检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Li, Jianing Chen, Bowen Wang, Zhiyong Liu, Honghai School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen State Key Laboratory of Robotics and System Harbin Institute of Technology China

Given an untrimmed video, repetitive actions counting aims to estimate the number of repetitions of class-agnostic actions. To handle the various length of videos and repetitive actions, also optimization challenges in end-to-end video model training, down-sampling is commonly utilized in recent state-of-the-art methods, leading to ignorance of several repetitive samples. In this paper, we attempt to understand repetitive actions from a full temporal resolution view, by combining offline feature extraction and temporal convolution networks. The former step enables us to train repetition counting network without down-sampling while preserving all repetition regardless of the video length and action frequency, and the later network models all frames in a flexible and dynamically expanding temporal receptive field to retrieve all repetitions with a global aspect. We experimentally demonstrate that our method achieves better or comparable performance in three public datasets, i.e., TransRAC, UCFRep and QUVA. We expect this work will encourage our community to think about the importance of full temporal *** Codes 68 © 2023, CC BY-NC-ND.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Dynamic Drive Chain Error Analysis of Industrial Robots with Cyber Sensing Technology

Dynamic Drive Chain Error Analysis of Industrial Robots with...

引用

IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent systems

作者： Meng Chen Zhi Li Shaodong Zhan Guanglie Zhang Institute of Intelligent Cyber Sensing System Shenzhen Academy of Robotics College of Computer Science and Software Engineering Shenzhen University

ISBN: (纸本)9781538604915

The drive chain error of industrial robots is one of the main effects of the robots' accuracy and repeatability. This paper presents a cyber sensing technology based dynamic drive chain error estimation method. Cyber sensing nodes are deployed on an industrial robot to monitor the vibration of robot joints while the robot is working. The dynamic drive chain error is obtained from the vibration noise signal analysis. The proposed method is validated experimentally.

关键词： Cyber sensing Industrial robot Drive chain error Health monitoring industrial robots HEALTH MONITORING Sensing Techniques robot joint Error analysis Robot

来源：评论

学校读者我要写书评

暂无评论

Stiffness analysis of the humanoid robot WABIAN-RIV: modelling

Stiffness analysis of the humanoid robot WABIAN-RIV: modelli...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： G. Carbone H. Lim A. Takanishi M. Ceccarelli Humanoid Robotics Institute Waseda University Tokyo Japan Laboratory of Robotics and MechatronicsDiMSAT University of Cassino Cassino Italy Department of System Design Engineering Kanagawa Institute of Technology Atsugi Kanagawa Japan

In this paper a humanoid robot named as WABIAN-RIV (WAseda BIpedal humANoid Refined IV) is analyzed in terms of stiffness characteristics. This paper proposes basic models and a formulation in order to deduce the stiffness matrix as a function of the most important stiffness parameters of the WABIAN architecture. The proposed formulation is useful for numerical estimation of stiffness performances.

关键词： Humanoid robots Leg Kinematics Neck Legged locomotion Shoulder Mechatronics Performance analysis Laboratories system analysis and design

来源：评论

学校读者我要写书评

暂无评论

Nonsmooth Dynamic Filtering for Mechanical Servo-systems

Nonsmooth Dynamic Filtering for Mechanical Servo-systems

引用

IEEE International Conference on Control and Automation

作者： Yonghong Tan Ruili Dong Yanyan Li Xiang Chen Hong He Department of Electrical Engineering Shanghai Normal University Institute of Robotics and Automatic Information System Tianjin Key Laboratory of Intelligent Robotics Nankai University Department of Electrical and Computer Engineering University of Windsor

ISBN: (纸本)9781509017393

In this paper, a nonsmooth dynamic filtering approach is proposed for stochastic noise filtering of mechanical servo-systems. In this approach, a stochastic nonsmooth state-space model with sandwich structure is developed to describe the nonsmooth dynamic feature of the system in random noisy case. Then, an approach for observability test of the nonsmooth system with sandwich architecture is proposed. Afterwards, a nonsmooth dynamic filtering method motivated by the structure of Kalman filter is proposed for noise suppression. The proposed nonsmooth Kalman filtering method is applied to random noise filtering of a servo-system with dead-zone feature.

