检索结果-内蒙古大学图书馆

Magnetic Continuum Robot for Intelligent Manipulation in Medical Applications

学校读者我要写书评

暂无评论

SmartBot

SmartBot 2025年

作者： Yuanbiao Ma Xuanyu An Qijun Yang Mingxue Cai Zhiqiang Tang Jinke Chang Veronica Iacovacci Tiantian Xu Li Zhang Qianqian Wang Jiangsu Key Laboratory for Design and Manufacture of Micro-Nano Biomedical Instruments School of Mechanical Engineering Southeast University Nanjing China Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Department of Mechanical Engineering National University of Singapore Queenstown Singapore Department of Engineering Science University of Oxford Oxford UK Department of Surgical Biotechnology Division of Surgery & Interventional Science Centre for Biomaterials in Surgical Reconstruction and Regeneration University College London London UK BioRobotics Institute Scuola Superiore Sant’Anna Pisa Italy Department of Excellence in Robotics & AI Scuola Superiore Sant’Anna Pisa Italy Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Hong Kong China Chow Yuk Ho Technology Center for Innovative Medicine The Chinese University of Hong Kong Hong Kong China Multi-Scale Medical Robotics Center Hong Kong Science Park Hong Kong China

Magnetic continuum robots (MCRs) have garnered substantial attention as a new class of flexible robotic systems capable of navigating complex and confined spaces with remarkable dexterity. By combining continuous, deformable structures with remotely applied magnetic fields, MCRs achieve contactless, remote manipulation, making them well-suited for medical applications. This review introduces recent advances in MCR research, focusing on design principles, structural configurations, and control strategies. Various MCR designs and structures, including those integrated with permanent magnets, magnetic matter, ferromagnetic sphere, and micro coil, are discussed. Furthermore, different magnetic actuation platforms are introduced, and the level of MCR automation is classified based on control strategies. Key intelligent manipulation capabilities of MCRs, including navigation, delivery, printing, grasping, imaging, and sensing are explored. Finally, future development priorities and directions are identified to provide insights for advancing intelligent robotic systems.

关键词： intelligent manipulation magnetic actuation magnetic continuum robot medical application

Spherical interpolated convolutional network with distance-feature density for 3D semantic segmentation of point clouds

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wang, Guangming Yang, Yehui Zhang, Huixin Liu, Zhe Wang, Hesheng Department of Automation Insititue of Medical Robotics Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Jiao Tong University Shanghai200240 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology China Department of Computer Science and Technology University of Cambridge United Kingdom

The semantic segmentation of point clouds is an important part of the environment perception for robots. However, it is difficult to directly adopt the traditional 3D convolution kernel to extract features from raw 3D point clouds because of the unstructured property of point clouds. In this paper, a spherical interpolated convolution operator is proposed to replace the traditional grid-shaped 3D convolution operator. This newly proposed feature extraction operator improves the accuracy of the network and reduces the parameters of the network. In addition, this paper analyzes the defect of point cloud interpolation methods based on the distance as the interpolation weight and proposes the self-learned distance-feature density by combining the distance and the feature correlation. The proposed method makes the feature extraction of spherical interpolated convolution network more rational and effective. The effectiveness of the proposed network is demonstrated on the 3D semantic segmentation task of point clouds. Experiments show that the proposed method achieves good performance on the ScanNet dataset and Paris-Lille-3D dataset. Copyright © 2020, The Authors. All rights reserved.

关键词： Semantic Segmentation

Dual Null-Space Based Controller Design with Signal Compensation for Formation with Conflicted Tasks

学校读者我要写书评

暂无评论

Dual Null-Space Based Controller Design with Signal Compensa...

