检索结果-内蒙古大学图书馆

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

作者： Pei, Tengfei Jin, Ying Yu, Hai Fang, Yongchun 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 Engineering Research Center of Trusted Behavior Intelligence Ministry of Education Tianjin300350 China

ISBN: (纸本)9798350315196

Trajectory planning has been an important research area for quadrotor transportation systems for a long time. However, generating feasible trajectories in real-time that allow quadrotor transportation systems to navigate safely in complex environments remains a challenging issue. This article proposes an efficient gradient-based safety constraint that helps keep the system away from obstacles. Furthermore, this paper combines safety constraint with a novel B-spline-based optimization method that utilizes an improved hybrid-state A* algorithm for path searching to generate desired trajectory. Strategies to speed up path searching and unconstrained optimization problem constructed in B-spline optimization guarantee the computational efficiency. The feasibility of the resulting trajectory has been verified through simulation. © 2023 IEEE.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

EXPLORING POLYPHONIC ACCOMPANIMENT GENERATION USING GENERATIVE ADVERSARIAL NETWORKS 20

EXPLORING POLYPHONIC ACCOMPANIMENT GENERATION USING GENERATI...

引用

20th Sound and Music Computing Conference, SMC 2023

作者： Charitou, Danae 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

Recently, various neural network architectures have shown capability of achieving compelling results in the field of automatic music generation. Motivated by this, in this work we design a generative framework that is structurally flexible and adaptable to different musical configurations and practices. At first, we examine the task of multi-track music generation without any human input, by modifying and proposing improvements to the MuseGAN architecture, an established GAN-based system, which we use as our baseline. Afterwards, we extend our developed framework to a cooperative human-AI setup for the generation of polyphonic accompaniments to user-defined tracks. We experiment with multiple structural variants of our model, and two different conditional instruments, namely piano and guitar. For both unconditional and conditional cases, we evaluate the produced samples objectively, using a set of widely used musical metrics, as well as subjectively, by conducting a listening test across 40 subjects. The experimental results, using the Lakh Pianoroll Dataset, reveal that our proposed modifications lead to improvements over the baseline from an auditory perspective in the unconditional case, and also provide useful insights about the properties of the produced music in the conditional setup, depending on the utilized configuration. © 2023 Danae Charitou et al.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

Optimized Design and Experimental Study of Shank Structure of Biped Robot

Optimized Design and Experimental Study of Shank Structure o...

引用

2023 IEEE International Conference on robotics and Biomimetics, ROBIO 2023

作者： Qin, Meijuan Kong, Lingyu Nie, Daming Jiang, Hongjian Zhang, Yu Fu, Yili Intelligent Robot Research Center Zhejiang Laboratory Hangzhou311100 China The National Key Laboratory of Robotics and Systems Harbin Institute of Technology Harbin150001 China

ISBN: (纸本)9798350325706

Lightweight design can improve the energy efficiency of biped robots, which is significant in the field of biped robot. Topology optimization has been widely used in the field of robot. However, the existing optimization is limited to the structural space based on traditional empirical design, and the potential of topology optimization is not fully utilized. Moreover, the finite element model is too simplified, which leads to a large optimization deviation. In this paper, a method of structural innovation design for the shank structure of biped robot is proposed. In the initial stage of conceptual design, the design space of optimization object is effectively maximized. Then, the load transmission characteristics of bearings are simulated by link10 element, and the topology optimization method of multiple load cases is carried out to obtain the optimized shank structure, which reduces the weight by 14.09 % compared with the existing shank. Finally, finite element extreme strength check and experiment test are both used to verify the feasibility and availability of the structure. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Rigid-Flexible Coupling Recursive Formulation for Dynamic Modeling of Biped Robots 16th

A Rigid-Flexible Coupling Recursive Formulation for Dynamic...

引用

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

作者： Tang, Lingling Liang, Dingkun Wang, Xin Xie, Anhuan Gu, Jason Research Center for Intelligent Robotics Research Institute of Interdisciplinary Innovation Zhejiang Laboratory 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)9789819964796

Biped robots are complex rigid-flexible coupling multibody systems that achieve the desired stable locomotion through foot-ground interactions. In the recent bio-inspired structure designs for biped robots, flexible parts are usually adopted to absorb the foot-ground impact and store the contact energy. However, most existing modeling formulations can only treat biped robots as rigid multibody systems, and the flexible parts are simply replaced by some linear or torsion springs. Since the deformations of the flexible parts have significant effects on the dynamic responses of the biped robot, the rigid multibody modeling method inevitably leads to a gap between the simulation model and the real prototype, and makes the sim-to-real transfer more difficult. To address this problem, a rigid-flexible coupling recursive modeling formulation is presented in this paper. In addition, the foot-ground interaction is modeled via a smooth normal contact model and a velocity-based Coulomb friction model. Finally, several numerical examples including inverse dynamics, kinematic closed-loop and frictional contact are given to verify the rigid-flexible coupling formulation. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Machine design

