检索结果-内蒙古大学图书馆

Social Presence in Evaluations for a Humanoid Robot and Its Effect on Children-Robot Relationship 23rd

学校读者我要写书评

暂无评论

Social Presence in Evaluations for a Humanoid Robot and Its ...

23rd International Conference on Human-Computer Interaction, HCII 2021

作者： Chen, Yi-Chen Gamborino, Edwinn Fu, Li-Chen Yueh, Hsiu-Ping Yeh, Su-Ling Department of Psychology National Taiwan University Taipei Taiwan Department of Electrical Engineering and Department of Computer Science and Information Engineering National Taiwan University Taipei Taiwan MOST Joint Research Center for AI Technology and All Vista Healthcare Taipei Taiwan Center for Artificial Intelligence and Advanced Robotics National Taiwan University Taipei Taiwan Department of Bio-Industry Communication and Development National Taiwan University Taipei Taiwan Graduate Institute of Brain and Mind Sciences National Taiwan University Taipei Taiwan

ISBN: (纸本)9783030786342

As children are at a critical stage in their lives in developing and practicing social skills, they tend to imagine objects as interactive agents. For example, even a toy dinosaur can be perceived as affable and more as a social entity, namely, with a strong social presence (SP). This study investigated whether perceived SP changes (measured using the SP questionnaire) as children interacted with a robot. Furthermore, we investigated how SP modulated children-robot relationships and children’s overall attitudes towards robots. Children aged 6–12 interacted with a companion robot, RoBoHoN, for short intervals. Attitude evaluations were completed at three-time points: prior-, mid-, and post-interaction. SP and rapport with RoBoHoN were measured and compared mid-and post-interaction, while attitudes towards the robot were tested prior- and post-interaction. The results showed a stronger intention to use robots before interaction correlated with higher SP scores with RoBoHoN. As SP level was stable across mid- and post-interaction, we analyzed SP as a between-groups factor to compare attitude evaluations among children who rated RoBoHoN with higher versus lower SP scores. The high SP group found RoBoHoN to be more likable and playing with it as more enjoyable, but the effect on rapport level was marginal. The Implicit Association Task revealed no bias towards robots among children in both groups. This study shows SP’s positive effect on children-robot interaction and highlights the importance of SP in designing social companion robots for children. © 2021, Springer Nature Switzerland AG.

关键词： Association reactions

Realtime Motion Generation with Active Perception Using Attention Mechanism for Cooking Robot

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Saito, Namiko Hiramoto, Mayu Kubo, Ayuna Suzuki, Kanata Ito, Hiroshi Sugano, Shigeki Ogata, Tetsuya Department of Modern Mechanical Engineering Waseda University Tokyo Japan The School of Informatics The University of Edinburgh Edinburgh United Kingdom The Alan Turing Institute London United Kingdom The Artificial Intelligence Laboratories Fujitsu Limited Kanagawa Japan The Center for Technology Innovation - Controls and Robotics Research & Development Group Hitachi Ltd. Ibaraki Japan The Department of Intermedia Art and Science Waseda University Tokyo Japan The National Institute of Advanced Science and Technology Tokyo Japan

To support humans in their daily lives, robots are required to autonomously learn, adapt to objects and environments, and perform the appropriate actions. We tackled on the task of cooking scrambled eggs using real ingredients, in which the robot needs to perceive the states of the egg and adjust stirring movement in real time, while the egg is heated and the state changes continuously. In previous works, handling changing objects was found to be challenging because sensory information includes dynamical, both important or noisy information, and the modality which should be focused on changes every time, making it difficult to realize both perception and motion generation in real time. We propose a predictive recurrent neural network with an attention mechanism that can weigh the sensor input, distinguishing how important and reliable each modality is, that realize quick and efficient perception and motion generation. The model is trained with learning from the demonstration, and allows the robot to acquire "human-like" skills. We validated the proposed technique using the robot, Dry-AIREC, and with our learning model, it could perform cooking eggs with unknown ingredients. The robot could change the method of stirring and direction depending on the status of the egg, as in the beginning it stirs in the whole pot, then subsequently, after the egg started being heated, it starts flipping and splitting motion targeting specific areas, although we did not explicitly indicate them. See our accompanying video here: https://***/PHHMDUO0mHU Copyright © 2023, The Authors. All rights reserved.

