Development of Ball Detection System with YOLOv3 in a Humanoid Soccer Robot

One of the practical researches of humanoid robots is research on the use of humanoid robots to play soccer. Research in this field is also encouraged by the existence of various humanoid robot soccer competitions. In humanoid robots for soccer, one of the important aspects is the robot’s ability to detect the ball, goal, field boundaries and other players, both friend players and opposing players. This study focuses on the ball detection system which is a basic ability that humanoid robots need to have. The ball detection system developed in this study uses the YOLOv3 method. The test results show that the system built and trained with 3000 image samples can detect balls at a distance of 50 to 900 cm. The time it takes to detect the ball is about 0.033 seconds.

Establishing ROS on Humanoid Soccer Robot-BarelangFC Software System

Humanoid robot is built on several sub-programs or systems which is integrated to each main programs in order to command the robot to move as a soccer player. Each main programs namely as a movement system, a visual sense system (vision), a sub-controller system, and a game strategy. Currently, each of main system constructed using different programming language, for instance: the vision system used python while the others used C and LUA for the movement kinematics. Employing different programming language will affect to response system because each of main system need to be integrated using socket in the beginning process. Robot response will be slow and cost a lot of memory usage. Therefore, in this paper will present a migrating process into robot operating system (ROS) and switch all the robot main system into python language. The integrated program will be examined in real-time application while the robot moved on the field. We used a python ROS in order to make the robot play autonomously on the field.

ADVANCE ATTACK AND DEFENSE STRATEGY ALGORITHM WITH DYNAMIC ROLE ASSIGNMENT FOR WHEELED SOCCER ROBOT

Game strategy is one of the most critical parts of winning a soccer robot match and cannot be separated from the cooperation among robots in making movements to score goals. In this paper, a wheeled soccer robot game strategy called advance attack and defense has been developed. The strategy is combined with dynamic role assignment, in which robot can change from an attacker to a defender and vice versa. Defender robots are not only based on defensive area but will always block opposing attacker to score goal. The attack strategy performs a rotational trajectory for attacker robot to overpass opponent robot. This strategy has been proven to increase defense and attack effectiveness. Test results using soccer robot gameplay environment simulator developed by Institut Teknologi Sepuluh Nopember Robot with Intelligent System (IRIS) team show that the advance strategies are superior compared with basic strategies. In 30 matches, the advance dynamic strategy won 80%, drew 6.7%, and obtained the highest goal difference, 85 goals. The test was then verified with the implementation in the IRIS robots and showed the same performance. The developed game algorithms were tested in 2019 Indonesian wheeled soccer robot contest (KRSBI-B) and the IRIS team won the title.

Sistem Kontrol Robot Sepak Bola Beroda menggunakan Finite State Machine (FSM)

ABSTRAKPerkembangan teknologi menuntut transisi alat yang berbasis manual menjadi otomatis. Hal ini tak terkecuali pada perkembangan robot, termasuk robot sepak bola. Robot ini mengalami perkembangan sangat pesat. Hal ini didukung dengan adanya Kontes Robot Sepak Bola Indonesia (KRSBI). Penelitian kali mengusulkan robot sepak bola beroda dengan omni-directional weel sebagai pergrakannya menggunakan Finite State Machine (FSM) sebagai metode kontrol untuk menjalankan misi yang ditentukan. Misi robot yang dikembangkan yaitu mencari bola (wander), mencari posisi lurus terhadap bola, mencari gawang, dan menendang bola. Robot ini menggunakan CMUCam5 sebagai sensor masukan untuk mendeteksi bola sebagai target bedasarkan warna dan jarak. Jarak yang digunakan yaitu antara 20 cm sampai 60 cm dengan sudut antara -40 derajat sampai 40 derajat dan intensitas cahaya antara 113 sampai 1213 lux. Implementasi FSM pada robot sepak bola beroda dengan 5 jenis percobaan mencapai tingkat keberhasilan yang bagus yaitu 86% dengan rata-rata waktu menjalankan misi 29.24 detik.Kata kunci: CMUCam5, Finite State Machine, Omni-directional wheel, Robot Sepak Bola ABSTRACTTechnological development demands a transition from manual to automatic tools. It includes soccer robots that have developed so rapidly. This development is supported by the Indonesian Football Robot Contest (KRSBI). This study proposes a wheeled soccer robot with Omni-directional weel as its movement using Finite State Machine (FSM) as a control to carry out the specified mission. The mission is wandering to seek the ball, looking for a straight position to the ball, looking for the goal, and kicking the ball. This robot uses CMUCam5 as an input to detect the ball as a target based on color and distance. The distance used is between 20-60 cm with an angle of -40 degree to 40 degree and light intensity between 113-1213 lux. The implementation of FSM on a wheeled soccer robot with five types of experiments achieved a good result of 86% with an average mission time of 29.24 seconds.Keywords: CMUCam5, Finite State Machine, Omni-directional weel, Wheeledsoccer robot