关键词： CONTRAST FILTERS Servo systems noise filtering Noise suppression Kalman filters sandwich structures Models, Space Sandwiches

来源：评论

学校读者我要写书评

暂无评论

Modeling and simulating the nonlinear characters of robot joints

Modeling and simulating the nonlinear characters of robot jo...

引用

IEEE International Conference on robotics and Biomimetics

作者： Yongqiang Xiao Zhijiang Du Wei You Ruifeng Li School of Mechatronics Engineering and State Key Laboratory of Robotics and System Harbin Harbin Institute of Technology Harbin Heilongjiang China

ISBN: (纸本)9781424493197

This paper presents a new approach to establish a dynamic model of robot joints. The model is constructed by ideally dividing a robot joint into high-speed block and low-speed block and described with nonlinear characteristics such as friction, backlash and hysteresis. The friction behavior of two blocks is captured by the Generalized Maxwell-Slip model. The Preisach model is used to describe the hysteresis character of joints. Because the “congruency” assumption of hysteresis, which is needed in the Preisach model, is not strictly tenable in complex joints, so there construct the hysteresis model through Preisach model plus a nonlinear stiffness. A simple and effective method is developed to model the backlash behavior in joints. The integrated joint model of an industry robot built by our laboratory is established and simulation model is constructed in Simulink of Matlab. The validity of this model is demonstrated and a new avenue opened in this way.

关键词： Friction Solid modeling Joints Hysteresis Mathematical model Robots Force

来源：评论

学校读者我要写书评

暂无评论

Development of a biped locomotor applicable to medical and welfare fields

Development of a biped locomotor applicable to medical and w...

引用

IEEE/ASME (AIM) International Conference on Advanced Intelligent Mechatronics

作者： Hun-Ok-Lim Y. Suhara A. Takanishi Department of System Design Engineering Kanagawa Institute of Technology Atsugi Japan Humanoid Robotics Institute Waseda University Japan Department of Mechanical Engineering Waseda University

This paper describes a new leg module for biped locomotors. We have developed a biped locomotor, WL-15 (Waseda Leg 15), which is applicable to various fields, such as medical, welfare and entertainment. WL-15 consists of parallel mechanisms such as a high stiffness, high positioning accuracy and easily calculated inverse kinematics. A walking control program is created on the basis of Simulink and RT-LAB executed on Windows NT and QNX target system. Using WL-15, dynamic walking with the step time of 0.8 [sec/step] to 1.92 [s/step] and turning step of 90 is conducted, and the effectiveness of WL-15's parallel mechanisms is confirmed.

关键词： Legged locomotion Leg Control systems Kinematics Mobile robots Humans Biomedical engineering Design engineering Humanoid robots Medical robotics

来源：评论

学校读者我要写书评

暂无评论

Dynamic Object Removal of Static 3D Point-Cloud Map Building in Casualty Collection Point

Dynamic Object Removal of Static 3D Point-Cloud Map Building...

引用

International Conference on Control, Automation, robotics and Vision (ICARCV)

作者： Haidong Wang Wanlei Li Yijie Dai Xiaogang Xiong Yunjiang Lou State Key Laboratory of Robotics and System School of Mechanical Engineering and Automation Harbin Institute of Technology ShenZhen Shenzhen China

ISBN: (数字)9798331518493

ISBN: (纸本)9798331518509

Understanding the environment is crucial for the autonomous navigation of vehicles. Accurately identifying and removing dynamic objects that cause occlusions and noisy pose issues is crucial to the task. The casualty collection point (CCP) is a designated location for treating casualties during disasters. These sites are commonly located in open fields to ensure that the injured receive timely and appropriate care. Therefore, the construction of a 3D map in CCP may encounter additional challenges. In this paper, we introduces a novel algorithm that integrates a learning-based multi-object detection network with a Kalman Filter tracking framework to remove dynamic object traces from the 3D map building, particularly in CCP scenarios, and it redirects attention on the velocity attribute of dynamic objects at the object-level scale. Additionally, we contribute a new dataset specifically designed for the CCP scenario. Comparative experiments conducted on the SemanticKITTI dataset and CCP dataset show that our proposed method achieves the state-of-the-art performance in removing traces of dynamic objects on 3D Map. Dataset is available at https://***/haidongwang96/ccp_dataset.

