检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Tao, Zeng Wang, Yan Lin, Junxiong Wang, Haoran Mai, Xinji Yu, Jiawen Tong, Xuan Zhou, Ziheng Yan, Shaoqi Zhao, Qing Han, Liyuan Zhang, Wenqiang Shanghai Engineering Research Center of AI & Robotics Academy for Engineering & Technology Fudan University Shanghai China School of Information Science and Technology Fudan University Shanghai China Institute of Automation Chinese Academy of Sciences Beijing China Engineering Research Center of AI & Robotics Ministry of Education Academy for Engineering & Technology Fudan University Shanghai China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China

The performance of CLIP in dynamic facial expression recognition (DFER) task doesn’t yield exceptional results as observed in other CLIP-based classification tasks. While CLIP’s primary objective is to achieve alignment between images and text in the feature space, DFER poses challenges due to the abstract nature of text and the dynamic nature of video, making label representation limited and perfect alignment difficult. To address this issue, we have designed A3lign-DFER, which introduces a new DFER labeling paradigm to comprehensively achieve alignment, thus enhancing CLIP’s suitability for the DFER task. Specifically, our A3lign-DFER method is designed with multiple modules that work together to obtain the most suitable expanded-dimensional embeddings for classification and to achieve alignment in three key aspects: affective, dynamic, and bidirectional. We replace the input label text with a learnable Multi-Dimensional Alignment Token (MAT), enabling alignment of text to facial expression video samples in both affective and dynamic dimensions. After CLIP feature extraction, we introduce the Joint Dynamic Alignment Synchronizer (JAS), further facilitating synchronization and alignment in the temporal dimension. Additionally, we implement a Bidirectional Alignment Training Paradigm (BAP) to ensure gradual and steady training of parameters for both modalities. Our insightful and concise A3lign-DFER method achieves state-of-the-art results on multiple DFER datasets, including DFEW, FERV39k, and MAFW. Extensive ablation experiments and visualization studies demonstrate the effectiveness of A3lign-DFER. The code will be available in the future. © 2024, CC BY.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Design and Mechatronics of a Neurosurgical Robot for Tumor Ablation under MRI

Automation, Robotics and Communications for Industry 4.0/5.0

引用

automation, robotics and Communications for Industry 4.0/5.0 2023年 2023卷 75-76页

作者： Ding, Qingpeng Yan, Wanquan Chen, Jianghua Yan, Kim Lam, Chun Ping Cheng, Shing Shin Dept. of Mechanical and Automation Engineering The Chinese University of Hong Kong Sha Tin Hong Kong Multi-Scale Medical Robotics Center Hong Kong Science Park N.T Hong Kong

Straight rigid instruments are still dominant tools used in most existing surgical cases in the human brain. The lack of distal dexterity and compatibility with the magnetic resonance imaging (MRI) limit the usage of these instruments in image-guided minimally invasive surgeries. Continuum robots built with MRI compatibility can potentially lead to wide adoption of surgical robots in intraoperative procedures. This paper introduces a 2-DoF 3D-printed continuum end effector and modular shape memory alloy (SMA) actuators for real-time tip motion in 3D workspace. The robot takes advantage of modular design to decouple linkage from the actuators to the end effector. This modular architecture facilitates establishment of a sterile interface and maintenance of the entire robotic system. Design of the robot and the control system are described, and the performance under MRI is evaluated experimentally. © 2023, International Frequency Sensor Association (IFSA). All rights reserved.

关键词： End effectors

来源：评论

学校读者我要写书评

暂无评论

PTC-FOZNN: A Strictly Predefined-Time Convergent Fractional-Order Recurrent Neural Network for Solving Time-Variant Quadratic Programming

PTC-FOZNN: A Strictly Predefined-Time Convergent Fractional-...

