Search

Your search keyword '"AMCL"' showing total 27 results
Start Over Descriptor "AMCL"

Refine your results

more »

more »

more »
27 results on '"AMCL"'

1. Implementing Autonomous Navigation on an Omni Wheeled Robot Using 2D LiDAR, Tracking Camera and ROS

Author

Bhorpe, Atharva, Padalkar, Pratik, Kadam, Pawan, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Jiming, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zamboni, Walter, Series Editor, Zhang, Junjie James, Series Editor, Tan, Kay Chen, Series Editor, Borah, Malaya Dutta, editor, Laiphrakpam, Dolendro Singh, editor, Auluck, Nitin, editor, and Balas, Valentina Emilia, editor

Published
2024
Full Text
View/download PDF

2. Autonomous Mobile Robot Navigation Using Lower Resolution Grids and PID-Based Pure Pursuit Controller

Author

Al-Naseri, Ahmed, Uslu, Erkan, Chaari, Fakher, Series Editor, Gherardini, Francesco, Series Editor, Ivanov, Vitalii, Series Editor, Haddar, Mohamed, Series Editor, Cavas-Martínez, Francisco, Editorial Board Member, di Mare, Francesca, Editorial Board Member, Kwon, Young W., Editorial Board Member, Trojanowska, Justyna, Editorial Board Member, Xu, Jinyang, Editorial Board Member, Şen, Zekâi, editor, Uygun, Özer, editor, and Erden, Caner, editor

Published
2024
Full Text
View/download PDF

3. L-PCM: Localization and Point Cloud Registration-Based Method for Pose Calibration of Mobile Robots.

Author

Ning, Dandan and Huang, Shucheng

Subjects
*MOBILE robots, *POINT cloud, *CALIBRATION, *KALMAN filtering, *UNITS of measurement, *LOCALIZATION (Mathematics), *ODOMETERS, *ANGLES
Abstract

The autonomous navigation of mobile robots contains three parts: map building, global localization, and path planning. Precise pose data directly affect the accuracy of global localization. However, the cumulative error problems of sensors and various estimation strategies cause the pose to have a large gap in data accuracy. To address these problems, this paper proposes a pose calibration method based on localization and point cloud registration, which is called L-PCM. Firstly, the method obtains the odometer and IMU (inertial measurement unit) data through the sensors mounted on the mobile robot and uses the UKF (unscented Kalman filter) algorithm to filter and fuse the odometer data and IMU data to obtain the estimated pose of the mobile robot. Secondly, the AMCL (adaptive Monte Carlo localization) is improved by combining the UKF fusion model of the IMU and odometer to obtain the modified global initial pose of the mobile robot. Finally, PL-ICP (point to line-iterative closest point) point cloud registration is used to calibrate the modified global initial pose to obtain the global pose of the mobile robot. Through simulation experiments, it is verified that the UKF fusion algorithm can reduce the influence of cumulative errors and the improved AMCL algorithm can optimize the pose trajectory. The average value of the position error is about 0.0447 m, and the average value of the angle error is stabilized at about 0.0049 degrees. Meanwhile, it has been verified that the L-PCM is significantly better than the existing AMCL algorithm, with a position error of about 0.01726 m and an average angle error of about 0.00302 degrees, effectively improving the accuracy of the pose. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

5. Peningkatan Akurasi Adaptive Monte Carlo Localization Menggunakan Convolutional Neural Network

Author

Riza Agung Firmansyah, Tri Arief Sardjono, and Ronny Mardiyanto

Subjects
lokalisasi robot, lidar, amcl, cnn, Engineering (General). Civil engineering (General), TA1-2040
Abstract

Makalah ini menjelaskan peningkatan akurasi sistem lokalisasi adaptive Monte Carlo localization (AMCL) pada robot menggunakan convolutional neural network (CNN). Sistem lokalisasi pada sebuah robot merupakan proses pengenalan posisi suatu robot dalam lingkungan kerjanya. Sistem ini penting karena memungkinkan robot untuk melakukan navigasi dan pemetaan (mapping) secara efisien dan akurat. Tanpa lokalisasi yang tepat, robot tidak dapat beroperasi dengan efektif dan dapat mengalami masalah, seperti kehilangan arah atau menabrak objek. AMCL merupakan sistem lokalisasi yang populer dan banyak digunakan dalam robot. Metode ini menggunakan perubahan posisi robot dan perubahan pembacaan sensor light detection and ranging (LiDAR) sebagai masukannya. Pembacaan perubahan posisi robot rentan terhadap kesalahan akibat slip maupun deformasi roda. Ketidaktepatan pembacaan perubahan posisi robot menyebabkan prediksi posisi robot oleh AMCL menjadi kurang tepat, sehingga diperlukan sebuah perbaikan. Pada makalah ini, kebaruan yang diangkat adalah memberikan nilai kompensasi dari hasil AMCL, sehingga error-nya menjadi kecil. Nilai kompensasi tersebut didapatkan dari hasil pelatihan CNN, sehingga metode yang diusulkan tersebut dapat disebut AMCL+CNN. Masukan yang diberikan pada CNN adalah perubahan nilai odometry roda dan perubahan pembacaan jarak oleh sensor LiDAR. Keluaran CNN tersebut dibandingkan dengan data target berupa posisi aktual robot dari hasil pengamatan. Pelatihan jaringan dilakukan sebanyak 200 epoch untuk mendapatkan validation loss terkecil. Pengujian dilakukan pada sebuah robot yang telah dilengkapi dengan robot operating system (ROS). Dataset pelatihan dan pengujian yang diujikan berasal dari data rosbag saat robot berjalan di area pengujian. Hasil yang didapatkan algoritma AMCL+CNN memiliki error yang lebih kecil dibandingkan AMCL dan Monte Carlo localization (MCL) reguler pada skenario lurus dan belok. Hasil yang diperoleh juga lebih baik pada metrik error posisi saat dibandingkan dengan beberapa metode pembanding lain.

