检索结果-内蒙古大学图书馆

Roller chain-like robot for steel bridge inspection 9

学校读者我要写书评

暂无评论

Roller chain-like robot for steel bridge inspection

9th International Conference on Structural Health Monitoring of Intelligent Infrastructure: Transferring Research into Practice, SHMII 2019

作者： Nguyen, Son Thanh La, Hung Manh Advanced Robotics and Automation Lab Department of Computer Science and Engineering University of Nevada RenoNV89557 United States

This paper presents a novel design of steel bridge/structure inspection robot. Compared to most existing robots designed to work on particular surface contour of steel structures such as flat or curving, the proposed roller chain-like robot can implement and transfer smoothly on many kind of steel surfaces. The developed robot can be applied to inspection tasks for steel bridges with complicated structures. The robot is able to carry cameras, sensors for visual and specialized examination. Rigorous analysis of robot kinematics, adhesion force and turn-over failure has been conducted to demonstrate the stability of the proposed design. Mechanical and magnetic force analysis together with turn-over failure investigation can serve as an useful framework for designing various steel climbing robots in the future. Experimental results and field deployments prove the adhesion, climbing, inspection capability of the developed robot. Copyright © SHMII 2019. All rights reserved.

关键词： Robots

A decision aid for the port placement problem in robot-assisted hysterectomy

学校读者我要写书评

暂无评论

Laparoscopic, Endoscopic and Robotic Surgery 2023年第2期6卷 43-56页

作者： Mohammad R.Maddah Jean-Marc Classe Isabelle Jaffre Keith A.Watson Katherine S.Lin Damien Chablat Cedric Dumas Caroline G.L.Cao Department of Biomedical Industrialand Human Factors EngineeringWright State University3640 Colonel Glenn HwyDaytonOHUSA Department of Automatique Productique et InformatiqueIMT Atlantique4 Rue Alfred KastlerNantesFrance Laboratoire des Sciences Du Numerique de Nantes(LS2N) 2 Chemin de La Houssini?ereNantesFrance Centre Rene Gauducheau ICO Institut de Cancerologie de L'Ouest BD Professeur Jacques MonodSaint-HerblainFrance Brethen Center for Surgical Advancement in Robotics and Minimally Invasive Surgery Miami Valley HospitalOne Wyoming StreetDaytonOHUSA Department of Computer Science IMT AtlantiqueTechnopole Brest-IroiseBrestFrance Laboratoire des Sciences et Techniques de L'information de La Communication et de La Connaissance(Lab-STICC) Technopole Brest-IroiseBrestFrance Future Industries Institute STEMUniversity of South AustraliaMawson Lakes BlvdMawson LakesAustralia

Objective:In robot-assisted minimally invasive surgery,proper port positioning ensures that surgical tools have adequate access to the surgical site and avoids mid-surgery collisions of robotic *** date,several guidelines have been proposed for more accurate port ***,challenges remain due to variations in patient morphology,anatomy,and,in particular,organ displacement due to insuf-flation in certain laparoscopic *** objective of this study was to design and develop a de-cision aid for optimal port placement in robot-assisted hysterectomy that accounts for patient variability and organ displacement due to ***:Three components were constructed:a robot model,a patient-specific model,and an opti-mization *** three components were integrated,and the system was verified using four different patients who underwent robotic *** verified,two expert surgeons were asked to evaluate the decision aid for face and construct validity.A usability test was conducted using a torso phantom with target organs located in three different *** expert surgeons performed a simulated hysterectomy task with and without the decision aid to evaluate performance and ***:The optimization algorithm was sensitive to individual differences in anatomy in the four *** surgeons successfully established face and construct *** test results showed a 28%-40% reduction in time to task completion with the optimized ports compared to expert-determined port locations without using the decision ***:The decision aid,based on an individualized patient-specific model,robot model,and optimization algorithm,was shown to be effective at addressing the challenges of displaced organs due to insufflation in robot-assisted *** face and construct validity of the decision aid was established by expert surgeons,while efficiency gains in task performance were demonstrated experim

