检索结果-内蒙古大学图书馆

IEEE Transactions on Intelligent Vehicles 2024年 1-13页

作者： Wang, Ze Yang, Kailun Shi, Hao Zhang, Yufan Xu, Zhijie Gao, Fei Wang, Kaiwei State Key Laboratory of Extreme Photonics and Instrumentation School of Robotics and the National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha China School of Computing and Engineering University of Huddersfield Huddersfield U.K State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou China

In this paper, we propose LF-PGVIO, a Visual-Inertial-Odometry (VIO) framework for large Field-of-View (FoV) cameras with a negative plane using points and geodesic segments. The purpose of our research is to unleash the potential of point-line odometry with large-FoV omnidirectional cameras, even for cameras with negative-plane FoV. To achieve this, we propose an Omnidirectional Curve Segment Detection (OCSD) method combined with a camera model which is applicable to images with large distortions, such as panoramic annular images, fisheye images, and various panoramic images. The geodesic segment is sliced into multiple straight-line segments based on the radian and descriptors are extracted and recombined. Descriptor matching establishes the constraint relationship between 3D line segments in multiple frames. In our VIO system, line feature residual is also extended to support large-FoV cameras. Extensive evaluations on public datasets demonstrate the superior accuracy and robustness of LF-PGVIO compared to state-of-the-art methods. The source code will be made publicly available at https://***/flysoaryun/LF-PGVIO. IEEE

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

MULTI-SOURCE CONTRASTIVE LEARNING FROM MUSICAL AUDIO 20

MULTI-SOURCE CONTRASTIVE LEARNING FROM MUSICAL AUDIO

引用

20th Sound and Music Computing Conference, SMC 2023

作者： Garoufis, Christos Zlatintsi, Athanasia Maragos, Petros Institute of Language and Speech Proc. Athena Research Center Athens Greece Institute of Robotics Athena Research Center Athens Greece School of ECE National Technical University of Athens Athens Greece

ISBN: (纸本)9789152773727

Contrastive learning constitutes an emerging branch of self-supervised learning that leverages large amounts of unlabeled data, by learning a latent space, where pairs of different views of the same sample are associated. In this paper, we propose musical source association as a pair generation strategy in the context of contrastive music representation learning. To this end, we modify COLA, a widely used contrastive learning audio framework, to learn to associate a song excerpt with a stochastically selected and automatically extracted vocal or instrumental source. We further introduce a novel modification to the contrastive loss to incorporate information about the existence or absence of specific sources. Our experimental evaluation in three different downstream tasks (music auto-tagging, instrument classification and music genre classification) using the publicly available Magna-Tag-A-Tune (MTAT) as a pre-training dataset yields competitive results to existing literature methods, as well as faster network convergence. The results also show that this pre-training method can be steered towards specific features, according to the selected musical source, while also being dependent on the quality of the separated sources. © 2023 Christos Garoufis et al.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

AUTONOMOUS MOBILE PLATFORM WITH UV RAY DISINFECTION SYSTEM, A MODULAR AND AFFORDABLE SOLUTION FOR VIRUS ELIMINATION

International Journal of Mechatronics and Applied Mechanics

引用

International Journal of Mechatronics and Applied Mechanics 2024年第15期2024卷 146-157页

作者： Țîțu, Aurel Mihail Bâlc, Daniel Gusan, Vasile Bogorin-Predescu, Adrian Tertereanu, Petrică Stanciu, Andreea Lucian Blaga University of Sibiu 10 Victoriei Street Sibiu Romania National University of Science and Technology POLITEHNICA Bucharest Faculty of Industrial Engineering and Robotics Splaiul Independenţei no. 313 6th District Bucharest Romania National Institute of Research and Development in Mechatronics and Measurement Technique INCDMTM Bucharest Romania