Published
2023
Full Text
View/download PDF

6. L-PCM: Localization and Point Cloud Registration-Based Method for Pose Calibration of Mobile Robots

Author

Dandan Ning and Shucheng Huang

Subjects
AMCL, UKF, PL-ICP point cloud registration, pose calibration, Information technology, T58.5-58.64
Abstract

The autonomous navigation of mobile robots contains three parts: map building, global localization, and path planning. Precise pose data directly affect the accuracy of global localization. However, the cumulative error problems of sensors and various estimation strategies cause the pose to have a large gap in data accuracy. To address these problems, this paper proposes a pose calibration method based on localization and point cloud registration, which is called L-PCM. Firstly, the method obtains the odometer and IMU (inertial measurement unit) data through the sensors mounted on the mobile robot and uses the UKF (unscented Kalman filter) algorithm to filter and fuse the odometer data and IMU data to obtain the estimated pose of the mobile robot. Secondly, the AMCL (adaptive Monte Carlo localization) is improved by combining the UKF fusion model of the IMU and odometer to obtain the modified global initial pose of the mobile robot. Finally, PL-ICP (point to line-iterative closest point) point cloud registration is used to calibrate the modified global initial pose to obtain the global pose of the mobile robot. Through simulation experiments, it is verified that the UKF fusion algorithm can reduce the influence of cumulative errors and the improved AMCL algorithm can optimize the pose trajectory. The average value of the position error is about 0.0447 m, and the average value of the angle error is stabilized at about 0.0049 degrees. Meanwhile, it has been verified that the L-PCM is significantly better than the existing AMCL algorithm, with a position error of about 0.01726 m and an average angle error of about 0.00302 degrees, effectively improving the accuracy of the pose.

Published
2024
Full Text
View/download PDF

7. Industrial Warehouse Robot Simulation Using ROS

Author

Padalkar, Pratik, Kadam, Pawan, Mirajgave, Shantanu, Mohite, Aniket, Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Prates, Raquel Oliveira, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Sk, Arif Ahmed, editor, Turki, Turki, editor, Ghosh, Tarun Kumar, editor, Joardar, Subhankar, editor, and Barman, Subhabrata, editor

Published
2022
Full Text
View/download PDF

8. Improved LiDAR Localization Method for Mobile Robots Based on Multi-Sensing.

Author

Liu, Yanjie, Wang, Chao, Wu, Heng, Wei, Yanlong, Ren, Meixuan, and Zhao, Changsen

Subjects
*MOBILE robots, *LIDAR, *GLOBAL Positioning System, *KALMAN filtering, *POINT cloud, *NONLINEAR systems
Abstract

In this paper, we propose a localization method applicable to 3D LiDAR by improving the LiDAR localization algorithm, such as AMCL (Adaptive Monte Carlo Localization). The method utilizes multiple sensing information, including 3D LiDAR, IMU and the odometer, and can be used without GNSS. Firstly, the wheel speed odometer and IMU data of the mobile robot are multi-source fused by EKF (Extended Kalman Filter), and the sensor data obtained after multi-source fusion are used as the motion model to participate in the positional prediction of the particle set in AMCL to obtain the initial positioning information of the mobile robot. Then, the position pose difference values output by AMCL at adjacent moments are substituted into the PL-ICP algorithm as the initial position pose transformation matrix, and the 3D laser point cloud is aligned with the nonlinear system using the PL-ICP algorithm. The three-dimensional laser odometer is obtained by LM (Levenberg--Marquard) iterative solution in the PL-ICP algorithm. Finally, the initial position pose output by AMCL is corrected by the three-dimensional laser odometer, and the AMCL particles are weighted and sampled to output the final positioning result of the mobile robot. Through simulation and practical experiments, it is verified that the improved AMCL algorithm has higher positioning accuracy and stability compared to the AMCL algorithm. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

9. Review of SLAM Algorithms for Indoor Mobile Robot with LIDAR and RGB-D Camera Technology

Author

Kolhatkar, Chinmay, Wagle, Kranti, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Jiming, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Hirche, Sandra, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Möller, Sebastian, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zhang, Junjie James, Series Editor, Favorskaya, Margarita N., editor, Mekhilef, Saad, editor, Pandey, Rajendra Kumar, editor, and Singh, Nitin, editor

Published
2021
Full Text
View/download PDF

10. Vision-Sensor-Assisted Probabilistic Localization Method for Indoor Environment.

Author

Shi, Hui, Yang, Jianyu, Shi, Jiashun, Zhu, Lida, and Wang, Guofa

Subjects
*LOCALIZATION (Mathematics), *KIDNAPPING, *LIDAR, *ROBOTS, *ALGORITHMS
Abstract

