Robot Football Research Articles

Comparison between an Adaptive Gain Scheduling Control Strategy and a Fuzzy Multimodel Intelligent Control Applied to the Speed Control of Non-Holonomic Robots

The main objective of this work is to address problems related to the speed control of mobile robots with non-holonomic constraints and differential traction—specifically, robots for football games in the VSS (Very Small Size) category. To achieve this objective, an implementation and comparison is carried out between two control strategies: an adaptive control strategy by gain scheduling and a fuzzy multimodel intelligent control strategy. The mathematical models of the wheel motors for each operating range are approximated by a first-order system since data acquisition is performed using the step response. Tuning of the proportional and integral gains of the local controllers is carried out using the root locus technique in discrete time. For each mathematical model obtained for an operating range, a local controller is tuned. Finally, with the local controllers in hand, the implementation of and comparison between the gain scheduling adaptive control strategy and the fuzzy multimodel intelligent control strategy are carried out, in which the control strategies are programmed into the low-level code of a non-holonomic robot with a differential drive to verify the performance of the speed tracking dynamics imposed on the wheel motors to improve robot navigation during a robot football match.

Real-time Ball Detection and Tracking using Raspberry PI

This paper presents a real-time system for ball detection and tracking system which is reliable in any conditions. Images from the webcam are processed by openCV library running on a Raspberry Pi to move the camera pan and tilt servo and two DC motors to drive the robot body using the Arduino Nano microcontroller. The webcam is integrated in a robot prototype to represent the wheel football robot type. The results show that a ball tracking webcam system is obtained with the capability to detect a ball with a diameter of 17cm within a maximum distance of 200 cm, a stable ball reading when the light intensity is at 32 lux and above. Furthermore, the experimental results demonstrated the system’s robustness in detecting and tracking ball in different distance and ligthing conditions.

Scaling multi-agent reinforcement learning to full 11 versus 11 simulated robotic football

Robotic football has long been seen as a grand challenge in artificial intelligence. Despite recent success of learned policies over heuristics and handcrafted rules in general, current teams in the simulated RoboCup football leagues, where autonomous agents compete against each other, still rely on handcrafted strategies with only a few using reinforcement learning directly. This limits a learning agent’s ability to find stronger high-level strategies for the full game. In this paper, we show that it is possible for agents to learn competent football strategies on a full 22 player setting using limited computation resources (one GPU and one CPU), from tabula rasa through self-play. To do this, we build a 2D football simulator with faster simulation times than the RoboCup simulator. We propose various improvements to the standard single-agent PPO training algorithm which help it scale to our multi-agent setting. These improvements include (1) using a policy and critic network with an attention mechanism that scales linearly in the number of agents, (2) sharing networks between agents which allow for faster throughput using batching, and (3) using Polyak averaged opponents, league opponents and freezing the opponent team when necessary. We show through experimental results that stable training in the full 22 player setting is possible. Agents trained in the 22 player setting learn to defeat a variety of handcrafted strategies, and also achieve a higher win rate compared to agents trained in the 4 player setting and evaluated in the full game.

Verification of a Newly Developed Mobile Robot’s Actuator Parameters

This paper addresses the issue of the verification and comparison of the selected properties of a newly developed electric actuator. This actuator is intended to act as the drive of a walking robot designed for robotic football. Its envisioned placement is inside the robot’s knee joint and in its upper part. An integral part of the actuator is a harmonic precision gearbox and an absolute rotation sensor. The prototype of the newly developed actuator consists of both aluminum and 3D-printed parts. The selected parameters were verified according to the selected characteristics of ISO standard 9283, namely a one-directional pose accuracy and repeatable pose accuracy. The obtained data were compared with those of the standard actuator used thus far in constructing robots for robotic football. The implemented verification is based on the need to improve the performance parameters of the actuator while ensuring the sufficient accuracy of stopping the actuator in the required position. This is ensured by the use of a more accurate harmonic reducer and rotation sensor compared to the standard actuator.

PERANCANGAN APLIKASI BASE STATION DALAM SISTEM KOORDINASI ROBOT SEPAK BOLA BERODA DENGAN MULTI THREAD

The Indonesian Wheeled Football Robot Contest (KRSBI Beroda) is one of the divisions of the Indonesian Robot Contest (KRI). At KRSBI Beroda robots are expected to be able to move automatically by using the Base Station as a communication center between robots in the same team. Base Station has a function to forward orders from the referee or RefBox (Referee Box) to the robot. This study aims to add features to the Base Station by displaying the position of two robots in the field in animation using the multi-thread method to facilitate strategy formulation. The result is that the Base Station that is made can display the position of two robots in the field without any errors.

