Navigasi Indoor Berbasis Peta pada Robot Beroda dengan Platform Robot Operating System

Putra, Tara Anggada; Muliady, Muliady; Setiadikarunia, Daniel

doi:10.25105/jetri.v17i2.5447

Cited by 3 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…memiliki tingkat keberhasilan 62,5% dalam menghasilkan jalur yang dapat dilewati robot dan robot memiliki tingkat keberhasilan 75% dalam mengikuti jalur. Robot memiliki tingkat kesalahan rata-rata 0,046m dalam bergerak menuju koordinat x target, 0,072m dalam bergerak menuju koordinat y target, dan 5,163 dalam berputar menuju sudut orientasi target [3].…”

Section: Pendahuluanunclassified

Sistem Lokalisasi Robot Humanoid Menggunakan Monocular Camera dan IMU

Rizaldy

Siradjuddin²,

Winarno³

2022

Elkolind

View full text Add to dashboard Cite

Robot humanoid merupakan jenis robot yang menyerupai bentuk tubuh manusia dengan motor servo ynag terpasang pada seluruh bagian tubuhnya. Fungsi dari robot ini yaitu membantu pekerjaan manusia untuk menyelesaikan masalah. Dalam kinerja robot ini diperlukan sistem lokalisasi sebagai umpan balik agar dapat diketahui posisinya sekarang. Kemampuan mengetahui posisi robot ini sangat penting perannya agar sistem jalan robot dapat terarah. Visual Odometry merupakan tipe sistem lokalisasi yang digunakan untuk mengetahui posisi dan orientasi menggunakan kamera tunggal. IMU merupakan sensor yang digunakan untuk mengetahui orientasi robot. Sistem lokalisasi ini dibutuhkan lebih dari satu sensor agar pembacaan data memiliki akurasi yang tinggi. Penggunaan kamera untuk mengetahui posisi dan orientasi akan menyebabkan drift yang menyebabkan tidak akuratnya pembacaan posisi. Dengan permasalahan ini, dibutuhkan penyaringan data odometry dengan menggunakan Extended Kalman Filter yang ada pada Robot Localization, sebuah package yang disediakan ROS untuk melakukan lokalisasi dengan masukan data odometry, pose, twist dan IMU. Output dari filter ini memiliki tingkat akurasi posisi sebesar 18,3% dan orientasi sebesar 5,2%

show abstract

Section: Pendahuluanunclassified

Sistem Lokalisasi Robot Humanoid Menggunakan Monocular Camera dan IMU

Rizaldy

Siradjuddin²,

Winarno³

2022

Elkolind

View full text Add to dashboard Cite

show abstract

“…The relative position of the robot is obtained through the AMCL Particle Filter algorithm by processing wheel odometry data. Wheel Odometry calculates the position of the robot based on the rotation of the wheel obtained from the rotary encoder which produces data on the linear speed of the robot on the x and y axes, the angular speed of the robot on the z-axis, and the angle of orientation of the robot on the z-axis (θ or yaw) [33].…”

Section: Navigation Systemmentioning

confidence: 99%

RPLiDAR-Based Mapping in Development of a Health Service Assisting Robot in COVID-19 Pandemic

Maknuny,

Ramadhan,

Turnip

et al. 2022

ICSECC

View full text Add to dashboard Cite

Due to the Covid-19 pandemic, robots with various functions in the health sector are growing, one of which is autonomous robots capable of supporting logistics, drug and food delivery, and monitoring the environment. In this study, a map-based indoor navigation system was developed on health service assisting robot based on LiDAR and Robot Operating System (ROS) platform. The robot with the SLAM GMapping algorithm was succeeded to perform mapping with an accuracy of 95.983%. Then the robot with an automatic navigation system using the AMCL Particle Filter algorithm for localization was succeeded to perform localization with an error of 1.3377 on the x-axis and 1.2109 on the y-axis and 45,72570 for orientation on the z-axis. And succeeded to do trajectory tracking using the move_base package for path planning with an error of 1.6477 on the x-axis and 0.4498 on the y-axis when moving towards the target coordinates.

show abstract

“…As a result, the mobile robot will require another autonomous navigation system in order to travel freely in the inside environment [3].…”

Section: Introductionmentioning

confidence: 99%

Performance Analysis of Hector Slam and Gmapping for Navigation for Mobile Robot Navigation

Laksono

Kusuma

2022

tekno

View full text Add to dashboard Cite

One of the most significant elements of a moving robot is mapping. The robot's capacity to identify its surroundings and translate them into a map allows it to navigate effectively from one spot to another while avoiding impediments that may arise during the navigation process. The SLAM method already has a mapping capability, so it can continuously localize the position against the map. In this experiment, 2D laser scanning data was obtained using RPlidar-A1 and then processed by the slam algorithm, namely gmapping and hector mapping to produce an occupancy grid map. The map is displayed by the RViz visualization widget, and its length is measured using the RViz measurement tools. The results of the occupancy grid map generated by the gmapping algorithm with a laser scan matcher have a lot of noise, and lose orientation. At the measured point length, the gmapping algorithm has slightly more error. The hector mapping algorithm has better performance than gmapping with a laser scan matcher on the RPLidar-A1 device.

show abstract

Navigasi Indoor Berbasis Peta pada Robot Beroda dengan Platform Robot Operating System

Cited by 3 publications

References 5 publications

Sistem Lokalisasi Robot Humanoid Menggunakan Monocular Camera dan IMU

Sistem Lokalisasi Robot Humanoid Menggunakan Monocular Camera dan IMU

RPLiDAR-Based Mapping in Development of a Health Service Assisting Robot in COVID-19 Pandemic

Performance Analysis of Hector Slam and Gmapping for Navigation for Mobile Robot Navigation

Contact Info

Product

Resources

About