检索结果-内蒙古大学图书馆

第34届中国控制与决策会议

作者： Ziyao Wang Yiye Wang Kanjian Zhang Haikun Wei Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of EducationSchool of AutomationSoutheast University

Natural Locomotion interface(NLI) is critical to expanding the users' exploration of scenes in virtual reality and improving user *** on the 2D motion platform,users can achieve a natural locomotion experience in a limited physical *** a small-scale 2D motion platform,an ideal situation is that the velocity of the platform can always be synchronized with the user's actual intended velocity,so that the user's center of mass is kept at the center of the *** puts a brand new requirement on the performance of the platform *** paper designs an acceleration-level state feedback controller for the small-scale 2D motion *** the user's intended acceleration as an external disturbance,it is estimated by introducing a disturbance state observer;for the user' s velocity on the platform,a linear state observer is used to estimate it;then takes the estimated values as feedforward terms to compensate the *** with the HCMK1 2D motion platform,we implemented the controller and verified it to be *** recording the data of the user walking along the circle and the square trajectory,it was verified that the designed controller has good control performance for the user's motion and the state observers a great performance to quickly track the user's intended acceleration and the user's velocity on the platform.

关键词： Virtual Reality Nature Locomotion Interface State Observer 2D-Motion Platform

来源：评论

学校读者我要写书评

暂无评论

Modified Deep Deterministic Policy Gradient Based Optimal Speed Tracking Strategy for PMSMs 13

Modified Deep Deterministic Policy Gradient Based Optimal Sp...

引用

13th IEEE Data Driven control and Learning systems Conference, DDCLS 2024

作者： Fan, Zhong-Xin Tang, Lintao Li, Shihua Liu, Rongjie School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China Florida State University Department of Statistics TallahasseeFL32304 United States

ISBN: (纸本)9798350361674

Achieving optimal speed regulation for permanent magnet synchronous motors (PMSMs) remains a challenging task, particularly in selecting the most suitable controller to meet desired objectives. This paper considers the optimal speed tracking problem of PMSMs. We employ a reinforcement learning algorithm to obtain optimal controller with a linear form. The reinforcement learning approach incorporates a critic-actor network structure, which approximates the value function and optimal control, respectively. Specifically, a weight updating method for the critic network is introduced, where the update of the actor network is guided by the critic network. Through data collection and neural network training, dynamic acquisition of the optimal controller gain is achieved. In addition, a novel activation function is implemented in the network, leading to improved control performance concerning dataset size and reduced training time. At final, a real-world PMSM application is presented along with comparisons to demonstrate effectiveness. The desire idea of resulting optimal controllers is not only applicable to linear systems but also capable of approximating arbitrary nonlinear optimal controllers, thus offering practical engineering versatility. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Dynamic Multi-Person Mesh Recovery from Uncalibrated Multi-View Cameras

arXiv

引用

arXiv 2021年

作者： Huang, Buzhen Shu, Yuan Zhang, Tianshu Wang, Yangang Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China

Dynamic multi-person mesh recovery has been a hot topic in 3D vision recently. However, few works focus on the multi-person motion capture from uncalibrated cameras, which mainly faces two challenges: the one is that inter-person interactions and occlusions introduce inherent ambiguities for both camera calibration and motion capture;The other is that a lack of dense correspondences can be used to constrain sparse camera geometries in a dynamic multi-person scene. Our key idea is incorporating motion prior knowledge into simultaneous optimization of extrinsic camera parameters and human meshes from noisy human semantics. First, we introduce a physics-geometry consistency to reduce the low and high frequency noises of the detected human semantics. Then a novel latent motion prior is proposed to simultaneously optimize extrinsic camera parameters and coherent human motions from slightly noisy inputs. Experimental results show that accurate camera parameters and human motions can be obtained through one-stage optimization. The codes will be publicly available at https://***. Copyright © 2021, The Authors. All rights reserved.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

A Robust Traffic Driver Face Detection Method

A Robust Traffic Driver Face Detection Method

引用

2016 IEEE International Conference on Progress in Informatics and Computing

作者： Dechao Luo Xiaobo Lu Changhui Hu Xiang Peng Wei Wang School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education

