检索结果-内蒙古大学图书馆

An approach to the bio-inspired control of self-reconfigurable robots 1

12th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2017

作者： Bie, Dongyang Gutiérrez-Naranjo, Miguel A. Zhao, Jie Zhu, Yanhe State Key Laboratory of Robotics and System Harbin Institute of Technology HarbinHeilongjiang China Department of Computer Science and Artificial Intelligence University of Seville Seville Spain

ISBN: (数字)9789811071799

ISBN: (纸本)9789811071782

Self-reconfigurable robots are robots built by modules which can move in relationship to each other. This ability of changing its physical form provides the robots a high level of adaptability and robustness. Given an initial configuration and a goal configuration of the robot, the problem of self-regulation consists on finding a sequence of module moves that will reconfigure the robot from the initial configuration to the goal configuration. In this paper, we use a bio-inspired method for studying this problem which combines a cluster-flow locomotion based on cellular automata together with a decentralized local representation of the spatial geometry based on membrane computing ideas. A promising 3D software simulation and a 2D hardware experiment are also presented. © Springer Nature Singapore Pte Ltd 2017.

关键词： Modular robots

来源：评论

学校读者我要写书评

暂无评论

Joint learning of discriminative low-dimensional image representations based on dictionary learning and two-layer orthogonal projections

arXiv

引用

arXiv 2019年

作者： Wei, Xian Shen, Hao Li, Yuanxiang Tang, Xuan Jin, Bo Zhao, Lijun Murphey, Yi Lu Fujian Institute of Research on the Structure of Matter Chinese Academy of Sciences China Technical University of Munich Germany and fortiss GmbH Munich Germany Shanghai Key Lab for Trustworthy Computing School of Computer Science and Software Engineering East China Normal University China School of Aeronautics & Astronautics Shanghai Jiao Tong University Shanghai200240 China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150006 China Department of Electrical and Computer Engineering University of Michigan-Dearborn DearbornMI48128 United States

This work investigates the problem of efficiently learning discriminative low-dimensional representations of multi-class large-scale image objects. We propose a generic deep learning approach by taking advantages of Convolutional Neural Networks (CNN), sparse dictionary learning, and orthogonal projections. CNN is not only powerful on feature extraction, but also robust to spatial variance and changes. Sparse dictionary learning is well known for disentangling nonlinear underlying discriminative factors in data. The orthogonal projection is a notable efficient tool to project multi-class data onto low dimensional discriminative subspace. The proposed procedure can be summarized as follows. At first, a CNN is employed to extract high-dimensional (HD) preliminary convolutional features. Secondly, to avoid the high computational cost of direct sparse coding on HD CNN features, we present to learn sparse representation (SR) in an orthogonal projected space over a task-driven sparsifying dictionary. We then exploit the discriminative projection on SR. The whole learning process is treated as a joint optimization problem of trace quotient maximization, which involves the CNN parameters, the orthogonal projection on CNN features, the dictionary and the discriminative projection on sparse codes. The related cost function is well defined on product manifold of the Stiefel manifold, the Oblique manifold, and the Grassmann manifold. It is optimized via a geometrical stochastic gradient descent algorithm. Finally, the quality of dictionary and projections learned by the proposed approach is further investigated in terms of image classification. The experimental results show that the approach can achieve a strongly competitive performance with state-of-the-art image classification methods. Copyright © 2019, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Quantification of Cell Adhesion Force with Atomic Force Microscope

Quantification of Cell Adhesion Force with Atomic Force Micr...

引用

2017 2nd International Conference on Materials Science,Machinery and Energy Engineering(MSMEE 2017)

作者： CHEN Sheng XIE Hui State Key Laboratory of Robotics and System Harbin Institute of Technology

Cell adhesion to cells or substrates is the basis for cell colonization and survival. Based on atomic force microscope(AFM), a single probe was used to quantitatively measure the adhesion of different cell types. The self-made pneumatic control system produces negative pressure to fix the cells, replacing the traditional chemical fixation method, reducing the fixation time from about 30 min to a few seconds, and a single probe can test about 15 cells, greatly improving single-cell force spectroscopy test speed. As a result, statistical data can be quickly recorded, the range of cells tested can be expanded, and the physiological activity of the cells during the test is preserved. In this paper, we studied the adhesion of three different mammalian cells to polystyrene substrates, and indicated that the adhesion forces depend on the probe retraction speed and the contact time: the adhesion forces are proportional to the logarithm of the probe retraction speed and increase with increasing contact time.

