检索结果-内蒙古大学图书馆

Productive multitasking for industrial robots

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wuthier, David Rovida, F. Fumagalli, M. Krüger, V. Automation and Control Department of Electrical Engineering Technical University of Denmark Elektrovej Building 326 Kgs. Lyngby2800 Denmark RiACT ApS A. C. Meyers Vænge 15 Copenhagen SV2450 Denmark Department of Computer Science Lund University Ole Römers Väg 3 Lund223 63 Sweden

The application of robotic solutions to small-batch production is challenging: economical constraints tend to dramatically limit the time for setting up new batches. Organizing robot tasks into modular software components, called skills, and allowing the assignment of multiple concurrent tasks to a single robot is potentially game-changing. However, due to cycle time constraints, it may be necessary for a skill to take over without waiting on another to terminate, and the available literature lacks a systematic approach in this case. In the present article, we fill the gap by (a) establishing the specifications of skills that can be sequenced with partial executions, (b) proposing an implementation based on the combination of finite-state machines and behavior trees, and (c) demonstrating the benefits of such skills through extensive trials in the environment of ARIAC (Agile Robotics for Industrial automation Competition). Copyright © 2021, The Authors. All rights reserved.

关键词： Competition

3D Hierarchical Refinement and Augmentation for Unsupervised Learning of Depth and Pose from Monocular Video

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Guangming Zhong, Jiquan Zhao, Shijie Wu, Wenhua Liu, Zhe Wang, Hesheng Department of Automation Institute of Medical Robotics Key Laboratory of System Control and Information Processing Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai200240 China Department of Engineering Mechanics Shanghai Jiao Tong University Shanghai200240 China Department of Computer Science and Technology University of Cambridge CambridgeCB2 1TN United Kingdom

Depth and ego-motion estimations are essential for the localization and navigation of autonomous robots and autonomous driving. Recent studies make it possible to learn the per-pixel depth and ego-motion from the unlabeled monocular video. A novel unsupervised training framework is proposed with 3D hierarchical refinement and augmentation using explicit 3D geometry. In this framework, the depth and pose estimations are hierarchically and mutually coupled to refine the estimated pose layer by layer. The intermediate view image is proposed and synthesized by warping the pixels in an image with the estimated depth and coarse pose. Then, the residual pose transformation can be estimated from the new view image and the image of the adjacent frame to refine the coarse pose. The iterative refinement is implemented in a differentiable manner in this paper, making the whole framework optimized uniformly. Meanwhile, a new image augmentation method is proposed for the pose estimation by synthesizing a new view image, which creatively augments the pose in 3D space but gets a new augmented 2D image. The experiments on KITTI demonstrate that our depth estimation achieves state-of-the-art performance and even surpasses recent approaches that utilize other auxiliary tasks. Our visual odometry outperforms all recent unsupervised monocular learning-based methods and achieves competitive performance to the geometry-based method, ORB-SLAM2 with back-end optimization. Copyright © 2021, The Authors. All rights reserved.

关键词： Robots

Relevant Region Prediction for Crowd Counting

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Chen, Xinya Bin, Yanrui Gao, Changxin Sang, Nong Tang, Hao Key Laboratory of Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Department of Information Engineering and Computer Science University of Trento

Crowd counting is a concerned and challenging task in computer vision. Existing density map based methods excessively focus on the individuals’ localization which harms the crowd counting performance in highly congested scenes. In addition, the dependency between the regions of different density is also ignored. In this paper, we propose Relevant Region Prediction (RRP) for crowd counting, which consists of the Count Map and the Region Relation-Aware Module (RRAM). Each pixel in the count map represents the number of heads falling into the corresponding local area in the input image, which discards the detailed spatial information and forces the network pay more attention to counting rather than localizing individuals. Based on the Graph Convolutional Network (GCN), Region Relation-Aware Module is proposed to capture and exploit the important region dependency. The module builds a fully connected directed graph between the regions of different density where each node (region) is represented by weighted global pooled feature, and GCN is learned to map this region graph to a set of relation-aware regions representations. Experimental results on three datasets show that our method obviously outperforms other existing state-of-the-art methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Directed graphs

