检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Chen, Siyu Liu, Kangcheng Wang, Chen Yuan, Shenghai Yang, Jianfei Xie, Lihua The School of Electrical and Electronic Engineering Nanyang Technological University 50 Nanyang Avenue Singapore639798 Singapore The Spatial AI & Robotics Lab The Department of Computer Science & Engineering State University of New York at Buffalo BuffaloNY14260 United States

Visual Odometry (VO) is vital for the navigation of autonomous systems, providing accurate position and orientation estimates at reasonable costs. While traditional VO methods excel in some conditions, they struggle with challenges like variable lighting and motion blur. Deep learning-based VO, though more adaptable, can face generalization problems in new environments. Addressing these drawbacks, this paper presents a novel hybrid visual odometry (VO) framework that leverages pose-only supervision, offering a balanced solution between robustness and the need for extensive labeling. We propose two cost-effective and innovative designs: a self-supervised homographic pre-training for enhancing optical flow learning from pose-only labels and a random patch-based salient point detection strategy for more accurate optical flow patch extraction. These designs eliminate the need for dense optical flow labels for training and significantly improve the generalization capability of the system in diverse and challenging environments. Our pose-only supervised method achieves competitive performance on standard datasets and greater robustness and generalization ability in extreme and unseen scenarios, even compared to dense optical flow-supervised state-of-the-art methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Attention in Attention for PET-CT Modality Consensus Lung Tumor Segmentation

Attention in Attention for PET-CT Modality Consensus Lung Tu...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yuzhou Zhao Xinyu Zhou Haijing Guo Qianyu Guo Yan Zuo Shaoli Song Shuyong Gao Wenqiang Zhang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Department of Nuclear Medicine Fudan University Shanghai Cancer Center China Shanghai Engineering Research Center of AI Robotics Academy for Engineering and Technology Fudan University

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Combination of multi-modal PET-CT imaging for lung tumor segmentation is significant for clinical treatment. Existing methods have not fully considered the impact of noise in PET-CT on the multi-modal interaction. To address this, we propose a novel Attention in Attention Network (AiANet). AiANet can mutually learn multi-modal characteristics for segmentation through its cross-learning modules. Within the cross-learning module, we introduce two nested-attention blocks, namely Attention in Self-Attention (AiSA) and Attention in Cross-Attention (AiCA), for multi-scale feature enhancement and multi-modal feature interaction. Importantly, since traditional attention weights calculated solely or unilaterally based on PET or CT can be vulnerable to the inevitable noisy information, we embed a novel Attention in Attention (AiA) module into AiSA and AiCA. The AiA module can seek cross-modal consensus for attention weights to alleviate their noise. Experimental results on clinical PET-CT data of lung cancer demonstrate the superiority of our method.

关键词： Image segmentation Computed tomography Aggregates Noise Lung cancer Imaging Noise measurement Tumors

来源：评论

学校读者我要写书评

暂无评论

Exploring Innovations in Autonomous robotics and Mechatronics: Application in Manufacturing and Healthcare

Exploring Innovations in Autonomous Robotics and Mechatronic...

引用

Smart Electronics and Communication (ICOSEC), International Conference on

作者： T.Grace Shalini L. Ganeshabu Priyanka Chemudugunta Nagendar Yamsani Ch.Ashok Kumar A. Athiraja Department of Computational Intelligence School of Computing SRM Institute of Science and Technology (SRMIST)Kattankulathur Chengalpattu Tamil Nadu India Department of Robotics and Automation Rajalakshmi Engineering College Rajalakshmi Nagar Thandalam Mevalurkuppam Chennai Tamil Nadu India Department of Robotics and Automation Karpaga Vinayaga College of Engineering and Technology Chengalpattu Tamil Nadu India Department of School of Computer Science and Artificial Engineering SR University Warangal India Department of Mechanical Engineering Malla Reddy Engineering College Main Campus Maisammaguda Hyderabad Telangana India Department of CSE (AIML) Malla Reddy College of Engineering Secunderabad Telangana India

ISBN: (数字)9798331504403

ISBN: (纸本)9798331504410

Autonomous robotics and mechatronics have drastically changed the manufacturing and healthcare sectors by increasing productivity, precision, and flexibility. This work addresses the pressing need for new methods to advance these sectors by merging intelligent algorithms with autonomous systems. A hybrid strategy was employed, combining Deep Reinforcement Learning (DRL) and Adaptive Control Systems (ACS), to develop and optimize robotic operations. Extensive studies were conducted to assess the success of this strategy, which demonstrated a 25% reduction in operating expenses and a 30% increase in production efficiency in manufacturing settings. The method produced a precision rate of about 99% in the healthcare industry, which is significantly better than the 93% average of current systems. It also reduced patient recovery times by an estimated 20%. These results highlight the improved performance and promise of ACS with DRL combination in autonomous robotics, which may have revolutionary implications for the manufacturing and healthcare industries. The success, highlighted by economic and medical benefits, demonstrates the efficacy of our methodology and provides a strong platform for future developments in autonomous robotics and mechatronics.