Face detection technology is a hot topic in the past recent years. It has been maturely applied to many practical areas. However, the driver face detection is still an open problem to solve. In this paper, we proposed an improved method to promote the face detection rate and apply it to the images from the monitoring videos. The first step is to detect the car from the images according to an off-line learning method. Then the method based on additional off-line learning method is the front level for skin color feature in order to correctly detect the driver face. The proposed systems are implemented on the various complicated road environment. The results show that the proposed method improves the efficiency of the driver face detection and is of strong robustness on having glasses, driver head rotation, and lighting change.

关键词： car detection driver face detection skin color feature Haar-like feature Adaboost

来源：评论

学校读者我要写书评

暂无评论

Nonsingular Terminal Sliding Mode control for Fuel Quantity Actuator System Using High-order Sliding Mode Observer

Nonsingular Terminal Sliding Mode Control for Fuel Quantity ...

引用

第三十八届中国控制会议

作者： Jianpei Hu Hao Sun Shihua Li School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education

Fuel quantity actuator can directly control fuel injection quantity of the diesel engine, so it is the main component of the electronic distribution pump. In this paper, a position tracking problem for fuel quantity actuator system under the influence of disturbances and system uncertainties is studied via a high-order sliding mode observer(HOSMO) based nonsingular terminal sliding mode control(NTSMC) approach. The proposed finite-time NTSMC method integrates the lumped disturbance estimation information estimated by the HOSMO into the designed control law, and realizes the finite time tracking performance under the influence of disturbances and uncertainties. The simulation results show the effectiveness of the proposed method.

关键词： Lumped Disturbances Fuel Quantity Actuator Non-singular Terminal Sliding Mode control(NTSMC) High-order Sliding Mode Observer(HOSMO)

来源：评论

学校读者我要写书评

暂无评论

Research on Vibration Suppression for Industrial Robots Based on Dynamic Feedforward control

Research on Vibration Suppression for Industrial Robots Base...

引用

第43届中国控制会议

作者： Bin Huang Yahui Gan Fang Fang Bo Zhou Xianzhong Dai School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

To address the challenges of low position tracking accuracy and high vibrations in mechanical arms controlled by PID closed-loop systems, this paper introduces a torque feedforward control scheme based on dynamic models. The paper initially analyzes the causes of vibrations during robot motion, establishing a mathematical model to quantify the trajectory accuracy and repeatability of vibrations. Subsequently, a torque feedforward control scheme based on dynamic models is designed, and its feasibility is theoretically analyzed. In this motion control scheme, precise dynamic models are utilized to calculate and output the desired torque. The torque values are then converted into motor current values, which are superimposed on the control output of the current loop in the servo to achieve real-time torque compensation. Finally, through simulation experiments, the paper validates that the dynamics-based torque feedforward control effectively suppresses robot vibrations, enhances tracking accuracy,and improves dynamic performance. The findings demonstrate the efficacy of the proposed control strategy in addressing the challenges associated with PID-controlled robotic arm systems.

关键词： Industrial robots feedforward control vibration suppression

来源：评论

学校读者我要写书评

暂无评论

Model Prediction Based Adaptive Variable Impedance control of Manipulator with Passivity

Model Prediction Based Adaptive Variable Impedance Control o...

引用

第43届中国控制会议

作者： Yang Xiao Wenbo Liu Shihua Li School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Aiming at the compliance control of rigid manipulators in human-robot interaction scenarios, a new variable impedance control(VIC) model is proposed to improve the adaptive ability of the manipulator to adjust compliance in different phases of the task. The parameter selection problem is transformed into a controller design problem. Impedance constraints are set by introducing the prior knowledge of the person, information about the state and contact force, and manipulability. The one-step model predictive control(MPC) method is used to search for the optimal solution of impedance parameters, so that the manipulator can adaptively select different balance relations between tracking accuracy and compliance. Moreover, in order to avoid the damage of time-varying impedance parameters to the stability, a tank-based method is implemented to ensure the passivity of the impedance system. Finally, the simulation results verify the effectiveness of the proposed control scheme.