Among the numerous indoor localization methods, Light-Detection-and-Ranging (LiDAR)-based probabilistic algorithms have been extensively applied to indoor localization due to their real-time performance and high accuracy. Nevertheless, these methods are challenged in symmetrical environments when tackling global localization and the robot kidnapping problem. In this paper, a novel hybrid method that combines visual and probabilistic localization results is proposed. Augmented Monte Carlo Localization (AMCL) is improved for position tracking continually. LiDAR-based measurements' uncertainty is evaluated to incorporate discrete visual-based results; therefore, a better diversity of the particle can be maintained. The robot kidnapping problem can be detected and solved by preventing premature convergence of the particle filter. Extensive experiments were implemented to validate the robustness and accuracy performance. Meanwhile, the localization error was reduced from 30 mm to 9 mm during a 600 m tour. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

11. Precise Positioning and Heading for Autonomous Scouting Robots in a Harsh Environment

Author

Obregón, David, Arnau, Raúl, Campo-Cossio, María, Arroyo-Parras, Juan G., Pattinson, Michael, Tiwari, Smita, Lluvia, Iker, Rey, Oscar, Verschoore, Jeroen, Lenza, Libor, Reyes, Joaquin, Hutchison, David, Editorial Board Member, Kanade, Takeo, Editorial Board Member, Kittler, Josef, Editorial Board Member, Kleinberg, Jon M., Editorial Board Member, Mattern, Friedemann, Editorial Board Member, Mitchell, John C., Editorial Board Member, Naor, Moni, Editorial Board Member, Pandu Rangan, C., Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Terzopoulos, Demetri, Editorial Board Member, Tygar, Doug, Editorial Board Member, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Ferrández Vicente, José Manuel, editor, Álvarez-Sánchez, José Ramón, editor, de la Paz López, Félix, editor, Toledo Moreo, Javier, editor, and Adeli, Hojjat, editor

Published
2019
Full Text
View/download PDF

12. Improved LiDAR Localization Method for Mobile Robots Based on Multi-Sensing

Author

Yanjie Liu, Chao Wang, Heng Wu, Yanlong Wei, Meixuan Ren, and Changsen Zhao

Subjects
3D LiDAR, AMCL, EKF, multi-sensing, PL-ICP, localization, Science
Abstract

In this paper, we propose a localization method applicable to 3D LiDAR by improving the LiDAR localization algorithm, such as AMCL (Adaptive Monte Carlo Localization). The method utilizes multiple sensing information, including 3D LiDAR, IMU and the odometer, and can be used without GNSS. Firstly, the wheel speed odometer and IMU data of the mobile robot are multi-source fused by EKF (Extended Kalman Filter), and the sensor data obtained after multi-source fusion are used as the motion model to participate in the positional prediction of the particle set in AMCL to obtain the initial positioning information of the mobile robot. Then, the position pose difference values output by AMCL at adjacent moments are substituted into the PL-ICP algorithm as the initial position pose transformation matrix, and the 3D laser point cloud is aligned with the nonlinear system using the PL-ICP algorithm. The three-dimensional laser odometer is obtained by LM (Levenberg--Marquard) iterative solution in the PL-ICP algorithm. Finally, the initial position pose output by AMCL is corrected by the three-dimensional laser odometer, and the AMCL particles are weighted and sampled to output the final positioning result of the mobile robot. Through simulation and practical experiments, it is verified that the improved AMCL algorithm has higher positioning accuracy and stability compared to the AMCL algorithm.

Published
2022
Full Text
View/download PDF

13. Vision-Sensor-Assisted Probabilistic Localization Method for Indoor Environment

Author

Hui Shi, Jianyu Yang, Jiashun Shi, Lida Zhu, and Guofa Wang

Subjects
AMCL, indoor localization, robot kidnapping problem, premature convergence, Chemical technology, TP1-1185
Abstract

Among the numerous indoor localization methods, Light-Detection-and-Ranging (LiDAR)-based probabilistic algorithms have been extensively applied to indoor localization due to their real-time performance and high accuracy. Nevertheless, these methods are challenged in symmetrical environments when tackling global localization and the robot kidnapping problem. In this paper, a novel hybrid method that combines visual and probabilistic localization results is proposed. Augmented Monte Carlo Localization (AMCL) is improved for position tracking continually. LiDAR-based measurements’ uncertainty is evaluated to incorporate discrete visual-based results; therefore, a better diversity of the particle can be maintained. The robot kidnapping problem can be detected and solved by preventing premature convergence of the particle filter. Extensive experiments were implemented to validate the robustness and accuracy performance. Meanwhile, the localization error was reduced from 30 mm to 9 mm during a 600 m tour.