Control technology and Applications (CCTA),

作者： Yen Cheng Huang Jui-Ting Shen Ming-Li Chiang Yu-Wen Chen Tuan Lian Chua Li-Chen Fu Department of Electrical Engineering National Taiwan University Graduate Institute of Automation Technology National Taipei University of Technology Department of Electrical Engineering and Center for Artificial Intelligence and Advanced Robotics National Taiwan University

In this paper, we consider the multi-agent formation problem with trajectory tracking and obstacle avoidance. Out of all the controllers proposed to solve the multi-task problem, null-space based controller stood out for its ability of task priority appointment, priority interchangeability, and the simplicity in Lyapunov stability analysis. However, the advantages above are mainly based on the assumption that the considered tasks are mutually non-conflicted, which is not always the case. We propose a null-space based controller that takes the lower-rank task's control signal as the higher-rank controller's input, and redesign higher-rank controller so that the eliminated control signal is partially compensated and the tasks' aggregated error is decreased. We also design a dual null-space controller in order to apply virtual leader for path planning, which enables obstacle avoidance and tracking while the target tracking point is in an inadmissible condition. We verify the performance of formation and tracking control with and without dynamic obstacles, and show the decrease in aggregated error compared with the traditional null-space controller.

关键词： Task analysis Collision avoidance Target tracking Jacobian matrices Artificial intelligence Robots Lyapunov methods

Real-time Obstacle Avoidance using Supervised Recurrent Neural Network with Automatic Data Collection and Labeling

学校读者我要写书评

暂无评论

Real-time Obstacle Avoidance using Supervised Recurrent Neur...

IEEE International Conference on Systems, Man and Cybernetics

作者： Shao-Hung Chan Xiaoyue Xu Ping-Tsang Wu Ming-Li Chiang Li-Chen Fu Department of Electrical Engineering National Taiwan University Taipei Taiwan Graduate Institute of Automation Technology National Taipei University of Technology Taipei Taiwan NTU Center for Artificial Intelligence Advanced Robotics Taipei Taiwan

The following topics are dealt with: learning (artificial intelligence); medical signal processing; neurophysiology; electroencephalography; mobile robots; feature extraction; brain-computer interfaces; neural nets; c... 详细信息

关键词： Collision avoidance Training Robot sensing systems Robot kinematics Path planning Labeling

Multi-Layer Environmental Affordance Map for Robust Indoor Localization, Event Detection and Social Friendly Navigation

学校读者我要写书评

暂无评论

Multi-Layer Environmental Affordance Map for Robust Indoor L...

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Ping-Tsang Wu Chee-An Yu Shao-Hung Chan Ming-Li Chiang Li-Chen Fu Department of Electrical Engineering National Taiwan University Taipei Taiwan Graduate Institute of Automation Technology National Taipei University of Technology Taipei Taiwan Director of NTU Center for Artificial Intelligence & Advanced Robotics Taipei Taiwan

In this paper, we propose a novel system architecture called multi-layer environmental affordance map for social and service companion robots. Based on this architecture, robots can organize the perception and inference information efficiently and generate social friendly navigation strategies. In other words, robots are able to strengthen their perception and inference abilities to interact with domestic environment and users under our efficient framework. The main feature of this architecture is that the relations between layers can be viewed as affordances to improve the accuracy and the robustness of the detection and inference. The results show that our architecture achieves robust indoor localization, scene localization, human event detection and socially friendly navigation in real time under limited computational resource.

