检索结果-内蒙古大学图书馆

IEEE International Conference on Autonomous Robot systems and Competitions (ICARSC)

作者： Luan C. Klein João Braun Felipe N. Martins Heinrich Wörtche Andre Schneider de Oliveira João Mendes Vítor H. Pinto Paulo Costa José Lima Universidade Tecnológica Federal do Paraná Campus Curitiba UTFPR/PR Brasil Research Centre in Digitalization and Intelligent Robotics (CeDRI) Instituto Politécnico de Braganca Campus de Santa Apolonia Portugal Laboratory for Sustainability and Technology in Mountain Regions (SusTEC) Instituto Politécnico de Bragança Bragança Portugal Faculty of Engineering of University of Porto Portugal INESC Technology and Science Porto Portugal Sensors and Smart Systems Group Institute of Engineering Hanze University of Applied Sciences The Netherlands Department of Electrical Engineering Eindhoven University of Technology The Netherlands SYSTEC (DIGI2) ARISE & ECE Dept. Fac. de Engenharia Universidade do Porto Rua Dr. Roberto Frias 4200-465 Porto Portugal

The use of machine learning in embedded systems is an interesting topic, especially with the growth in popularity of the Internet of Things (IoT). The capacity of a system, such as a robot, to self-localize, is a fundamental skill for its navigation and decision-making processes. This work focuses on the feasibility of using machine learning in a Raspberry Pi 4 Model B, solving the localization problem using images and fiducial markers (ArUco markers) in the context of the RobotAtFactory 4.0 competition. The approaches were validated using a realistically simulated scenario. Three algorithms were tested, and all were shown to be a good solution for a limited amount of data. Results also show that when the amount of data grows, only Multi-Layer Perception (MLP) is feasible for the embedded application due to the required training time and the resulting size of the model.

关键词： Location awareness Training Embedded systems Machine learning algorithms Navigation Decision making Machine learning

来源：评论

学校读者我要写书评

暂无评论

Mobile Robot Localization with Reinforcement Learning Map Update Decision aided by an Absolute Indoor Positioning System

Mobile Robot Localization with Reinforcement Learning Map Up...

引用

2019 IEEE/RSJ International Conference on Intelligent Robots and systems (IROS)

作者： Luís Garrote Miguel Torres Tiago Barros João Perdiz Cristiano Premebida Urbano J. Nunes Institute of Systems and Robotics Department of Electrical and Computer Engineering University of Coimbra Portugal Dept. of Aeronautical and Automotive Engineering Loughborough University UK

This paper introduces a new mobile robot localization solution consisting of two main modules: a Particle-Filter based Localization (PFL) and a Reinforcement-Learning based map updating, integrating relative measurements and absolute indoor positioning sensor (A-IPS) data. Concerning localization using 2D-LiDARs, featureless areas are known to be problematic. To solve this problem a classic PFL approach was modified to incorporate A-IPS position measurements in the prediction and update stages. The localization approach has the particularity of including the possibility of updating the map whenever major modifications are detected in the environment in relation to the current localization map. Due to the random sampling-based nature of the PFL, an associated map update solution is not trivial since small inconsistencies in the estimated pose can lead to erroneous map associations. The proposed method learns to decide by assigning higher rewards the greater is the overlap between the map and the 2DLIDAR scans, via RL, and then a proper update of the map is achieved. Validation of the proposed pipeline was carried out in a differential drive platform with algorithms developed in ROS. Tests were performed in two scenarios in order to assess the performance of both the localization module and the map update stage. The results show that the proposed localization method offers improvements in relation to known approaches, and consequently suggest promising perspectives for the proposed map update decision framework.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Distributed Functional Safety for Modular Process Plants

Distributed Functional Safety for Modular Process Plants

引用

International Conference on Emerging Technologies and Factory Automation (ETFA)