Published
2022
Full Text
View/download PDF

14. Approach for Supervising Self-localization Processes in Mobile Robots

Author

Farias, P. C. M. A., Sousa, Ivo, Sobreira, Héber, Moreira, António Paulo, Hutchison, David, Editorial Board Member, Kanade, Takeo, Editorial Board Member, Kittler, Josef, Editorial Board Member, Kleinberg, Jon M., Editorial Board Member, Mattern, Friedemann, Editorial Board Member, Mitchell, John C., Editorial Board Member, Naor, Moni, Editorial Board Member, Pandu Rangan, C., Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Terzopoulos, Demetri, Editorial Board Member, Tygar, Doug, Editorial Board Member, Weikum, Gerhard, Series Editor, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Oliveira, Eugénio, editor, Gama, João, editor, Vale, Zita, editor, and Lopes Cardoso, Henrique, editor

Published
2017
Full Text
View/download PDF

15. Control system for wheelchair based mobile robot

Author

Krešić, Martin, Marković, Kristina, Vrcan, Željko, Senčić, Tomislav, and Basan, Robert

Subjects
Robot Operating System, Mobilni robot, Robot Operating System, SLAM, AMCL, Gazebo, Gazebo, SLAM, mobile robot, AMCL
Abstract

U ovom diplomskom radu napravljen je upravljački sustav mobilnog robota konstruiranog na platformi invalidskih kolica. Upravljački sustav napravljen je koristeći Robot Operating System (ROS). Pomoću ROS-a implementirani su SLAM (eng. Simultaneous Localization and Mapping) i autonomni način rada robota. SLAM način rada koristi teleoperaciju za upravljanje i koristi se za mapiranje robotu nepoznatih okruženja. Autonomni način rada koristi AMCL (eng. Adaptive Monte Carlo Localization) i planere putanje za samostalnu navigaciju robota u prijašnje mapiranim okruženjima. Ispravnost sustava testirana je unutar Gazebo simulatora koristeći simulacijsko okruženje sa preprekama., In this master thesis control system for mobile robot for a wheelchair based mobile robot was made. Control system was made using the Robot Operating System (ROS). ROS was used to implement SLAM (Simultaneous Localization and Mapping) and autonomous mode of operation for the robot. SLAM mode uses teleoperation as means of control and it is used for mapping of environments which are previously unknown for the robot. Autonomous mode uses AMCL (Adaptive Monte Carlo Localization) and route planners for fully autonomous navigation of the robot in previously mapped environments. Validity of the system was tested via Gazebo simulator using a simulated obstacle course.

Published
2022

16. Diseño de un controlador PI para las ruedas de un robot móvil diferencial utilizando NI MyRio

Author

Oliveira, Ronaldo do Amaral, Cuadros, Marco Antonio de Souza Leite, and Valadão, Carlos Torturella

Subjects
Enseñanza en robótica, Controlador de trajetória, Robótica móvil, LabVIEW, Robotics teaching, Robótica móvel, ROS, Controlador de trayectoria, Trajectory controller, Mobile robotics, AMCL, Ensino de robótica
Abstract

Introduction. This article proposes a navigation architecture for non-holonomic mobile robots for known positions on the navigation map. This architecture can plan a path from the current point to the destination. Navigation is ensured by the move_base controller package of Robot Operating System (ROS) that guides the robot in the predetermined trajectory. Objectives. This article shows the navigation of a non-holonomic robot using (Adaptive Monte Carlo Localization) AMCL algorithm and ROS for educational and development purposes. Methodology. The developed control is compatible with ROS and some examples are shown using a differential robot developed at the Federal Institute of Espirito Santo. The encoders, wheel and robot speed controllers are read in an embedded NI-MyRio system, which is programmed using LabVIEW. ROS is installed on a Linux ODROID minicomputer, which is part of the robot and is connected via Ethernet to a LiDAR laser sensor and to the NI-MyRio. ROS ability to work in a network environment allows control and supervision of devices through computer network. Results. It was possible to perform the navigation of the mobile robot, making it reach the desired final location. Within the experiments, it was possible to prove the functionality of the AMCL algorithm and the proposed architecture. Conclusion. Through the tests performed with the robot, it was possible to conclude that the navigation objective was successfully completed, validating the system and the applicability of the AMCL algorithm. Introducción. Este artículo propone una arquitectura de navegación para robots móviles no-holonómicos en posiciones conocidas en el mapa de navegación. Esta arquitectura tiene la capacidad de planificar un camino entre el punto actual y el deseado. La navegación es asegurada con el controlador move_base del Robot Operating System (ROS) que garantiza que el robot va a seguir una trayectoria predeterminada. Objectivos. Este artículo muestra la navegación de un robot con AMCL utilizando ROS para fines didácticos y de desarrollo. Metodología. El control desarrollado es compatible con ROS y algunos ejemplos de aplicación de este sistema en un robot diferencial desarrollado en el Instituto Federal do Espírito Santo son presentados. La lectura de los encoders, los controladores de velocidad de las ruedas y del robot están en un sistema embebido de National Instruments, NI My Rio, programado usando LabVIEW. El ROS está instalado en un miniordenador ODROID Linux integrado en el robot que está conectado a través de Ethernet a un sensor láser LiDAR ya NI-MyRio. La capacidad de ROS para trabajar en un entorno de red permite controlar y supervisar equipos a través de computadoras en la misma red. Resultados. Se logró realizar la navegación del robot móvil, haciéndolo llegar a la ubicación final deseada. Además, se logró probar la funcionalidad del algoritmo AMCL y de la arquitectura propuesta. Conclusión. A través de las pruebas realizadas con el robot se concluye que el objetivo de navegación se cumplió con éxito, validando el sistema y la aplicabilidad del algoritmo AMCL. Introdução. Este artigo propõe uma arquitetura de navegação para robôs móveis não Holonômicos em posições conhecidas no mapa de navegação. Esta arquitetura tem a capacidade de planejar um caminho entre o ponto atual e o destino. A navegação é garantida com o controlador move_base do Robot Operating System (ROS) para percorrer uma trajetória pré-determinada. Objetivo. Este artigo mostra a navegação de um robô com AMCL utilizando o ROS para fins didáticos e de desenvolvimento. Metodologia. O controle desenvolvido é compatível com o ROS e são apresentados alguns exemplos da aplicação desse sistema em um robô diferencial desenvolvido no Instituto Federal do Espírito Santo. A leitura dos encoders, os controladores de velocidade das rodas e do robô encontram-se num sistema embarcado da National Instruments, o NI‑MyRio, programado utilizando LabVIEW. O ROS está instalado no Linux no minicomputador ODROID embarcado no robô que está conectado via Ethernet a um sensor laser LiDAR e ao NI-MyRio. A capacidade do ROS em trabalhar em ambiente de rede permite controlar e supervisionar os equipamentos através de computadores na mesma rede. Resultados. Foi possível realizar a navegação do robô móvel, fazendo‑o chegar até a localização final desejada. Dentro dos experimentos, foi possível comprovar a funcionalidade do algoritmo AMCL e da arquitetura proposta. Conclusão. Por meio dos testes realizados com o robô, foi possível concluir que o objetivo de navegação foi concluído com êxito, validando o sistema e a aplicabilidade do algoritmo AMCL.