Implementation of Base Station as An Intermediary Referee Box in the delivery of Wheeled Football Robot Movement Commands

In the contest of Indonesian wheeled robot football or KRSBI wheeled robot which competes with wheeled football robots, there is a referee who controls the course of the match, the referee box. For referee box to provide commands that can set the course of the robot, a base station is required that serves to receive data from the referee box and translated and then sent it to the robot. The use of TCP socket programming is quite successful whereby 17 attempts to send commands from referee box can be accepted all by base station with a success rate of 100%. The use of robot operating system (ROS) to pass data in the form of coordinate points and commands for robots chasing balls or stops was also successfully carried out where from 17 attempts the delivery of orders, it can reach 100% success rate. After that, the measurement of distance analysis against quality of service (QoS) with 3 different distances, and obtained the following results, at a distance of 3 meters obtained an average delay of 44.41 ms, throughput of 767.29 kbps and no missing package, at a distance of 8 meters obtained an average delay of 7.22 ms, an average throughput of 1065.17 kbps and no missing packages, lastly at a distance of 15 meters obtained an average delay of 103.99 ms, an average throughput of 835.51 kbps and there was a missing package of 6.9% on 1 order so that the average lost package was obtained by 0.405%.

Application of Deep Learning Technology in Strength Training of Football Players and Field Line Detection of Football Robots.

The purpose of the study is to improve the performance of intelligent football training. Based on deep learning (DL), the training of football players and detection of football robots are analyzed. First, the research status of the training of football players and football robots is introduced, and the basic structure of the neuron model and convolutional neural network (CNN) and the mainstream framework of DL are mainly expounded. Second, combined with the spatial stream network, a CNN-based action recognition system is constructed in the context of artificial intelligence (AI). Finally, by the football robot, a field line detection model based on a fully convolutional network (FCN) is proposed, and the effective applicability of the system is evaluated. The results demonstrate that the recognition effect of the dual-stream network is the best, reaching 92.8%. The recognition rate of the timestream network is lower than that of the dual-stream network, and the maximum recognition rate is 88%. The spatial stream network has the lowest recognition rate of 86.5%. The processing power of the four different algorithms on the dataset is stronger than that of the ordinary video set. The recognition rate of the time-segmented dual-stream fusion network is the highest, which is second only to the designed network. The recognition rate of the basic dual-stream network is 88.6%, and the recognition rate of the 3D CNN is the lowest, which is 86.2%. Under the intelligent training system, the recognition accuracy rates of jumping, kicking, grabbing, and starting actions range to 97.6, 94.5, 92.5, and 89.8% respectively, which are slightly lower than other actions. The recognition accuracy rate of passing action is 91.3%, and the maximum upgrade rate of intelligent training is 25.7%. The pixel accuracy of the improved field line detection of the model and the mean intersection over union (MIoU) are both improved by 5%. Intelligent training systems and the field line detection of football robots are more feasible. The research provides a reference for the development of AI in the field of sports training.

Stability and Dynamic Walk Control of Humanoid Robot for Robot Soccer Player

Robotic football with humanoid robots is a multidisciplinary field connecting several scientific fields. A challenging task in the design of a humanoid robot for the AndroSot and HuroCup competitions is the realization of movement on the field. This study aims to determine a walking pattern for a humanoid robot with an impact on its dynamic stability and behavior. The design of the proposed technical concept depends on its stability management mechanism, walking speed and such factors as the chosen stability approaches. The humanoid robot and its versatility, along with the adaptability of the terrain, are somewhat limited due to the complexity of the walking principle and the control of the robot’s movement itself. The technical concept uses dynamic stability as the potential force of the inertial bodies and their parts so that the humanoid robot does not overturn. The total height of the robot according to the rules of the competition will be 50 cm. In the performed experiment, only the lower part of the humanoid robot with added weight was considered, which is more demanding due to the non-use of the upper limbs for stabilization. The performed experiment verified the correctness of the design, where the torso of the robot performed eight steps in inclinations of a roll angle +4/−2° and a pitch angle +4/−6°.

Cooperation Mode of Soccer Robot Game Based on Improved SARSA Algorithm

Football is one of the most popular sports in the world, and its competition has received increasing people’s attention. With the increasing number of robot football competitions, more strategic planning is needed for robot football matches. In a tournament, each player has their own task and must have the skills to complete it. In this paper, we use the RoboCup2D platform to give details of the server and client roles, introduce the agent model in RoboCup2D, and compare the plan design and scheme design presented in the current study using the SARSA algorithm, one of the augmented methods classified as TD learning metrics. In addition, heuristic information was introduced and implemented to enhance learning through the sharing of Q values between participants and reinforcement learning. A comparative analysis of the feasibility of the SARSA algorithm in the context of its application in RoboCup2D was carried out, and the experimental results proved that our algorithm was effective in improving the team’s offensive and defensive capabilities.