引用

International Conference on Control and automation (ICCA)

作者： Yi Yang Weibing Li Jianshu Zhou Junda Huang Jinfei Hu Richard M. Voyles Xin Ma Department of Mechanical and Automation Engineering Multi-Scale Medical Robotics Center The Chinese University of Hong Kong Hong Kong China School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Hong Kong China School of Engineering Technology Purdue University West Lafayette IN USA

ISBN: (数字)9798350354409

ISBN: (纸本)9798350354416

This study presents a Predefined-Time Convergent Fractional-Order Zeroing Neural Network (PTC-FOZNN) as an innovative solution for Time-Invariant Quadratic Programming (TIQP) and Time-Variant Quadratic Programming (TVQP) problems. This model represents a noteworthy integration of fractional calculus into recurrent neural networks for cyclic motion planning of robots. The PTC-FOZNN diverges from the conventional Zeroing Neural Network (ZNN) by implementing a conformable fractional derivative that complies with the Leibniz rule-a standard often unmet by existing fractional derivatives. Additionally, it employs a novel predefined-time stabilizer as its activation function. When compared to the traditional ZNN, the PTC-FOZNN, configured with $0 < \alpha\leq 1$ , exhibits enhanced convergence speed and greater positional accuracy for both TIQP and TVQP tasks. Through meticulous theoretical and empirical validation, including simulation trials with a Franka Emika Panda robotic arm, the PTC-FOZNN model has proven its effectiveness in precise trajectory tracking and computational efficacy.

关键词： Recurrent neural networks Trajectory tracking Kinematics Manipulators Planning Quadratic programming Task analysis

来源：评论

学校读者我要写书评

暂无评论

Variational Feature Disentanglement for Few-Shot Domain Adaptation

Variational Feature Disentanglement for Few-Shot Domain Adap...

引用

IEEE International Conference on Image Processing

作者： Weiduo Wang Yun Gu Jie Yang Department of Automation Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China Institute of Medical Robotics Shanghai Jiao Tong University China Shanghai Center for Brain Science and Brain-Inspired Technology

In this paper, we focus on the few-shot domain adaptation problem. With limited training data in target domain, a new approach is emerging to acquire the transferable knowledge from the source domain. Previous methods aligned the embedding space between domains by reducing the pair-wise distance. However, these methods are reporting the misalignment and poor generalization. To solve this problem, we propose a variational feature disentanglement framework. The embedding features are explicitly disentangled into domaininvariant and domain-specific components. The distributions of domain-invariant variance are estimated and aligned by the variational inference. For further disentanglement, the domain-invariant and domain-specific components are separated by the orthogonal constraints of subspaces. The experiments on Digits dataset and VisDA-C dataset demonstrate that the proposed method can outperform the state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SAGD: Boundary-Enhanced Segment Anything in 3D Gaussian via Gaussian Decomposition

arXiv

引用

arXiv 2024年

作者： Hu, Xu Wang, Yuxi Fan, Lue Luo, Chuanchen Fan, Junsong Lei, Zhen Li, Qing Peng, Junran Zhang, Zhaoxiang The Hong Kong Polytechnic University Hong Kong Center for Artificial Intelligence and Robotics HKISI CAS Hong Kong Institute of Automation Chinese Academy of Sciences China University of Chinese Academy of Sciences China University of Science and Technology Beijing China Shandong University China

3D Gaussian Splatting has emerged as an alternative 3D representation for novel view synthesis, benefiting from its high-quality rendering results and real-time rendering speed. However, the 3D Gaussians learned by 3D-GS have ambiguous structures without any geometry constraints. This inherent issue in 3D-GS leads to a rough boundary when segmenting individual objects. To remedy these problems, we propose SAGD, a conceptually simple yet effective boundary-enhanced segmentation pipeline for 3D-GS to improve segmentation accuracy while preserving segmentation speed. Specifically, we introduce a Gaussian Decomposition scheme, which ingeniously utilizes the special structure of 3D Gaussian, finds out, and then decomposes the boundary Gaussians. Moreover, to achieve fast interactive 3D segmentation, we introduce a novel training-free pipeline by lifting a 2D foundation model to 3D-GS. Extensive experiments demonstrate that our approach achieves high-quality 3D segmentation without rough boundary issues, which can be easily applied to other scene editing tasks. Our code is publicly available at https://***/XuHu0529/SAGS. Copyright © 2024, The Authors. All rights reserved.