Published
2022

17. Evaluation of SLAM methods and Adaptive Monte Carlo Localization

Author

Milanovic, Sinisa

Subjects
SLAM, Robot localization, AMCL
Abstract

Mobile robots that perform tasks autonomously must be able to solve two fundamental problems on their own to ensure autonomy. On the one hand, a map of an unknown environment must be created and the robot’s position determined simultaneously, for which the Simultaneous Localization and Mapping (SLAM) solution is used. On the other hand, an autonomous localization algorithm, such as Adaptive Monte Carlo Localization (AMCL), must be used to solve the kidnapped-robot problem.Every sensor has some measurement inaccuracy, which in the case of a laser distance sensor (LDS) is very small and has no significant effect on the accuracy of the generated map, but this inaccuracy adds up with each measurement until there is an offset in the map and makes it unusable. Therefore, SLAM algorithms must be able to produce a detailed map and cover a wide range of LDS with various measurement inaccuracies as well.The localization algorithm AMCL, in contrast, shows major limitations in localization after the occurrence of the kidnapped-robot problem, if the position of the robot has been changed significantly, or several particles have already formed a swarm and represent a possible position of the robot. For this reason, AMCL is often used only as a base for improved localization algorithms. In this work, we evaluated how robustly and reliably the three SLAM methods Gmapping, Hector, and Karto perform when using LDS with different technical characteristics. In addition, an optimized parameterization of AMCL was performed and adapted to the environment to ensure autonomous localization after the occurrence of the kidnapped-robot problem, without the need for external intervention.This work was carried out in a simulation in the Robot Operation System (ROS), where an apartment was created as a simulated world. Maps of this virtual environment were created with different technical characteristics of the LDS, which were compared to the floor plan of the apartment using a program developed for this work. This allowed us to determine how the different inaccuracies of the LDS affected the accuracy of the map.For the evaluation of AMCL with the adjusted parameters, different scenarios simulating the Kidnapped-Robot problem with different difficulty levels were performed. In order not to reduce the efficiency of this localization in the presence of small position shifts, the referencing process was divided into three phases, which allowed for fast localization even in the presence of small position changes.The results of this work show that both Gmapping and Karto are very robust and reliable SLAM methods that produce usable maps even in the presence of high inaccuracies in the LDS, while Hector has problems determining the position of the robot even in the presence of small deviations, resulting in an overlap in the map. Furthermore, it has been shown using various kidnapped-robot scenarios that AMCL is always able to perform localization, provided that the parameters are adapted to the environment.

Published
2022
Full Text
View/download PDF

18. Localization accuracy of a mobile robot in indoor environments based on a laser range sensor

Author

Mustapić, Nives and Seder, Marija

Subjects
LiDAR Velodyne, TEHNIČKE ZNANOSTI. Elektrotehnika, OptiTrack, gmapping, mapiranje, ROS, AMCL, Husky mobilna platforma, mobilna robotika, mobile robotics, TECHNICAL SCIENCES. Electrical Engineering, Localization, Lokalizacija, laserski senzor udaljenosti Velodyne, Husky mobile platform
Abstract

Zadatak diplomskog rada je ispitivanje točnosti lokalizacije mobilnog robota koristeći AMCL algoritam. Algoritam je implementiran unutar ROS paketa ‘amcl’. Uz prethodno izgradenu kartu prostora i očitanja laserskog senzora udaljenosti odreduje se pozicija i orijentacija mobilnog robota. U ROS operacijskom sustavu točnost je prvo ispitana u simulaciji, zatim i eksperimentalno na Husky mobilnom robotu. Provedeno je 6 eksperimenata gdje je u svakom ostvaren različit oblik gibanja robota kako bi se utvrdilo utječe li smjer i način skretanja na točnost lokalizacije. Rezultati su obrađeni također unutar ROS-a i prikazani grafički i tablično. The task of the thesis is to examine the accuracy of the localization of a mobile robot using the AMCL algorithm. With the previously built map and distance laser sensor readings, the position and orientation of the mobile robot are determined. In ROS operating system, accuracy is firstly tested using simulation and then experimentally on a Husky mobile robot. 6 experiments were performed to determine whether the direction and way of rotation affect the accuracy of localization. The results were also processed within ROS and presented graphically and numerically.