Exploring intelligent image recognition technology of football robot using omnidirectional vision of internet of things

Exploring intelligent image recognition technology of football robot using omnidirectional vision of internet of things

Perancangan Sistem Pengisian Capacitor Bank Secara Otomatis Pada Penendang Solenoid Robot Sepak Bola Universitas Jambi

One of the KRI fields is the Indonesian Football Robot Contest (KRSBI). In a match the robot does not know when the ball from the robot in one team is ready to be kicked into the opponent's goal. The kicking robot has an important role in creating goals against the opponent's goal. At the KRSBI solenoid kicker, Jambi University, using a booster converter zvz 390 to charge a capacitor bank which has a capacitance of 3900 F with a high voltage of 387 V, takes 6.34 seconds. However, 387 V is the maximum booster converter voltage. To minimize the occurrence of damage, a voltage of 310 V is set as the setpoint voltage for charging the capacitor bank with a charging time span of 4.3 seconds. Then the automatic control system for charging capacitor banks has a maximum error of 1.9%

Action Design of Lobbing Ball for Humanoid Robot Soccer

Robot soccer is a classic research direction in the field of robotics. From the appearance of soccer robot, it is mainly divided into wheeled robot and humanoid robot. At present, humanoid robots and small group wheeled robots mainly compete on two-dimensional plane. Because of the small competitive dimension, the offensive and defensive tactics tend to be simple. In order to enhance the competitiveness and appreciation of humanoid. And complex motion devices based on human motion capture data (HMCD) are designed Human simulation has gradually become one of the effective means of robot design. In order to enhance the competitiveness and appreciation of humanoid, this paper innovatively designs a set of consistent kicking actions based on darwin-op2 robot, combined with HMCD method, realizes the effect of actively lobbing ball. Ideally, the robot can basically kick the ball above 35cm. Besides the robot can basically kick the ball above 30cm in practice, and the success rate is as high as 75%. It improves the competitiveness from two-dimensional to three-dimensional, which provides new ideas and schemes for attack and defense tactics and expands the dimension of competition. It also provides a new direction for the development of humanoid robot football in the future.

Robotic Football: Developing Engineering Leaders Through Competition

Design is a fundamental component in various engineering curricula. Programs across the nation teach this component via design projects in different courses, culminating in a capstone design course in the final year. While these projects may achieve the goal of teaching the use of mathematics and sciences to meet design objectives and constraints, they are limited in terms of the team size, scope of the project, and diversity of team members.

Real-Time Evaluation Algorithm of Human Body Movement in Football Training Robot

As one of the most challenging topics in the field of artificial intelligence, soccer robots are currently an important platform for humanoid robotics research. Its fields cover a wide range of fields, including robotics, artificial intelligence, and automatic control. Kinematics analysis and action planning are the key technologies in the research of humanoid soccer robots and are the basis for realizing basic actions such as walking. This article mainly introduces the real-time evaluation algorithm of human motion in the football training robot. The football robot action evaluation algorithm proposed here designs the angle and wheel speed of the football robot movement through the evaluation of the angular velocity and linear velocity of the center of mass of the robot. The overall system of the imitation human football robot is studied, including the mechanical system design. The design of the leg structure, the decision-making system based on the finite state machine, the robot vision system, and the image segmentation technology are introduced. The experimental results in this article show that the action of the football training robot model is very stable, the static rotation movement time is about 220 ms, and the fixed-point movement error is less than 1 cm, which fully meets the accuracy requirements of the large-space football robot.

PERANCANGAN SISTEM NAVIGASI ROBOT SEPAKBOLA BERODA DENGAN MENGGUNAKAN METODE GREEDY

Development in the world of robotics at this time is growing where robots can be useful in every human activity, the role of robots at this time canalready help in human work. In Indonesia, robot contests have been held every year at both regional and national levels. One of the categories to bediscussed in this research is the Indonesian Football Robot Contest (KRSBI). In the indonesian football robot contest is divided into two more categories,namely humanoid division football robot and wheel division football robot. In this category, robots must be able to navigate to find the ball and kicktowards the goal. The main objective of this robot is to navigate and search for the ball to reach the opponent's goal. However, at the time of the matchthe robot has problems in the ball search system quickly, so it can slow down in taking the decision to chase the ball because the robot can not knowthe distance of the ball and the robot. One solution that can help the problem in wheeled football robots is to add greedy methods to wheeled footballrobots in taking the best option. So that the robot can vaccinate quickly and can chase the ball well. The test area uses a field of 180cm x 360cm. Thetest is declared successful if the robot can reach the ball and avoid the obstacle. From the test results, the robot managed to reach the ball well, so it canbe concluded that the robot can navigate using the greedy algorithm

