检索结果-内蒙古大学图书馆

Decentralized Reinforcement Learning for Multiple Robotic Fish in Cooperative Pursuit Task

IEEE Transactions on Cognitive and Developmental systems 2025年

作者： Feng, Yukai Wu, Zhengxing Wang, Jian Li, Sijie Huang, Yupei Yu, Junzhi Tan, Min Institute of Automation Chinese Academy of Sciences Key Laboratory of Cognition and Decision Intelligence for Complex Systems Beijing100190 China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100049 China College of Engineering Peking University State Key Laboratory for Turbulence and Complex Systems Department of Advanced Manufacturing and Robotics Beijing100871 China

The control of multi-robot systems, particularly in the pursuit-evasion (PE) with multiple robots, has gained significant attention in both academic and non-academic settings. However, the collaborative operation of multi-robotic fish systems encounters substantial challenges due to the complex underwater environment and unique movement mode. In this paper, we propose a multi-agent reinforcement learning (MARL) approach to develop a viable strategy for underwater cooperative pursuit. Initially, considering the hydrodynamic model and motion characteristics of robotic fish, we construct a specific simulation environment with multiple fish-like agents, which provides a highly realistic state transition model. Next, we develop a MARL-based strategy learning framework that incorporates appropriate reward functions and agent actions for policy learning. Finally, a series of comprehensive simulations and practical experiments are conducted to validate the effectiveness of the proposed method and confirm its successful application in underwater pursuit scenarios. These findings offer valuable insights for further research in underwater multiple robot systems. © 2016 IEEE.

关键词： Chatbots

来源：评论

学校读者我要写书评

暂无评论

Distributed Event-Triggered Formation Control for a Multi-robotic Fish System

Distributed Event-Triggered Formation Control for a Multi-ro...

引用

International Conference on Guidance, Navigation and Control, ICGNC 2022

作者： Dai, Shijie Wu, Zhengxing Tan, Min Yu, Junzhi School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China State Key Laboratory for Turbulence and Complex System Department of Advanced Manufacturing and Robotics BIC-ESAT College of Engineering Peking University Beijing100871 China

ISBN: (纸本)9789811966125

This paper investigates the formation control problem for a multi-robotic fish system and a distributed event-triggered-based formation control framework is proposed. The framework consists of a communication topology, a distributed formation control law, and a dynamic event-triggered communication mechanism. In particular, a position-based formation control law is presented to drive the multi-robotic fish system to an anticipated configuration based on local measurements while keeping pace with a moving target. Meanwhile, a dynamic event-triggered mechanism is utilized to measure importance of the interactive information and decide the communication timing. The proposed formation control method shows its merits to greatly reduce communication consumption with a limited loss of formation control performance. Finally, simulations with quantitative comparisons are presented to verify the effectiveness of the proposed framework. This formation control framework provides a solid foundation for future marine cooperative control of the multi-robotic fish system. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Estimating the Lateral Motion States of an Underwater Robot by Propeller Wake Sensing Using an Artificial Lateral Line

arXiv

引用

arXiv 2024年

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

The artificial lateral line (ALL), comprising distributed flow sensors, has been successful in sensing motion states of bioinspired underwater robots like robotic fish. However, its application to robots driven by rotating propellers remains unexplored due to the complexity of propeller wake flow. This paper investigates the feasibility of using ALL to sense propeller wake for underwater robot leader-follower formation. To estimate the lateral motion states of a leader propeller, this paper designs a multi-output deep learning network that extracts temporal and spatial features from distributed pressure measurements of propeller wake. Extensive experiments are conducted on a designed testbed, the results of which validate the effectiveness of the proposed propeller wake sensing method. Copyright © 2024, The Authors. All rights reserved.

关键词： Wakes

来源：评论

学校读者我要写书评

暂无评论

Optimal Fuel Feed Strategy for Asymmetric Arranged Multi-tanks Aircraft 3

Optimal Fuel Feed Strategy for Asymmetric Arranged Multi-tan...

引用

3rd International Conference on Industrial Artificial Intelligence, IAI 2021

作者： Miao, Haoyu Ouyang, Zikai Yang, Shunpeng Yan, Weichao Cao, Mengfan Chen, Shibo Yang, Zaiyue Guangdong Prov. Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities Southern University of Science and Technology Shenzhen Key Laboratory of Biomimetic Robotics and Intelligent Systems Department of Mechanical and Energy Engineering Shenzhen518055 China

ISBN: (纸本)9781665435178

Aircraft fuel system, which provides a continuous source of fuel to the engine, is an important component of the aircraft. Although the sequential fuel feed strategy for the symmetric arranged multi-tanks aircraft is widely used in today's aircraft, the fuel feed strategy of the asymmetric arranged multi-tanks is still a challenge. In this article, a two layer offline approach is developed to obtain the fuel feed strategy to minimize the difference between the actual center of gravity (CG) and the desired CG. The performance of the proposed approach is tested in a case study based on the test data of aircraft pitch movement. The result indicates that the proposed approach solves the problem with an offline manner from the optimization perspective. © 2021 IEEE.

