检索结果-内蒙古大学图书馆

International Conference on Unmanned Aircraft systems (ICUAS)

作者： Nada E. Abbas Tamara Petrovic Faculty of Electrical Engineering and Computing LARICS Laboratory for Robotics and Intelligent Control Systems University of Zagreb Zagreb Croatia

ISBN: (数字)9798331513283

ISBN: (纸本)9798331513290

This paper presents a decentralized graph-based exploration and inspection framework for Multi-Robot systems, designed to address challenges in subterranean and largescale environments. Unlike prior works that focus solely on exploration or inspection, this framework integrates volumetric exploration, semantic inspection, and dynamic task allocation into a unified decentralized system. A key novelty of this work is the seamless integration of these modules in a multi-robot setting, allowing UAVs to autonomously coordinate their tasks without relying on centralized control. The framework employs a hierarchical graph structure, utilizing a dense local graph for immediate navigation and a sparse global graph for long-term planning and repositioning. Extensive simulations in large-scale complex-shaped environments demonstrate that the proposed approach improves the completeness of the generated maps, reduces inconsistencies in the constructed mesh, and accelerates the overall exploration-inspection process compared to existing decentralized strategies.

关键词： Semantics Inspection Prediction algorithms Dynamic scheduling Aircraft navigation Robustness Planning Multi-robot systems Resource management Centralized control

来源：评论

学校读者我要写书评

暂无评论

Contextual Multi-Armed Bandit-Based Dynamic Cooperative Link Configuration for AUV in UWASNs With Energy Harvesting

引用

IEEE Transactions on Cognitive Communications and Networking 2025年

作者： Dai, Jun Li, Xinbin Han, Song Yu, Junzhi Liu, Zhixin Yanshan University Key Lab of Industrial Computer Control Engineering of Hebei Province Qinhuangdao066004 China Yanshan University Key Laboratory of Intelligent Rehabilitation and Neuromodulation of Hebei Province Qinhuangdao066004 China Peking University State Key Laboratory for Turbulence and Complex Systems Department of Advanced Manufacturing and Robotics BIC-ESAT College of Engineering Beijing100871 China

This paper investigates the cooperative link configuration problem for Autonomous Underwater Vehicle (AUV) in Underwater Acoustic (UWA) sensor networks with Energy Harvesting (EH), which aims to maximize long-term cumulative capacity by jointly optimizing cooperation relay, AUV transmission power, and relay transmission power. Subject to unknown time-varying Channel State Information (CSI), unpredictable stochastic EH, and variable communication topology caused by AUV mobility, the proposed problem is an unknown dynamic combination decision optimization problem. To resist the change of the dynamic UWA communication topology with unknown time-varying CSI and EH, a novel collaborative contextual multi-armed bandit learning framework is proposed, which allows relay nodes to learn cooperatively and enriches the learning information of relays. Consequently, the proposed learning framework can resist the change of the dynamic UWA communication topology efficiently, thereby achieving the superior link configuration quickly. Besides, a learning-rate adjustment rule for the dynamic UWA communication topology is proposed to adaptively balance the exploration-exploitation, thereby avoiding missing the real superior joint relay-power configuration. Finally, simulation results show the significantly superiority of the proposed scheme. © 2015 IEEE.

关键词： Cooperative communication

来源：评论

学校读者我要写书评

暂无评论

Obstacle-Avoidance Motion Planning Method of Manipulator Based on Deep Reinforcement Learning

引用

Unmanned systems 2025年

作者： Liu, Yiyang Wu, Defan Fu, Yukai Bai, Hongfei Deng, Chao State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Key Laboratory of Networked Control Systems Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China University of Chinese Academy of Sciences Beijing100049 China Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing210023 China

In recent years, driven by the rapid advancement of industrial automation and intelligent manufacturing, the demand for manipulators to perform tasks in complex environments has significantly increased. Traditional motion planning methods face challenges of computational complexity and lack of adaptability when handling robots with redundant degrees of freedom. To address these issues, this paper proposes a novel obstacle avoidance motion planning method for manipulators based on deep reinforcement learning (DRL), which is especially important when unmanned systems operate in a GPS-free environment. The primary contributions are twofold: (i) we propose an innovative algorithm, termed PPO-HER, which incorporates hindsight experience replay (HER) into proximal policy optimization (PPO) during training, effectively leveraging failed experiences to enhance policy learning efficiency;(ii) an adaptive action exploration strategy is designed to accelerate training convergence and avoid local optima. Experimental results demonstrate that the PPO-HER algorithm and the adaptive action exploration strategy perform exceptionally well across three environments of varying difficulty, significantly improving network training speed and success rates, shortening planned paths, and enhancing autonomous obstacle avoidance capabilities. These findings provide new ideas for target location and tracking of unmanned systems, and lay the foundation for future learning and data-driven approaches in complex environments. © World Scientific Publishing Company.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

control Aspects in Programming by Demonstation for Robotic Deep- Micro- Hole Drilling 32

Control Aspects in Programming by Demonstation for Robotic D...

