RoboCup

We develop and apply several novel methods quantifying dynamic multi-agent team interactions. These interactions are detected information-theoretically and captured in two ways: via (i) directed networks (interaction diagrams) representing significant coupled dynamics between pairs of agents, and (ii) state-space plots (coherence diagrams) showing coherent structures in Shannon information dynamics. This model-free analysis relates, on the one hand, the information transfer to responsiveness of the agents and the team, and, on the other hand, the information storage within the team to the teamʼs rigidity and lack of tactical flexibility. The resultant interaction and coherence diagrams reveal implicit interactions, across teams, that may be spatially long-range. The analysis was verified with a statistically significant number of experiments (using simulated football games, produced during RoboCup 2D Simulation League matches), identifying the zones of the most intense competition, the extent and types of interactions, and the correlation between the strength of specific interactions and the results of the matches.

Abstract. In RoboCup Middle Size league (MSL) the main referee uses assisting technology, controlled by a second referee, to support him, in particular for conveying referee decisions for robot players with the help of a wireless communication system. In this paper a vision-based system is introduced, able to interpret dynamic and static gestures of the referee, thus eliminating the need for a second one. The referee's ges-tures are interpreted by the system and sent directly to the Referee Box, which sends the proper commands to the robots. The system is divided into four modules: a real time hand tracking and feature extraction, a SVM (Support Vector Machine) for static hand posture identification, an HMM (Hidden Markov Model) for dynamic unistroke hand gesture recognition, and a FSM (Finite State Machine) to control the various system states transitions. The experimental results showed that the system works very reliably, being able to recognize the combination of gestures a...

As time goes on, there are more and more robotics  applications. The limit is almost the imagination of each person. A great deal of industrial work can yet be done by robots and new ideas are blossoming. The entertainment industry is arriving and there are already
many ideas as well as real robots on the field. It is important to point out that the entertainment applications not just entertain people as it also brings new research which will then be used in industrial work applications. This paper describes a team of robot football players which compete in a worldwide scientific challenge – the RoboCup.

Our F180 team, the FU-Fighters, participated for the third time at the RoboCup competition. This year we used a heterogeneous team, consisting of improved differential drive robots and new omnidirectional robots. We designed new electronics and added prediction and path planning to the behavior control. Our team won fourth place in the SmallSize league competition.

This article presents a brief explanation of research interests and team description of MRL SPL team intending to participate in RoboCup 2013 Standard Platform League. This team description includes various sub sections such as software structure, perception, global modeling and localization, behavior control and dynamic head motion, and locomotion control. Related published articles, future research topics, and research experiences are also provided here in this paper.

The aim of this paper is to provide a guideline for the design of an omnidirectional vision system for the Robocup domain. We report the design steps undertaken, with a detailed description of the design of an omnidirectional mirror with a custom profile. In the second part, we present the software written to exploit the properties of the designed mirror. The application for which the vision system is designed is the Middle-Size Robocup Championship. The task performed by the vision system is to localise the robot and to locate the ball and other robots in the field of play. Several practical tricks and suggestions are provided.

یکی از مهم‌ترین قسمت‌ها در طراحی روباتهای عاملِ هوشمندِ خودمختار، تعیین محل قرارگیری روبات در محیط می‌باشد. در صورتی که روبات عامل برای فعالیت در محیطهای ناشناخته طراحی گردیده باشد، نتایج این قسمت از اهمیت خاصی برخوردار می‌گردد؛ زیرا، نتایج حاصل از مکان یابی به صورت مستقیم در لایه‌های هوشمند مورد استفاده قرار می‌گیرد. تصمیم گیری در اکثر روشهای متداول، برای روبات‌های عامل هوشمند با مقادیر قطعی (حاصل از مکان یابی) انجام می‌پذیرد که بدست آوردن این مقادیر به صورت قطعی توسط الگوریتم‌های سنگین و با پردازش زیاد صورت می‌گیرد. در این مقاله سعی در بیان علل و مزایای تغییر این روش و جایگزینی محدوده‌های غیر قطعی بجای مکان یابی قطعی گردیده است.
در این روش بجای تصمیم گیری بر اساس مکان دقیق هر عامل، تصمیم گیری براساس ناحیة محل استقرار آن عامل در محیط انجام می‌گیرد. این نواحی در هر لحظه با تأثیر گیری از محل عامل و پارامترهای محیط، اساس حرکات پایه‌ای تیم و مبنای تصمیم گیری در ساختار هوشمند عامل قرار می‌گیرد.

