检索结果-内蒙古大学图书馆

8th International Conference on Big Data, Knowledge and Control Systems Engineering, BdKCSE 2023

作者： Boneva, Ani Ivanova, Veronika Vasilev, Plamen Ivanov, Stoyan Ivanova, Tsvetelina Institute of Information and Communication Technologies Bulgarian Academy of Sciences Department of Communication Systems and Services Sofia Bulgaria Institute of Robotics Bulgaria Academy of Sciences Department of Robotized and Mechatronics Intelligent Systems Sofia Bulgaria University of Chemical Technologies and Metallurgy Department of Industrial Automation Sofia Bulgaria

ISBN: (纸本)9798350313246

This publication presents a review of the application of large databases (Big Data) in medicine. The aim of the work is to provide some positive guidelines for the optimization of health care and improvement of patient care in Bulgaria. Therefore, the article discusses designed applications that can find their place in various fields of medicine. Our proposed optimization is the introduction of electronic chip cards. The development assumes that each patient will be provided with a processor card carrying information about basic data related to the condition and its personalization and possible access to this data when necessary. Thus, the proposed solution provides an opportunity to upgrade (for the future) and build an information system with a connection to the health fund. In addition, an early-stage project is described to integrate data from personal portable devices with the electronic health record, thereby providing information to medical personnel about the individual's health status. Portable personal devices and other non-medical equipment generate a huge, almost continuous flow of data that can be useful in making decisions regarding the treatment of patients with various health conditions. The applications described are a continuation of the team's previous developments. © 2023 IEEE.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Bifurcation variation of a novel line-symmetric double-centered 6R metamorphic mechanism based on ellipses

Bifurcation variation of a novel line-symmetric double-cente...

引用

2023 IEEE International Conference on robotics and Biomimetics, ROBIO 2023

作者： Lin, Song Song, Yifeng Wang, Hongguang Yuan, Bingbing Dai, Jiansheng Jing, Fengren Shenyang Institute of Automation Chinese Academy of Sciences Institutes for Robotics State Key Laboratory of Robotics Shenyang110016 China Chinese Academy of Sciences Intelligent Manufacturing Shenyang110169 China University of Chinese Academy of Sciences Beijing100049 China Southern University of Science and Technology Department of Mechanical and Energy Engineering Shenzhen518055 China

ISBN: (纸本)9798350325706

This paper proposed a line-symmetric double-centered 6R metamorphic mechanism with bifurcation properties. The mechanism is constructed based on elliptical geometric properties, which is a comprehensive design method for constructing novel metamorphic mechanisms through intuitive geometric figures. Firstly, the geometric constraints of the 6R metamorphic mechanism are revealed, and the parameter constraints and closed-loop kinematic equations of the 6R metamorphic mechanism are deduced. Through the analysis of mechanism geometric constraints, four motion branches of the 6R metamorphic mechanism are obtained: collinear deployable motion branch MB1, spherical 4R motion branch MB2, spherical 4R motion branch MB3, and line-symmetrical Bricard motion branch MB4. Meanwhile, according to the screw theory, the analytical expressions and mobility of the constraint-screw systems under different motion branches are deduced. This led to the identification of the constraint and motion branch variations of the 6R metamorphic mechanism. Finally, the four serial link 4R singular configurations of the 6R metamorphic mechanism are specially studied, and the characteristics of the mutual reconfiguration of these four singular configurations are revealed. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Raising Body Ownership in End-to-End Visuomotor Policy Learning via Robot-Centric Pooling

Raising Body Ownership in End-to-End Visuomotor Policy Learn...

引用

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

作者： Zheyu Zhuang Ville Kyrki Danica Kragic Robotics Perception and Learning Lab EECS KTH Royal Institute of Technology Stockholm Sweden Department of Electrical Engineering and Automation (EEA) Intelligent Robotics Group Aalto University Espoo Finland

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

We present Robot-centric Pooling (RcP), a novel pooling method designed to enhance end-to-end visuomo-tor policies by enabling differentiation between the robots and similar entities or their surroundings. Given an image-proprioception pair, RcP guides the aggregation of image features by highlighting image regions correlating with the robot’s proprioceptive states, thereby extracting robot-centric image representations for policy learning. Leveraging contrastive learning techniques, RcP integrates seamlessly with existing visuomotor policy learning frameworks and is trained jointly with the policy using the same dataset, requiring no extra data collection involving self-distractors. We evaluate the proposed method with reaching tasks in both simulated and real-world settings. The results demonstrate that RcP significantly enhances the policies’ robustness against various unseen distractors, including self-distractors, positioned at different locations. Additionally, the inherent robot-centric characteristic of RcP enables the learnt policy to be far more resilient to aggressive pixel shifts compared to the baselines. Code available at: https://***/Zheyu-Zhuang/RcP

关键词： Propioception Performance gain Image representation Data collection Feature extraction Robustness History Robots Intelligent robots Resilience