Published
2021

19. Sistema inteligente para un vehículo aéreo no tripulado que realiza servicios de domicilio en un entorno virtual

Author

Barrios Ariza, Stephany, Orozco Sánchez, Michellie Sarif, and Quintero Monroy, Christian Giovanny

Subjects
Autonomous, Autonomo, Gazebo, Vehículo aéreo no tripulado, SLAM, Rviz, Domicilio, ROS, Unmanned Aerial Vehicle, Delivery, AMCL
Abstract

El proyecto tiene como propósito diseñar y desarrollar un sistema inteligente para un vehículo aéreo no tripulado que realiza servicios de domicilio en un entorno virtual. Esto se logró con el sistema operativo robótico ROS, el cual proporciona librerías y herramientas mediadoras. Debido a su compatibilidad y alcance, se implementó el entorno virtual en Gazebo, que ofrece la capacidad de simular robots de forma precisa y eficiente, de la mano de la interfaz de visualización Rviz que permite la visualización de información, usando plugins que brindan robustez y gráficos de alta calidad. El proyecto se divide en tres fases: La elaboración del entorno, una etapa de mapeo y por último la etapa de navegación. La primera etapa fue elaborada a través del simulador Gazebo. Blender y Sketchup fueron claves para exportar y escalar los modelos al entorno, brindando la perspectiva de un área urbana. Para la fase de mapeo se utilizó el paquete de gmapping que viene integrado con SLAM, el cual realiza un proceso de escaneo del mundo en 3D, para producir un mapa de cuadricula de ocupación en 2D por medio de un sensor LIDAR de Hokuyo integrado en el UAV. Finalmente, para la etapa de navegación, usando los paquetes de move_base y amcl, fue posible obtener una planeación de ruta optima capaz de navegar y evadir obstáculos para realizar la correcta logística de un proceso de entrega.

Published
2021

20. Implementation of a mobile robotic system for access control and protection of a structured indoor environment

Author

Andrić, Jure and Kovačić, Zdenko

Subjects
RFID, Pepper robot, MATLAB, TEHNIČKE ZNANOSTI. Elektrotehnika, ROS, Face detection, Epsimax sustav, AMCL, lokalizacija, EKF, TECHNICAL SCIENCES. Electrical Engineering, robot Pepper, Python, C, Arduino, detekcija lica, Localization, Epsimax
Abstract

U ovom radu analizirani su najvažniji algoritmi lokalizacije robota. EKF je testiran na Matlab-ovom simulatoru dok je AMCL testiran na simulatoru robota Pepper-a te su oba algoritma dala dobre rezultate. Za kontrolu pristupa izrađen je RFID. Napravljena su dva algoritma. Prvi je namijenjen za iščitavanje kodova svih kartica dok je drugi namijenjen kontroli pristupa, tj. osobe čije se kartice nalaze unutar programa, mogu pristupiti prostoriji. Potpuna integracija svega s Epsimax sustavom nije napravljena, ali se rad na projektu nastavlja. Na kraju svega analizirana je tema zaštite robota od kibernetičkih napada koja je, posebno za ovo područje, od velike važnosti. Razrađene su dvije metode zaštite. Prva se odnosi na zaštitu lokalne mreže, a druga se odnosi na kriptiranje podataka unutar ROS-a. In this paper, the most important algorithms of robot localization have been analysed. The EKF was tested on the Matlab simulator while the AMCL was tested on the Pepper robot simulator and both algorithms gave good results. RFID was created for access control. Two algorithms have been made. The first one is intended for reading the codes of all cards while the second one is intended for access control, i.e. persons whose cards are inside the program, can access the room. Complete integration of everything with the Epsimax system has not been done, but work on the project continues. At the end of the day, the topic of protection of robots against cyber attacks was analyzed, which, especially for this area, is of great importance. Two methods of protection have been elaborated. The first relates to the protection of the local network, and the second refers to the encryption of data within the ROS.

Published
2020

21. Flow injection potentiometric determination of amitriptyline hydrochloride

Author

El-Nashar, R.M., Abdel Ghani, N.T., and Bioumy, A.A.

Subjects
*POTENTIOMETRY, *HYDROGEN chloride, *ELECTRODES, *IONS
Abstract

New plastic membrane electrodes for amitriptyline hydrochloride (AmCl) based on amitriptylinium phosphotungstate (Am-PTA); amitriptylinium phosphomolybdate (Am-PMA) and a mixture of both (Am-PTA/PMA) were prepared. The electrodes were fully characterized in terms of their composition, life span, pH and temperature and then were applied to the potentiometric determination of the amitriptylinium ion in its pure state and pharmaceutical preparations and flow injection conditions. The selectivity of the electrodes towards many inorganic cations, sugars and amino acids was also tested. [Copyright &y& Elsevier]

Published
2004
Full Text
View/download PDF

22. Localização de robôs móveis utilizando o novo algoritmo de Morcegos baseado em Líderes

Author

Araujo Neto, Wolmar, Marcato, André Luís Marques, Silva Junior, Ivo Chaves da, Belati, Edmarcio Antonio, Oliveira, Fernando Luiz Cyrino, Oliveira, Leonardo Willer de, and Aguiar, Eduardo Pestana de

