skid-steering rover. © 2024 International Society for Terrain-Vehicle systems. All rights reserved.

关键词： Rovers

来源：评论

学校读者我要写书评

暂无评论

Feedback-Based Quantum Algorithm for Constrained Optimization Problems 15th

Feedback-Based Quantum Algorithm for Constrained Optimizati...

引用

15th International Conference on Parallel Processing and Applied Mathematics, PPAM 2024

作者： Abdul Rahman, Salahuddin Karabacak, Özkan Wisniewski, Rafal Automation and Control Section Department of Electronic Systems Aalborg University Aalborg Denmark Department of Mechatronics Engineering Kadir Has University Istanbul Turkey

ISBN: (纸本)9783031856990

The feedback-based algorithm for quantum optimization (FALQON) has recently been proposed to find ground states of Hamiltonians and solve quadratic unconstrained binary optimization problems. This paper efficiently generalizes FALQON to tackle quadratic constrained binary optimization (QCBO) problems. For this purpose, we introduce a new operator that encodes the problem’s solution as its ground state. Using control theory, we design a quantum control system such that the state converges to the ground state of this operator. When applied to the QCBO problem, we show that our proposed algorithm saves computational resources by reducing the depth of the quantum circuit and can perform better than FALQON. The effectiveness of our proposed algorithm is further illustrated through numerical simulations. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Multilevel Waveforming Inverter Output Voltage Stabilization Technique Based on Short-Term Load Current Prediction

Multilevel Waveforming Inverter Output Voltage Stabilization...

引用

2023 International Conference on Industrial engineering, Applications and Manufacturing, ICIEAM 2023

作者： Mirgorodskaya, Ekaterina Mityashin, Nikita Mamonychev, Mikhail Yuri Gagarin State Technical University of Saratov Department of Systems Engineering and Control in Technical Systems Saratov Russia

ISBN: (纸本)9781665475952

The paper presents studying results of the output voltage stabilizing processes of a multilevel inverter based on two-channel impulse converters, the structure of the power circuit of which does not depend on the number of levels of the output curve. The principle of a multilevel curve forming, used in the studied inverter, makes it possible to obtain a high speed of the output voltage stabilizing process, when the load value and the mains voltage are changing. A feature of the stabilization method is its adaptation to the amount of current consumed by the converter, which makes it possible to reduce energy losses in circuits of impulse converters. Adaptation is provided by a short-term forecast of the load current due to the similarity of its curve shape in a multilevel inverter. Presented results of computer simulation confirm the declared advantages of the converter. © 2023 IEEE.

关键词： Reactive power

来源：评论

学校读者我要写书评

暂无评论

All-Fabric Bi-directional Actuators for Multi-joint Assistance of Upper Limb

引用

Journal of Bionic engineering 2023年第6期20卷 2661-2669页

作者： Junlin Ma Diansheng Chen Zhe Liu Jie Wei Xianglin Zhang Zihan Zeng Yongkang Jiang Institute of Robotics Beihang UniversityBeijing100191China Department of Control Science and Engineering Tongji UniversityShanghai201804China Frontiers Science Center for Intelligent Autonomous Systems Shanghai201210China

According to clinical studies,upper limb robotic suits are vital to reduce therapist fatigue and accelerate patient *** pneumatic actuators have drawn increasing attention for the development of wearable robots due to their low weight,flexibility,and high power-to-weight ***,most of current actuators were designed for the flexion assistance of a specific joint,and that for joint extension requires further ***,designing an actuator for diverse working scenarios remains a *** this paper,we propose an all-fabric bi-directional actuator to assist the flexion and extension of the elbow,wrist,and fingers.A mathematical model is presented that predicts the deformation and guides the design of the proposed bi-directional *** further validate the applicability and adaptability of the proposed actuator for different joints,we developed a 3-DOF soft robotic *** results show that the robotic suit can assist the motion of the elbow,wrist,and finger of the subject.

关键词： Soft robotic suits Fabric-based actuators Multi-DOF motion Upper limb rehabilitation

来源：评论

学校读者我要写书评

暂无评论

Incremental Reinforcement Learning via Performance Evaluation and Policy Perturbation

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第5期5卷 2253-2263页

作者： Deng, Guizhou Fu, Huiqiao Wang, Xinpeng Liu, Canghai Tang, Kaiqiang Chen, Chunlin Southwest University of Science and Technology Mechanical Engineering School of Manufacturing Science and Engineering Mianyang621000 China Nanjing University School of Management and Engineering Nanjing210093 China Nanjing University Department of Control and Systems Engineering School of Management and Engineering Nanjing210093 China

Rapid adaptation to the environment is the long-term task of reinforcement learning. However, reinforcement learning faces great challenges in dynamic environments, especially with continuous state-action spaces. In this article, we propose a systematic incremental reinforcement learning method via performance evaluation and policy perturbation (IRL-PEPP) to improve the adaptability of reinforcement learning algorithms in dynamic environments with continuous state-action spaces, which mainly includes three parts, i.e., performance evaluation, policy perturbation, and importance weighting. First, in performance evaluation, we apply the learned optimal policy to sample a few episodes in the original environment and use these samples to evaluate the policy applicability in the new environment. Then, in policy perturbation, the policy is perturbed according to the policy applicability to balance the tradeoff between exploration and exploitation in the new environment. Finally, importance weighting is applied to weight the information to speed up the adjustment process of the policy. Experimental results demonstrate the feasibility and efficiency of the proposed IRL-PEPP method for continuous control tasks in comparison with the existing state-of-the-art methods. © 2023 IEEE.

关键词： Reinforcement 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：