来源：评论

学校读者我要写书评

暂无评论

Computer-aided Detection of Tuberculosis from Microbiological and Radiographic Images

引用

Data Intelligence 2023年第4期5卷 1008-1032页

作者： Abdullahi Umar Ibrahim Ayse Gunnay Kibarer Fadi Al-Turjman Department of Biomedical Engineering Near East UniversityNicosiaMersin 10Turkey Research Center for Al and loT Faculty of EngineeringUniversity of KyreniaMersin 10Turkey Artificial Intelligence Engineering Dept. Al and Robotics InstituteNear East UniversityMersin 1Turkey

Tuberculosis caused by Mycobacterium tuberculosis have been a major challenge for medical and healthcare sectors in many underdeveloped countries with limited diagnosis *** can be detected from microscopic slides and chest X-ray but as a result of the high cases of tuberculosis,this method can be tedious for both Microbiologists and Radiologists and can lead to *** challenges can be solved by employing Computer-Aided Detection(CAD)via Al-driven models which learn features based on convolution and result in an output with high *** this paper,we described automated discrimination of X-ray and microscope slide images into tuberculosis and non-tuberculosis cases using pretrained AlexNet *** study employed Chest X-ray dataset made available on Kaggle repository and microscopic slide images from both Near East University Hospital and Kaggle *** classification of tuberculosis using microscopic slide images,the model achieved 90.56%accuracy,97.78%sensitivity and 83.33%specificity for 70:30 *** classification of tuberculosis using X-ray images,the model achieved 93.89%accuracy,96.67%sensitivity and 91.11%specificity for 70:30 *** result is in line with the notion that CNN models can be used for classifying medical images with higher accuracy and precision.

关键词： Tuberculosis Deep Learning Pretrained AlexNet Chest X-ray Microscopic slide

来源：评论

学校读者我要写书评

暂无评论

A Study of Climbing Strategy on Unitree Aliengo

A Study of Climbing Strategy on Unitree Aliengo

引用

2023 International Conference on Intelligent Communication and Computer engineering, ICICCE 2023

作者： Jiong, Wang Rui, Wang Ao, Xi Huishen, Zhu The 21st Research Institute of China Electronics Technology Group Corporation Robotics Engineering Center Shanghai China Qiyuan Lab Beijing China

ISBN: (纸本)9798350395617

This paper designs a novel climbing strategy that can assist in heavy-duty work even when perception is disturbed. Several touchdown times of swing feet is aimed to differentiate the ground and stairs, deciding which gait planning methods to use without the help of vision system The legged robot climb up the four steps 10 cm stairs smoothly and can tentatively measure the lifting height by contact force detection algorithm, which show the effectiveness of the proposed method. © 2023 IEEE.

关键词： Stairs

来源：评论

学校读者我要写书评

暂无评论

Blockchain-based Federated Learning via Model Training 4

Blockchain-based Federated Learning via Model Training

引用

4th International Conference on Computer, Big Data and Artificial Intelligence, ICCBD+AI 2023

作者： Wang, Rui Wang, Jiong Qiyuan Lab Beijing China The 21st Research Institute of China Electronics Technology Group Corporation Robotics Engineering Center Shanghai China

ISBN: (纸本)9798350373233

The existing federated learning models have issues such as malicious central servers and malicious participants publishing false data to poison the model. Aiming at this case, this thesis proposed an improved decentralized federated learning model (IDFL), which moves the aggregation work from the central server to the local participants. In this paper, a proof-of-training consensus mechanism is proposed, which makes the election of block producers based on the quality of model training rather than the competition mechanism, thus effectively avoiding the block generation delay caused by the mining process, and also alleviating the blocking problem in the verification of model parameters in an asynchronous manner. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Study on Different Optimizations of Pure Reference Counting Garbage Collectors

A Comprehensive Study on Different Optimizations of Pure Ref...

