检索结果-内蒙古大学图书馆

IEEE International Conference on robotics and Biomimetics

作者： Chunyuan Shi Zixin Wang Dapeng Yang Jingdong Zhao State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin China Artificial Intelligence Laboratory Harbin Institute of Technology Harbin China

ISBN: (纸本)9781665481106

In this paper, an augmented reality-based perceptual feedback method of dexterous prosthesis has been proposed, which can establish an intuitive and convenient feedback pathway and reduce the use load of prosthetic hands. The proprioception and force feedback strategy was proposed and established based on augmented reality technology. Finally, the effectiveness and feasibility of the above strategies are verified by experiments. First, the feasibility of the proprioception feedback strategy is tested, and then the force feedback strategy is tested. The experimental results show that the proposed method establishes an effective perceptual feedback closed-loop control, improving patients' cognition of the prosthesis, including force, grasping gestures and other information, and improving users' perception ability.

关键词： Visualization Biomimetics Force feedback Force Grasping Cognition Prosthetic hand

来源：评论

学校读者我要写书评

暂无评论

Cable Length Estimation for a Hyper-Redundant Robot Based on Cable Hole Clearance Calculation

Cable Length Estimation for a Hyper-Redundant Robot Based on...

引用

IEEE International Conference on Automation Science and Engineering (CASE)

作者： Ziqing Li Jiangqin Deng Yang Zheng Chao Liu Guoying Gu Robotics Institute School of Mechanical Engineering Shanghai Jiao Tong University Shanghai China State Key Laboratory of Mechanical System and Vibration Shanghai Jiao Tong University Shanghai China

For the cable-driven hyper-redundant robot, most of the current drive cable length estimation methods consider that the cable always passes through the center of the hole, and do not consider the effect of cable-hole clearance, resulting in a large motion error. In this paper, we propose a cable length estimating method by considering cable-hole clearance. Based on the simplified space model of the cable hole, it uses the recursive algorithm to obtain the approximate solution of the actual drive cable length. The algorithm can meet the requirements of real-time control while ensuring calculation accuracy. The correctness of the approximate solution is verified by using the interior point penalty function method. Taking a 24DoF hyper-redundant manipulator with joint angle closed-loop control as an example, the effectiveness of the proposed method is proved by comparing the theoretical calculation results with the actual drive cable length.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Energetic Approach to Task-Invariant Ankle Exoskeleton Control

An Energetic Approach to Task-Invariant Ankle Exoskeleton Co...

引用

IEEE/RSJ International Conference on Intelligent Robots and systems (IROS)

作者： Katharine Walters Gray C. Thomas Jianping Lin Robert D. Gregg The Department of Robotics University of Michigan Ann Arbor MI USA The State Key Laboratory of Mechanical System and Vibration School of Mechanical Engineering Shanghai Jiao Tong University Shanghai China

Robotic ankle exoskeletons have been shown to reduce human effort during walking. However, existing ankle exoskeleton control approaches are limited in their ability to apply biomimetic torque across diverse tasks outside of the controlled lab environment. Energy shaping control can provide task-invariant assistance without estimating the user's state, classifying task, or reproducing pre-defined torque trajectories. In previous work, we showed that an optimally task-invariant energy shaping controller implemented on a knee-ankle ex-oskeleton reduced the effort of certain muscles for a range of tasks. In this paper, we extend this approach to the sensor suite available at the ankle and present its implementation on a commercially-available, bilateral ankle exoskeleton. An experiment with three healthy subjects walking on a circuit and on a treadmill showed that the controller can approximate biomimetic profiles for varying terrains and task transitions without classifying tasks or switching control modes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Aerial Non-contact Detection system For Quayside Crane Using A Hexacopter

An Aerial Non-contact Detection System For Quayside Crane Us...