作者： Anselm Klose Florian Pelzer Mike Barth Rainer Drath Rainer Oehlert Silvia Vélez León Alexander Horch Christoph Kotsch Jochen Knab Bernhard Gut Hartmut Manske Leon Urbas Process Control Systems & Process Systems Engineering TU Dresden Dresden Germany Research Training Group 2323 TU Dresden Dresden Germany IoS³ - Institute of Smart Systems and Services Pforzheim University Pforzheim Germany Retired Process Engineering & Automation The Dow Chemical Company Stade Germany Dept. Global Consulting HIMA Paul Hildebrandt GmbH Brühl Germany R. D. & Product Management HIMA Paul Hildebrandt GmbH Brühl Germany Control Systems Technology BASF SE Ludwigshafen Germany Engineering Services Merck KGaA Darmstadt Germany Retired Electrical Engineering for Process Automation Endress+Hauser Germany Automation and Robotics Merck KGaA Darmstadt Germany

ISBN: (数字)9781728189567

ISBN: (纸本)9781728189574

Modular process plants enable the process industry to adapt to volatile and fluctuating markets. The preferred process technology concept for these market scenarios is realized through combining pre-engineered process equipment assemblies (PEA) from different manufacturers with standardized interfaces. While the flexibility gain for this type of plants is high, the design of the safety systems of these modular plants in terms of exchangeability and compatibility is challenging. One solution could be the development of a safety-interface for PEAs to create flexible and scalable safety systems. The principles of modular basic process control are analyzed and requirements with respect to safety design are discussed. The authors provide a differentiation of the intramodular safety concept of a single PEA from the intermodular safety concept of a complete modular plant. A concept for safe and modular interaction of PEAs in a modular plant is developed and additionally validated on a basic demonstrator. Finally, from these findings, standardization requirements are provided and aspects for further research are pointed out.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Assis - cicerone robot with visual obstacle avoidance using a stack of odometric data

IAENG International Journal of Computer Science

引用

IAENG International Journal of Computer Science 2018年第1期45卷 219-227页

作者： Mendesy, Mateus Coimbray, A. Paulo Crisóstomo, Manuel M. ESTGOH Polytechnic Institute of Coimbra Portugal ISR - Institute of Systems and Robotics Dept. of Electrical and Computer Engineering University of Coimbra Portugal

Modern research has shown that intelligent behaviour is, to a great extent, strongly supported on the use of a sophisticated memory. Additionally, vision is the main source of information for the average human. Constant increase of sensing and processing power and constant decrease of the cost of memory have made vision-based approaches in robotics more attractive. ASSIS is a prototype of an assistant robot which uses vision and memory-based navigation, including intelligent obstacle avoidance. ASSIS uses a parallel implementation of a Sparse Distributed Memory to store images and use them later for localisation and navigation. Obstacle avoidance is achieved using a stack-based method and odometric data. Users can command the robot through a web-based interface. ASSIS implements behaviours such as courier or cicerone.

关键词： Navigation

来源：评论

学校读者我要写书评

暂无评论

Using 2 point+normal sets for fast registration of point clouds with small overlap

Using 2 point+normal sets for fast registration of point clo...

引用

2017 IEEE International Conference on robotics and Automation, ICRA 2017

作者： Raposo, Carolina Barreto, Joao P. Institute of Systems and Robotics Dept. of Electrical and Computer Engineering University of Coimbra Portugal

ISBN: (纸本)9781509046331

Global 3D point cloud registration has been solved by finding putative matches between the point clouds for establishing alignment hypotheses. A naive approach would try to perform exhaustive search of triplets with a cubic runtime complexity in the number of data points. Super4PCS reduces this complexity to linear by making use of sets of 4 coplanar points. This paper proposes 2-Point-Normal Sets (2PNS), a new global 3D registration approach that advances Super4PCS by using 2 points and their normals for generating alignment hypotheses. The dramatic improvement in the complexity of 2PNS when compared to Super4PCS is demonstrated by the experiments that show speed-ups of two orders of magnitude in noise-free datasets and up to 5.2× in Kinect scans, while improving robustness and alignment accuracy, even in datasets with overlaps as low as 5%. © 2017 IEEE.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Dynamic Human Gait VGRF Reference Profile Generation via Extreme Learning Machine