Subjects
Robôs móveis, Localização, Localization, Mobile robots, ENGENHARIAS::ENGENHARIA ELETRICA [CNPQ], Algoritmo de morcegos, Localização de Monte Carlo adaptativa, AMCL, Bat algorithm
Abstract

Um problema estocástico complexo de importância essencial em aplicações de robôs móveis é a localização do robô. Esta pode ser tratada como um problema de otimização, devido à sua característica de apresentar diferentes possíveis soluções (mínimos locais). O método proposto nesse trabalho é baseado no Algoritmo de Morcegos, o qual apresentou melhores resultados para o problema de localização global e sequestro de robô quando comparado com outros métodos da literatura. Apresentou-se resultados favoráveis tanto para localização global, com uma celeridade tão hábil quanto os algoritmos comparados, como resultados significativos em uma situação de sequestro de robô. A nome proposto para a modificação do algoritmo clássico de morcegos foi Algoritmo de Morcegos Baseado em Líderes (Leader-Based Bat Algorithm - LBBA), em virtude de ter a característica de simular ações de líderes de grupo, os quais influenciam outros menos qualificados. A consequência da utilização de mais de um líder implica em uma busca, da melhor posição, mais diversificada no mapa, lidando melhor com cenários que apresentem muitas ambiguidades no decorrer da localização. Foram realizados testes em diferentes cenários (além do teste em um mapa real). O algoritmo bioinspirado de morcegos na sua forma clássica (BA) foi comparado com outros algoritmos (otimização de enxame de partículas - PSO e Filtro de Partículas - FP) e obteve bons resultados. Estes inspiraram a proposta de uma variante no algoritmo de morcegos capaz de lidar com situações mais complexas de localização onde o BA apresentava dificuldades, o LBBA obteve resultados notáveis quando comparado com Localização de Monte Carlo Adaptativa (AMCL). A complex stochastic problem of essential importance in mobile robot applications is the location of the robot. This can be treated as an optimization problem, due to its characteristic of presenting different possible solutions (local minimums). The method proposed in this work is based on the Bats Algorithm, which presented better results for the problem of global localization and robot sequestration when compared to other methods in the literature. We presented favorable results for both global localization, with a speed as skillful as the compared algorithms, as significant results in a robot sequestration situation. The proposed name for the modification of the classic bats algorithm was Leader-Based Bat Algorithm (LBBA), because it has the characteristic of simulating actions of group leaders, which influence others less skilled. The consequence of using more than one leader implies a search, the best position, the most diversified on the map, dealing better with scenarios that present many ambiguities during the localization. Tests were performed in different scenarios (besides the test on a real map). The bio - inspired algorithm of bats in its classical form (BA) was compared with other algorithms (particle swarm optimization - PSO and Particle Filter - FP) and obtained good results. These inspired the proposal of a variant in the bats algorithm capable of dealing with more complex situations of location where the BA presented difficulties, the LBBA obtained remarkable results when compared to Monte Carlo Adaptive Location (AMCL).

Published
2019

23. Navegación de robots móviles en entorno Matlab-ROS

Author

Carrasco Limeros, Sandra, López Guillén, María Elena, and Universidad de Alcalá. Escuela Politécnica Superior

Subjects
Localización, Navegación autónoma, PRM, Robótica e Informática Industrial, ROS (Robot Operating System), SLAM (Simultaneous Localization and Mapping), Robotics, Mapeado, VFH, Spline, CARLA Challenge, AMCL, Robotics System Toolbox, GMapping, Planificación
Abstract

En el presente documento se describe el proceso llevado a cabo para desarrollar una serie de aplicaciones relacionadas con la navegación autónoma de robots móviles destinadas al ámbito docente y de investigación, utilizando como entorno la Robotics System Toolbox de Matlab y ROS. Estas incluyen algoritmos de: mapeado y SLAM, localización (AMCL), evitación de obstáculos (VFH), seguimiento de pasillos usando lógica difusa y la transformada de Hough, y planificación global (PRM). Además, se diseña un aplicación para el guiado de vehículos autónomos en el simulador CARLA, con la cual se participa en el primer CARLA Challenge, celebrado entre abril y junio del 2019., The main aim of this project is to develope a set of algorithms related to autonomous navigation in the academic and research fields. They were implemented in a ROS-Matlab environment, using the Robotics System Toolbox framework. The algorithms cover a wide range of applications: mapping and SLAM, localization (AMCL), obstacle avoidance (VFH), hallway tracking using fuzzy logic and Hough Transform, and global planning (PRM). Furthermore, an aditional goal was set. The design and implementation of an application for an automated guided vehicle in CARLA simulator, with the participation in the first CARLA Challenge., Grado en Ingeniería en Electrónica y Automática Industrial

Published
2019

24. Svjesnost humanoidnog robota Pepper o prostoru scene u predstavi R.U.R

Author

Barišić, Josip and Kovačić, Zdenko

Subjects
orijentacija, path following, TEHNIČKE ZNANOSTI. Elektrotehnika, ROS, mapa, robot Pepper, ROS, orijentacija, mapa, AMCL, slijeđenje putanje, 3D kamera, 3D camera, AMCL, 3D kamera, orientation, TECHNICAL SCIENCES. Electrical Engineering, map, robot Pepper, slijeđenje putanje
Abstract