关键词： Variable Impedance control(VIC) Model Predictive control(MPC) Tank-based method Passivity

来源：评论

学校读者我要写书评

暂无评论

Finite-time disturbance Observer Based Active Anti-disturbance control for Disturbed Inverted Pendulum System

Finite-time disturbance Observer Based Active Anti-disturban...

引用

第40届中国控制会议

作者： Xueying Lu Huazhou Hou Shihua Li School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education

The balance control problem of disturbed inverted pendulum systems is *** of the existing advanced control methods for disturbed inverted pendulum systems are developed only to suppress constant or bounded *** results in a degradation of system performance when meeting severe *** this end,a finite-time disturbance observer is developed to estimate time-varying ***,an integral terminal sliding mode controller is designed for the inverted pendulum *** on the finite-time disturbance observer and the integral terminal sliding mode technique,a composite controller with finite-time convergence is proposed,which rejects the time-varying disturbances and alleviates the *** simulation results on the inverted pendulum system are presented to demonstrate the advantage and effectiveness of the proposed method.

关键词： Anti-disturbance Finite-time Disturbance Observer Integral Terminal Sliding Mode control

来源：评论

学校读者我要写书评

暂无评论

Nonsingular Terminal Sliding Mode control for PMSM Servo System Based on Backlash Compensation and High-order Sliding Mode Observer

Nonsingular Terminal Sliding Mode Control for PMSM Servo Sys...

引用

第32届中国控制与决策会议

作者： Jianwei Gui Lu Zhang Shihua Li Xiangyu Wang School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education

In this paper,the permanent magnet synchronous motor（PMSM） servo system with backlash is *** the mechanical transmission of the servo system uses gears,screw rods,on the one hand,the proper backlash can ensure the normal operation of the transmission mechanism;on the other hand,the existence of backlash nonlinearity will reduce the rigidity of the transmission mechanism,affect the tracking performance of the system,and even lead to mechanical *** order to eliminate the influence of the backlash nonlinearity,the modeling and identification of the backlash nonlinearity are introduced,and the influence of the backlash is compensated in the *** addition,in order to reject the possible model deviation and uncertain interference,reduce steady states fluctuations,a high-order sliding mode observer（HOSMO） based nonsingular terminal sliding mode control（NTSMC） is *** simulation verification,the compound controller proposed in this paper can effectively reduce the influence of the backlash nonlinearity and improve the position tracking performance of the system.

关键词： Permanent Magnet Synchronous Motor（PMSM） Servo System Backlash Nonsingular Terminal Sliding Mode control（NTSMC） High-order Sliding Mode Observer（HOSMO）

来源：评论

学校读者我要写书评

暂无评论

Smoky Vehicle Detection Algorithm Based On Improved Transfer Learning

Smoky Vehicle Detection Algorithm Based On Improved Transfer...

引用

International Conference on systems and Informatics (ICSAI)

作者： Guangming Zhang Dexiong Zhang Xiaobo Lu Yichao Cao Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China

ISBN: (数字)9781728152561

ISBN: (纸本)9781728152578

With the demand for pollution prevention has increased. Establishing a smoky vehicle inspection and evidence collection system will help to supervise the problem of excessive emissions of vehicles. Because the sample in the training data set is insufficient and unbalanced, the existing methods cannot obtain sufficient classification accuracy in the classification task of the smoky vehicle. This paper uses the transfer learning method to compare the effects of smoky car classification tasks on the five basic networks of DenseNet, NasNet, Inception, VGG19, MobileNet. In addition, for the classification task of the smoke vehicle, it is necessary to consider both the global information of the tail of the vehicle and the detailed information of the smoke area. In this paper, the global average pooling layer is changed to the spatial pyramid pooling layer, and it has achieved better results. Finally, the classification Precision nearly 0.1, Recall 0.3 are obtained, which is much better than the traditional classification method and the shallow non-transfer deep learning method.

关键词： Informatics

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：