关键词： Robots

Learning-Based Keypoint Registration for Fetoscopic Mosaicking

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Casella, Alessandro Bano, Sophia Vasconcelos, Francisco David, Anna L. Paladini, Dario Deprest, Jan De Momi, Elena Mattos, Leonardo S. Moccia, Sara Stoyanov, Danail Department of Computer Science University College London United Kingdom Department of Advanced Robotics Istituto Italiano di Tecnologia Italy Department of Electronics Information and Bioengineering Politecnico di Milano Italy Fetal Medicine Unit Elizabeth Garrett Anderson Wing University College London Hospital United Kingdom EGA Institute for Women’s Health Faculty of Population Health Sciences University College London United Kingdom Department of Development and Regeneration University Hospital Leuven Belgium Department of Fetal and Perinatal Medicine Istituto "Giannina Gaslini" Italy The BioRobotics Institute Department of Excellence in Robotics and AI Scuola Superiore Sant’Anna Italy

In Twin-to-Twin Transfusion Syndrome (TTTS), abnormal vascular anastomoses in the monochorionic placenta can produce uneven blood flow between the two fetuses. In the current practice, TTTS is treated surgically by closing abnormal anastomoses using laser ablation. This surgery is minimally invasive and relies on fetoscopy. Limited field of view makes anastomosis identification a challenging task for the surgeon. To tackle this challenge, we propose a learning-based framework for in-vivo fetoscopy frame registration for field-of-view expansion. The novelties of this framework relies on a learning-based keypoint proposal network and an encoding strategy to filter (i) irrelevant keypoints based on fetoscopic image segmentation and (ii) inconsistent homographies. We validate of our framework on a dataset of 6 intraoperative sequences from 6 TTTS surgeries from 6 different women against the most recent state of the art algorithm, which relies on the segmentation of placenta vessels. The proposed framework achieves higher performance compared to the state of the art, paving the way for robust mosaicking to provide surgeons with context awareness during TTTS surgery. Copyright © 2022, The Authors. All rights reserved.

关键词： Image segmentation

Novel Methods Inspired by Reinforcement Learning Actor-Critic Mechanism for Eye-in-Hand Calibration in robotics

学校读者我要写书评

暂无评论

Novel Methods Inspired by Reinforcement Learning Actor-Criti...

IEEE International Conference on development and Learning, ICDL

作者： Chenxing Li Yinlong Liu Yingbai Hu Fabian Schreier Jan Seyler Shahram Eivazi Department of Computer Science University of Tübingen Tübingen Germany Advanced Development Analytics and Control Festo SE and Co. KG Esslingen Germany State Key Laboratory of Internet of Things for Smart City (SKL-IOTSC) University of Macau Macau China HUA Cloud Intelligent Healthcare Co. Ltd. Ningbo China Multi-Scale Medical Robotics Centre and the Chow Yuk Ho Technology Centre for Innovative Medicine The Chinese University of Hong Kong Hong Kong China

Eye-in-hand camera calibration is an essential step in robotic vision systems. Traditional methods perform the calibration via geometry computation methods where the calibration points are acquired by moving the robot arm while capturing images of a static object (often a checkerboard) of known geometry. Our work aims to explore deep reinforcement learning (DRL) techniques for solving common calibration optimization problems. Inspired by the actor-critic mechanism of DRL, we propose a novel approach to perform eye-in-hand camera calibration on the robot arm. Numerical and real-world experiments prove the feasibility of the proposed method as such here we show the potential of the reinforcement learning method to solve the camera calibration problem.

关键词：

Detection and Location Estimation of Object in Unmanned Aerial Vehicle using Single Camera and GPS

学校读者我要写书评

暂无评论

Detection and Location Estimation of Object in Unmanned Aeri...

Power, Control and Computing Technologies (ICPC2T), Conference on

作者： Snehil Sanyal Shashank Bhushan K Sivayazi Department of Mechanical Engineering Defence Institute of Advanced Technology Pune India Center for Artificial Intelligence & Robotics (CAIR) Defence Research & Development Organization (DRDO) Bengaluru India

ISBN: (数字)9781728149974

ISBN: (纸本)9781728149981

It is important for an Unmanned Aerial Vehicle (UAV) to detect any object in its view. This enables the UAV to locate the object with respect to itself and is required for locking and tracking the object. Object detection and location estimation makes the UAV capable of manipulating the environment as well as to follow the target. In the present work, object detection has been carried out using You Only Look Once (YOLO) to detect the object in the image stream of the Robot Operating System (ROS) bag file. The GPS information of the UAV is used to further calculate the GPS coordinates of the object. The images are acquired using a single monocular camera.