关键词： Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

FeCAM: exploiting the heterogeneity of class distributions in exemplar-free continual learning 23

FeCAM: exploiting the heterogeneity of class distributions i...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Dipam Goswami Yuyang Liu Bartłomiej Twardowski Joost van de Weijer Department of Computer Science Universitat Autònoma de Barcelona and Computer Vision Center Barcelona University of Chinese Academy of Sciences and State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences and Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Department of Computer Science Universitat Autònoma de Barcelona and Computer Vision Center Barcelona and IDEAS-NCBR

Exemplar-free class-incremental learning (CIL) poses several challenges since it prohibits the rehearsal of data from previous tasks and thus suffers from catastrophic forgetting. Recent approaches to incrementally learning the classifier by freezing the feature extractor after the first task have gained much attention. In this paper, we explore prototypical networks for CIL, which generate new class prototypes using the frozen feature extractor and classify the features based on the Euclidean distance to the prototypes. In an analysis of the feature distributions of classes, we show that classification based on Euclidean metrics is successful for jointly trained features. However, when learning from non-stationary data, we observe that the Euclidean metric is suboptimal and that feature distributions are heterogeneous. To address this challenge, we revisit the anisotropic Mahalanobis distance for CIL. In addition, we empirically show that modeling the feature covariance relations is better than previous attempts at sampling features from normal distributions and training a linear classifier. Unlike existing methods, our approach generalizes to both many- and few-shot CIL settings, as well as to domain-incremental settings. Interestingly, without updating the backbone network, our method obtains state-of-the-art results on several standard continual learning benchmarks. Code is available at https://***/dipamgoswami/FeCAM.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of an Automated Wheelchair for Visually Impaired People 23

Development of an Automated Wheelchair for Visually Impaired...

引用

23rd IEEE International Multi-Topic Conference, INMIC 2020

作者： Siddiqui, Arslan Anwer, Talha Zafar, Saqib Maqbool, Hafiz Farhan Siddiqi, Dilruba Ahmad, Nasir Mehmood, Muhammad Armghan Riaz, Ahsan University of Engineering and Technology Department of Mechatronics and Control Engineering Lahore Pakistan Human Centered Robotics Lab National Center of Robotics and Automation Lahore Pakistan

ISBN: (纸本)9781728198934

This paper presents the development of an automated wheelchair, a mobility-assistive device that helps visually impaired people in the community. For such people, there are many constraints associated while moving to their desired destination. One of the main objectives of the current work is to design and develop a low-cost smart wheelchair that navigates to its destination autonomously. This smart navigation system (SNS) uses a machine vision technique for localization and path planning and proximity sensors for obstacle avoidance. The wheelchair can autonomously navigate to the location selected by the user through a braille keypad interface. The mechanical design is focused to make a finished product that is stable and according to basic medical considerations. The hardware design in the paper aims to enable a visually impaired person to perform daily routine tasks without the need for any assistance. © 2020 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

A High-sensitivity Three-Dimensional Force Sensing Sensor for Minimally Invasive Cardiac Ablation Surgery

A High-sensitivity Three-Dimensional Force Sensing Sensor fo...

引用

IEEE International Conference on Mechatronics and automation

作者： Jie Jiang Linshuai Zhang Shiqi Jiang Yuyang Luo Xin Tian Shuoxin Gu Tao Jiang School of Automation Chengdu University of Information Technology Chengdu China School of Intelligent Medicine Chengdu University of Traditional Chinese Medicine Chengdu China International Joint Research Center of Robotics and Intelligence System of Sichuan Province Chengdu University of Information Technology Chengdu China

ISBN: (数字)9798350388077

ISBN: (纸本)9798350388084

This paper introduces a high-sensitivity distal three-dimensional force sensor designed for cardiac ablation surgery. The sensor combines a force-sensitive structure with fiber Bragg gratings (FBGs) for the measurement of triaxial forces. At the tip of the sensor, an elastic flexure structure is designed, with four pairs of symmetrically arranged U-shaped slots for axial force perception and a modified I-beam structure for lateral force measurement. Five FBG elements are embedded into the elastic flexure structure, with each FBG placed in a tightly suspended manner and fixed at both ends using an adhesive to detect micro-strain and ensure sensitivity. The theoretical force-strain relationship is derived, and decoupling methods are provided. Simulation experiments based on finite element modeling are conducted for static calibration analysis. Simulation results indicate that under axial forces ranging from 0 to 2N, the axial force resolution is 4.46mN, and under lateral forces ranging from -1 to 1N, the lateral force resolutions in the two directions are 0.294mN and 0.293mN, respectively. These findings demonstrate that the sensor exhibits high sensitivity, validating the effectiveness of the design.