Push-Pull Finite-Time Convergence Distributed Optimization Algorithm

学校读者我要写书评

暂无评论

American Journal of Computational Mathematics 2020年第1期10卷 118-146页

作者： Xiaobiao Chen Kaixin Yan Yu Gao Xuefeng Xu Kang Yan Jing Wang Department of Science Taiyuan University of Technology Taiyuan China Department of Automation Taiyuan University of Technology Taiyuan China Department of Automation School of Control and Computer Engineering North China Electric Power University Beijing China Department of Economics and Management Taiyuan University of Technology Taiyuan China Department of Mechanical and Electrical Engineering Shanxi Energy Institute Taiyuan China School of Medicine Clinical Medicine Datong University Datong China

With the widespread application of distributed systems, many problems need to be solved urgently. How to design distributed optimization strategies has become a research hotspot. This article focuses on the solution rate of the distributed convex optimization algorithm. Each agent in the network has its own convex cost function. We consider a gradient-based distributed method and use a push-pull gradient algorithm to minimize the total cost function. Inspired by the current multi-agent consensus cooperation protocol for distributed convex optimization algorithm, a distributed convex optimization algorithm with finite time convergence is proposed and studied. In the end, based on a fixed undirected distributed network topology, a fast convergent distributed cooperative learning method based on a linear parameterized neural network is proposed, which is different from the existing distributed convex optimization algorithms that can achieve exponential convergence. The algorithm can achieve finite-time convergence. The convergence of the algorithm can be guaranteed by the Lyapunov method. The corresponding simulation examples also show the effectiveness of the algorithm intuitively. Compared with other algorithms, this algorithm is competitive.

关键词： Distributed Optimization Finite Time Convergence Linear Parameterized Neural Network Push-Pull Algorithm Undirected Graph

Acceleration Command based Visual Servoing with Artificial Induced Time-Delay 19

学校读者我要写书评

暂无评论

Acceleration Command based Visual Servoing with Artificial I...

Proceedings of the 2019 4th International Conference on Advances in Robotics

作者： Madhu Yadav Chimmula Kishore Indra Narayan Kar Sumantra Dutta Roy Control & Automation Group Department of Electrical Engineering Indian Institute of Technology Delhi New Delhi India Computer Technology Group Department of Electrical Engineering Indian Institute of Technology Delhi New Delhi India

ISBN: (纸本)9781450366502

The tracking of an object using visual feedback by controlling the camera motion is known as Visual Servoing. In general most of visual servoing techniques use camera velocity as control input. In this paper, camera acceleration is used for deriving the control law. The use of acceleration input can accomplish smoother operating trajectory. However, this controller requires the first order feature measurement which may not be available. In this paper, to circumvent the issue, a time-delayed approximation is used for the non-measurable system states. The controller parameters are obtained from the stability analysis of the closed-loop time-delay system using Lyapunov-Razumikhin approach. The implemented controller is able to track the desired feature smoothly. These results establish a complementary approach to the existing acceleration-based augmented controller design.

关键词： Acceleration input

Efficient 3D Deep LiDAR Odometry

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Guangming Wu, Xinrui Jiang, Shuyang Liu, Zhe Wang, Hesheng Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai200240 China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China The Key Laboratory of Artificial Intelligence of Ministry of Education Shanghai Jiao Tong University Shanghai200240 China

An efficient 3D point cloud learning architecture, named EfficientLO-Net, for LiDAR odometry is first proposed in this paper. In this architecture, the projection-aware representation of the 3D point cloud is proposed to organize the raw 3D point cloud into an ordered data form to achieve efficiency. The Pyramid, Warping, and Cost volume (PWC) structure for the LiDAR odometry task is built to estimate and refine the pose in a coarse-to-fine approach. A projection-aware attentive cost volume is built to directly associate two discrete point clouds and obtain embedding motion patterns. Then, a trainable embedding mask is proposed to weigh the local motion patterns to regress the overall pose and filter outlier points. The trainable pose warp-refinement module is iteratively used with embedding mask optimized hierarchically to make the pose estimation more robust for outliers. The entire architecture is holistically optimized end-to-end to achieve adaptive learning of cost volume and mask, and all operations involving point cloud sampling and grouping are accelerated by projection-aware 3D feature learning methods. The superior performance and effectiveness of our LiDAR odometry architecture are demonstrated on KITTI, M2DGR, and Argoverse datasets. Our method outperforms all recent learning-based methods and even the geometry-based approach, LOAM with mapping optimization, on most sequences of KITTI odometry dataset. We open sourced our codes at: https://***/IRMVLab/EfficientLO-Net. Copyright © 2021, The Authors. All rights reserved.