关键词：

CholecTriplet2021: A benchmark challenge for surgical action triplet recognition

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Nwoye, Chinedu Innocent Alapatt, Deepak Yu, Tong Vardazaryan, Armine Xia, Fangfang Zhao, Zixuan Xia, Tong Jia, Fucang Yang, Yuxuan Wang, Hao Yu, Derong Zheng, Guoyan Duan, Xiaotian Getty, Neil Sanchez-Matilla, Ricardo Robu, Maria Zhang, Li Chen, Huabin Wang, Jiacheng Wang, Liansheng Zhang, Bokai Gerats, Beerend Raviteja, Sista Sathish, Rachana Tao, Rong Kondo, Satoshi Pang, Winnie Ren, Hongliang Abbing, Julian Ronald Sarhan, Mohammad Hasan Bodenstedt, Sebastian Bhasker, Nithya Oliveira, Bruno Torres, Helena R. Ling, Li Gaida, Finn Czempiel, Tobias Vilaça, João L. Morais, Pedro Fonseca, Jaime Egging, Ruby Mae Wijma, Inge Nicole Qian, Chen Bian, Guibin Li, Zhen Balasubramanian, Velmurugan Sheet, Debdoot Luengo, Imanol Zhu, Yuanbo Ding, Shuai Aschenbrenner, Jakob-Anton van der Kar, Nicolas Elini Xu, Mengya Islam, Mobarakol Seenivasan, Lalithkumar Jenke, Alexander Stoyanov, Danail Mutter, Didier Mascagni, Pietro Seeliger, Barbara Gonzalez, Cristians Padoy, Nicolas ICube University of Strasbourg CNRS France IHU Strasbourg France Department of Computer Science University of Chicago United States Lab for Medical Imaging and Digital Surgery Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China School of Management Hefei University of Technology Hefei China Institue of Medical Robotics Shanghai Jiao Tong University Shanghai China Argonne National Laboratory 9700 S Cass Ave LemontIL60439 United States Digital Surgery A Medtronic Company London United Kingdom Institute of Automation Chinese Academy of Sciences China Department of Computer Science School of Informatics Xiamen University Xiamen China Johnson & Johnson Meander Medical Centre Netherlands Indian Institute of Technology Kharagpur India Muroran Institute of Technology Japan Department of Biomedical Engineering National University of Singapore Singapore Department for Translational Surgical Oncology National Center for Tumor Diseases Partner Site Dresden Germany 2Ai School of Technology IPCA Barcelos Portugal School of Medicine University of Minho Braga Portugal Algoritimi Center School of Engineering University of Minho Guimeraes Portugal Technical University of Munich Germany Department of Electronic Engineering The Chinese University of Hong Kong Hong Kong Wellcome EPSRC Center for Interventional and Surgical Science University College London United Kingdom Fondazione Policlinico Universitario Agostino Gemelli IRCCS Rome Italy University Hospital of Strasbourg France

Context-aware decision support in the operating room can foster surgical safety and efficiency by leveraging real-time feedback from surgical workflow analysis. Most existing works recognize surgical activities at a coarse-grained level, such as phases, steps or events, leaving out fine-grained interaction details about the surgical activity;yet those are needed for more helpful AI assistance in the operating room. Recognizing surgical actions as triplets of combination delivers comprehensive details about the activities taking place in surgical videos. This paper presents CholecTriplet2021: an endoscopic vision challenge organized at MICCAI 2021 for the recognition of surgical action triplets in laparoscopic videos. The challenge granted private access to the large-scale CholecT50 dataset, which is annotated with action triplet information. In this paper, we present the challenge setup and assessment of the state-of-the-art deep learning methods proposed by the participants during the challenge. A total of 4 baseline methods from the challenge organizers and 19 new deep learning algorithms by competing teams are presented to recognize surgical action triplets directly from surgical videos, achieving mean average precision (mAP) ranging from 4.2% to 38.1%. This study also analyzes the significance of the results obtained by the presented approaches, performs a thorough methodological comparison between them, in-depth result analysis, and proposes a novel ensemble method for enhanced recognition. Our analysis shows that surgical workflow analysis is not yet solved, and also highlights interesting directions for future research on fine-grained surgical activity recognition which is of utmost importance for the development of AI in surgery. © 2022, CC BY-NC-SA.

关键词： Deep learning

A registration-aided domain adaptation network for 3D Point cloud based place recognition

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Qiao, Zhijian Hu, Hanjiang Shi, Weiang Chen, Siyuan Liu, Zhe Wang, Hesheng Department of Automation Insititue of Medical Robotics Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Jiao Tong University Shanghai200240 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology China Department of Mechanical Engineering Carnegie Mellon University United States Department of Computer Science and Technology University of Cambridge United Kingdom

In the field of large-scale SLAM for autonomous driving and mobile robotics, 3D point cloud based place recognition has aroused significant research interest due to its robustness to changing environments with drastic daytime and weather variance. However, it is time-consuming and effort-costly to obtain high-quality point cloud data for place recognition model training and ground truth for registration in the real world. To this end, a novel registration-aided 3D domain adaptation network for point cloud based place recognition is proposed. A structure-aware registration network is introduced to help to learn features with geometric information and a 6-DoFs pose between two point clouds with partial overlap can be estimated. The model is trained through a synthetic virtual LiDAR dataset through GTA-V with diverse weather and daytime conditions and domain adaptation is implemented to the real-world domain by aligning the global features. Our results outperform state-of-the-art 3D place recognition baselines or achieve comparable on the real-world Oxford RobotCar dataset with the visualization of registration on the virtual dataset. Copyright © 2020, The Authors. All rights reserved.