引用

2023 International Conference on Computational Intelligence, Networks and Security, ICCINS 2023

作者： Tabassum, Faria Islam, Md. Rahatul Ur Rahman, Md Shoaib Majumder, Jimmy Bangladesh University of Engineering and Technology Department of Cse Dhaka Bangladesh Kyushu Institute of Technology Department of Human Intelligence Systems Engineering Japan Chittagong National Engineering College Department of Mechanical Engineering Bangladesh Bangladesh Advance Robotics Research Center Bangladesh

ISBN: (纸本)9798350313796

With the gradual increase of program complexity for utilities and various appliances, memory management has always been a challenge for computer scientists. Garbage collection is a very effective memory management system that comprises techniques that aim to claim unused objects which in turn returns reusable memory space for further use. Among the array of garbage collection techniques, pure reference counting (RC) is very popular that actively tracks down any unused object reference by means of keeping reference counts. It offers better reliability compared with other passive techniques. However this process cannot track cyclic garbage references. In order to solve this cycle detection issue along with other various improvements available for other techniques different methods have been proposed and developed. This paper offers an extensive examination of diverse optimization approaches designed to improve the effectiveness of garbage collectors based on Pure Reference Counting. Some of these optimizations look for loaning concepts from tracing to improve tracking down performance while others add up cycle detection from various existing techniques to gain the pros of both techniques or others simply emphasize memory allocation for reducing time complexity overhead. Our findings provide insights for researchers seeking to leverage Pure RC as a memory management solution, shedding light on the advantages and limitations of different optimization techniques. This study contributes to the ongoing discourse on memory management, offering a perspective on the specifics of Pure RC-based garbage collectors and their potential for optimization. © 2023 IEEE.

关键词： Storage allocation (computer)

来源：评论

学校读者我要写书评

暂无评论

Point cloud segmentation network based on multi-scale feature fusion

Point cloud segmentation network based on multi-scale featur...

引用

2024 China Automation Congress, CAC 2024

作者： Deng, Hao Cheng, Peng Cheng, Shengmei Liu, Cheng Du, Shaoyi Wang, Lin State-Province Joint Engineering and Research Center of Advanced Networking and Intelligent Information Service School of Information Science and Technology Northwest University Xi’an China National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an China

ISBN: (纸本)9798350368604

Aiming at improving the local feature extraction for point cloud learning, we introduce a point cloud segmentation network that enhances the PointNet++ framework with a local feature transformation module and a multi-scale feature fusion module. The local feature transformation module employs operations akin to convolution to restructure the point cloud's local feature dimensions, thus boosting the network's ability to extract detailed local features. Additionally, the multi-scale feature fusion module integrates semantic features of point clouds across various scales using a layered network design, aiming to heighten segmentation precision. Experimental results indicate that the proposed network can achieve a robust point cloud segmentation accuracy, reaching an accuracy rate of 85.8%. © 2024 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Inherently integrated microfiber-based flexible proprioceptive sensor for feedback-controlled soft actuators

引用

npj Flexible Electronics 2024年第1期8卷 803-816页

作者： Hwajoong Kim Hyunbin Na Seungbeom Noh Shinwon Chang Jinho Kim Taejune Kong Gyowook Shin Chankyu Lee Seonggyu Lee Yong-Lae Park Sehoon Oh Jaehong Lee Department of Robotics and Mechatronics Engineering Daegu Gyeongbuk Institute of Science and Technology(DGIST)333 Techno jungang-daeroHyeonpung-eupDalseong-gunDaeguRepublic of Korea Department of Mechanical Engineering Seoul National University1 Gwanak-roGwanak-guSeoulRepublic of Korea University of California BerkeleyCAUSA

For the accurate and continuous control of soft actuators in dynamic environments,the movements of the soft actuators must be monitored in *** this end,various soft actuators capable of selfmonitoring have been developed by separately integrating sensing devices into ***,integrating such heterogeneous sensing components into soft actuators results in structural complexity,high manufacturing costs,and poor interfacial ***,we report on intelligent pneumatic fiber-reinforced soft actuators with an inherent flexible proprioceptive sensor that uses only the essential components of typical fiber-reinforced soft *** inherent flexible proprioceptive sensor is achieved by leveraging two parallel conductive microfibers around an elastomeric chamber of the soft actuator,which simultaneously acts as both a capacitive bending sensor and radial expansion limiting fibers of typical fiber-reinforced soft *** proprioceptive soft actuator exhibits excellent mechanical actuation up to 240°bending motion and proprioceptive sensing performance with high sensitivity of 1.2 pF rad^(−1).Mathematical analysis and simulations of the soft actuator can effectively predict the bending actuation and capacitive responses against input *** that proprioceptive soft actuators can be used to construct a soft gripping system and prosthetic hand which express various hand gestures and perform dexterous manipulation with real-time proprioceptive sensing capability.

关键词： prop integrating sensor

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：