关键词： Industries Technological innovation Mechatronics Service robots Scalability Medical services Manufacturing Adaptive control Tuning Testing

来源：评论

学校读者我要写书评

暂无评论

Using Curiosity for an Even Representation of Tasks in Continual Offline Reinforcement Learning

arXiv

引用

arXiv 2023年

作者： Pathmanathan, Pankayaraj Díaz-Rodríguez, Natalia Ser, Javier Del Department of Computer Science University of Maryland College Park20740 United States Department of Computer Science and Artificial Intelligence University of Granada CITIC Granada18071 Spain Granada AI Lab DaSCI Andalusian Institute in Data Science and Computational Intelligence University of Granada Granada18071 Spain Derio48160 Spain Bilbao48013 Spain

INTRODUCTION. In this work, we investigate the means of using curiosity on replay buffers to improve offline multi-task continual reinforcement learning when tasks, which are defined by the non-stationarity in the environment, are non labeled and not evenly exposed to the learner in time. METHODS. In particular, we investigate the use of curiosity both as a tool for task boundary detection and as a priority metric when it comes to retaining old transition tuples, which we respectively use to propose two different buffers. Firstly, we propose a Hybrid Reservoir Buffer with Task Separation (HRBTS), where curiosity is used to detect task boundaries that are not known due to the task agnostic nature of the problem. Secondly, by using curiosity as a priority metric when it comes to retaining old transition tuples, a Hybrid Curious Buffer (HCB) is proposed. We ultimately show that these buffers, in conjunction with regular reinforcement learning algorithms, can be used to alleviate the catastrophic forgetting issue suffered by the state of the art on replay buffers when the agent’s exposure to tasks is not equal along time. RESULTS. We evaluate catastrophic forgetting and the efficiency of our proposed buffers against the latest works such as the Hybrid Reservoir Buffer (HRB) and the Multi-Time Scale Replay Buffer (MTR) in three different continual reinforcement learning settings. These settings are defined based on how many times the agent encounters the same task, how long they last, and how different new tasks are when compared to the old ones (i.e., how large the task drift is). The three settings are namely, 1. prolonged task encounter with substantial task drift, and no task re-visitation, 2. frequent, short-lived task encounter with substantial task drift and task re-visitation, and 3. every timestep task encounter with small task drift and task re-visitation. Experiments were done on classical control tasks and Metaworld environment. CONCLUSION. Experiments show t

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Coresets for near-convex functions 34

Coresets for near-convex functions

引用

34th Conference on Neural Information Processing Systems, NeurIPS 2020

作者： Tukan, Murad Maalouf, Alaa Feldman, Dan The Robotics and Big Data Lab. Department of Computer Science University of Haifa Haifa Israel

Coreset is usually a small weighted subset of n input points in Rd, that provably approximates their loss function for a given set of queries (models, classifiers, etc.). Coresets become increasingly common in machine learning since existing heuristics or inefficient algorithms may be improved by running them possibly many times on the small coreset that can be maintained for streaming distributed data. Coresets can be obtained by sensitivity (importance) sampling, where its size is proportional to the total sum of sensitivities. Unfortunately, computing the sensitivity of each point is problem dependent and may be harder to compute than the original optimization problem at hand. We suggest a generic framework for computing sensitivities (and thus coresets) for wide family of loss functions which we call near-convex functions. This is by suggesting the f-SVD factorization that generalizes the SVD factorization of matrices to functions. Example applications include coresets that are either new or significantly improves previous results, such as SVM, Logistic regression, M-estimators, and z-regression. Experimental results and open source are also provided. © 2020 Neural information processing systems foundation. All rights reserved.