关键词： Iterative methods

Acceleration command based visual servoing with artificial induced time-delay

学校读者我要写书评

暂无评论

Acceleration command based visual servoing with artificial i...

2019 Conference on Advances in Robotics, AIR 2019

作者： Yadav, Madhu Kishore, Chimmula Kar, Indra Narayan Roy, Sumantra Dutta Control and Automation Group Department of Electrical Engineering Indian Institute of Technology Delhi New Delhi India Computer Technology Group Department of Electrical Engineering Indian Institute of Technology Delhi New Delhi India

ISBN: (纸本)9781450366502

关键词： Visual servoing

A data driven fractional-order terminal sliding mode control method 8

学校读者我要写书评

暂无评论

A data driven fractional-order terminal sliding mode control...

8th IEEE Data Driven control and Learning Systems Conference, DDCLS 2019

作者： Hou, Mingdong Wang, Yinsong Shandong Labor Vocational and Technical College Department of Electrics and Automation Jinan250300 China School of Control and Computer Engineering North China Electric Power University Baoding071003 China

ISBN: (纸本)9781728114545

For a class of discrete-time nonlinear systems with disturbances, a data-driven discrete-time fractional-order terminal sliding mode control (DD-DFOTSMC) method is proposed in this paper. The algorithm is based on the compact form dynamic linearization (CFDL) technique, and the controller is designed based on the discrete terminal sliding mode technology and the Grünwald-Letnikov fractional-order definition. The parameter of the CFDL data model is called pseudo-partial derivative (PPD) and is estimated using merely I/O measurement data of the system. Theoretical analysis proves the stability of the proposed algorithm, and simulation studies demonstrate that the proposed method has higher precision and faster response speed. Finally, the effectiveness of the proposed method is validated through a continuous stirred tank reactor (CSTR) process. © 2019 IEEE.

关键词： Sliding mode control

How developers believe Invisibility impacts NFRs related to User Interaction

学校读者我要写书评

暂无评论

How developers believe Invisibility impacts NFRs related to ...

IEEE International Conference on Requirements Engineering

作者： Rainara Maia Carvalho Rossana M. C. Andrade Káthia M. Oliveira Computer Science Department (DC) Federal University of Ceará Fortaleza Brazil Laboratory of Industrial and Human Automation Control Mechanical Engineering and Computer Science Université Polytechnique Hauts-de-France Valenciennes LAMIH UMR CNRS 8201 France

ISBN: (数字)9781728174389

ISBN: (纸本)9781728174396

The advance of Ubiquitous Computing (UbiComp) and Internet of Things (IoT) brought a new set of Non-Functional Requirements (NFRs), especially related to Human-computer Interaction (HCI). Invisibility is one of these NFRs, and it refers to either the merging of technology in the user environment or the decrease of the interaction workload. This new NFR may impact traditional NFRs (e.g., Usability), revealing positive correlations, when one NFR helps another, and negative correlations, when a procedure favors an NFR but creates difficulty for another one. Software engineers need to know about these correlations, so they can select appropriate strategies to satisfy Invisibility and traditional NFRs. Correlations between NFRs are usually stored in catalogs, which is a well-defined body of knowledge gathered from previous experience. Although Invisibility has been recently cataloged with development strategies, the literature still lacks catalogs with correlations for this NFR. Therefore, this work aims at capturing and cataloging invisibility correlations for UbiComp and IoT systems. To do that, we also propose to systematize the definition of correlations using the following well-defined research methods: Interview, Content Analysis and Questionnaire. As a result, we defined a catalog with 110 positive and negative correlations with 9 NFRs. This well-defined body of knowledge is useful for supporting software engineers to select strategies to satisfy Invisibility and other NFRs related to user interaction.

关键词： Correlation Pervasive computing Usability Interviews Security Internet of Things Human computer interaction