关键词： Aircraft

来源：评论

学校读者我要写书评

暂无评论

Path Tracking Control for Helical Microrobots Based on Fusion of Geometric and Model-Free Methods 13

Path Tracking Control for Helical Microrobots Based on Fusio...

引用

13th IEEE International Conference on CYBER Technology in Automation, Control, and Intelligent systems, CYBER 2023

作者： Zhong, Shihao Wang, Huaping Shi, Qing Hou, Yaozhen Qiu, Yukang Sun, Tao Huang, Qiang Fukuda, Toshio School of Medical Technology Beijing Institute of Technology Beijing100081 China Key Laboratory of Biomimetic Robots and Systems Beijing Institute of Technology Ministry of Education Beijing100081 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology Beijing100081 China Intelligent Robotics Institute School of Mechatronical Engineering Beijing Institute of Technology Beijing100081 China

ISBN: (纸本)9798350315196

Helical micron-sized robots driven by magnetic fields have garnered significant interest, particularly in the field of tracking control. However, at the microscale, time-varying uncertain perturbations in both the environment and electromagnetic system can cause these robots to deviate from their preset state. Here, we propose a novel control method that combines geometric and model-free controllers in a complementary manner to achieve accurate path-tracking of a helical microrobot on underwater unstructured surfaces. The geometric controller acts as a feedforward controller handling path information and formulating guidance law, while the model-free controller responds directly to the lateral error. To compensate for unmodeled nonlinear dynamics and unknown disturbances and achieve system dynamic linearization, we employ an extended state observer. To validate the proposed method and determine suitable ranges for input parameters of the controllers, simulations were carried out. The effectiveness of our path-tracking control method is validated through experimental results. The control technique provides an initial investigation into addressing the effects of uncertainties and perturbation on the control capabilities of magnetic microrobots. © 2023 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Identification of PMSM Moment of Inertia based on Model Reference Adaptive Algorithm 4

Identification of PMSM Moment of Inertia based on Model Refe...

引用

4th IEEE International Conference on Power, Intelligent Computing and systems, ICPICS 2022

作者： Ding, Fan Zhang, Tao Jia, Danping Zhang, Hualiang Pei, Quanshen Huang, Haoran School of Information Science and Engineering Shenyang University of Technology Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang Institute of Automation Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences School of Electrical Engineering Dalian University of Technology Dalian China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang Institute of Automation Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China

ISBN: (数字)9781665467735

ISBN: (纸本)9781665467735

A method that can identify the rotational inertia in a timely manner is proposed because the performance of a permanent magnet synchronous motor servo system is easily affected by the rotational inertia. Firstly, principles of model-referenced adaptive recognition algorithm is introduced, and the influence of the adaptive gain on the identification results is analyzed. Then, design a suitable range of adaptive gain value, use the set error value to compare the identification error with the set value, and then select the appropriate gain for identification. Finally, through simulation verification, this method has fast identification convergence speed, high precision and strong anti-disturbance. © 2022 IEEE.

关键词： Adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

Crawling Gait Enables Stable Quadrupedal Locomotion in A Bioinspired Robotic Rat

Crawling Gait Enables Stable Quadrupedal Locomotion in A Bio...

引用

IEEE International Conference on Real-time Computing and robotics (RCAR)

作者： Ruochao Wang Xiaolong Quan Hang Xiao Rongjie Du Boyang Qin Qing Shi Intelligent Robotics Institute School of Mechatronical Engineering Beijing Institute of Technology Beijing China Ministry of Education Key Laboratory of Biomimetic Robots and Systems (Beijing Institute of Technology) Beijing China

ISBN: (数字)9798350372601

ISBN: (纸本)9798350372618

Constrained by the performance of actuators and controllers, achieving stable walking in small-scale quadruped robots has been more challenging compared to larger ones. Rats, in their natural habitat, can achieve stable walking even in extreme environments like narrow spaces by utilizing crawling motion to lower their center of mass. Inspired by this, we conducted a comparative study of the walking stability between crawling and trot gaits on a ratinspired robot named SQuRo. Initially, we collected motion data for both crawling and trot gaits of SQuRo in a simulated environment. Subsequently, we analyzed the dynamic stability of the robot using Poincaré maps. The results indicate that SQuRo’s phase trajectories converged into closed loops with periodicity under both gaits, demonstrating the presence of limit cycles. Moreover, fixed points were observed in the Poincaré maps for both gaits, suggesting the dynamic stability of quadrupedal locomotion. Compared to the trot gait, the convergence loops of the crawling gait phase trajectories were smaller, indicating more stable locomotion. We tested the performance of SQuRo’s crawling gait in challenging outdoor environments, where SQuRo demonstrated stable walking consistently. This work provides a new approach for achieving stable walking in small-scale quadruped robots and can be readily applied to controller design across different sizes of legged robots.