关键词： Optimization Planning tool Patient model Robotic hysterectomy

Deep Learning for Brain Age Estimation: A Systematic Review

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Tanveer, M. Ganaie, M.A. Beheshti, Iman Goel, Tripti Ahmad, Nehal Lai, Kuan-Ting Huang, Kaizhu Zhang, Yu-Dong Ser, Javier Del Lin, Chin-Teng Department of Mathematics Indian Institute of Technology Indore Simrol Indore453552 India Department of Robotics University of Michigan Ann ArborMI48109 United States Department of Human Anatomy and Cell Science Rady Faculty of Health Sciences Max Rady College of Medicine University of Manitoba WinnipegMB Canada Biomedical Imaging Lab National Institute of Technology Assam Silchar788010 India Department of Electrical Engineering and Computer Science National Taipei University of Technology Taipei Taiwan Department of Electronic Engineering National Taipei University of Technology Taipei Taiwan Data Science Research Center Duke Kunshan University China School of Computing and Mathematical Sciences University of Leicester United Kingdom Derio48160 Spain Bilbao48013 Spain School of Computer Science Faculty of Engineering and Information Technology University of Technology Sydney Sydney Australia

Over the years, Machine Learning models have been successfully employed on neuroimaging data for accurately predicting brain age. Deviations from the healthy brain aging pattern are associated to the accelerated brain aging and brain abnormalities. Hence, efficient and accurate diagnosis techniques are required for eliciting accurate brain age estimations. Several contributions have been reported in the past for this purpose, resorting to different data-driven modeling methods. Recently, deep neural networks (also referred to as deep learning) have become prevalent in manifold neuroimaging studies, including brain age estimation. In this review we offer a comprehensive analysis of the literature related to the adoption of deep learning for brain age estimation with neuroimaging data. We detail and analyze different deep learning architectures used for this application, pausing at research works published to date quantitatively exploring their application. We also examine different brain age estimation frameworks, comparatively exposing their advantages and weaknesses. Finally, the review concludes with an outlook towards future directions that should be followed by prospective studies. The ultimate goal of this paper is to establish a common and informed reference for newcomers and experienced researchers willing to approach brain age estimation by using deep learning models. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

Development of Microcontroller-Based Manipulator Arm: A Trilemma Problem-Solving Framework for robotics and STEM Education in Nigerian Schools

学校读者我要写书评

暂无评论

Development of Microcontroller-Based Manipulator Arm: A Tril...

Technologies Applied to Electronics Teaching (TAEE)

作者： Mbadiwe S. Benyeogor Tobore L. Igbigbi Olusegun I. Lawal Udoh T. Akpan Andrew O. Benyeogor Nnaemeka M. Mbachu Kosisochukwu P. Nnoli Muhammad S. Aliero Adeboye Olatunbosun Institute of Physics University of Münster Münster Germany Department of Public Utilities City of Cleveland Ohio State USA Advanced Aerospace Engines Lab. Nat. Space Research & Dev. Agency Oka Akoko Ondo State Nigeria Dept. Mechatronics Engineering Lagos State Univ. of Sc. & Tech. Ikorodu Lagos State Nigeria CTE Computer Science & Robotics International Leadership of Texas Aggieland Texas USA Dept. Comp. Sc. & Electrical Engineering Constructor University Bremen Germany ICT Department Kebbi State Univ. of Sc. & Tech Aliero Nigeria Dept. Electrical & Electronics Engineering Ajayi Crowther University Oyo Town Oyo State Nigeria