We consider the problem of disaster mitigation in the RoboCup Rescue Simulation Environment [3] to be a task allocation problem where the tasks arrive dynamically and can change in intensity. These tasks can be performed by ambulance teams, fire brigades and police forces with the help of an ambulance center, a fire station and a police office. However the agents don’t get automatically notified of the tasks as soon as they arrive and hence it is necessary for the agents to explore the simulated world to discover new tasks and to notify other agents of these.

In a dynamic situation like robot soccer any individual player can only observe a limited portion of their environment at any given time. As such to develop strategies based upon planning and cooperation between different players it is imperative that they be able to share information which may or may not be in any individual player’s field of vision. In this paper we propose a method for multi-agent cooperation for perception based upon the Extended Kalman Filter (EKF) which enables players to track objects absent from their field of vision and also to improve the accuracy of position and velocity estimates of objects in their field of vision.

This paper describes the activities of the research group Bahia Robotics Team (BRT) in preparation of the Bahia-PV team for the Physical Visualization(PV) Sub-League, disputed for the first time in RoboCup 2007 at Atlanta. In this paper we give an overview of this new sub-league, and present the proposal for the architecture and strategies of a robotic soccer team in PV environment. We also present new applications that explores the potentiality of the PV environment.

Large state spaces and incomplete information are two problemsthat stand out in learning in multi-agent systems. In this paper wetackle them both by using a combination of decision trees and Bayesiannetworks (BNs) to model the environment and the Q-function. Simulatedrobotic soccer is used as a testbed, since there agents are facedwith both large state spaces and incomplete information. The long-termgoal of this research is to dene generic techniques that allow agents tolearn in large-scaled multi-agent systems.

Abstract. Due to the critical role of midlevel actions such as walk, kick, etc in the decision making processes of a soccer agent, our main efforts have been concentrated on the design and implementation of an adequate midlevel decision and action management layer .In this paper we ...

RoboCup is an international research aimed at improving artificial intelligence and robotics. It is a standard issue to get a wide range of technologies together and obtain new achievements. In 2D simulation league, after each game, server saves a log that contains all information about the game. By using data mining techniques knowledge can be discovered from this massive data. In this research we aimed to extract ball and player positions from log files and pre-process this data to specify some information including the action that have been taken place, start point, and involving players, etc. We mined this data to predict own and opponent action using C4.5 algorithm. The result showed that after applying our method the goal scoring was increased 251.39% with 64.13% confidence interval (with alpha = 0.1).

"Robot sepak bola merupakan perpaduan antara olah raga, teknologi robotika, dan multi agent system. Untuk mencapai tujuan, selain membutuhkan kecerdasan individu, juga menuntut kemampuan kerja sama antar individu. Posisi robot ketika bermain mempengaruhi kemampuan robot dalam bekerja sama dan memilih aksi yang sesuai. Dalam tulisan ini akan disajikan hasil penelitian kami dalam penerapan algoritma particle swarm optimization (PSO) untuk menentukan posisi robot ketika bermain sepak bola. Hasil pengujian pada simulasi RoboCup Soccer dua dimensi menunjukkan bahwa tim robot sepak bola yang menggunakan algoritma PSO memiliki performa bermain lebih
baik ketimbang tim sebelum menggunakan algoritma PSO."

High-level programming of robotic agents requires the use of a representation formalism able to cope with several sources of complexity (e.g. parallel execution, partial observability, exogenous events, etc.) and the ability of the designer to model the domain in a precise way. Reinforcement Learning has proved promising in improving the performance, adaptability and robustness of plans in under-specified domains, although it does not scale well with the complexity of common robotic applications. In this paper we propose to combine an extremely expressive plan representation formalism (Petri Net Plans), with Reinforcement Learning over a stochastic process derived directly from such a plan. The derived process has a significantly reduced search space and thus the framework scales well with the complexity of the domain and allows for actually improving the performance of complex behaviors from experience. To prove the effectiveness of the system, we show how to model and learn the behavior of the robotic agents in the context of Keepaway Soccer (a widely accepted benchmark for RL) and the RoboCup Standard Platform League.

Football is one of the best sport and the most popular sport which played by all the people in the world. Football has a high element of cooperation, contain tactics, strategy, state, and has goal to target  and also plenty of complexity. Nowadays, football or soccer played by all kind of things not only human but also animals and Robots.
A lot of researcher has develop Robo Soccer as a project that used for educational purposes, and to stimulate the interest of the public for robotics and artificial intelligence (AI), independent agent, and other disciplines. The following studies attempt to simulate robot soccer game in two dimensions simulator (2D Simulator) that runs on the RoboCup™ Soccer Simulator. In this research, the authors propose the use of particle  swarm optimization for the movement of the player (player movement), in this case moves to bring the ball (dribbling), shoot the ball into the opponent's goal (Shooting), or pass the ball (passing) to the
other players in a team. The soccer agents used in the soccer
team, are adopted from UvA Trilearn Agents which were developed by University of Amsterdam. The action selection
mechanism is then implemented, and tested. From the test
result, it can be seen that the agent is represented as a real
player and in their best position, hopefully are the best team in Robo Soccer too.