引用

IEEE International Conference on Real-time Computing and robotics (RCAR)

作者： Yehui Zhang Zhaoying Wang Wei Dong State Key Laboratory of Mechanical System and Vibration Shanghai Jiao Tong University Shanghai China Robotics Institute School of Mechanical Engineering Shanghai Jiao Tong University Shanghai China

In recent years, aerial robots have been widely used and developed in high-altitude defect detection in academia and business. To solve the detection problem of beams at quayside cranes, reduce the cost of staffing in the traditional manual detection process and improve detection safety, a non-contact detection system using a hexacopter is designed. This article analyzes the task requirements of flaw detection for quayside cranes and the workflow. The Unmanned Aerial Vehicle (UAV) system is equipped with a non-contact detective transmitter, a non-contact detective imaging plate and other task detection equipment to detect the crack of quayside crane beams. The system is based on multi-sensor modules. Besides, the system is designed as light as possible to increase the flight endurance of the UAV. On this basis, the system takes the UAV as the carrier and carries the detection equipment to the location which needs detection. At the same time, people on the ground can control the non-contact detective transmitter and imaging plate to move to the defect area through remote radio control, then can obtain the internal crack. The reliability and effectiveness of the whole system are verified by performing an actual detection experiment with a crane model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-Time Deformation Simulation of Kidney Surgery Based on Virtual Reality

引用

Journal of Shanghai Jiaotong university(Science) 2021年第3期26卷 290-297页

作者： JING Mengjie CUI Zhixin FU Hang CHEN Xiaojun Institute of Biomedical Manufacturing and Life Quality Engineering State Key Laboratory of Mechanical System and VibrationSchool of Mechanical EngineeringShanghai Jiao Tong UniversityShanghai200240China Institute of Medical Robotics Shanghai Jiao Tong UniversityShanghai200240China

Virtual reality-based surgery simulation is becoming popular with the development of minimally invasive abdominal surgery,where deformable soft tissue is modelled and *** mass-spring model(MSM)and finite element method(FEM)are common methods used in the simulation of soft tissue ***,MSM has an issue concerning accuracy,while FEM has a problem with *** achieve higher accuracy and efficiency at the same time,we applied a co-rotational FEM in the simulation of a kidney with a tumour inside,achieving a real-time and accurate deformation *** addition,we set a multi-model representation for mechanical simulation and visual *** implicit Euler method and conjugate gradient method were adopted for setting and solving the linear *** a realistic simulation of surgery,constraints outside the kidney and between the kidney and tumour were set with two series of mechanical properties for the two *** were conducted to validate the accuracy and real-time performance.

关键词： computer-assisted surgery virtual reality real-time simulation finite element method(FEM) corotation FEM

来源：评论

学校读者我要写书评

暂无评论

YOWOv2: A Stronger yet Efficient Multi-level Detection Framework for Real-time Spatio-temporal Action Detection

arXiv

引用

arXiv 2023年

作者： Yang, Jianhua Dai, Kun The State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150001 China Wuhu Robot Industry Technology Research Institute Harbin Institute of Technology Wuhu241000 China

Designing a real-time framework for the spatiotemporal action detection task is still a challenge. In this paper, we propose a novel real-time action detection framework, YOWOv2. In this new framework, YOWOv2 takes advantage of both the 3D backbone and 2D backbone for accurate action detection. A multi-level detection pipeline is designed to detect action instances of different scales. To achieve this goal, we carefully build a simple and efficient 2D backbone with a feature pyramid network to extract different levels of classification features and regression features. For the 3D backbone, we adopt the existing efficient 3D CNN to save development time. By combining 3D backbones and 2D backbones of different sizes, we design a YOWOv2 family including YOWOv2-Tiny, YOWOv2-Medium, and YOWOv2-Large. We also introduce the popular dynamic label assignment strategy and anchor-free mechanism to make the YOWOv2 consistent with the advanced model architecture design. With our improvement, YOWOv2 is significantly superior to YOWO, and can still keep real-time detection. Without any bells and whistles, YOWOv2 achieves 87.0% frame mAP and 52.8% video mAP with over 20 FPS on the UCF101-24. On the AVA, YOWOv2 achieves 21.7% frame mAP with over 20 FPS. Our code is available on https://***/yjh0410/YOWOv2. Copyright © 2023, The Authors. All rights reserved.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Iterative learning control of trajectory tracking of robot manipulator based the SoC platform integrated motor drive and motion control 10

Iterative learning control of trajectory tracking of robot m...

引用

10th International Conference on Power Electronics, Machines and Drives, PEMD 2020

作者： Sun, Yongping Yang, Ming Chen, Yangyang Ni, Qinan Xu, Dianguo State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin China

ISBN: (纸本)9781839535635

With the development of SoC technology, the integration of FPGA+ARM has become the development direction of SoC. For the characteristics of integrated multi-axis motion control and motor drive, this paper selects Xilinx ZYNQ-7020 system-on-chip (SOC) with integrated dual-core ARM CPU and FPGA as the hardware platform control chip, an arm core motor drive algorithm. Another ARM core completes the interactive function and motion control, and the FPGA to complete the multi-axis hardware current loop and improve the system bandwidth. The iterative learning control (ILC) technology is widely used in robots to reduce the trajectory error of robots performing repetitive tasks. Using P-type iterative learning ILC combined with feedback control, which can compensate for nonrepeating disturbance. Finally, analysis of experimental results shows that iterative learning control combined with feedback control can significantly improve tracking accuracy. © PEMD *** right reserved.