引用

32nd Mediterranean Conference on control and Automation, MED 2024

作者： Maric, Bruno Petric, Frano Orsag, Matko University of Zagreb LARICS Laboratory for Robotics and Intelligent Control Systems Faculty of Electrical Engineering and Computing Zagreb10000 Croatia

ISBN: (纸本)9798350395440

This paper explores control aspects in a collab-orative robotic system designed to replicate human operators' drilling skills in deep- micro- hole tasks, focusing on the glass-container mould industry. To replicate human performance, we develop a single-DOF Impedance-based drill controller for a standard industrial position-controlled robot, enhancing safe and smooth interactions between the drill bit and the mould. To address high feed rates observed in worker demonstrations and prevent bit breaks, we focus on minimizing non-axial motion during drilling on an off-the-shelf available industrial manipulator KUKA KR 10. This involves analyzing the impact of joint dynamics on drill motion and designing a control system for the robot's low-level control to achieve axial drill motion. We show that the proposed joint control system that takes into account relationship between joint and tool dynamics outperforms available robot low-level control in minimizing non-axial motion, leading to the robot being able to outperform the human in deep- micro- hole drilling. © 2024 IEEE.

关键词： Molds

来源：评论

学校读者我要写书评

暂无评论

Autonomous docking and energy sharing between two types of robotic agents

引用

IFAC-PapersOnLine 2018年第29期51卷 406-411页

作者： Babi, Anja Mandi, Filip Vasiljevi, Goran Mikovi, Nikola Faculty of Electrical Engineering and Computing LABUST Laboratory for Underwater Systems and Technologies University of Zagreb Unska 3 Zagreb Croatia Faculty of Electrical Engineering and Computing LARICS Laboratory for Robotics and Intelligent Control Systems University of Zagreb Unska 3 Zagreb Croatia

In order to achieve long-term autonomy after deployment, a method of energy sharing within a heterogeneous swarm of marine robots was devised and implemented. This paper describes hardware and software solutions as well as guidance and control algorithms developed with the goal of allowing powerful energy-rich overactuated surface platforms to approach, dock, and wirelessly recharge less mobile sensor-rich agents upon request using visual servoing. The basic image processing algorithm uses data acquired by the Microsoft Kinect sensor alternating between RGB and infra-red camera modes, depending on lighting conditions. The full search and docking procedure developed for long-term operation is described. The results of a series of experiments done both in an indoor testbed and in realistic outdoor conditions are discussed and some goals for future work are given. © 2018

关键词： Autonomous agents

来源：评论

学校读者我要写书评

暂无评论

An Indoor Positioning Algorithm Against NLOS Error Based on UWB 41

An Indoor Positioning Algorithm Against NLOS Error Based on ...

引用

第41届中国控制会议

作者： Mingxiang Liao Yongbo Li Guangyao Wang Zhenyu Lei Zihao Zhang School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems System Integration and Industrial Robotics Laboratory

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Ultra-wideband（UWB） positioning technology has absolute advantages due to its centimeter-level accurate positioning ***,the positioning accuracy is greatly reduced because of the inability to completely solve the error caused by non-line-of-sight（NLOS） and multi-path *** present,the Chan-Taylor（C-T） combination algorithm proposed by scholars can achieve a good positioning effect in the line-of-sight（LOS） environment,but in the NLOS environment,positioning deviation of this algorithm is large .Aiming at the problem of low localization accuracy in NLOS environment,this paper presents a Chan-Taylor-Kalman（CTK） joint positioning algorithm based on UWB and adapted to NLOS *** basic idea of CTK joint positioning algorithm is to introduce weight coefficients on the basis of C-T combination algorithm to reduce the situation of non-convergence of positioning results;then combined with the improved Kalman filter to eliminate outliers and eliminate the influence of the non-line-of-sight *** show that under the same NLOS environment,the probability of the positioning error of the C-T combination positioning algorithm greater than 20 cm is about 60%,while the probability of the positioning error of the CTK joint positioning algorithm greater than 10 cm is only about 10%.

关键词： UWB NLOS indoor positioning Chan-Taylor combination algorithm Kalman filter

来源：评论

学校读者我要写书评

暂无评论

Kinematics analysis of lower limb rehabilitation robot based on D-H method 41

Kinematics analysis of lower limb rehabilitation robot based...