关键词： Cameras Object detection Global Positioning System Drones Three-dimensional displays Estimation

Placental Vessel Segmentation and Registration in Fetoscopy: Literature Review and MICCAI FetReg2021 Challenge Findings

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Bano, Sophia Casella, Alessandro Vasconcelos, Francisco Qayyum, Abdul Benzinou, Abdesslam Mazher, Moona Meriaudeau, Fabrice Lena, Chiara Cintorrino, Ilaria Anita De Paolis, Gaia Romana Biagioli, Jessica Grechishnikova, Daria Jiao, Jing Bai, Bizhe Qiao, Yanyan Bhattarai, Binod Gaire, Rebati Raman Subedi, Ronast Vazquez, Eduard Plotka, Szymon Lisowska, Aneta Sitek, Arkadiusz Attilakos, George Wimalasundera, Ruwan David, Anna L. Paladini, Dario Deprest, Jan De Momi, Elena Mattos, Leonardo S. Moccia, Sara Stoyanov, Danail Department of Computer Science University College London United Kingdom Department of Advanced Robotics Istituto Italiano di Tecnologia Italy Department of Electronics Information and Bioengineering Politecnico di Milano Italy The BioRobotics Institute Department of Excellence in Robotics and AI Scuola Superiore Sant'Anna Italy Fetal Medicine Unit Elizabeth Garrett Anderson Wing University College London Hospital United Kingdom EGA Institute for Women's Health Faculty of Population Health Sciences University College London United Kingdom Department of Development and Regeneration University Hospital Leuven Belgium Department of Fetal and Perinatal Medicine Istituto Giannina Gaslini Italy ENIB UMR CNRS 6285 LabSTICC 29238 France Department of Computer Engineering and Mathematics University Rovira i Virgili Spain ImViA Laboratory University of Bourgogne Franche-Comté France Physics Department Lomonosov Moscow State University Russia Fudan University China Medical Computer Vision and Robotics Group Department of Mathematical and Computational Sciences University of Toronto Canada Co. Ltd China NepAL Applied Mathematics and Informatics Institute for Research Nepal Redev Technology United Kingdom Sano Center for Computational Medicine Poland Quantitative Healthcare Analysis Group Informatics Institute University of Amsterdam Amsterdam Netherlands Center for Advanced Medical Computing and Simulation Massachusetts General Hospital Harvard Medical School BostonMA United States

Fetoscopy laser photocoagulation is a widely adopted procedure for treating Twin-to-Twin Transfusion Syndrome (TTTS). The procedure involves photocoagulation pathological anastomoses to restore a physiological blood exchange among twins. The procedure is particularly challenging, from the surgeon's side, due to the limited field of view, poor manoeuvrability of the fetoscope, poor visibility due to amniotic fluid turbidity, and variability in illumination. These challenges may lead to increased surgery time and incomplete ablation of pathological anastomoses, resulting in persistent TTTS. Computer-assisted intervention (CAI) can provide TTTS surgeons with decision support and context awareness by identifying key structures in the scene and expanding the fetoscopic field of view through video mosaicking. Research in this domain has been hampered by the lack of high-quality data to design, develop and test CAI algorithms. Through the Fetoscopic Placental Vessel Segmentation and Registration (FetReg2021) challenge, which was organized as part of the MICCAI2021 Endoscopic Vision (EndoVis) challenge, we released the first large-scale multi-center TTTS dataset for the development of generalized and robust semantic segmentation and video mosaicking algorithms with a focus on creating drift-free mosaics from long duration fetoscopy videos. For this challenge, we released a dataset of 2060 images, pixel-annotated for vessels, tool, fetus and background classes, from 18 in-vivo TTTS fetoscopy procedures and 18 short video clips of an average length of 411 frames for developing placental scene segmentation and frame registration for mosaicking techniques. Seven teams participated in this challenge and their model performance was assessed on an unseen test dataset of 658 pixel-annotated images from 6 fetoscopic procedures and 6 short clips. The challenge provided an opportunity for creating generalized solutions for fetoscopic scene understanding and mosaicking. In this paper,

关键词： Pixels

Deep Learning-Based Automatic Multi-Level Airway Collapse Monitoring on Obstructive Sleep Apnea Patients