关键词： Legged locomotion Limit-cycles Aerospace electronics Robot sensing systems Stability analysis Trajectory Sensors

来源：评论

学校读者我要写书评

暂无评论

Impact of Employing Weather Forecast Data as Input to the Estimation of Evapotranspiration by Deep Neural Network Models**

arXiv

引用

arXiv 2024年

作者： Vaz, Pedro J. Schütz, Gabriela Guerrero, Carlos Cardoso, Pedro J.S. Universidade do Algarve Portugal CEOT – Centre for Electronics Optoelectronics and Telecommunications Portugal MED – Mediterranean Institute for Agriculture Environment and Development Portugal LARSyS Laboratory of Robotics and Engineering Systems Portugal

Reference Evapotranspiration (ET!) is a key parameter for designing smart irrigation scheduling, since it is related by a coefficient to the water needs of a crop. The United Nations Food and Agriculture Organization, proposed a standard method for ET! computation (FAO56PM), based on the parameterization of the Penman-Monteith equation, that is widely adopted in the literature. To computeET ! using the FAO56-PM method, four main weather parameters are needed: temperature, humidity, wind, and solar radiation (SR). One way to make daily ET! estimations for future days is to use freely available weather forecast services (WFSs), where many meteorological parameters are estimated up to the next 15 days. A problem with this method is that currently, SR is not provided as a free forecast parameter on most of those online services or, normally, such forecasts present a financial cost penalty. For this reason, several ET! estimation models using machine and deep learning were developed and presented in the literature, that use as input features a reduced set of carefully selected weather parameters, that are compatible with common freely available WFSs. However, most studies on this topic have only evaluated model performance using data from weather stations (WSs), without considering the effect of using weather forecast data. In this study, the performance of authors’ previous models is evaluated when using weather forecast data from two online WFSs, in the following scenarios: (i) direct ET! estimation by an Artificial Neural Network (ANN) model, and (ii) estimate SR by (another) ANN model, and then use that estimation for ET! computation, using the FAO56-PM method. Employing data collected from two WFSs and a WS located in Vale do Lobo, Portugal, the latter approach achieved the best result, with a coefficient of determination (R") ranging between 0.893 and 0.667, when considering forecasts up to 15 days. © 2024, CC BY.

关键词： Irrigation

来源：评论

学校读者我要写书评

暂无评论

Design of a Miniature Flapping-Wing Robot Capable of Quick and Energy-Efficient Takeoff

Design of a Miniature Flapping-Wing Robot Capable of Quick a...

引用

IEEE International Conference on robotics and Biomimetics

作者： Yi Xu Yishi Shen Liang Peng Qi Li Jin Yu Shi Zhang Qing Shi Key Laboratory of Biomimetic Robots and Systems Beijing Institute of Technology Ministry of Education Beijing China Intelligent Robotics Institute School of Mechatronical Engineering Beijing Institute of Technology Beijing China

ISBN: (数字)9798331509644

ISBN: (纸本)9798331509651

Micro areal vehicles are widely used in civilian and military applications, but it is still challenging for them to take off in place with both high speed and energy utilization efficiency. Inspired by locusts, one solution is to integrate the flying with the jumping motion, utilizing the speed generated by jumping to provide sufficient aerodynamic forces for the flight. In this paper, we develop a miniature locust-inspired robot capable of jumping and flying. By coupling the jumpingleg mechanism and flapping-wing mechanism, the robot has a compacted size (with a body length of 15 cm and a weight of 23 g). Furthermore, we design a cascaded jump-flying controller to achieve stable transition and maneuverable flight. A series of experimental results reveal that the robot achieves a maximum jumping height of 50 cm and a minimum flying turning radius of 0.8 m. Remarkably, the robot is capable of taking off in place through controlling the hindleg and wings coordinately.

关键词： Couplings Attitude control Robot kinematics Biomimetics Robot sensing systems Turning Control systems Energy efficiency Sensors Biosensors

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Analysis of Skin Cancer Classification with Convolutional Neural Networks for E-Health Applications

Data-Driven Analysis of Skin Cancer Classification with Conv...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Ahmed, Imran Ahmad, Misbah Chehri, Abdellah Jeon, Gwanggil Anglia Ruskin University School of Computing and Information Science Cambridge United Kingdom Hartpury University Animal and Agriculture Department Gloucester United Kingdom University of the West of England Centre for Machine Vision Bristol Robotics Laboratory Bristol United Kingdom Department of Mathematics and Computer Science Canada Incheon National University Department of Embedded Systems Engineering Incheon Korea Republic of

ISBN: (纸本)9798350351255

This study explores the effectiveness of Convolutional Neural Networks (CNNs) in automatically classifying skin cancer for e-health applications. The trained model showcases impressive performance by leveraging the HAM10000 dataset, which includes a wide range of skin lesion images from seven different classes. The parameters and architecture of the CNN model are presented in a systematic manner, providing valuable insights into the reasoning behind its design. The model is optimized using the Adam optimizer and annealing techniques to ensure efficient convergence. The model's performance is assessed on validation and test datasets, showcasing an accuracy of 78.55% and 76.49%, respectively, for skin cancer classification. This study highlights the significant potential of CNN as a powerful tool for automating the diagnosis of skin cancer, which is in line with the growing trend of using deep learning for medical image analysis. © 2024 IEEE.

关键词： Electronic health record

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：