Razraditi način za projektiranje virtualnog modela scene koji će omogućiti robotu da bude svjestan značajki svih elemenata prostora (lokacija, funkcija, sigurnost i dr.) u kojem se predstava odvija (primjerice pomoću XML datoteke). Razmotriti mogućnost dinamičke promjene prostornih značajki scene (nestajanje sa scene, pojavljivanje, pomicanje/rotiranje, povećanje/smanjenje i dr.). Koristiti tako dobiveni model scene za rješavanje problema početne lokalizacije robota tijekom odvijanja predstave. Na temelju poznate početne lokacije robota i podloga o ulozi robota kod odvijanja pojedinih scena nastalih iz scenske analize predstave RUR, treba za planiranje putanje robota implementirati algoritam čistog slijeđenja. Kao dodatni mogući način navigacije robota, razmotriti korištenje markera (primjerice linija na podu ili markera instaliranih u okolini) za slijeđenje putanja primjenom vizualne povratne veze. .

Published
2018

25. Cleaning up Smart Cities - Localization of Semi- Autonomous Floor Scrubber

Author

Čelan, Višeslav, Stančić, Ivo, and Musić, Josip

Subjects
service robotics, localization, AMCL, UWB, floor scrubber
Abstract

The paper describes design and features of novel semi-autonomous floor scrubber add-on module, used for cleaning large indoor and outdoor tile/marbles spaces found in modern (smart) cities. Module is designed in such a manner that it can be easily added to and removed from scrubber machine and that additional sensors and capabilities can be introduced (modular design). In the paper localization capabilities of the machine in three sensor setups are presented and analyzed. Analysis is performed in terms of localization accuracy and reliability as well as associated advantages and disadvantages. Obtained results demonstrated that inclusion of UWB subsystem, despite its price and accuracy ( 20 cm in ideal, line of sight, conditions), yields more reliable and accurate results in open spaces (up to 25 times in position and 2 times in orientation) where performance of used Lidar might be sub-optimal.

Published
2016

26. Improvement of Mobile Robot Localisation Accuracy by Using Multiple Laser Range Sensors

Author

Ovčarić, Gordan and Kovačić, Zdenko

Subjects
OptiTrack system, MATLAB, TEHNIČKE ZNANOSTI. Elektrotehnika, OptiTrack, gmapping, laser rangefinder SICK-LMS100, ROS, AMCL, laser SICK-LMS100, mobilni robot Pioneer P3-DX, TECHNICAL SCIENCES. Electrical Engineering, SLAM, mobilna robotika, lokalizacija, mapiranje, Pioneer P3-DX, laserski senzor udaljenosti, SICK LMS100, p2os, mobile robot Pioneer P3-DX
Abstract

Zadatak ovog završnog rada bio je ispitati toˇcnost lokalizacije mobilnog robota Pioneer P3-DX pomo´cu AMCL (eng. Adaptive Monte Carlo Localization) algoritma. Laserski senzori udaljenosti SICK LMS100 spojeni su na robota za potrebe mjerenja. Mjerenje je obavljeno prvo sa jednim laserskim senzorom udaljenosti, a zatim i istovremeno sa dva. Za generiranje karte prostora i lokalizaciju na dobivenoj karti koristili su se gotovi algoritmi implementirani u ROS (eng. Robot Operating System) operacijskom sustavu za rad s robotima. Rezultati lokalizacije AMCL algoritma provjereni su pomoću visoko preciznog OptiTrack sustava praćenja objekata. Rezultati su prikazali kako AMCL zadovoljava osnovne uvjete lokalizacije, te je precizan do određene granice. Također su rezultati pokazali da AMCL postaje zamjetno precizniji korištenjem dva laserska senzora udaljenosti istovremeno u usporedbi sa samo jednim. The task of this bachelor thesis was to investigate the accuracy of localization of mobile robot Pioneer P3-DX using AMCL (Adaptive Monte Carlo Localization) algorithm. For the purpose of measurement two laser rangefinder sensors SICK LMS100 were connected to the robot. The measurement was performed first with a single laser rangefinder sensor, and then with two of them at the same time. To generate maps of workspace, and localize on those maps, algorithms implemented in ROS (Robot Operating System) were used. Results of AMCL localization algorithms have been tested using high precision OptiTrack objects tracking system. Results show that AMCL meets the basic requirements of localization, but only to a certain point. Also, the results showed that AMCL becomes noticeably more precise when using two laser rangefinder sensors simultaneously instead of just one.

Published
2014

27. A Deep Learning Approach To Coarse Robot Localization

Author

Bettaieb, Luc Alexandre

Subjects
Robotics, Computer Science, Electrical Engineering, robotics, localization, deep learning, neural networks, machine learning, state estimation, robots, robot, robot operating system, ROS, AMCL, monte carlo localization, particle filter, ConvNets, convolutional neural networks
Abstract

This thesis explores the use of deep learning for robot localization with applications in re-localizing a mislocalized robot. Seed values for a localization algorithm are assigned based on the interpretation of images. A deep neural network was trained on images acquired in and associated with named regions. In application, the neural net was used to recognize a region based on camera input. By recognizing regions from the camera, the robot can be localized grossly, and subsequently refined with existing techniques. Explorations into different deep neural network topologies and solver types are discussed. A process for gathering training data, training the classifier, and deployment through a robot operating system (ROS) package is provided.

Published
2017

Catalog

Books, media, physical & digital resources
See catalog results