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hsu, Ying-Chieh Liu, Stanley Yung-Chuan Huang, Chao-Jung Wu, Chi-Wei Cheng, Ren-Kai Hsu, Jane Yung-Jen Huang, Shang-Ran Cheng, Yuan-Ren Hsu, Fu-Shun Department of Biomedical Engineering National Taiwan University Taipei Taiwan Department of Otolaryngology Head and Neck Surgery Taipei Tzu Chi Hospital Buddhist Tzu Chi Medical Foundation Taipei Taiwan Tzu Chi University School of Medicine Hualien Taiwan Department of Oral & Maxillofacial Surgery Nova Southeastern University College of Dental Medicine College of Allopathic Medicine Florida United States All Vista Healthcare Center Center for AI and Advanced Robotics National Taiwan University Taipei Taiwan Department of Computer Science and Information Engineering National Taiwan University Taipei Taiwan Department of Artificial Intelligence Chang Gung University College of Intelligent Computing Taoyuan Taiwan Heroic Faith Medical Science Co. Ltd. New Taipei Taiwan School of Medicine Chung Shan Medical University Taichung Taiwan Department of Internal Medicine Chung Shan Medical University Taichung Taiwan Hospital Development Affairs Office Chung Shan Medical University Hospital Taichung Taiwan

This study investigated the use of deep learning to identify multi-level upper airway collapses in obstructive sleep apnea (OSA) patients based on snoring sounds. We fi-ne-tuned ResNet-50 and Audio Spectrogram Transformer (AST) models using snoring recordings from 37 subjects undergoing drug-induced sleep endoscopy (DISE) between 2020 and 2021. Snoring sounds were labeled according to the VOTE (Velum, Orophar-ynx, Tongue Base, Epiglottis) classification, resulting in 259 V, 403 O, 77 T, 13 E, 1016 VO, 46 VT, 140 OT, 39 OE, 30 VOT, and 3150 non-snoring (N) 0.5-second clips. The models were trained for two multi-label classification tasks: identifying obstructions at V, O, T, and E levels, and identifying retropalatal (RP) and retroglossal (RG) obstruc-tions. Results showed AST slightly outperformed ResNet-50, demonstrating good abil-ity to identify V (F1-score: 0.71, MCC: 0.61, AUC: 0.89), O (F1-score: 0.80, MCC: 0.72, AUC: 0.94), and RP obstructions (F1-score: 0.86, MCC: 0.77, AUC: 0.97). However, both models struggled with T, E, and RG classifications due to limited data. Retrospective analysis of a full-night recording showed the potential to profile airway obstruction dynamics. We expect this information, combined with polysomnography and other clinical parameters, can aid clinical triage and treatment planning for OSA patients. © 2024, CC BY-SA.

关键词： Endoscopy

Redesigning dispenser component to enhance performance crop-dusting agriculture drones

学校读者我要写书评

暂无评论

Materials Today: Proceedings 2023年 81卷 166-172页

作者： Rajvin Subramaniam Sami Salama Hussen Hajjaj Kisheen Rao Gsangaya Mohamed Thariq Hameed Sultan Mohd Fazly Mail Lee Seng Hua Department of Mechanical Engineering Universiti Tenaga Nasional Jalan IKRAM-UNITEN 43000 Kajang Selangor Darul Ehsan Malaysia Centre for Advanced Mechatronics and Robotics (CaMaRo) Universiti Tenaga Nasional Jalan IKRAM-UNITEN 43000 Kajang Selangor Darul Ehsan Malaysia Institute of Informatics and Computing in Energy (IICE) Universiti Tenaga Nasional Jalan IKRAM-UNITEN 43000 Kajang Selangor Darul Ehsan Malaysia Laboratory of Biocomposite Technology Institute of Tropical Forestry and Forest Products (INTROP) Universiti Putra Malaysia 43400 UPM Serdang Selangor Darul Ehsan Malaysia Department of Aerospace Engineering Faculty of Engineering Universiti Putra Malaysia 43400 UPM Serdang Selangor Darul Ehsan Malaysia Aerospace Malaysia Innovation Centre (944741-A) Prime Minister’s Department MIGHT Partnership Hub Jalan Impact 63000 Cyberjaya Selangor Darul Ehsan Malaysia Farm Mechanization Program Engineering Research Centre Malaysian Agricultural Research and Development Institute (MARDI) 43400 Serdang Selangor Darul Ehsan Malaysia Laboratory of Biopolymer and Derivatives Institute of Tropical Forestry and Forest Products (INTROP) Universiti Putra Malaysia 43400 UPM Serdang Selangor Darul Ehsan Malaysia