关键词： Optical fibers Optical fiber sensors Sensitivity Force measurement Minimally invasive surgery Simulation Force

来源：评论

学校读者我要写书评

暂无评论

Dynamic Control Barrier Function-based Model Predictive Control to Safety-Critical Obstacle-Avoidance of Mobile Robot

Dynamic Control Barrier Function-based Model Predictive Cont...

引用

IEEE International Conference on robotics and automation (ICRA)

作者： Zhuozhu Jian Zihong Yan Xuanang Lei Zihong Lu Bin Lan Xueqian Wang Bin Liang Center for Artificial Intelligence and Robotics Shenzhen International Graduate School Tsinghua University Shenzhen China Department of D-MAVT ETH Zurich Zurich Switzerland School of Mechanical Engineering and Automation at Harbin Institute of Technology Shenzhen China Jianghuai Advance Technology Center China

This paper presents an efficient and safe method to avoid static and dynamic obstacles based on LiDAR. First, point cloud is used to generate a real-time local grid map for obstacle detection. Then, obstacles are clustered by DBSCAN algorithm and enclosed with minimum bounding ellipses (MBEs). In addition, data association is conducted to match each MBE with the obstacle in the current frame. Considering MBE as an observation, Kalman filter (KF) is used to estimate and predict the motion state of the obstacle. In this way, the trajectory of each obstacle in the forward time domain can be parameterized as a set of ellipses. Due to the uncertainty of the MBE, the semi-major and semi-minor axes of the parameterized ellipse are extended to ensure safety. We extend the traditional Control Barrier Function (CBF) and propose Dynamic Control Barrier Function (D-CBF). We combine D-CBF with Model Predictive Control (MPC) to implement safety-critical dynamic obstacle avoidance. Experiments in simulated and real scenarios are conducted to verify the effectiveness of our algorithm. The source code is released for the reference of the community 1 1 Code: https://***/jianzhuozhuTHU/MPC-D-CBF..

关键词：

来源：评论

学校读者我要写书评

暂无评论

Review of Inference Time Prediction Approaches of DNN: Emphasis on Service robots with cloud-edge-device architecture

Review of Inference Time Prediction Approaches of DNN: Empha...

引用

IEEE International Conference on robotics and Biomimetics

作者： Tian Xiang Qiwei Meng Ji Zhang Beibei Zhang Wei Song Anhuan Xie Jason Gu Research Center for Intelligent Robotics Research Institute of Interdisciplinary Innovation Zhejiang Laboratory Hangzhou China Department of Mechanical and Automation Engineering T Stone Robotics Institute The Chinese University of Hong Kong HKSAR China Research Center for Intelligent Computing Software Research Institute of Intelligent Computing Zhejiang Laboratory Hangzhou China Electrical and Computer Engineering Dalhousie University Halifax Canada

In recent years, the global robot market has witnessed substantial growth, particularly in the domain of service robots. Despite their expanding presence, service robots encounter limitations when operating autonomously in unstructured environments, primarily due to their constrained computational capacities. As a solution, the fusion of cloud and edge computing resources becomes imperative to expedite task inference and enhance scenario perception capabilities. The integration of cloud-edge-device models holds significant promise in bolstering the operational efficiency of robots. This entails the dynamic partitioning of intricate robotic tasks, executed collaboratively across cloud, edge, and device resources. In this landscape, deep neural network (DNN) models play a pivotal role in facilitating a wide array of robotic tasks. The inference time for each layer of a DNN model in actual deployment, emerges as a critical determinant in the model’s partitioning strategy. It also serves as an important metric influencing the model’s suitability for a specific hardware platform. This article presents an overview of recent advancements in predicting inference and training time of DNN models, summarizes the related methods, and finally discusses the challenges in this field and the research that can be studied in the future.

关键词：

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：