In the post-COVID erа, there hаs been а growing emphasis on the significance of disinfecting objects individuals come into contаct with. Mobile disinfection robots hаve emerged аs а definitive solution to meet this demаnd. However, inherent issues in their current design mаy pose chаllenges leаding to: continuous virus contamination (there is a risk that mobile UV robots may fail to reach all areas or fully eliminate pathogens, which could allow viruses to survive and subsequently spread infections);increase in the number of disease cases (incomplete disinfection may lead to the persistence of viruses in the environment, thereby increasing the likelihood of disease transmission and the emergence of a greater number of infection cases);illness among medical staff (if the environment in which medical staff operate is not fully disinfected, they may be exposed to the risk of infection with various pathogens, jeopardizing their health and ability to provide adequate medical care);the loss of human lives (inefficiency in disinfection can contribute to the spread of infectious diseases, leading to a higher number of deaths among the population, underscoring the need to address and resolve these issues). This scientific endeаvor аims to outline the primаry chаllenges аssociаted with conventional mobile disinfection robots and introduce a solution through the implementation of аn Аutonomous Mobile Plаtform equipped with а UV Ray Disinfection System. A critical issue identified in conventional mobile disinfection robots pertаins to their inаbility to ensure mаximum efficiency in preventing the spreаd of viruses. This limitаtion is often linked to their stаtic structure аnd the incаpacity to efficiently cover the entire space. Furthermore, the risk of continuous аthe introduction of аn Аutonomous Mobile Plаtform integrated with а UV Rаy Disinfhumection System. This innovаtive аpproаch effectively addresses existing limitations in conventional robots. The autonomous mobile plа

关键词： Disinfection

来源：评论

学校读者我要写书评

暂无评论

Disturbance Compensation Based Sliding Mode Control for Aerial Soft Manipulator System 13

Disturbance Compensation Based Sliding Mode Control for Aeri...

引用

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

作者： Jin, Ying Pei, Tengfei Yu, Hai Zhang, Zhaopeng Han, Jianda Liang, Xiao Institute of Robotics and Automatic Information System Tianjin Key Laboratory of Intelligent Robotics College of Artificial Intelligence Nankai University Tianjin300350 China Nankai University Ministry of Education Engineering Research Center of Trusted Behavior Intelligence Tianjin300350 China

ISBN: (纸本)9798350315196

Aerial manipulation is an emerging area of research that is experiencing rapid growth and has immense potential across various domains, including precision agriculture, construction, and search and rescue operations. The combination of quadrotor with manipulation capabilities can provide access to remote or hazardous areas, precise control over tasks, and increased efficiency and safety in operations. However, traditional aerial manipulation platforms equipped with rigid manipulators have such drawbacks greater weight and less safety. Consequently, a novel complaint aerial manipulation system is considered to be developed. In this paper, a novel structure of an aerial manipulation platform with a single-section continuum manipulator is developed. In order to address the center-of-mass displacement resulting from manipulator movements, a sliding mode controller is introduced as a means to ensure the quadrotor's flight remains smooth. Afterward, the Lyapunov theorem is employed to ensure stability of the entire closed-loop system. Subsequently, numerical simulations are carried out to showcase the superior performance of the proposed control scheme in comparison to the PD controller. © 2023 IEEE.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

Research on Robot Path Planning Algorithm for Filter Plate Cleaning of Plate and Frame Filter Press 4

Research on Robot Path Planning Algorithm for Filter Plate C...

引用

4th International Symposium on Artificial Intelligence and Intelligent Manufacturing, AIIM 2024

作者： Xu, Jie Cui, Long Zhao, Yongguo Tian, Xincheng Center for Robotics School of Control Science and Engineering Shandong University Jinan China Engineering Research Center of Intelligent Unmanned System Ministry of Education Jinan China Institute of Automation Qilu University of Technology Shandong Academy of Sciences Jinan China

ISBN: (纸本)9798331541729

Plate and frame filter press is an important solid-liquid separation equipment that plays an important role in many fields. The filter plate is one of the core components of the frame filter press, and its main function is to support the filter cloth and form a filter chamber. After the filtration process of the filter press is completed, a large number of impurities are often attached to the filter plate, so it is of great value to study the impurity cleaning problem of the filter plate of the plate and frame filter press. In this paper, aiming at the cleaning process of the filter plate of the plate and frame filter press, the image information of the filter plate is obtained by visual means, and then the image is analyzed and processed to obtain the position information of the impurities of the filter plate, the path planning of the obtained position information is carried out, and finally the robot is made to complete the cleaning task efficiently and accurately according to the planned path, which has certain practical value. © 2024 IEEE.