Agricultural drones are Unmanned Aerial Vehicles (UAVs) applied to farming in order to help increase crop production and improve farm efficiency. Crop-dusting drones are able to spray powdered fertilizer, pesticide, or insecticide on crops from the air, resulting in reduced costs and increased efficiency compared to traditional methods. The objective of this research work was to improve and enhance the performance of the crop-dusting process using agricultural drones. This research paper details the development of an improved storage container design and stabilized release mechanism for crop-dusting. To stabilise the release of payload when the drone is moving or swaying in the air, a gimbal mechanism was added to the release mechanism in which weights were used to produce constant downward force which balances the mechanism. Tests conducted on the prototype system showed that it performs as required. The stabilization tests show an improvement in accuracy of granule spread when using the stabilized release mechanism developed in this research work. As such, the wastage of fertilizers and pesticides can be reduced. The prototype system was also found to much more capable at carrying heavier loads for a longer period of time compared to current designs. Thus, using the prototype system developed for this research work, the size of storage container as well as the weight of fertilizer or pesticide granule payloads can be increased.

关键词：

Autonomous fertilizer mixer through the Internet of Things (IoT)

学校读者我要写书评

暂无评论

Materials Today: Proceedings 2023年 81卷 295-301页

作者： Abdul Hadi Ishak Sami Salama Hussen Hajjaj Kisheen Rao Gsangaya Mohamed Thariq Hameed Sultan Mohd Fazly Mail Lee Seng Hua Department of Mechanical Engineering Universiti Tenaga Nasional Jalan IKRAM-UNITEN 43000 Kajang Selangor Darul Ehsan Malaysia Centre for Advanced Mechatronics and Robotics (CaMaRo) Universiti Tenaga Nasional Jalan IKRAM-UNITEN 43000 Kajang Selangor Darul Ehsan Malaysia Institute of Informatics and Computing in Energy (IICE) Universiti Tenaga Nasional Jalan IKRAM-UNITEN 43000 Kajang Selangor Darul Ehsan Malaysia Laboratory of Biocomposite Technology Institute of Tropical Forestry and Forest Products (INTROP) Universiti Putra Malaysia 43400 UPM Serdang Selangor Darul Ehsan Malaysia Department of Aerospace Engineering Faculty of Engineering Universiti Putra Malaysia 43400 UPM Serdang Selangor Darul Ehsan Malaysia Aerospace Malaysia Innovation Centre (944741-A) Prime Minister’s Department MIGHT Partnership Hub Jalan Impact 63000 Cyberjaya Selangor Darul Ehsan Malaysia Farm Mechanization Program Engineering Research Centre Malaysian Agricultural Research and Development Institute (MARDI) 43400 Serdang Selangor Darul Ehsan Malaysia Laboratory of Biopolymer and Derivatives Institute of Tropical Forestry and Forest Products (INTROP) Universiti Putra Malaysia 43400 UPM Serdang Selangor Darul Ehsan Malaysia

Organic fertilizers have been used since the dawn of mankind to improve soil fertility and promote crop growth. However, the process of preparing organic fertilizers for use in agricultural activities is a labour-intensive and time-consuming procedure. Thus, in order to reduce labour costs and improve the efficiency of organic fertilizer preparation, automated organic fertilizer mixers were developed. For this research work, an improved organic fertilizer mixer based on the Internet of Things (IoT) technology capable of monitoring the status of fertilizer production remotely and providing updates and alerts to workers was developed. The aim of this work was to further reduce labour workload and costs, thus increasing efficiency of the organic fertilizer mixing process. In order to accommodate the IoT monitoring system, several modifications and design changes were carried out on the prototype of an automated organic fertilizer mixer. Tests conducted on the prototype unit showed that it performs as required. The IoT monitoring system successfully captures and uploads information on the weight of agricultural waste mixture in the storage drum to the IoT platform. This information can then be used to alert workers on when to add more agricultural waste material to the mixture or remove the processed organic fertilizer. Furthermore, an overall operational cost comparison of different organic fertilizer production methods showed that the automated organic fertilizer prototype provides operational cost savings of over 5 times when compared to current automated systems. Future work includes further automation to the agricultural waste filling and organic fertilizer removal process.

关键词：