关键词： Factorization

来源：评论

学校读者我要写书评

暂无评论

Decomposition of dynamic transcriptomic responses during effector-triggered immunity reveals conserved responses in two distinct plant cell populations

引用

Plant Communications 2024年第8期5卷 1-17页

作者： Xiaotong Liu Daisuke Igarashi Rachel A.Hillmer Thomas Stoddard You Lu Kenichi Tsuda Chad L.Myers Fumiaki Katagiri Department of Plant and Microbial Biology University of Minnesota-Twin CitiesSt PaulMN 55108USA Department of Computer Science and Engineering University of Minnesota-Twin CitiesMinneapolisMN 55455USA Bioinformatics and Computational Biology Graduate Program University of Minnesota-Twin CitiesMinneapolisMN 55455USA Institute for Innovation Ajinomoto Co.Inc.KawasakiJapan State Key Laboratory of Agricultural Microbiology Hubei Hongshan LaboratoryHubei Key Lab of Plant PathologyCollege of Plant Science and TechnologyHuazhong Agricultural UniversityWuhan 430070China Present address:225 S 6th St MinneapolisMN 55402USA Present address:Biotalys Inc.2520 Meridian Parkway Suite 480DurhamNC 27713USA Present address:Life Sciences Institute and Department of Cell and Developmental Biology University of Michigan Medical SchoolAnn ArborMI 48109USA

Rapid plant immune responses in the appropriate cells are needed for effective defense against *** transcriptome analysis is often used to describe overall immune responses,collection of transcriptome data with sufficient resolution in both space and time is *** reanalyzed public Arabidopsis time-course transcriptome data obtained after low-dose inoculation with a Pseudomonas syringae strain expressing the effector AvrRpt2,which induces effector-triggered immunity in ***-peak time-course patterns are prevalent among thousands of upregulated *** implemented a multicompartment modeling approach to decompose the double-peak pattern into two single-peak patterns for each *** decomposed peaks reveal an“echoing”pattern:the peak times of the first and second peaks correlate well across most upregulated *** demonstrated that the two peaks likely represent responses of two distinct cell populations that respond either cell autonomously or indirectly to ***,the peak decomposition has extracted spatial information from the time-course *** echoing pattern also indicates a conserved transcriptome response with different initiation times between the two cell populations despite different elicitor types.A gene set highly overlapping with the conserved gene set is also upregulated with similar kinetics during pattern-triggered *** of a WRKY network via different entry-point WRKYs can explain the similar but not identical transcriptome responses elicited by different elicitor *** discuss potential benefits of the properties of the WRKY activation network as an immune signaling network in light of pressure from rapidly evolving pathogens.

关键词： Arabidopsis Pseudomonas syringae plant immune response multi-compartment model WRKY transcription factors resilient immune signaling network

来源：评论

学校读者我要写书评

暂无评论

Physical Human-Aerial Robot Interaction and Collaboration: Exploratory Results and Lessons Learned

Physical Human-Aerial Robot Interaction and Collaboration: E...

引用

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Amr Afifi Gianluca Corsini Quentin Sable Youssef Aboudorra Daniel Sidobre Antonio Franchi Robotics and Mechatronics lab Faculty of Electrical Engineering Mathematics & Computer Science University of Twente Enschede The Netherlands LAAS-CNRS UPS Université de Toulouse Toulouse France Department of Computer Control and Management Engineering Sapienza University of Rome Rome Italy

In this work, we present, a first of its kind, physical human-aerial robot interaction (pHARI) experiment, with an articulated aerial manipulator (AM). The robotic platform is a fully-actuated multi-rotor aerial vehicle (MRAV) with fixedly-tilted propellers endowed with a 3degree of freedom (DoF) robotic arm. We implemented a state-of-the-art control architecture composed of a feedback linearization motion controller, an admittance filter and a hybrid wrench observer. The experiments prove the viability of a new use case in aerial robotics, namely pHARI. The experimental results also shed light on the limitations of the current state-of-the-art and provide insights into possible research directions. The video of the experiments, which is available at https://***/LrQxXbQ5IHc, shows an experiment simulating work at height, where a human manually guides an AM and then attaches a tool to its end effector (EE).

关键词：

来源：评论

学校读者我要写书评

暂无评论

HGIC: A Hand Gesture Based Interactive Control System for Efficient and Scalable Multi-UAV Operations

HGIC: A Hand Gesture Based Interactive Control System for Ef...