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

A Comparison of Model-Free Controllers for Trajectory Tracking in a Plant-Inspired Soft Arm 13th

A Comparison of Model-Free Controllers for Trajectory Tracki...

引用

13th International Conference on Biomimetic and Biohybrid Systems, Living Machines 2024

作者： Nazeer, Muhammad Sunny Ansari, Yasmin Tauqeer Falotico, Egidio Laschi, Cecilia Department of Mechanical Engineering College of Design and Engineering National University of Singapore Singapore Singapore Bioinspired Soft Robotics Lab Istituto Italiano di Tecnologia Genoa Italy The Biorobotics Institute Scuola Superiore Sant’Anna Pontedera Italy

ISBN: (纸本)9783031725968

The field of soft robotics is experiencing a transformative phase with the emergence of self-supporting modular soft robot arms, inspired by design principles drawn from climbing plants, which are gaining recognition as a rich source of bio-inspiration. The vision to deploy these systems in highly unstructured environments, qualifies the need to investigate model-free algorithms that facilitate motion capabilities based solely on data regarding system-environment interactions. This paper delves into the development of model-free controllers to enable tracking capabilities in these systems. While the trajectory tracking task is already recognized as challenging in the context of redundant continuum/soft arms, the difficulty is compounded when aiming to generate control policies solely from sequential feedback from the environment. The novelty of this work lies in the development of both learning-based and learning-free model-free computational frameworks to address this task. Both controllers are validated on a 9-DoF modular cable-driven plant-inspired soft arm for moving through multiple trajectories in 3D space. The comparison of these controllers holds significant insights to future directions for the practical applicability of these systems in real-world scenarios, and are promising to pave way for novel application scenarios. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Robotic arms

来源：评论

学校读者我要写书评

暂无评论

Pest Detection and Identification Guided by Feature Maps 12

Pest Detection and Identification Guided by Feature Maps

引用

12th International Conference on Image Processing Theory, Tools and Applications, IPTA 2023

作者： Chen, Miao Chen, Yanan Guo, Minghui Wang, Jianji Xi'an Jiaotong University National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics China Xi'an Jiaotong University School of Software Engineering Xi'an China

ISBN: (纸本)9798350325416

Effective pest detection and identification are of great significance for agricultural activities, and morden machine learning methods, especially the deep neural network, undoubtedly provide convenient and effective ways for this issue. Most of the mainstream methods for pest detection require annotation of manual bounding box. However, the public pest datasets usually lack the labeling information. In this work, we propose a method for detecting pests with weak supervision. We obtain the key regions of the pest targets by deeply mining the information in the feature maps of the convolutional neural networks (CNNs). First, using the class activation mapping technique to generate activation maps of the target class during forward propagation of the model, and then obtaining the key regions of the target based on the hotspots extracted from the activation maps. In addition, our proposed method can be deployed as a general strategy to other CNNs, and experimental results demonstrate that our method can steadily improve the classification accuracy of the model. By applying our method to the single Resnet50, we can achieve 74.27% classification accuracy on the publicly accessible IP102 dataset. Another attribution of this paper is that we propose a lightweight approach to find solutions for pest detection in agricultural automation applications. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Intention-Oriented Fast Joint Prediction and Planning for Safe Driving 27

Intention-Oriented Fast Joint Prediction and Planning for Sa...

引用

27th IEEE International Conference on Intelligent Transportation Systems, ITSC 2024

作者： Zhang, Mingyi Xue, Jianru Lv, Chen Fang, Jianwu Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University National Key Laboratory of Human-Machine Hybrid Augmented Intelligence China School of Mechanical and Aerospace Engineering Nanyang Technological University Singapore

