检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Li, Qiufu Jia, Xi Zhou, Jiancan Shen, Linlin Duan, Jinming National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Computer Vision Institute Shenzhen University China School of Computer Science University of Birmingham United Kingdom Aqara Lumi United Technology Co. Ltd China Alan Turing Institute United Kingdom SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China

Sample-to-class-based face recognition models can not fully explore the cross-sample relationship among large amounts of facial images, while sample-to-sample-based models require sophisticated pairing processes for training. Furthermore, neither method satisfies the requirements of real-world face verification applications, which expect a unified threshold separating positive from negative facial pairs. In this paper, we propose a unified threshold integrated sample-to-sample based loss (USS loss), which features an explicit unified threshold for distinguishing positive from negative pairs. Inspired by our USS loss, we also derive the sample-to-sample based softmax and BCE losses, and discuss their relationship. Extensive evaluation on multiple benchmark datasets, including MFR, IJB-C, LFW, CFP-FP, AgeDB, and MegaFace, demonstrates that the proposed USS loss is highly efficient and can work seamlessly with sample-to-class-based losses. The embedded loss (USS and sample-to-class Softmax loss) overcomes the pitfalls of previous approaches and the trained facial model UniTSFace exhibits exceptional performance, outperforming state-of-the-art methods, such as CosFace, ArcFace, VPL, AnchorFace, and UNPG. Our code is available at https://***/CVI-SZU/UniTSFace. © 2023, CC BY.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Long and Short-Term Constraints Driven Safe Reinforcement Learning for Autonomous Driving

arXiv

引用

arXiv 2024年

作者： Hu, Xuemin Chen, Pan Wen, Yijun Tang, Bo Chen, Long School of Artificial Intelligence Hubei University Wuhan430062 China Key Laboratory of Intelligent Sensing System and Security Hubei University Ministry of Education Hubei Wuhan430062 China Department of Electrical and Computer Engineering Worcester Polytechnic Institute WorcesterMA01609 United States State Key Laboratory of Multimodal Artificial Intelligence Systems State Key Laboratory of Management and Control for Complex Systems Chinese Academy of Sciences Beijing100190 China WAYTOUS Inc. Beijing100083 China Shenzhen518107 China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi’an710049 China

Reinforcement learning (RL) has been widely used in decision-making and control tasks, but the risk is very high for the agent in the training process due to the requirements of interaction with the environment, which seriously limits its industrial applications such as autonomous driving systems. Safe RL methods are developed to handle this issue by constraining the expected safety violation costs as a training objective, but the occurring probability of an unsafe state is still high, which is unacceptable in autonomous driving tasks. Moreover, these methods are difficult to achieve a balance between the cost and return expectations, which leads to learning performance degradation for the algorithms. In this paper, we propose a novel algorithm based on the long and short-term constraints (LSTC) for safe RL. The short-term constraint aims to enhance the shortterm state safety that the vehicle explores, while the long-term constraint enhances the overall safety of the vehicle throughout the decision-making process, both of which are jointly used to enhance the vehicle safety in the training process. In addition, we develop a safe RL method with dual-constraint optimization based on the Lagrange multiplier to optimize the training process for end-to-end autonomous driving. Comprehensive experiments were conducted on the MetaDrive simulator. Experimental results demonstrate that the proposed method achieves higher safety in continuous state and action tasks, and exhibits higher exploration performance in long-distance decision-making tasks compared with state-of-the-art methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Lagrange multipliers

来源：评论

学校读者我要写书评

暂无评论

Tactile grasp stability classification based on graph convolutional networks

Tactile grasp stability classification based on graph convol...

引用

2021 IEEE International Conference on Real-Time Computing and robotics, RCAR 2021

作者： Mi, Tingting Que, Dashun Fang, Senlin Zhou, Zhenning Ye, Chaoxiang Liu, Chengliang Yi, Zhengkun Wu, Xinyu School of Information Engineering Wuhan University of Technology Wuhan430070 China Shenzhen Institute of Advanced Technology CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen518055 China Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Shenzhen Key Laboratory of Smart Sensing and Intelligent Systems Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518055 China

ISBN: (纸本)9781665436786

One of the challenges for robots to grasp unknown objects is to predict whether objects will fall at the beginning of grasping. Evaluating robotic grasp state accurately and efficiently is a significant step to address this issue. In this paper, based on the different fusion approaches of multi-sensor tactile signals, we propose two novel methods based on Graph Convolution Network (GCN) for robotic stability classification. Specifically, we propose two deep learning methods including GCN based on data-level fusion (GCN-DF) and GCN based on feature-level fusion (GCN-FF). We explore the optimal parameters for transforming sensor signals into a graph structure. Furthermore, we verify the effectiveness of the proposed methods on the BioTac Grasp Stability (BiGS) dataset. The experimental results prove that the proposed approaches achieve higher classification accuracy than Support Vector Machine (SVM) and Long Short-Term Memory (LSTM). © 2021 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Force control in flexible object grasping based on position predictor

Force control in flexible object grasping based on position ...

引用

2019 IEEE International Conference on robotics and Biomimetics, ROBIO 2019

作者： Tang, Qirong Wu, Shun Tu, Haibo Chu, Zhugang Tongji University Laboratory of Robotics and Multibody System School of Mechanical Engineering Shanghai China

ISBN: (纸本)9781728163215

A novel manipulation method for grasping flexible objects with a simple rigid robot hand is proposed in this study. Based on a position predictor, it mainly focuses on force control during the object grasping. A desired force for grasping is given at first, then during the process of grasping it is converted to a predicted displacement. An online linear approximator for solving the predicted displacement iteratively is proposed. Here Model Predictive Control (MPC) is adopted to achieve accurate position control. Meanwhile a flexible model is designed for the simulation and verification. This method is verified in a flexible object contact situation and the result indicates that it can control the force precisely in flexible object grasping and achieve better performance compared with admittance control. © 2019 IEEE.

关键词： Force control

来源：评论

学校读者我要写书评

暂无评论

Sample hardness based gradient loss for long-tailed cervical cell detection

arXiv

引用

arXiv 2022年

作者： Liu, Minmin Li, Xuechen Gao, Xiangbo Chen, Junliang Shen, Linlin Wu, Huisi Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence of Robotics of Society Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China University of California Irvine United States

Due to the difficulty of cancer samples collection and annotation, cervical cancer datasets usually exhibit a long-tailed data distribution. When training a detector to detect the cancer cells in a WSI (Whole Slice Image) image captured from the TCT (Thinprep Cytology Test) specimen, head categories (e.g. normal cells and inflammatory cells) typically have a much larger number of samples than tail categories (e.g. cancer cells). Most existing state-of-the-art long-tailed learning methods in object detection focus on category distribution statistics to solve the problem in the long-tailed scenario, without considering the "hardness" of each sample. To address this problem, in this work we propose a Grad-Libra Loss that leverages the gradients to dynamically calibrate the degree of hardness of each sample for different categories, and re-balance the gradients of positive and negative samples. Our loss can thus help the detector to put more emphasis on those hard samples in both head and tail categories. Extensive experiments on a long-tailed TCT WSI image dataset show that the mainstream detectors, e.g. RepPoints, FCOS, ATSS, YOLOF, etc. trained using our proposed Gradient-Libra Loss, achieved much higher (7.8%) mAP than that trained using cross-entropy classification loss. Copyright © 2022, The Authors. All rights reserved.

关键词： Cytology

来源：评论

学校读者我要写书评

暂无评论

Redistributing Controller Orders to Increase Positioning Bandwidth in Nanopositioners

引用

IFAC-PapersOnLine 2021年第21期54卷 97-102页

作者： Adedayo K. Babarinde Linlin Li Jakub Kuncak LiMin Zhu Sumeet S. Aphale Artificial Intelligence Robotics and Mechatronic Systems Group School of Engineering University of Aberdeen Aberdeen AB24 3UE UK State Key Laboratory of Mechanical System and Vibration School of Mechanical Engineering Shanghai Jiao Tong University Shanghai 200240 China

Integer-order damping and tracking controllers are typically used in tandem to overcome resonance and hysteresis induced positioning errors in piezo-actuated nanopositioners. This paper takes a novel approach of strategically redistributing the controller orders to achieve significant positioning bandwidth improvement, without any significant increase in the design complexity. The Positive Position Feedback (PPF) controller combined with a suitably gained Integral tracking controller is used as a candidate to demonstrate the efficacy of the proposed technique. The resulting fractional-order PPF damping and Integral tracking controllers result in increasing the overall positioning bandwidth of the closed-loop system by 37%; and subsequent improvement in positioning accuracy while tracking high-frequency triangular trajectories.

关键词： Nanopositioners piezoelectric actuator positive position feedback tracking control fractional-order control

来源：评论

学校读者我要写书评

暂无评论

Robust Self-Expression Learning with Adaptive Noise Perception

SSRN

引用

SSRN 2023年

作者： Wang, Yangbo Zhou, Jie Lu, Jianglin Wan, Jun Gao, Can Lin, Qingshui College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China SMILE Lab Department of ECE College of Engineering Northeastern University Boston02115 United States School of Information and Safety Engineering Zhongnan University of Economics and Law Wuhan430073 China Basic Teaching Department Liaoning Technical University Huludao125105 China

Self-expression learning methods often obtain a coefficient matrix to measure the similarity between pairs of samples. However, directly using the raw data to represent each sample under the self-expression framework may not be ideal, as noise points are inevitably involved in the process of representing clean samples. To address this issue, this work proposes a novel self-expression model called robust Self-Expression learning with adaptive Noise Perception (SENP). SENP decomposes each sample into a clean part and a noisy part, and samples with large self-expression losses can be recognized as the noise points. A reliable coefficient matrix can then be learned by using only the clean points to reconstruct the clean part of each sample. By simultaneously detecting the noisy part of each sample and noise points, and adaptively mitigating their negative impacts, the representative ability of the generated coefficient matrix is improved. Moreover, inspired by the solution of non-negative matrix factorization (NMF), an effective algorithm is formed to optimize SENP. Extensive experiments on well-known benchmark datasets demonstrate the superiority of SENP compared to several state-of-the-art methods. © 2023, The Authors. All rights reserved.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Dual closed-loop impedance control for wheeled mobile manipulator in trajectory tracking

Dual closed-loop impedance control for wheeled mobile manipu...

引用

2019 IEEE International Conference on robotics and Biomimetics, ROBIO 2019

作者： Tang, Qirong Xu, Pengjie Yu, Fangchao Zhang, Jingtao Xu, Zhipeng Laboratory of Robotics and Multibody System School of Mechanical Engineering Tongji University Shanghai China

ISBN: (纸本)9781728163215

This paper presents a dual closed-loop impedance control scheme for a nonholonomic wheeled mobile manipulator in trajectory tracking with nonlinear contact disturbance. The kinematics and dynamics models of the mobile platform and n-links manipulator are established based on the Euler-Lagrangian approach. In order to control and eliminate the influences caused by system uncertainties and nonlinear contact disturbance, a control scheme which consists of double closed loops is proposed. The impedance control is applied to realize force tracking control in the outer loop. The inner loop is then designed to deal with chattering of measured parameters by using extended Kalman filter. The proposed controller ensures the tracking error in workspace converges to zero and the input torques are smooth. Utilizing the Lyapunov method, the stability of the system is proved. Simulation compared with conventional control methods on two driving wheeled mobile manipulator shows the effectiveness and robustness of the proposed control scheme. © 2019 IEEE.

关键词： Extended Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection of Marine Diesel Engine Valve system based on Mahalanobis Distance

Anomaly Detection of Marine Diesel Engine Valve System based...

引用

2020 Global Reliability and Prognostics and Health Management, PHM-Shanghai 2020

作者： Sun, Yue Xu, Aidong Wang, Kai Jia, Shuli Guo, Haifeng Han, Xiaojia Laboratory of Industrial Control Network and System State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Shenyang China Automation Engineering Department Shanghai Marine Diesel Engine Research Institute Shanghai China

ISBN: (纸本)9781728159454

Diesel engine is an important energy equipment. The valve system is the core component of diesel engine with high failure rate. It is of great significance to study the abnormal detection method of the diesel engine valve system and realize the failure warning before the failure occurs for avoiding the unexpected shutdown of the diesel engine. In this paper, an anomaly detection method of marine diesel engine valve system based on Mahalanobis distance (MD) is proposed. The failure mode of diesel engine system is analyzed. Three thermal parameters are selected as monitoring parameters for the failure mode of roller fragmentation. Fault features are extracted by MD method and the failure threshold is determined by Box-Cox transformation. Finally, the effectiveness of the proposed method is verified by the durability test of diesel engine. © 2020 IEEE.

关键词： Diesel engines

来源：评论

学校读者我要写书评

暂无评论

An Efficient Planning and Control Framework for Quadrotors Based on Heuristic Search and Data-Driven Model Predictive Control

引用

IEEE Transactions on Industrial Electronics 2025年

作者： Wang, Sifei Wang, Yaonan Miao, Zhiqiang Wang, Xiangke He, Wei Wang, Hesheng Hunan University College of Electrical and Information Engineering Changsha 410082 China National Engineering Research Center for Robot Visual Perception and Control Changsha 410082 China National University of Defense Technology College of Intelligence Science and Technology Changsha 410073 China Beijing Information Science and Technology University School of Automation Institute of Artificial Intelligence Beijing 100083 China University of Science and Technology School of Intelligence Science and Technology Beijing 100083 China Shanghai Jiao Tong University Department of Automation Shanghai 200240 China Ministry of Education of China Key Laboratory of System Control and Information Processing Shanghai 200240 China Harbin Institute of Technology State Key Laboratory of Robotics and System Harbin 150001 China

This article presents a framework for quadrotors that integrate planning and control, which employs a heuristic depth-first search (HDFS) with data-driven model predictive control (MPC). The proposed framework intends to enable multiquadrotor systems to traverse cluttered environments containing obstacles and disturbances. The heuristic function enables quadrotors to identify a secure route in a timely manner. The heuristic function setup employed by HDFS results in a reduction in the number of rasters accessed, particularly in scenarios that are not labyrinthine. This consequently leads to an enhancement in computational speed for multiquadrotor systems when compared to the A* algorithm. Furthermore, data-driven MPC enhances the nominal model of the quadrotor by modeling the disturbance while tracking the desired states. Consequently, data-driven MPC is capable of attaining superior tracking precision in a disturbance environment when compared to MPC without data-driven. The transformation from the path to the desired states of the quadrotor is achieved through the utilization of B-splines and differential flatness. Simulations and experiments substantiate the efficacy of the proposed approach. © 1982-2012 IEEE.

关键词： Collision avoidance data-driven depth-first search model predictive control multiquadrotor systems

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：