关键词： atomic force microscope probe single-cell force spectroscopy adhesion force

来源：评论

学校读者我要写书评

暂无评论

Design of a Soft Robot with Multiple Motion Patterns Using Soft Pneumatic Actuators

Design of a Soft Robot with Multiple Motion Patterns Using S...

引用

The 4th Advanced Materials,Mechanics and Structural Engineering Conference(AMMSE 2017)

作者： Yu Miao Wei Dong Zhijiang Du State Key Laboratory of Robotics and System Harbin Institute of Technology

ISBN: (纸本)9781510852686

Soft robots are made of soft materials and have good flexibility and infinite degrees of freedom in theory. These properties enable soft robots to work in narrow space and adapt to external environment. In this paper, a 2-DOF soft pneumatic actuator is introduced, with two chambers symmetrically distributed on both sides and a jamming cylinder along the axis. Fibers are used to constrain the expansion of the soft actuator. Experiments are carried out to test the performance of the soft actuator,including bending and elongation characteristics. A soft robot is designed and fabricated by connecting four soft pneumatic actuators to a 3 D-printed *** soft robotic system is then established. The pneumatic circuit is built by pumps and solenoid valves. The control system is based on the control board Arduino Mega 2560. Relay modules are used to control valves and pressure sensors are used to measure pressure in the pneumatic circuit. Experiments are conducted to test the performance of the proposed soft robot.

关键词： Design of a Soft Robot with Multiple Motion Patterns Using Soft Pneumatic Actuators

来源：评论

学校读者我要写书评

暂无评论

Design and Dynamic Simulation of a Wide-Range Binocular Head-Eye Platform

Design and Dynamic Simulation of a Wide-Range Binocular Head...

引用

2017 International Conference on Advances in Materials,Machinery,Electrical Engineering(AMMEE 2017)

作者： Jihong Yan Rufei Cai State Key Laboratory of Robotics and System Harbin Institute of Technology

ISBN: (纸本)9781510842915

Binocular head-eye platform is mainly used in the recognition of active objects, and can quickly and flexibly achieve a wide-range image information collection. The existing binocular head-eye platform usually uses small camera with fixed focus lens to obtain image information, so there are some problems, such as close target distance, narrow view, small motion range and etc. For these reasons, this paper presents a new type of binocular head-eye platform. The 7-dof head-eye platform has long target distance, wide-range view, large motion range and high speed performance for zoom lens camera and series parallel hybrid mechanism. Monocular mechanism has enough stiffness to ensure the high-speed movement of heavy payload, due to the parallel design. For motion control, kinematics solution is solved by DH parameter method and analytical method. DH parameter method is easy to establish the coordinate transformation relation. And analytical method can obtain accurate mathematical expressions. To verify the rationality and feasibility of the platform, dynamic simulation is carried out by software ADAMS, while achieving its performance specification in three axes.

关键词： Head-Eye Platform Binocular Mechanism W ide-Range Object Recognition Dynamic Simulation

来源：评论

学校读者我要写书评

暂无评论

Robust Scalable Part-Based Visual Tracking for UAV with Background-Aware Correlation Filter

Robust Scalable Part-Based Visual Tracking for UAV with Back...

引用

IEEE International Conference on robotics and Biomimetics

作者： Changhong Fu Yinqiang Zhang Ran Duan Zongwu Xie School of Mechanical Engineering Tongji University Shanghai China Interdisciplinary Division of Aeronautical and Aviation Engineering Hong Kong Polytechnic University HKSAR China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin China

ISBN: (纸本)9781728103785;9781728103778

Robust visual tracking for the unmanned aerial vehicle (UAV) is a challenging task in different types of civilian UAV applications. Although the classical correlation filter (CF) has been widely applied for UAV object tracking, the background of the object is not learned in the classical CF. In addition, the classical CF cannot estimate the object scale changes, and it is not able to cope with object occlusion effectively. Part-based tracking approach is often used for the visual tracker to solve the occlusion issue. However, its real-time performance for the UAV cannot be achieved due to the high cost of object appearance updating. In this paper, a novel robust visual tracker is presented for the UAV. The object is initially divided into multiple parts, and different background-aware correlation filters are applied for these divided object parts, respectively. An efficient coarse-to-fine strategy with structure comparison and Bayesian inference approach is proposed to locate object and estimate the object scale changes. In addition, an adaptive threshold is presented to update each local appearance model with a Gaussian process regression method. Qualitative and quantitative tests show that the presented visual tracking algorithm reaches real-time performance (i.e., more than twenty frames per second) on an i7 processor with 640×360 image resolution, and performs favorably against the most popular state-of-the-art visual trackers in terms of robustness and accuracy. To the best of our knowledge, it is the first time that this novel scalable part-based visual tracker is presented, and applied for the UAV tracking applications.