关键词： Three dimensional computer graphics

Anchor-based spatio-temporal attention 3D convolutional networks for dynamic 3D point cloud sequences

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wang, Guangming Chen, Muyao Liu, Hanwen Yang, Yehui Liu, Zhe Wang, Hesheng The Department of Automation Institute of Medical Robotics Key Laboratory of System Control and Information Processing Ministry of Education Key Laboratory of Marine Intelligent Equipment System of Ministry of Education Shanghai Jiao Tong University Shanghai200240 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology China The Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China The Department of Computer Science and Technology University of Cambridge

With the rapid development of measurwement technology, LiDAR and depth cameras are widely used in the perception of the 3D environment. Recent learning based methods for robot perception most focus on the image or video, but deep learning methods for dynamic 3D point cloud sequences are underexplored. Therefore, developing efficient and accurate perception method compatible with these advanced instruments is pivotal to autonomous driving and service robots. An Anchor-based Spatio-Temporal Attention 3D Convolution operation (ASTA3DConv) is proposed in this paper to process dynamic 3D point cloud sequences. The proposed convolution operation builds a regular receptive field around each point by setting several virtual anchors around each point. The features of neighborhood points are firstly aggregated to each anchor based on the spatio-temporal attention mechanism. Then, anchor-based 3D convolution is adopted to aggregate these anchors' features to the core points. The proposed method makes better use of the structured information within the local region and learns spatio-temporal embedding features from dynamic 3D point cloud sequences. Anchor-based Spatio-Temporal Attention 3D Convolutional Neural Networks (ASTA3DCNNs) are built for classification and segmentation tasks based on the proposed ASTA3DConv and evaluated on action recognition and semantic segmentation tasks. The experiments and ablation studies on MSRAction3D and Synthia datasets demonstrate the superior performance and effectiveness of our method for dynamic 3D point cloud sequences. Our method achieves the state-of-the-art performance among the methods with dynamic 3D point cloud sequences as input on MSRAction3D and Synthia datasets. Copyright © 2020, The Authors. All rights reserved.

关键词： Embeddings

A robust and accurate SLAM algorithm for omni-directional mobile robots based on a novel 2.5D lidar device 13

学校读者我要写书评

暂无评论

A robust and accurate SLAM algorithm for omni-directional mo...

13th IEEE Conference on Industrial Electronics and Applications, ICIEA 2018

作者： Yang, Yu Yang, Guilin Tian, Yingzhong Zheng, Tianjiang Li, Long Wang, Zhenhua Ningbo Institute of Materials Technology and Engineering CAS Ningbo315201 China Zhejiang Key Laboratory of Robotics and Intelligent Manufacturing Equipment Technology China School of Mechatronic Engineering and Automation Shanghai University Shanghai China Jiangsu Provincial Key Laboratory of Advanced Robotics Collaborative Innovation Center of Suzhou Nano Science and Technology Soochow University Suzhou215123 China

ISBN: (纸本)9781538637579

Lidars are commonly employed in mobile robot SLAM applications due to their high stability and high measuring accuracy. For a conventional 2D Lidar, only the planar points can be detected in once scan, which limits the robustness of SLAM algorithms. Omni-directional mobile robots with powered caster wheels have 3-DOF planar motion capabilities so that they are widely deployed in narrowly constrained environment. This paper presents a novel design of a 2.5D Lidar device, in which a 2D Lidar is mounted onto a 1-DOF liner stage that moves along the vertical direction. As a result, the 2.5D Lidar device can also perform vertical scanning within the motion range of the liner stage. Consequently, a robust SLAM algorithm based on the 2.5D Lidar device is proposed for the omni-directional mobile robot, where a frame-to-frame scan matching using ICP algorithm is employed to improve the robustness and accuracy of the scan matching. As the 2.5D points cloud is actually located in a belt-shaped space, the map can be finally constructed in a 2D mode to reduce the computational complexity. In addition, when an incorrect matching occurs, the odometry information of the mobile robot will be employed to further improve the robustness and accuracy of the scan matching algorithm. The effectiveness of the proposed approach is validated through computer simulations. © 2018 IEEE.

关键词： Optical radar