Holonomic Implementation of Three Wheels Omnidirectional Mobile Robot using DC Motors

In the Indonesian Wheeled Football Robot Contest (KRSBI) wheeled division, the robot that is made must be able to complete a predetermined task, one of which is the robot for chasing the ball and catching it. Holonomic is one of the methods used in navigating the omnidirectional movement of mobile robot applications. Because the movement is designed without changing the position of the robot in the direction of the facing, the omnidirectional wheels are used which has the ability to move freely in two directions. The mobile robot has three omnidirectional wheels and DC motors each used for movement. DC motors controlled by EMS 30A H-Bridge as a driver and Arduino Mega 2560 as the main microcontroller. Holonomic and inverse kinematic calculations are conducted to control the mobile robot movement of x, y, and ω toward angular velocity and direction of s1, s2, and s3 for each wheel. The length of the wheel axis to the middle of the body of robot is 160 mm. In this study, a robot was implemented on the robot movement for moving forward, backward, sideways, and diagonal direction. Based on the data evaluation, it is determined that an angular error of 2.84% exists in the movement of the omnidirectional robot at a velocity of 0.256 m/s to 1.403 m/s.

RETRACTED: Research on Arm Embedded System for Football Robot

Two degrees of freedom to play a gift collision board game robot design, manufacture, and the primary control of real-time vision. The information processing and communication unit is one of the high resolution digital cameras. The robot consists of two servo motors and an impact mechanism: three significant elements will be included in the system. On the platform, the camera takes the image and sends it to the central office. Photo processing and adaptive map technology to capture important data to use the. The file will integrate the purchased product; In terms of the structure after it is forwarded via a serial interface to the microcontroller. motor drive control algorithm and orthogonal compression codec for medium distance and angles to better coordinate negative. When it is in line with the disk or the goal post, an impressive unit, and delivers, the firing pin controls the force. Players will kick the maximum power that is generated from his foot into the goal post. Intelligent meet the concept of technology entertainment, cost-effective, is to develop a user-friendly system.

Analysis and Design of Coil Rolling Machines on Robot Solenoids using Macroergonomic Analysis Method and Design (MEAD) and Rapid Entire Body Assesment (REBA) Based on Arduino Microcontroller

The making of Indonesian soccer robot in the division of the Indonesian Football Robot Contest (KRSBI) especially in the process of coil rolling machines on a solenoid does not pay attention to ergonomic factors. The process of winding the wire on the solenoid is done using only the hands manually and in an un ergonomic body position, which is turning and bending. As a result, the convolution process lasts longer and in the wrong posture, causing fatigue and back pain. Macroergonomic Analysis and Design (MEAD) and Rapid Entire Body Assessment (REBA) approaches are used to analyze the posture of the wire. The solution is obtained by design and making an ergonomic and semi-automatic coil rolling machines to solenoid Robot based on the Arduino Microcontroller

PEMANFAATAN METODE WAVELET PADA ROBOT SEPAKBOLA BERBASIS MACHINE LEARNING GOOGLE TENSORFLOW

Humanoid Football robot that will be investigated is a wheeled model developed with the ability to predict or prediction in a football field with high accuracy and image resolution. This robot is expected to be able to keep the goal for up to 25 minutes with a cruising reach of 100 m. Also, the robot can monitor or monitor the desired area so that it can keep the goal from attacks from the opposing robot. This robot is expected to complete prediction missions towards the ball and autonomous monitoring without being controlled by the pilot. Robot control is carried out by a Ground Control Station (GCS) computer. The goalkeeper's robot process uses Google TensorFlow's machine learning technology that is integrated with the wavelet method to enable this robot to keep the goalposts from the area effectively and efficiently. Keywords: robot, machine learning, prediction, Ground Control Station, wavelet method

Design of Wheeled Football Robot Coordination System at Base Station Using TCP / IP

Wheel Soccer Division, Indonesian Robot Contest is an annual competition held by the Ministry of Education. One team in this division consists of 3 robots connected in wireless communication coordinated by base station. Besides that, base station computer also connects the robots with referee computer or called Refbox (Referee Box). Refbox as server for base station computer and base station computer as server for robots. The problem arises in base station has to play double roles, as server and client. In testing had two the results of communication from the referee box to basestation and basestation to the client so the data from the referee box can be accepted by the client with a success rate of 93%.