来源：评论

学校读者我要写书评

暂无评论

Exploiting Hybrid Policy in Reinforcement Learning for Interpretable Temporal Logic Manipulation

arXiv

引用

arXiv 2024年

作者： Zhang, Hao Wang, Hao Huang, Xiucai Chen, Wenrui Kan, Zhen The Department of Automation the University of Science and Technology of China Anhui Hefei230026 China The School of Automation Chongqing University Chongqing China School of Robotics Hunan University Changsha China

Reinforcement Learning (RL) based methods have been increasingly explored for robot learning. However, RL based methods often suffer from low sampling efficiency in the exploration phase, especially for long-horizon manipulation tasks, and generally neglect the semantic information from the task level, resulted in a delayed convergence or even tasks failure. To tackle these challenges, we propose a Temporal-Logic-guided Hybrid policy framework (HyTL) which leverages three-level decision layers to improve the agent’s performance. Specifically, the task specifications are encoded via linear temporal logic (LTL) to improve performance and offer interpretability. And a waypoints planning module is designed with the feedback from the LTL-encoded task level as a high-level policy to improve the exploration efficiency. The middle-level policy selects which behavior primitives to execute, and the low-level policy specifies the corresponding parameters to interact with the environment. We evaluate HyTL on four challenging manipulation tasks, which demonstrate its effectiveness and interpretability. Our project is available at: https://***/view/hytl-0257/. Copyright © 2024, 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

Method for Improvement of Biosignal Measurement Accuracy in the IoB System

Method for Improvement of Biosignal Measurement Accuracy in ...

引用

International Conference on Soft Computing and Measurements (SCM)

作者： Yeldos A. Altay Raisa K. Uskenbayeva Alexey V. Fedorov Department of Robotics and Technical Means of Automation Satbayev University Almaty Kazakhstan Satbayev University Almaty Kazakhstan Faculty of Control Systems and Robotics ITMO University Saint-Petersburg Russian Federation

ISBN: (数字)9798350363708

ISBN: (纸本)9798350363715

This paper presents filtering methods for improvement of biosignal measurement accuracy - an ECG signal under the influence of electromagnetic interference, which has a significant impact on the operation of the IoB system. A single-frequency polynomial notch filter has been synthesized to filter this noise to improve the accuracy of ECG signal measurement. The results of the implementation of the synthesized notch filter demonstrated that the filter makes it possible to separate the informative component from the distorting noise and increase the accuracy of signal measurement during its implementation in comparison with wavelet filters.

关键词： Accuracy Shape Filtering Electromagnetic interference Measurement uncertainty Electrocardiography Polynomials

来源：评论

学校读者我要写书评

暂无评论

Underwater Soft Gripper Hydraulic Drive Control System Based on Rigid-flexible Coupling Accumulator

Underwater Soft Gripper Hydraulic Drive Control System Based...

引用

2022 Chinese automation Congress, CAC 2022

作者： Bai, Li Zhang, Daohui Fu, Xin Mo, Liyan Bai, Yunfei Zhang, Qifeng Zhao, Xingang The State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China Department of Information Science and Engineering Northeastern University Shenyang China

ISBN: (纸本)9781665465335

Underwater manipulators are critical in the development of marine resources. Traditional rigid manipulators cannot be applied for underwater operations requiring non-destructive grasping, such as biological sampling and artifact salvage, due to their large size and dimensions and complex force feedback control. Soft robotics underwater manipulators overcome this challenge by providing a dexterous and lightweight arm and gripper, but still require high power drive elements and high-frequency valve control components to achieve the required dynamic performance. In this work, we propose a rigid-flexible coupling accumulator that takes into account the lightweight characteristics of the flexible accumulator and the strong energy storage characteristics of the rigid accumulator, starting from the high-power drive unit. On this basis, we propose a hydraulic drive control system based on the rigid-flexible coupling accumulator for the submerged soft gripper. The system can achieve depth self-adaptation and a fast and stable drive for different volumes of the soft gripper, facilitating the application of soft grippers in marine resource exploitation. The proposed design method and analytical model of the rigid-flexible accumulator can also be used as a guide for other applications. © 2022 IEEE.