引用

第41届中国控制会议

作者： Kui Jie Wangyong He Renjie Gui School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems System Integration and Industrial Robotics Laboratory

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

At present,rehabilitation robots usually work together with patients and train them to achieve therapeutic effects by assisting them to complete movement within a certain *** this paper,it analyzes the average length and proportion of Chinese human lower limbs,as well as the range of extreme motion and comfortable motion of each joint of human lower *** on the error transfer matrix of rigid body connecting rod,the three-DOF lower limb rehabilitation robot human lower limb static pose error model and human/machine integration model are *** D-H method was used to solve the kinematic function between the angle of each joint and the position of the end of human lower *** analysis of the kinematics of human lower limbs is to calculate its inverse kinematics *** the motion control of rehabilitation robots,the inverse kinematics is more important than the forward kinematics,which is the basis for rehabilitation robot to realize trajectory planning under the training mode of passive trajectory traction,as well as the basis for compliant ***,a simulation model is established with Matlab software,and the simulation results show the feasibility and safety of the rehabilitation training process.

关键词： Lower limb rehabilitation robot Range of motion Human kinematics

来源：评论

学校读者我要写书评

暂无评论

Automated Suckering of Vines with a Mobile Robot and a Torque-controlled Suckering Tool 5

Automated Suckering of Vines with a Mobile Robot and a Torqu...

引用

5th IEEE International Conference on Smart systems and Technologies, SST 2022

作者： Stuhne, Dario Vatavuk, Ivo Hrabar, Ivan Vasiljević, Goran Kovačić, Zdenko University of Zagreb Faculty of EE&C Zagreb Croatia University of Zagreb LARICS Laboratory for Robotics and Intelligent Control Systems Faculty of Electrical Engineering and Computing Zagreb10000 Croatia

ISBN: (数字)9781665482158

ISBN: (纸本)9781665482158

The research presented in this paper focuses on the development of fully automated and autonomous vine suckering, a seasonal viticulture activity required to remove all unwanted shoots from the vine trunks. This requires human workers to do a lot of strenuous work, often using only their hands or tools such as clippers or shears. The suckering is done during the early growing season (usually April-May) to provide more energy, water, and nutrients to the main shoots. Commercially available suckering machines appear to be a large-scale solution. However, their performance varies between 10% and 85% and their purely mechanical nature can easily cause damage to the vines. In this paper, we present a concept for autonomous suckering using a mobile robot equipped with a special suckering tool driven by a torque-controlled DC motor that protects the vine from damage. The proposed suckering system was designed, analysed and experimentally validated in a real vineyard. The results showed that the system was able to remove about two thirds of the unwanted shoots, reaching a suckering rate of more than 86 vines per hour. © 2022 IEEE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Procedural Generation of Synthetic Dataset for Robotic Applications in Sweet Pepper Cultivation 5

Procedural Generation of Synthetic Dataset for Robotic Appli...

引用

5th IEEE International Conference on Smart systems and Technologies, SST 2022

作者： Vuletić, Jelena Polić, Marsela Orsag, Matko University of Zagreb Faculty of EE&C Zagreb Croatia University of Zagreb LARICS Laboratory for Robotics and Intelligent Control Systems Faculty of Electrical Engineering and Computing Zagreb10000 Croatia

ISBN: (数字)9781665482158

ISBN: (纸本)9781665482158

In this paper, a deep learning based object detection model is developed for robotic applications in structured agricultural cultivation of sweet peppers (Capsicum annuum). We propose a realistic simulation based method for procedural generation of a labeled sweet pepper dataset. Realistic 3D models of fruit, leaves, and other relevant plant body parts are generated through photogrammetry, enabling generation of a large and relevant dataset. The dataset is labeled for both object detection and semantic segmentation by scene rendering in multiple layers and using artificial depth information. Smart augmentation techniques are deployed in procedural generation, as well as label filtering techniques for more realistic dataset labels. A MobileNet-SSD based deep learning model is trained through transfer learning on the generated dataset. The trained model is tested both in simulated environment, as well as on a relevant real-world setup. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Matrix-Based Approach to Sequence analysis in Multiple Reentrant Flowlines

Matrix-Based Approach to Sequence analysis in Multiple Reent...

引用

2008 American control Conference (ACC), vol.3

作者： Tamara Petrovic Stjepan Bogdan LARICS-Laboratory for Advanced Robotics and Intelligent Control Systems Faculty of Electrical Engeneering and Computing University of Zagreb Croatia

This paper presents a method for extension of matrix model of manufacturing system in order to provide an efficient tool for analysis of systems with various dispatching sequences of shared resources. Proposed method is used for transformation of system matrices in linear max-plus model. Once the linear model is determined sequence feasibility can be checked. Furthermore, the method provides a straightforward procedure for production cycle calculation and resource utilisation. Efficiency of presented technique is demonstrated on a manufacturing system example at the end of the paper.

关键词： Manufacturing systems Dispatching Resource management Production Flexible manufacturing systems Algebra Laboratories intelligent robots intelligent control Computer aided manufacturing

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：