关键词： Visualization Correlation Target tracking Unmanned aerial vehicles Object tracking Real-time systems Robustness

来源：评论

学校读者我要写书评

暂无评论

A Relative Localization Method Based on Encoders and Micro-inertial system

A Relative Localization Method Based on Encoders and Micro-i...

引用

2017 2nd International Conference on Mechatronics, Control and Automation Engineering (MCAE2017)

作者： Hao-yue YAN Hui ZHANG Jin-zhong YUE Jun-hong JI State Key Laboratory of Robotics and System Harbin Institute of Technology

Odometer is used to measure the distance that the wheels rolled when the robot is moving and can be replaced by the motor encoders. But when the wheel comes to idling or skid, there will be errors. Idling or skid generally occurs in the turning process where the information of inertia sensors is required to correct the localization. In this paper, we discuss a relative localization method to keep small error during a relatively long time without using external sensors. The initial alignment is used to reduce the error caused by inclination of the ground. The Kalman filter algorithm which is used to fuse the odometer and micro-inertial system information are proposed to reduce the relative positioning error.

关键词： Relative localization Encoder Micro-inertial system Initial alignment

来源：评论

学校读者我要写书评

暂无评论

Singularity-Robust Hybrid Visual Servoing Control for Aerial Manipulator

Singularity-Robust Hybrid Visual Servoing Control for Aerial...

引用

IEEE International Conference on robotics and Biomimetics

作者： Fengyu Quan Haoyao Chen Yanjie Li Yunjiang Lou Jian Chen Yunhui Liu School of Mechanical Engineering and Automation State Key Laboratory of Robotics and System China State Key Laboratory (SKL) of PhotoVoltaic Science and Technology (PVST) Trinasolar Co. Ltd Changzhou Jiangsu P.R. China Department of Mechanical and Automation Engineering Chinese University of Hong Kong Hong Kong P. R. China

ISBN: (纸本)9781728103785;9781728103778

Control of aerial manipulation has attracted increasing attention in robotics these years. It is still a challenge to precisely control the manipulator under the influence of dynamical motion coupling between the aerial platform and manipulator. In this paper we develop a hybrid visual servoing approach for aerial manipulators to complete aerial manipulations. The hybrid controller integrates both advantages of the image-based and position-based visual servoing controllers; it ensures the target features staying in the field of view as well as guaranteeing the global convergence of error. Furthermore, to address the singularity problem existing in the flexible aerial manipulator, a SVD-based variant damped least square solution is developed. Experiments are performed on a custom-built aerial manipulator which consists of a 6-DoF serial manipulator and a coaxial octocopter. The experimental results have illustrated the effectiveness of the proposed approach.

关键词： Manipulator dynamics Cameras Visual servoing End effectors Kinematics Convergence

来源：评论

学校读者我要写书评

暂无评论

Multimaterials: Microtopography-Guided Radial Gradient Circle Array Film with Nanoscale Resolution (Small 50/2019)

引用

Small 2019年第50期15卷

作者： Fengqiang Zhang Changhai Li Jia Zhang Zhenlong Wang Key Laboratory of Microsystems and Microstructures Manufacturing Ministry of Education Harbin Institute of Technology No. 2 Yikuang Street Harbin 150080 China State Key Laboratory of Robotics and System Harbin Institute of Technology No. 2 Yikuang Street Harbin 150080 China

来源：评论

学校读者我要写书评

暂无评论

Transporting trajectory optimization method for large space manipulator system

引用

Hangkong Xuebao/Acta Aeronautica et Astronautica Sinica 2018年 39卷

作者： Jie, Dangyang Lu, Haoran Wu, Hanling Ni, Fenglei Beijing Institute of Aerospace System Engineering Beijing100076 China State Key Laboratory of Robotics and Systems Harbin150001 China

The large space manipulator which is assembled on the space station will bring attitude reactions to the space station in moving or assembling tens of tons objects process. To resolve this problem, a new Cartesian trajectory optimization method was proposed. The attitude disturbance control of base is realized by using the decomposition and velocity control and optimization algorithm based on the Generalized Jacobian Matrix (GJM). An objective function was established for measuring the variation of the space station attitude. Based on the consideration of the joints angle and the influence of dynamic singularity. By using Particle Swarm Optimization (PSO) method for the objective function, the attitude influence on space station was reduced significantly. The validity of the algorithm was verified by simulation results. © 2018, Press of Chinese Journal of Aeronautics. All right reserved.

关键词： Trajectories

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：