关键词： Point cloud compression Three-dimensional displays Simultaneous localization and mapping Heuristic algorithms Buildings Object detection Kalman filters Object recognition Noise measurement Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

Personality Filter in Mobile Networks with Communication Constraints

Personality Filter in Mobile Networks with Communication Con...

引用

International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)

作者： Maya Dimitrova Anna Lekova Mo Adda Institute of System Engineering and Robotics Bulgarian Academy of Sciences Sofia Bulgaria School of Computing University of Portsmouth Portsmouth UK

A new psychological model for efficient data transmission in mobile networks under communication constrains is proposed. It accounts for user personality characteristics to determine the feasible path for packet transmission from source to target and to predict the availability of the communication resources based on dynamically determined level of node generosity. Two case studies are presented with initial performance better than chance. The model is designed for the developed framework of evolving fuzzy modeling in mobile Ad hoc networks via lightweight online unsupervised learning.

关键词： Mobile computing Filtering theory Mobile ad hoc networks Sensors Social network services Mobile communication

来源：评论

学校读者我要写书评

暂无评论

Encoderless Rotor Position Estimation of a Switched Reluctance Drive Operated under Model Predictive Control

Encoderless Rotor Position Estimation of a Switched Reluctan...

引用

International Scientific Conference on Power and Electrical engineering of Riga Technical University (RTUCON)

作者： Alecksey Anuchin Dmitry Shpak Anastasia Kotelnikova Alexey Dmitriev Andrei Bogdanov Galina Demidova Moscow Power Engineering Institute Moscow Russia Faculty of Control System and Robotics ITMO University Saint-Petersburg Russia

ISBN: (数字)9781728195100

ISBN: (纸本)9781728195117

One of the promising technologies of encoderless rotor position and speed estimation for the motors with magnetic anisotropy is the analysis of operation of model predictive control. Idea of the method is to track the difference between the prediction and actual behaviour of the motor currents which should match if the rotor position estimation is correct. However, this method was not applied for switched reluctance drive yet. This paper proposes the rotor position and speed estimator for switched reluctance motor operated under continuous control set model predictive control. It implements phase-locked loop fed by the error between the referenced current and it actual value. The estimator was examined using a simulation model and provides fast and accurate speed and position tracking.

关键词： Rotors Control systems Pulse width modulation Estimation Switches Permanent magnet motors Magnetization

来源：评论

学校读者我要写书评

暂无评论

Model Predictive Control of a Direct Current Motor Utilizing Lookup Tables

Model Predictive Control of a Direct Current Motor Utilizing...

引用

International Conference on Power Drives systems (ICPDS)

作者： Alecksey Anuchin Andrei Bogdanov Galina Demidova Dmitrii Savkin Ksenya Fedorova Maria Gulyaeva Moscow Power Engineering Institute Moscow Russia Faculty of Control System and Robotics ITMO University Saint-Petersburg Russia

ISBN: (数字)9781728165387

ISBN: (纸本)9781728165394

The problem of unpredictable acoustic behaviour of the finite control set model predictive control (MPC) can be solved in continuous control set MPC. However, continuous control set MPC usually requires huge computation efforts or analytical solution of the non-linear equations of the motor, which is not always possible. This paper considers the option of precalculation of all control commands for each combination of the input variables. This approach is applicable for the drives with limited number of state variables, such as direct current motor or switched reluctance machine. An example of the control system of direct current motor with torque stabilization and minimization of the ohmic losses was implemented using simulation model. The 4-dimensional lookup table was used for armature current control and 2-dimensional lookup table was used for field winding control. The simulation results show rapid torque stabilization together with losses minimization.

关键词： Torque Memory management Switches DC motors Control systems Minimization Predictive control

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：