关键词： Two term control systems

来源：评论

学校读者我要写书评

暂无评论

Comparative study of voltage source inverter nonlinearity compensation using different signal information for table look up in PMSM drives 10

Comparative study of voltage source inverter nonlinearity co...

引用

10th International Conference on Power Electronics, Machines and Drives, PEMD 2020

作者： Long, Jiang Yang, Ming Chen, Yangyang Ni, Qinan Xu, Dianguo State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin China

ISBN: (纸本)9781839535635

The inverter nonlinearity compensation has been studied by the researchers widely, however, due to the poor polarity detection ability of the discrete control system and unavoidable noises from current feedback, unideal compensation happens when the motor speed is low and the load is small. In order to tackle with this problem. This paper presents an inverter nonlinearity compensation method in permanent magnet synchronous motor (PMSM) drives. The overall process is achieved by voltage signal injection, the only requirements are stator resistance and the maximum current of a given motor. The corresponding voltage errors are saved in look up table (LUT) and being used together with field-oriented control (FOC). In addition, a comparative study when using phase current feedback, phase current reference and phase voltage reference for compensation voltages look-up in the already established LUT is conducted. A 750-W voltage-source inverter PMSM drive controlled by the FOC algorithm is used for experiment verification, the results show that the phase current reference is the most proper signal for compensation voltages look-up, especially around the current zero-crossing condition. The comparative study in this paper can be easily applied in the real industrial application with no hardware introduction and very little algorithm change. © PEMD *** right reserved.

关键词： Table lookup

来源：评论

学校读者我要写书评

暂无评论

Dynamic Visual SLAM Based on Semantic Information and Multi-View Geometry 5

Dynamic Visual SLAM Based on Semantic Information and Multi-...

引用

5th International Conference on Automation, Control and robotics Engineering, CACRE 2020

作者： Shi, Junyi Zha, Fusheng Guo, Wei Wang, Pengfei Li, Mantian Harbin Institute of Technology State Key Laboratory of Robotics and System Harbin China

ISBN: (纸本)9781728198880

Visual Simultaneous Localization and Mapping (Visual SLAM) is considered to be one of the important foundations for mobile robots to move toward intelligence, which gives robots the ability to autonomously locate and construct maps in an unknown environment. In the past decades, great progress has been made in the field of visual SLAM, relatively mature algorithm system and program architecture are gradually developed. However, the current researches on visual SLAM mostly assume that the surrounding environment is static, which greatly limits the application of SLAM systems in real world. Aiming at the urgent need of mobile robots for precise localization and map construction in dynamic environment, methods are proposed in this paper. Image semantic segmentation based on deep learning and multi-view geometry methods are combined to recognize and segment moving objects. Only background features are used for camera tracking to avoid the impact of moving objects. Furthermore, an experimental platform is built using RGB-D camera and motion capture device, the effectiveness of the algorithm is verified by public datasets and real scene data. © 2020 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A RCDNet for outdoor unmanned sweeping vehicles based on graph convolutional network

A RCDNet for outdoor unmanned sweeping vehicles based on gra...

引用

第33届中国控制与决策会议

作者： Dianyong Yu Saiyingnan Bian Changan Hu Jieming Lou State Key Laboratory of Robotics and System Harbin Institute of Technology

This paper proposes a graph convolutional network for road curb point detection(RCDNet) which converts road curb point detection into a point cloud segmentation *** input of the network comes from the point cloud below the segmented road ***,the point cloud enters a permutation network to ensure that the spatial permutability of the point cloud remains *** a neighbor number k is given,and k neighbor points of each point are calculated through the xyz attribute of the point *** k neighbor points used as the local features of the point are fused with the xyz attributes of the point to construct the edge *** convolving the edge features to extract higher-level point cloud spatial *** this method of fusion of local features and global features,more local information of the point cloud can be obtained,so that the network can segment the three-dimensional point cloud with higher accuracy.

关键词： Graph convolution Point cloud Local features RCDNet

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：