The paper describes some main methods that we used in ShahedTech. This project has been started in Shahed University as a scientific project with vision of showing new methods that never used in machine learning techniques. On this way we placed 2nd of China Open 2007, 4th of China Open 2009, 2nd of AUTcup 2009, 3rd of Iran Open 2009, Top 10 of Iran Open 2010, Top 16 of Iran Open 2008, Top 6 of PRIMA RoboCup Games and this year we have success to qualify for RoboCup 2010.

This paper describes the current state of CEIT Department of Amirk-abir University of Technology's submission to the 2016 RoboCup Rescue Virtual Robot competition with team S.O.S VR. We address our system architecture and software structure of the robot, which based on ROS Framework. Along with the algorithms involved in the vital components of the system architecture. We also discuss high-level architectural interaction of the components, and provide relevant flow diagrams. 1 Introduction Maybe it's time for humankind to take advantage of robots' aid in tough situations such as earthquakes, floods, natural disasters and urban accidents. In these cases, even if smart and automatic robots save a single person's life, science has reached its goal. In the ahead challenge regardless of hardware implementation, we are focused on achieving accurate perception of the (simulated) world from sensors input, make a right decision, plan considering the global goal, select and execute the best action. We aim to develop basic modules for the challenge, which later can form a framework where they interact with each other. This document briefly explains these modules and the framework that we are prototyping to optimize them, with respect to the tasks

Outline. A formalism for the specification of multiagent systems should be expressive enough to model not only the behavior of one single agent, but also the collaboration among several agents and the influences caused by external events. For this, state machines [4] seem to provide an adequate means. Therefore, the approach of the team RoboLog Koblenz 2001 employs techniques from software engineering and artificial intelligence research by using UML statecharts and implementing them systematically with logic and deduction in Prolog [3].

This paper describes a modified potential fields method for robot navigation, especially suited for unicycle-type non-holonomic mobile robots. The potential field is modified so as to enhance the relevance of obstacles in the direction of the robot motion. The relative weight assigned to front and side obstacles can be modified by the adjustment of one physically interpretable parameter. The resulting angular speed and linear acceleration of the robot can be expressed as functions of the linear speed, distance and relative orientation to the obstacles. For soccer robots, moving to a desired posture with and without the ball are relevant issues. To enable a soccer robot to dribble a ball, i.e., to move while avoiding obstacles and pushing the ball without losing it, under severe restrictions to ball holding capabilities, a further constraint among the angular speed, linear speed and linear acceleration is introduced. This dribbling behavior has been used successfully in the robots of the RoboCup Middle-Size League ISocRob team.

In this article a hand gesture recognition system that allows interacting with a service robot, in dynamic environments and in real-time, is proposed. The system detects hands and static gestures using cascade of boosted classifiers, and recognize dynamic gestures by computing temporal statistics of the hand’s positions and velocities, and classifying these features using a Bayes classifier. The main novelty of the proposed approach is the use of context information to adapt continuously the skin model used in the detection of hand candidates, to restrict the image’s regions that need to be analyzed, and to cut down the number of scales that need to be considered in the hand-searching and gesture-recognition processes. The system performance is validated in real video sequences. In average the system recognized static gestures in 70% of the cases, dynamic gestures in 75% of them, and it runs at a variable speed of 5-10 frames per second.

Decision making is an important issue in robot soccer, which has not been investigated deeply enough by the RoboCup research community. This paper proposes a probabilistic approach to decision making. The proposed methodology is based on the maximization of a game situation score function, which generalizes the concept of accomplishing different game objectives as: passing, scoring a goal, clearing the ball, etc. The methodology includes a quantitative method for evaluating the game situation score. Experimental results in a high-level strategy simulator, which runs our four-legged code in simulated AIBOs’ robots, show a noticeable improvement in the scoring effectiveness achieved by a team that uses the proposed approach for making decisions.

This document introduces AUTMan humanoid joint team for participating in Humanoid Kid Size Robot League in RoboCup 2016, Leipzig, Ger-many. This joint team was founded in 2015 on collaboration between two teams from Amirkabir University of Technology (Tehran Polytechnic), Iran and University of Manitoba, Canada. A brief history of Team AUTMan and its' research interests and directions for future research will be described. Our main research interests within the scope of humanoid robots are to propose a new open platform 3D-printed kid size robot, based on the new changes due to long-term road map for the future of the league, active balancing, running robots, accurate localiza-tion, and strategic reasoning for soccer.