关键词： Control systems

来源：评论

学校读者我要写书评

暂无评论

Integrating Expert Guidance for Efficient Learning of Safe Overtaking in Autonomous Driving Using Deep Reinforcement Learning

arXiv

引用

arXiv 2023年

作者： Lu, Jinxiong Alcan, Gokhan Kyrki, Ville The Intelligent Robotics Group Department of Electrical Engineering and Automation Aalto University Espoo02150 Finland

Overtaking on two-lane roads is a great challenge for autonomous vehicles, as oncoming traffic appearing on the opposite lane may require the vehicle to change its decision and abort the overtaking. Deep reinforcement learning (DRL) has shown promise for difficult decision problems such as this, but it requires massive number of data, especially if the action space is continuous. This paper proposes to incorporate guidance from an expert system into DRL to increase its sample efficiency in the autonomous overtaking setting. The guidance system developed in this study is composed of constrained iterative LQR and PID controllers. The novelty lies in the incorporation of a fading guidance function, which gradually decreases the effect of the expert system, allowing the agent to initially learn an appropriate action swiftly and then improve beyond the performance of the expert system. This approach thus combines the strengths of traditional control engineering with the flexibility of learning systems, expanding the capabilities of the autonomous system. The proposed methodology for autonomous vehicle overtaking does not depend on a particular DRL algorithm and three state-of-the-art algorithms are used as baselines for evaluation. Simulation results show that incorporating expert system guidance improves state-of-the-art DRL algorithms greatly in both sample efficiency and driving safety. Copyright © 2023, 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

Foreword

Lecture Notes in Networks and Systems

引用

Lecture Notes in Networks and Systems 2024年 1219 LNNS卷 vi页

作者： Szewczyk, Roman Zieliński, Cezary Kaliczyńska, Malgorzata Bučinskas, Vytautas Lukasiewicz Research Network Industrial Research Institute for Automation and Measurements Warsaw Poland Department of Mechatronics Robotics and Digital Manufacturing Faculty of Mechanics Vilnius Lithuania

来源：评论

学校读者我要写书评

暂无评论

Effect of Pneumatic Based Hybrid Robotic Gripper for Safer Handling of Complex Geometries

Effect of Pneumatic Based Hybrid Robotic Gripper for Safer H...

引用

International Conference on Advanced Computer Control, ICACC

作者： Santhosh Sivaraj Ajay Ravi Bibin Joe Jose Gobinath Velu Kaliyannan Rajkamal Sivakumar Riya Catherine Amalraj Department of Robotics and Automation Easwari Engineering College Chennai TamilNadu India Department of Mechatronics Engineering Kongu Engineering College Perundurai TamilNadu India

ISBN: (数字)9798350379136

ISBN: (纸本)9798350379143

The present research work mainly concentrates on development of hybrid grippers with the integration of hard and soft components for achieving object manipulation. By combining pneumatic actuation with mechanical fingers, complex geometries can be handled effectively. Pneumatic hybrid gripper fabricated with PLA and silicone rubber offers adaptability and versatility. Resistive sensors over silicone surface of gripper lead to cost-effective force detection and tactile sensing. The proposed gripper was designed and analyzed using Fusion 360 and ANSYS. Inflatable silicone rubber and gripper body were fabricated using liquid casting and Fused Deposited Modelling 3D printing techniques. Real-time feedback sensors were employed with fabricated gripper to get better performance. Testing proves its capability to handle loads up to 500g with a force of 3.3N. Finally, the assembled hybrid gripper offers a versatile solution for robotic manipulation, ensuring stability and minimizing damage across various industries.

关键词： Service robots Force Tactile sensors Pneumatic systems Real-time systems Sensors Rubber Grippers Intelligent sensors Testing

来源：评论

学校读者我要写书评

暂无评论

Optimizing Route Efficiency in Formula One (F1) Vehicles Using Reinforcement Learning Algorithms 4

Optimizing Route Efficiency in Formula One (F1) Vehicles Usi...

引用

4th IEEE International Conference on Artificial Intelligence in Cybersecurity, ICAIC 2025

作者： Narejo, Sanam Khan, Muhammad Taimoor Shaikh, Muhammad Zakir Dhirani, Lubna Luxmi Chowdhery, Bhawani Shankar Mehran Univerity of Engineering and Technology Department of Computer Systems Jamshoro Pakistan Mehran Univerity of Engineering and Technology Jamshoro National Centre for Robotics Automation and Artificial Intelligence Pakistan University of Malaga Mechanical Engineering and Energy Efficiency School of Industrial Engineering Malaga Spain University of Limerick Department of Electronic and Computer Engineering Limerick Ireland

ISBN: (纸本)9798331518882

This research explores the application of reinforcement learning (RL) to enhance route efficiency and performance of a Formula One (F1) car within a simulation environment. The simulation is implemented using Python, NEAT (NeuroEvolution of Augmenting Topologies), and PyGame to create a dynamic system where neural networks control the car's navigation. RL enables the F1 car, acting as an agent, to learn optimal decisions through a fitness-based reward mechanism by interacting with its environment. Equipped with radar sensors to detect obstacles and measure distances, the virtual car adjusts its speed and steering to avoid collisions and optimize movement. Over successive generations, the RL algorithm refines the car's driving ability, improving speed and directional control to maximize distance covered and minimize lap times. A fitness-based evaluation system tracks progress, providing metrics such as best and average fitness scores, which highlight the car's evolving performance. Results demonstrate the effectiveness of RL in enhancing autonomous driving capabilities, enabling the car to navigate complex environments and improve decision-making across generations. © 2025 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：