Deteksi Fitur dan Penentuan Posisi Humanoid Soccer Robot dalam Lapangan Standar Robocup Bebasis Sensor Orientasi dan Penanda Tidak Unik

Dahlan, Ach Hadi (2014) Deteksi Fitur dan Penentuan Posisi Humanoid Soccer Robot dalam Lapangan Standar Robocup Bebasis Sensor Orientasi dan Penanda Tidak Unik. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 2210100180_Undergraduate_Thesis.pdf Restricted to Repository staff only Download (2MB) | Request a copy

Abstract

Dalam strategi sepak bola robot, kemampuan dasar yang harus dimiliki setiap robot adalah kemampuan mengenali fitur-fitur dalamlapangan. Fitur yang dimaksud adalah bola, gawang dan garis. Dengan mengetahui fitur-fitur yang ada, robot dapat memperkirakan posisidirinya dalam lapangan pertandingan. Koordinat didapatdari metode triangulasi sedangkan diperoleh dari sensor orientasi yang ditanam pada robot sebagai modul tambahan. Sehingga dengan mengetahui estimasi posisi di lapangan, robot akan lebih mudah dalam melakukan strategi permainan. Pada tugas akhir ini dibahas mengenaipengenalan fitur lapangan berupa bola, gawang dan tepi lapangan.Pendeteksian gawang dilakukan menggunakan transformasi garis Hough.Metode Polynomial curve fitting diterapakan untuk menentukan jarak robot dengan gawang berdasarkan perbandingan tinggi (piksel) dan jarak(meter). Dalam aturan RoboCup 2013, gawang yang terdapat di lapangan memiliki warna yang sama yaitu kuning. Untuk dapat membedakan gawang lawan dan gawang sendiri digunakan masukan berupa sudut dari sensor orientasi. Pada pendeteksian bola, robot dapat membedakan boladan objek diluar lapangan yang memiliki warna sama dengan bola. Danjarak maksimal pendeteksian bola adalah 4,5 meter. Hasil penentuanposisi robot di lapangan cukup akurat dengan rata-rata galat 0,1154 meter.Untuk lebih mudah dalam melakukan strategi permainan, maka lapangan dibagi dalam 24 grid. Dari grid-grid tersebut perilaku robot ditentukan.
=============================================================================================================================
In humanoid soccer robot strategy, basic ability which every robot must have the ability to recognize features in the field. The features are a ball, the goals and field line. By knowing the features, robot can estimate his position in the field. Coordinates obtained from the triangulation method, and obtained from the orientation sensors which planted in the robot. If it was equipped with a self-localization module, he could participate in global decision making for his team's best interest, such as game strategy, team coordination and role assignment among the players. This final project discussed about features extraction for the ball, goal and field boundary. Goal identification is done by applying hough transform to detect lines that represent goalposts and crossbar. Polynomial curve fitting method used to get the distance between robot and the goal. In the RoboCup 2013’s rules, the goal between opponent and our goal have the same color. To improve our robot performance, an orientation sensor was added. This sensor can be used to distinguish between oponent’s side and our side. At this research robot can distinguish the ball and objects outside the field that has the same color with the ball. And the maximum distance of ball detection is 4.5 meters. The results of self-localization in the field is quite accurate with an average error 0.1154 meters.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	RoboCup, penanda tidak unik, sensor orientasi, ekstraksi fitur, penentuan posisi, triangulasi. RoboCup, non unique landmark, orientation sensor, feature extraction, localization, triangulation
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5105.585 TCP/IP (Computer network protocol)
Divisions:	Faculty of Industrial Technology > Electrical Engineering > 20201-(S1) Undergraduate Thesis
Depositing User:	Eko Sulistiono
Date Deposited:	22 Sep 2025 04:05
Last Modified:	22 Sep 2025 04:05
URI:	http://repository.its.ac.id/id/eprint/128338

Actions (login required)

View Item