Dynamic Human Gait VGRF Reference Profile Generation via Ext...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Alexandra Vieira Bernardete Ribeiro Heloísa Sobral A. Paulo Coimbra Manuel Crisóstomo João P. Ferreira Tao Liu Dept. of Informatics Engineering CISUC Univ. of Coimbra Coimbra Portugal Dept. of Electrical and Computer Eng. Institute of Systems and Robotics Univ. of Coimbra Coimbra Portugal Dept. of Electrical Eng. Superior Institute of Eng. of Coimbra Institute of Systems and RoboticsUniv. of Coimbra Coimbra Portugal State Key Laboratory of Fluid Power and Mechatronic Systems School of Mechanical Engineering Zhejiang University Hangzhou China

Vertical Ground Reaction Forces (VGRF) reference profiles of human gait are important in medicine, for the recognition of gait disorders and in the assessment of rehabilitation treatments. A walking human is a dynamic varying system and in spite of the VGRF reference dependence on several patient's variables, doctors traditionally use the same static reference for all patients. The purpose of this study is to find out if an Extreme Learning Machine (ELM) is adequate to generate the dynamic VGRF reference profiles of healthy people depending on the subject's age, weight, height and stride duration. The ELM is compared with two other baseline Computational Intelligence (CI) methods, the Backpropagation Neural Network (BNN) and Multioutput Support Vector Regression (MSVR). Data from 28 healthy males walking at five different stride durations, collected using instrumented shoes, were used to train and test the CI models. The results showed that ELM is a well suited method to generate the dynamic VGRF reference profile for both dominant and non-dominant limbs, showing the lowest root mean square errors for the test set, 0.0201 and 0.0243 (fraction of body weight) for the dominant and non-dominant limbs respectively. This study reveals a promising methodology that can be implemented in real time gait analysis, allowing doctors to find a specific reference gait pattern for the gait analysis of an unhealthy person by specifying the age, weight, height and stride duration.

关键词： Training Biological neural networks Support vector machines Neurons Backpropagation Legged locomotion Adaptation models

来源：评论

学校读者我要写书评

暂无评论

Circumventing obstacles for visual robot navigation using a stack of odometric data

Circumventing obstacles for visual robot navigation using a ...

引用

2017 World Congress on engineering, WCE 2017

作者： Mendes, Mateus Coimbra, A. Paulo Crisóstomo, Manuel M. ESTGOH Polytechnic Institute of Coimbra Portugal ISR - Institute of Systems and Robotics Dept. of Electrical and Computer Engineering University of Coimbra Portugal

ISBN: (纸本)9789881404749

Recent advances in understanding the source of intelligent behaviour show that it is strongly supported on the use of a large and sophisticated memory. Constant increase of processing power and constant cost decrease of computer memory have encouraged research in vision-based methods for robot navigation. The present approach uses images stored into a Sparse Distributed Memory, implemented in parallel in a Graphics Processing Unit, as a method for robot localization and navigation. Algorithms for following previously learnt paths using visual and odometric information are described. A stack-based method for avoiding random obstacles, using visual information, is proposed. The results show the algorithms are adequate for indoors robot localization and navigation.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Low cost vision system for human gait acquisition and characterization

Low cost vision system for human gait acquisition and charac...