ISBN: (纸本)9798331505929

The primary challenges for Autonomous Vehicle (AV) navigation in complex scenarios are to effectively handle the interactions between the Ego-Vehicle (EV) and surrounding participants and generate safe yet non-conservative plans. Current approaches employ Planning-Informed Prediction (PIP) and Joint Prediction and Planning (JPP) to model these interactions. At the same time, information loss exists in PIP and JPP always ignores the intention interactions for a free space generation. To this end, this paper incorporates intention interactions into JPP, where a shared intention interaction module is adopted to both the planning and the prediction tasks via a cross-query mechanism, enabling the model to reduce the model size and accelerate inference speed. In contrast to previous methods that typically plan a single trajectory and result in conservative behaviors, we introduce a contingent-masked planner to balance the safety and efficiency, so as to fulfill the scene-level prediction and greatly improve computational efficiency. We evaluate our approach through closed-loop experiments on the CARLA longest6 and Town05 benchmarks, and faster inference speed and more robust performance against state-of-the-art methods. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Nonsmooth Dynamic Modeling of a Humanoid Robot with Parallel Mechanisms 16th

Nonsmooth Dynamic Modeling of a Humanoid Robot with Paral...

引用

16th International Conference on Intelligent robotics and Applications, ICIRA 2023

作者： Xiong, Jiaming Liang, Dingkun Wang, Xin Huang, Yongshan Xie, Anhuan Gu, Jason Research Center for Intelligent Robotics Research Institute of Interdisciplinary Innovation Zhejiang Lab Hangzhou311100 China Zhejiang Engineering Research Center for Intelligent Robotics Hangzhou311100 China Department of Electrical and Computer Engineering Dalhousie University HalifaxNSB3H 4R2 Canada

ISBN: (纸本)9789819964918

This paper establishes a nonsmooth dynamic model for a humanoid robot with parallel mechanisms. Firstly, the constraint equations of the parallel mechanism are derived through kinematic analysis. By combining the links involved in closed-loop constraints into aggregate nodes, the topology of the robot can be equivalent to a tree structure. Equivalent physical quantities for the aggregate nodes are defined to unify their treatment with individual nodes during dynamic modeling. Subsequently, the contact and impact dynamics of the robot are modeled using constraint-based methods, with a frictional multiple impacts model employed for impacts. Due to the high degree of freedom of the robot, recursive methods are adopted to calculate the corresponding dynamic matrices. Finally, numerical examples are provided to illustrate the dynamic model of the robot. A comparison with the compliance-based methods of Simscape Multibody demonstrates that our dynamic model can reflect more realistic physical processes, providing a more accurate simulation environment for the motion control of the robot. The simulation of standing balance control is also performed based on our dynamic model. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

Exoskeleton-Based Lower Limb Rehabilitation Robot Design and Simulation for Children with Cerebral Palsy

Exoskeleton-Based Lower Limb Rehabilitation Robot Design and...

引用

2024 International Convention on Rehabilitation engineering and Assistive Technology and World Rehabilitation Robot Convention, i-CREATE and WRRC 2024

作者： Cao, Wujing Zhang, Shuo Zou, Yupeng Guo, Xinqiang Li, Changyu Wang, Jingxin Kobsiriphat, Worawarit Wu, Xinyu Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen518005 China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society SIAT-CUHK Joint Laboratory of Robotics and Intelligent Systems China School of Mechanical Engineering China University of Petroleum China Jining Zhongke Intelligent Technology Co. Ltd. China Zhengzhou Central Hospital Zhengzhou University Department of Rehabilitation Medicine Zhengzhou China National Metal and Materials Technology Center Thailand

ISBN: (纸本)9798350355123

Squat gait is the most common abnormal gait in children with cerebral palsy. Gait training with lower limb rehabilitation robots can improve rehabilitation efficiency and reduce manual labor for them. A novel exoskeleton-based lower limb rehabilitation robot for children with cerebral palsy is proposed, considering the squat gait characteristics of children with cerebral palsy. The structure of the lower limb rehabilitation robot, which combines hip and knee with 4 active degrees of freedom exoskeleton and mobile walker, is designed and optimized. Static analysis of the key mechanical structure of the exoskeleton is conducted using ANSYS Workbench, and local structures are optimized to ensure the safety factor of the mechanical structure is greater than 1, guaranteeing reasonable structural strength and stiffness design. Dynamic simulation analysis based on the ADAMS model validates the reliability and dynamic walking effect of the lower limb exoskeleton rehabilitation robot, obtaining the curve relationship between joint angles and motion cycles, thus verifying the effectiveness of the mechanical system motion. © 2024 IEEE.

关键词： Exoskeleton (robotics)

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：