ISBN: (数字)9798350348675

ISBN: (纸本)9798350348682

Advances in microprocessor technology and software engineering have resulted in the development of sophisticated robots that are used in modern society as assistive automata for production, security, and farming, among other things. To sustain the development of robots, robotics education should be included in school curricula (i.e., teaching and learning process). However, schools in many developing nations, such as Nigeria, are unable to adapt to this trend due to personnel, technological, infrastructural, and fiscal limitations. To address this problem, a low-cost robotic manipulator arm with real-time control algorithms and a human-robot interface that allows it to be controlled by a microcomputer is developed. This includes its functional model, geometry of link movement, mechanical design, control circuitries, and a Teraterm-based human-robot interface (HRI). Furthermore, an encryption method was developed that maps selected control keys to actuation functions in manipulator chains. We also explored how this robotic manipulator may be used as a teaching tool, particularly for teaching three major industrial technologies: machine-making, electronics, and computing. Our manipulator arm has undergone both unit and system tests and has been used for classroom teaching. Results of its applicability assessment show that our system could aid the teaching of robotics and STEM subjects in schools, as a way to solve the trilemma of harmonizing the concept of machines, electronic control, and computation in multidisciplinary domains.

关键词： Service robots Educational robots Education Manipulators Real-time systems Production facilities Security

Optimizing gait libraries via a coverage metric

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Bittner, Brian Revzen, Shai Robotics Institute University of Michigan Ann Arbor United States Johns Hopkins University Applied Physics Lab LaurelMD United States Electrical Engineering and Computer Science Department Ecology and Evolutionary Biology Department University of Michigan Ann Arbor United States

Many robots move through the world by composing locomotion primitives like steps and turns. To do so well, robots need not have primitives that make intuitive sense to humans. This becomes of paramount importance when robots are damaged and no longer move as designed. Here we propose a goal function we call "coverage", that represents the usefulness of a library of locomotion primitives in a manner agnostic to the particulars of the primitives themselves. We demonstrate the ability to optimize coverage on both simulated and physical robots, and show that coverage can be rapidly recovered after injury. This suggests that by optimizing for coverage, robots can sustain their ability to navigate through the world even in the face of significant mechanical failures. The benefits of this approach are enhanced by sample-efficient, data-driven approaches to system identification that can rapidly inform the optimization of primitives. We found that the number of degrees of freedom improved the rate of recovery of our simulated robots, a rare result in the fields of gait optimization and reinforcement learning. We showed that a robot with limbs made of tree branches (for which no CAD model or first principles model was available) is able to quickly find an effective high-coverage library of motion primitives. The optimized primitives are entirely non-obvious to a human observer, and thus are unlikely to be attainable through manual tuning. © 2021, CC BY.

关键词： Reinforcement learning

Automatic Context-Driven Inference of Engagement in HMI: A Survey

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Salam, Hanan Celiktutan, Oya Gunes, Hatice Chetouani, Mohamed SMART Lab New York University Abu Dhabi United Arab Emirates Department of Engineering King’s College LondonWC2R 2LS United Kingdom Department of Computer Science and Technology University of Cambridge CB3 0FD United Kingdom Institute of Intelligent Systems and Robotics CNRS UMR7222 Sorbonne University Paris France

An integral part of seamless human-human communication is engagement, the process by which two or more participants establish, maintain, and end their perceived connection. Therefore, to develop successful human-centered human-machine interaction applications, automatic engagement inference is one of the tasks required to achieve engaging interactions between humans and machines, and to make machines attuned to their users, hence enhancing user satisfaction and technology acceptance. Several factors contribute to engagement state inference, which include the interaction context and interactants’ behaviours and identity. Indeed, engagement is a multi-faceted and multi-modal construct that requires high accuracy in the analysis and interpretation of contextual, verbal and non-verbal cues. Thus, the development of an automated and intelligent system that accomplishes this task has been proven to be challenging so far. This paper presents a comprehensive survey on previous work in engagement inference for human-machine interaction, entailing interdisciplinary definition, engagement components and factors, publicly available datasets, ground truth assessment, and most commonly used features and methods, serving as a guide for the development of future human-machine interaction interfaces with reliable context-aware engagement inference capability. An in-depth review across embodied and disembodied interaction modes, and an emphasis on the interaction context of which engagement perception modules are integrated sets apart the presented survey from existing surveys. Copyright © 2022, The Authors. All rights reserved.