引用

2016 International Conference on Industrial engineering and engineering Management, IEEM 2016

作者： Ferreira, Paulo A. Ferreira, João P. Crisóstomo, Manuel Coimbra, A. Paulo Institute of Systems and Robotics Dept. of Electrical and Computer Engineering University of Coimbra Portugal Department of Electrical Engineering Superior Institute of Engineering of Coimbra Coimbra Portugal

ISBN: (纸本)9781509036653

This paper presents a low cost system for human gait analysis. Two opposite-faced web cameras are used to acquire images of the walking of a person carrying a set of passive marks, where the color is chosen to contrast with the ambient dominant color. It is also used a treadmill with passive marks, where the user walks at different speeds. The acquired trajectories of the marks are used to determine body joint angles and other 3D crossed angles, obtained by both opposite sides from video images processing. With this low cost measurement system the analysis and reconstruction of human gait can be done with a mean error of 2 degrees, becoming a good alternative to more expensive systems to be used in human gait characterization. The system can be used to detect human gait pathologies and to accomplish physical rehabilitation. © 2016 IEEE.

关键词： Cost benefit analysis

来源：评论

学校读者我要写书评

暂无评论

High-resolution LIDAR-based dept. Mapping using Bilateral Filter

High-resolution LIDAR-based Depth Mapping using Bilateral Fi...

引用

IEEE International Conference on Intelligent Transportation systems

作者： Cristiano Premebida Luis Garrote Alireza Asvadi A. Pedro Ribeiro Urbano Nunes Institute of Systems and Robotics Dept. of Electrical and Computer Engineering University of Coimbra

ISBN: (纸本)9781509018901

High resolution dept.-maps, obtained by upsampling sparse range data from a 3D-LIDAR, find applications in many fields ranging from sensory perception to semantic segmentation and object detection. Upsampling is often based on combining data from a monocular camera to compensate the low-resolution of a LIDAR. This paper, on the other hand, introduces a novel framework to obtain dense dept.-map solely from a single LIDAR point cloud;which is a research direction that has been barely explored. The formulation behind the proposed dept.-mapping process relies on local spatial interpolation, using sliding-window (mask) technique, and on the Bilateral Filter (BF) where the variable of interest, the distance from the sensor, is considered in the interpolation problem. In particular, the BF is conveniently modified to perform dept.-map upsampling such that the edges (foreground-background discontinuities) are better preserved by means of a proposed method which influences the range-based weighting term. Other methods for spatial upsampling are discussed, evaluated and compared in terms of different error measures. This paper also researches the role of the mask's size in the performance of the implemented methods. Quantitative and qualitative results from experiments on the KITTI Database, using LIDAR point clouds only, show very satisfactory performance of the approach introduced in this work.

关键词： Laser radar Interpolation Cameras Three-dimensional displays Vehicles Spatial resolution Estimation

来源：评论

学校读者我要写书评

暂无评论

AUV terrain-aided navigation using a doppler velocity logger

引用

IFAC-PapersOnLine 2015年第2期28卷 137-142页

作者： Teixeira, Francisco Curado Quintas, João Pascoal, António Institute of Systems and Robotics Dept. Electrical Engineering Instituto Superior Técnico Lisboa Portugal

The potential of terrain-aided navigation (TAN) of autonomous underwater vehicles (AUVs) has been demonstrated in the last ten years in a series of trials where high localization accuracy was obtained during long periods of time in different types of terrain. Despite these recent advances, it is recognized by the navigation community that further research is necessary to transform TAN into a mature navigation methodology. The present paper describes the work developed towards the development of terrain navigation methods for small AUVs, relying on standard navigation sensors and dispensing with the need of dedicated sensors for terrain data acquisition. The research described addresses the problem of implementation of terrain navigation in underwater scenarios characterized by smooth sea-bottom topography and very shallow water, where the terrain information available for navigation is scarce. The TAN algorithms and the data fusion methods whose tests are documented in the paper build upon prior theoretical work published by the authors. The experimental results reported were obtained recently through trials in the water performed with an autonomous surface vehicle acting as a proxy to an AUV. © 2015, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.

关键词： Autonomous underwater vehicles Air navigation Data acquisition Data fusion Landforms Navigation Ocean structures Autonomous surface vehicles Doppler Localization accuracy Of autonomous underwater vehicles Particle filter Sea bottom topography Terrain aided navigation Very shallow waters

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：