引用

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： Mengsha Hu Jinzhou Li Runxiang Jin Chao Shi Lei Xu Rui Liu Cognitive Robotics and AI Lab (CRAI) College of Aeronautics and Engineering Kent State University Kent OH USA Department of Computer Science Kent State University Kent OH USA College of Engineering Cornell University Ithaca NY USA Department of Systems Science and Industrial Engineering Binghamton University Binghamton NY USA

ISBN: (数字)9798350375022

ISBN: (纸本)9798350375039

As technological advancements continue to expand the capabilities of multi unmanned-aerial-vehicle systems (mUAV), human operators face challenges in scalability and efficiency due to the complex cognitive load and operations associated with motion adjustments and team coordination. Such cognitive demands limit the feasible size of mUAV teams and necessitate extensive operator training, impeding broader adoption. This paper developed a Hand Gesture Based Interactive Control (HGIC), a novel interface system that utilize computer vision techniques to intuitively translate hand gestures into modular commands for robot teaming. Through learning control models, these commands enable efficient and scalable mUAV motion control and adjustments. HGIC eliminates the need for specialized hardware and offers two key benefits: 1) Minimal training requirements through natural gestures; and 2) Enhanced scalability and efficiency via adaptable commands. By reducing the cognitive burden on operators, HGIC opens the door for more effective large-scale mUAV applications in complex, dynamic, and uncertain scenarios. HGIC will be open-sourced after the paper being published online for the research community, aiming to drive forward innovations in human-mUAV interactions.

关键词： Training Technological innovation computer vision Scalability Robot kinematics computational modeling Control systems Hardware Motion control Faces

来源：评论

学校读者我要写书评

暂无评论

A Unified Deep Imitation Learning and Control Framework for Robot-Assisted Sonography

A Unified Deep Imitation Learning and Control Framework for ...

引用

IEEE International Conference on Development and Learning, ICDL

作者： Weiyong Si Cheng Guo Ning Wang Minyu Yang Rebecca Harris Chenguang Yang Bristol Robotics Lab University of the West of England School of Computer Science and Electronic Engineering University of Essex Faculty of Engineering University of Bristol Department of Engineering University of Cambridge University Hospitals Bristol and Weston.

Medical ultrasound scanning is a challenging dexterous manipulation task for robots, even for experienced sonogra-phers, since it involves motion control and force regulation based on the real-time ultrasound image and patient feedback. In this work, we proposed a novel robot-assisted ultrasound scanning framework, integrating deep multimodal imitation learning and model-based compliant control. We investigated the deep imitation learning model to fuse multimodal information, including the RGB image, force profile, ultrasound image, and proprioceptive information for robot-assisted ultrasound scanning artery. The deep imitation learning module predicts reference motion and force command. We designed a compliant controller in Cartesian space to track reference trajectory and desired force. The generalization capability of the deep multimodal imitation learning module and control performance and the quality of the acquired ultrasound image through Phantom. The results show that the proposed approach is able to improve the success rate of procedure completion, and the complete time is reduced.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Multi-model Fusion of LiDAR-inertial Odometry via Localization and Mapping

A Multi-model Fusion of LiDAR-inertial Odometry via Localiza...

引用

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

作者： An Duy Nguyen Chuong Phuoc Le Pratik Walunj Anton Netchaev Thanh Nho Do Hung Manh La Department of Computer Science and Engineering Advanced Robotics and Automation (ARA) Lab University of Nevada Reno NV USA USACE Engineer Research and Development Center (ERDC) Information Technology Lab Vicksburg MS USA Graduate School of Biomedical Engineering UNSW Sydney Kensington Campus NSW Australia

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

This work presents a comprehensive LiDAR-inertial odometry framework featuring robust smoothing and mapping capabilities, effectively correcting LiDAR feature point skewness using an inertial measurement unit (IMU). While the Extended Kalman Filter (EKF) is a common choice for nonlinear motion estimation, its complexity grows when handling maneuvering targets. To overcome this challenge, a new framework that incorporates the Iterated Interactive Multiple Models of Kalman Filter (IMMKF) is given, providing a solution for reliable navigation in dynamic motion and noisy conditions. To ensure map consistency, an ikd-tree that facilitates continuous updates and adaptive rebalance is employed, preserving the map’s integrity. To guarantee the robustness of our approach, it undergoes extensive testing across diverse scales of indoor and outdoor environments. This testing scenario simulates absolute GPS denial. In terms of estimated motion, the new algorithm demonstrates superior accuracy compared to existing approaches. The implementation is openly accessible on GitHub 4 for further exploration.

关键词： Location awareness Technological innovation Laser radar Accuracy Smoothing methods computational modeling Feature extraction Odometry Kalman filters Testing

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：