关键词： Surveys

Cascaded Constrained Optimization For Cheetah-Inspired Galloping Robot Leg Mechanism ⁎

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2020年第2期53卷 9232-9237页

作者： Artem A. Egorov Ivan I. Borisov Sergey A. Kolyubin Stefano Stramigioli Biomechatronics and Energy-Efficient Robotics Lab ITMO University St. Petersburg Russia Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis Russia Department of Electrical Engineering Mathematics and Computer Science University of Twente The Netherlands

The paper describes one of the key steps in creating a bio-inspired galloping robot, namely parametric optimization of a multi-link leg mechanism. We introduce the cascaded constrained optimization procedure for finding optimal values for geometric parameters of a femur, knee, and foot segments for given design constraints and various gait specifications. The presented approach is computationally efficient and guarantees convergence to the unique solution. Steps on free parameters, constraints, and cost function selection are discussed. The efficiency of the proposed procedure is illustrated via a series of simulations. The proposed approach can also be implemented for the design of wearable robots like upper and lower-limb exoskeletons and rehabilitation systems that should follow sometimes sophisticated human-like trajectories.

关键词： Mobile robots robot design legged robots parametric optimization

M2FN: Multi-step modality fusion for advertisement image assessment

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Park, Kyung-Wha Ha, Jung-Woo Lee, JungHoon Kwon, Sunyoung Kim, Kyung-Min Zhang, Byoung-Tak Interdisciplinary Program in Neuroscience Seoul National University Korea Republic of NAVER AI LAB NAVER CLOVA Statistics and Actuarial Science Soongsil University Korea Republic of School of Biomedical Convergence Engineering Pusan National University Korea Republic of Department of Computer Science and Engineering Seoul National University Korea Republic of Surromind Robotics

Assessing advertisements, specifically on the basis of user preferences and ad quality, is crucial to the marketing industry. Although recent studies have attempted to use deep neural networks for this purpose, these studies have not utilized image-related auxiliary attributes, which include embedded text frequently found in ad images. We, therefore, investigated the influence of these attributes on ad image preferences. First, we analyzed large-scale real-world ad log data and, based on our findings, proposed a novel multi-step modality fusion network (M2FN) that determines advertising images likely to appeal to user preferences. Our method utilizes auxiliary attributes through multiple steps in the network, which include conditional batch normalization-based low-level fusion and attention-based high-level fusion. We verified M2FN on the AVA dataset, which is widely used for aesthetic image assessment, and then demonstrated that M2FN can achieve state-of-the-art performance in preference prediction using a real-world ad dataset with rich auxiliary attributes. © 2021, CC BY-NC-SA.

关键词： Marketing

Look and Listen: A Multi-modality Late Fusion Approach to Scene Classification for Autonomous Machines

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Bird, Jordan J. Faria, Diego R. Premebida, Cristiano Ekárt, Anikó Vogiatzis, George School of Engineering and Applied Science Aston University Birmingham United Kingdom Lab Institute of Systems and Robotics Department of Electrical and Computer Engineering University of Coimbra Coimbra Portugal

The novelty of this study consists in a multi-modality approach to scene classification, where image and audio complement each other in a process of deep late fusion. The approach is demonstrated on a difficult classification problem, consisting of two synchronised and balanced datasets of 16,000 data objects, encompassing 4.4 hours of video of 8 environments with varying degrees of similarity. We first extract video frames and accompanying audio at one second intervals. The image and the audio datasets are first classified independently, using a fine-tuned VGG16 and an evolutionary optimised deep neural network, with accuracies of 89.27% and 93.72%, respectively. This is followed by late fusion of the two neural networks to enable a higher order function, leading to accuracy of 96.81% in this multi-modality classifier with synchronised video frames and audio clips. The tertiary neural network implemented for late fusion outperforms classical state-of-the-art classifiers by around 3% when the two primary networks are considered as feature generators. We show that situations where a single-modality may be confused by anomalous data points are now corrected through an emerging higher order integration. Prominent examples include a water feature in a city misclassified as a river by the audio classifier alone and a densely crowded street misclassified as a forest by the image classifier alone. Both are examples which are correctly classified by our multi-modality approach. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks