检索结果-内蒙古大学图书馆

30th International Conference on Mechatronics and Machine Vision in Practice, M2VIP 2024

作者： Liu, Yuanhao Liang, Wei Wang, Chu Zhang, Xin Gao, Huanbing Zhang, Yinlong State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China School of Information and Electrical Engineering Shandong Jianzhu University Jinan China Shandong Key Laboratory of Intelligent Buildings Technology Jinan China

ISBN: (纸本)9798350391916

Safe & smart move (SSM) aims to help industrial vehicular robot (IVR), such as warehousing robots, running safely and smartly by detecting the obstacles in front and maintaining a safe distance & attitude. However, the traditional SSM methods suffer the drawbacks of limited ranges, inaccurate regression of safety distance & orientation between the robot and the forward unexpected obstacles, and the inappropriate IVR control strategies. To solve these issues, this paper designs an innovative real-time safety-aware framework using the complementary Wheel-Encoder and Inertial-RGB-Depth measurements to ensure the IVR running safely, reasonably and reliably. To estimate the robot running states, we take advantages of the complementary wheel encoder, monocular RGB images and inertial measurements to obtain the robot positions, orientations, angular and linear velocities in a tightly-coupled manner. To improve the safety relative distance & attitude estimation accuracy, we exploit the RGB and depth measurements in a task-oriented fashion. The forward obstacles with the specific contours are detected using the Mask-RCNN model, followed by the Gaussian Mixture Model to obtain the forward obstacle depth. Eventually, an IVR control strategy is designed to maintain the robot safety distance and orientation, and to keep the minimum damage to the robot mechanical system. The presented method has been evaluated on the developed industrial vehicular robot safety perception platform. The experimental results prove the competitiveness against the state-of-the-art methods. © 2024 IEEE.

关键词： Industrial robots

来源：评论

学校读者我要写书评

暂无评论

Dynamic Performance Prediction in Batch-Based Assembly System with Bernoulli Machines and Changeovers

引用

Complex System Modeling and Simulation 2022年第3期2卷 224-237页

作者： Zunjun Wang Zhiyang Jia Xiuxuan Tian Jingchuan Chen Bei Pan State Key Laboratory of Intelligent Control and Decision of Complex Systems School of AutomationBeijing Institute of TechnologyBeijing 100081China Department of Industrial and Manufacturing Systems Engineering University of Hong KongHong Kong 999077China School of Engineering Tokyo University of TechnologyTokyo 192-0982Japan

Worldwide competition and diverse demand of customers pose great challenges to manufacturing enterprises. How to organize production to achieve high productivity and low cost becomes their primary task. In the mean time, the rapid pace of technology innovation has contributed to the development of new types of flexible automation. Hence, increasing manufacturing enterprises convert to multi-product and small-batch production, a manufacturing strategy that brings increased output, reduced costs, and quick response to the market. A distinctive feature of small-batch production is that the system operates mainly in the transient states. Transient states may have a significant impact on manufacturing systems. It is therefore necessary to estimate the dynamic performance of systems. As the assembly system is a typical class of production systems, in this paper, we focus on the problem of dynamic performance prediction of the assembly systems that produce small batches of different types of products. And the system is assumed to be characterized with Bernoulli reliability machines, finite buffers, and changeovers. A mathematical model based on Markovian analysis is first derived and then, the analytical formulas for performance evaluation of three-machine assembly systems are given. Moreover, a novel approach based on decomposition and aggregation is proposed to predict dynamic performance of large-scale assembly systems that consist of multiple component lines and additional processing machines located downstream of the assemble machine. The proposed approach is validated to be highly accurate and computationally efficient when compared to Monte Carlo simulation.

关键词： flexible assembly system dynamic performance Bernoulli machines finite buffers changeovers

来源：评论

学校读者我要写书评

暂无评论

ADAPTIVE ITERATIVE LEARNING TORQUE control OF ELECTRO-HYDRAULIC LOAD SIMULATOR

ADAPTIVE ITERATIVE LEARNING TORQUE CONTROL OF ELECTRO-HYDRAU...

引用

2024 CSAA/IET International Conference on Aircraft Utility systems, AUS 2024

作者： Shu, Sheng Wu, Shuai School of Automation Science and Electrical Engineering Beihang University Beijing China National Key Laboratory of Aircraft Integrated Flight Control Beihang University Beijing China Key Laboratory of Advanced Aircraft Systems Beihang University Ministry of Industry and Information Technology Beijing China Ningbo Institute of Technology Beihang University Ningbo China

The electro-hydraulic load simulator which can simulate the load executed on the aircraft actuator in the process of flight is an important ground test equipment. The uncertainties of the system including the disturbances caused by the motion of actuator make it challenging to achieve high performance. This study develops an adaptive iterative learning controller for the torque control of electro-hydraulic load simulator utilizing the backstepping method. On the basis of adaptive backstepping control, this controller incorporates iterative learning law to learn unknown nonlinear functions. By utilizing the repetitive characteristic of the test equipment, the iterative learning law sacrifices learning time to achieve enhanced control performance. To handle unknown disturbances, filter error, and learning error, a robust term described by dynamic equations is constructed. The calculation of the derivative of the virtual control law is simplified with a first-order command filter. Simulations with three different controllers are obtained to illustrate the learning ability of the proposed controller. © The Institution of Engineering & Technology 2024.

关键词： Backstepping

来源：评论

学校读者我要写书评

暂无评论

CSDNet: Contrastive Similarity Distillation Network for Multi-lingual Image-Text Retrieval 12th

CSDNet: Contrastive Similarity Distillation Network for Mul...

引用

12th International Conference on Image and Graphics, ICIG 2023

作者： Lu, Shichen Guo, Longteng He, Xingjian Zhu, Xinxin Liu, Jing Liu, Si School of Computer Science and Engineering Beihang University Beijing100191 China The Laboratory of Cognition and Decision Intelligence for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100080 China Institute of Artificial Intelligence Beihang University Beijing100191 China

ISBN: (纸本)9783031463105

Cross-modal image-text retrieval is a crucial task in the field of vision and language, aimed at retrieving the relevant samples from one modality as per the given user expressed in another modality. While most methods developed for this task have focused on English, recent advances expanded the scope of this task to the Multi-lingual domain. However, these methods face challenges due to the limited availability of annotated data in non-English languages. In this work, we propose a novel method that leverages an English pre-training model as a teacher to improve Multi-lingual image-text retrieval performance. Our method trains a student model that produces better Multi-lingual image-text similarity scores by learning from the English image-text similarity scores of the trained teacher. We introduce the contrastive loss to align the two different representations of the image and text, and the Contrastive Similarity Distillation loss to align the Multi-lingual image-text distribution of the student with that of the English teacher. We evaluate our method on two popular datasets, i.e., MS-COCO and Flickr-30K, and achieve state-of-the-art performance. Our approach shows significant improvement over existing methods and has potential for practical applications. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Advances and Challenges in Large Model Compression: A Survey 24

Advances and Challenges in Large Model Compression: A Survey

引用

2024 Guangdong-Hong Kong-Macao Greater Bay Area International Conference on Digital Economy and Artificial Intelligence, DEAI 2024

作者： Xu, Yingying Song, Chunhe Sun, Yong Yu, Shimao State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing100049 China

ISBN: (纸本)9798400717147

With the development of computer technology, large-scale models have gradually evolved from early simple algorithms to today's complex deep neural networks with huge parameter scale and high computational complexity. These large-scale models have greatly advanced the artificial intelligence technology, which has realized revolutionary progress in the fields of image, speech, text and so on. However, the computational and storage requirements of large-scale models are also growing rapidly, which seriously constrains their deployment and application in computing resource-constrained environments. In order to solve this problem, model compression technology has emerged and has been greatly developed. In this paper, we systematically review the key technologies, application scenarios, challenges and future directions of large-scale model compression from the perspective of model compression technology. Our work aims to provide practitioners and researchers with detailed references on the development of the technology, and emphasizes the important role of model compression technology in promoting the development of lightweight artificial intelligence. © 2024 Owner/Author.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

CFSeRec:A Contrastive Framework for Sequential Recommendation

CFSeRec:A Contrastive Framework for Sequential Recommendatio...

引用

第42届中国控制会议

作者： Tong Wang Yaping Dai Shuai Shao School of Automation Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex Systems

In sequential recommender systems,the main problems are the long-tailed distribution of data and noise interference.A Contrastive Framework for Sequential Recommendation(CFSeRec) is proposed to solve these two problems *** shuffling and adversarial attack data augmentation methods are used in the framework to improve the quality and quantity of training data,so that the long-tailed problem is *** the application of projection head method,the sequence representation becomes more general and robust,rather than just adapted to the task of contrastive ***,the impact of noise on sequence recommender systems is effectively *** on four public datasets show that CFSeRec achieves state-of-the-art performance in the metrics of hit ratio and normalized discounted cumulative gain,when comparing to the seven previous frameworks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Electric dual variable pump controlled hydraulic motor

Electric dual variable pump controlled hydraulic motor

引用

第42届中国控制会议

作者： Jianmin Yang Junzheng Wang Shanshuai Niu State Key Laboratory of Intelligent Control and Decision of Complex Systems School of AutomationBeijing Institute of Technology

The combined control of variable speed and variable displacement is a new type of volume control with high efficiency and fast ***,due to the inherent nonlinearity of multiplication,it brings certain difficulties to the *** electric double-variable pump[1] is a dual-input single-output system,and it is a nonlinear system[2].It is necessary to linearize the system or use a nonlinear control method to control and solve the control problem of the *** this paper,an intelligent control rule is proposed for the nonlinear problem of double input and single *** backstepping design[3],the nonlinear system is transformed into multiple linear *** the original system is turned into two independent subsystems with single input and single output,which are controlled *** co-simulation platform based on AMESIM and Simulink[4] has been verified and compared with a single PID control algorithm to simulate the step response and sinusoidal tracking performance of the *** results show that the response speed of the system has been greatly improved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Gear Shift Schedule Design for 2-AMT Electric Vehicles Based on Sparrow Search Algorithm

Comprehensive Gear Shift Schedule Design for 2-AMT Electric ...

引用

第42届中国控制会议

作者： Tianyi Wang Liling Ma Junzheng Wang State Key Laboratory of Intelligent Control and Decision of Complex Systems School of AutomationBeijing Institute of Technology

With the aim of 2-AMT electric vehicles,a comprehensive shift schedule that considers both power and economy is ***,the objective function of the comprehensive shift schedule is constructed,which is the weighted sum of vehicle acceleration time and vehicle power consumption per unit ***,Sparrow Search Algorithm is used to solve the objective function and obtain the comprehensive shift ***,AVL Cruise simulation software is used to simulate vehicle dynamics and economy under an *** results show that the comprehensive shift schedule is similar to the optimal power shift schedule in terms of dynamic performance,and the economy is optimized by 3%.The feasibility of the comprehensive shift schedule is verified.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Application of Geometric Invariants in the Problem of Trajectory Tracking for UAVs

Application of Geometric Invariants in the Problem of Trajec...

引用

2022 International Siberian Conference on control and Communications, SIBCON 2022

作者： Khachumov, Mikhail Ailamazyan Program Systems Institute of RAS Intelligent Control Laboratory Pereslavl-Zalessky Russia Federal Research Center 'Computer Science and Control' Russian Academy of Sciences Moscow Russia

ISBN: (纸本)9781665476287

The study discusses approaches and an apply example of using geometric invariants in problems of control theory. An analytical review of modern papers in the field of trajectory tracking and path following control problems for unmanned aerial vehicles (UAVs) has been carried out. To increase the autonomy and ability to cope with uncertainties, it is proposed to use the theory of intelligent-geometric control. The problem of the trajectory tracking is considered in the framework of the pursuit-evasion differential game. control invariants are considered in the form of ellipsoids, that can be used, for example, in pursuit-evasion problems. The task of determining the parameters of the pursuer's motion to meet the evader on an ellipsoid is solved. The dependence of the pursuer's speed on the parameters of the ellipse is shown. A modeling scheme is proposed aimed at joint application of optimal and intelligent control methods to solve trajectory tracking problem in difficult conditions. Simulations carried out in a disturbed environment on controlling the motion of a UAV group showed prospects of the proposed approach. © 2022 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Two Degree of Freedom Active Disturbance Rejection control Strategy for Time Delay systems

Two Degree of Freedom Active Disturbance Rejection Control S...

引用

第42届中国控制会议

作者： Xiyuan Shan Tao Cai School of Automation Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex Systems

This paper is concerned with the controller design and the theoretical analysis for time-delay systems,a two degree of freedom(feedforward and feedback) control method is proposed,which combines advantages of the Smith predictor and the active disturbance rejection control(ADRC).The feedforward part of controller is used to track the set point,the feedback part of controller(ADRC) is used to suppress interferences and the Smith predictor is used to correct time *** proposed control design is easy to tune parameters and has been proved to effectively control systems with large time *** bounded input bounded output(BIBO) stability of closed-loop system is ***,numerical simulations show the effectiveness and practicality of the proposed design.

关键词： Time-delay Active Disturbance Rejection control(ADRC) Smith Predictor(SP)

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：