AutoRef - Autonomous Referee System

Note: This page is being actively modified as of 30 March 2021.

The AutoRef system is a proposed fully autonomous referee for RoboCop Middle Size League robot soccer under development as a continuous project at Eindhoven University of Technology (TU/e). Development of the system architecture and implementation began in 2016 by TU/e PDEng trainees in the 2015–2017 cohort of the Mechatronic Systems Design (MSD) program as their Block II in-house project; since then, each MSD cohort has contributed to AutoRef's continuation in their respective Block II in-house projects. In 2019, a team of students from the TU/e Honors program High Tech Systems realized the control of drones as part of AutoRef's implementation, with continued efforts in drone control by these students leading to the Firefly-project.

AutoRef has experienced multiple iterations of its project definition, consequently leading to poor progress between different teams. While earlier MSD cohorts emphasized a fully autonomous referee, later years scoped the project towards an assistive system for human referees to use for complex refereeing duties. To prevent further repetitive efforts in the design of AutoRef, the 2020–2022 MSD cohort (AutoRef MSD 2020 or simply MSD 2020) was specifically tasked with ensuring continuity for future work. Therefore, as of MSD 2020, the AutoRef's system architecture and implementation pages describe the current state of the project "as-is" without the voice or perspective of any specific team's contribution. Contributions from previous teams (i.e., MSD 2015–2019 and Honors 2019) are described on their own respective pages, with an archive provided by MSD 2020 to systematically describe team contributions https://teams.microsoft.com/l/file/EA8BF37F-3469-4424-9010-BEADD8E96EE9?tenantId=cc7df247-60ce-4a0f-9d75-704cf60efc64&fileType=xlsx&objectUrl=https%3A%2F%2Ftuenl.sharepoint.com%2Fsites%2FMCS_Drone_Referee_project_Team%2FShared%20Documents%2FGeneral%2FAutoRef%20Project%202020%20Final%20Deliverables%2FDocumentation%20%26%20Archive%2FArchive%20of%20past%20year's%20work.xlsx&baseUrl=https%3A%2F%2Ftuenl.sharepoint.com%2Fsites%2FMCS_Drone_Referee_project_Team&serviceName=teams&threadId=19:67b92555afdd4fdbbc40f984fb35696c@thread.tacv2&groupId=1efe2c69-ea31-43f1-9b96-c1c8cfa600e6.

Background

RoboCup

A football referee can hardly ever make "the correct decision", at least not in the eyes of the thousands or sometimes millions of fans watching the game. When a decision will benefit one team, there will always be complaints from the other side. It is oft-times forgotten that the referee is also merely a human. To make the game more fair, the use of technology to support the referee is increasing. Nowadays, several stadiums are already equipped with goal line technology and referees can be assisted by a Video Assistant Referee (VAR). If the use of technology keeps increasing, a human referee might one day become entirely obsolete. The proceedings of a match could be measured and evaluated by some system of sensors. With enough (correct) data, this system would be able to recognize certain events and make decisions based on these event.

The aim of this project is to do just that:
Creating a system which can evaluate a soccer match, detect events and make decisions accordingly.

AutoRef motivation

RoboCup is an international initiative to promote and advance research in robotics and artificial intelligence. Founded in 1997, its main goal is to ‘develop a team of fully autonomous humanoid robot soccer players that is able to win against the winner of the most recent World Cup, complying with the official rules of FIFA, by the middle of the 21st century’. In the Middle Size League (MSL), two teams of five autonomous robots play a soccer match on an artificial field. These robots are able to drive around while using several on-board camera's to position themselves on the field. Moreover, they can determine the position of the ball, opponents and team mates. Through radio signals they can communicate with each other and decide upon a strategy. With a ball-handling system the ball can be captured and controlled and a shooting mechanism is able to shoot a ball over the ground or through the air.

As discussed in this tutorial, a standard RoboCup field measures 18 by 12 meters. During a match, there are two teams consisting of five robots on this field, driving around with velocities up to 5 m/s and possibly even higher. These robots are all competing for the same thing: scoring goals. This means that getting possession of the ball is a primary goal. When several robots are competing for the ball, collisions, pushing and scrummages are nearly inevitable. To make sure the match is played in a fair way, a human referee keeps a keen eye on the events on the field from the sideline. This human referee is backed up by an auxiliary referee which is standing on the opposite side, next to the field. Both can decide on stopping the game, due to a committed foul, a scored goal, a ball out of bound or any other event. The rules for MSL are based on the official FIFA rules, but adapted to robot football rules were necessary. However, the large set of rules and the interpretation thereof can often lead to situations where a referee might decide to continue the game, while another might decide to interrupt. This can and will often lead to frustrations in the aggrieved team. Moreover, a decision made by a referee can affect the outcome of a game and even an entire championship.

An example of this is the final match of the RoboCup world championship 2016 in Leipzig, Germany (see full match/highlights). The final was played between team TechUnited from the Netherlands and team WATER from China. The winner of this would become world champion robot soccer in the MSL. At the end of the match the scoreboard showed 2-2. As in human soccer, this means extra time to decide on the winner. During the match, team WATER had some trouble with the ball handling, preventing the ball to rotate in a ‘natural’ way over the field. When it happens that the ball does not rotate in the direction it is being moved, this is considered clamping and regarded as a foul in favor of the other team. In the last couple of minutes the score was 3-3 when WATER turned towards the TechUnited goal, shot and scored the winning goal. While the Chinese team was already celebrating their victory, the auxiliary referee decided that the scoring robot was clamping the ball before scoring the goal. After a discussion with the main referee, it was decided to declare the goal invalid. Since the extra time also ended in a draw, penalties were needed to decide who would become the new world champion. After all penalties of the Chinese team were stopped by the Dutch keeper, the first shot of the TechUnited robot went into the net. The Dutch team won the penalty series with 1-0 and thus TechUnited became the world champion of 2016.

This example shows how important the decisions of the human referee team can be in shaping the course of a match or even a tournament. Rules are always prone to interpretation and a team which is disadvantaged by this will always complain. The referee has no means to justify his decision other than his own intuition and interpretation on the rules. This lead to the question on whether it would be possible to develop a system which can support the human referee team in making decisions. Such system might even become fully autonomous and could replace the human factor in refereeing entirely.

Development

History 2015–2020

This project started in 2015 with the idea to use drones, equipped with cameras, to help monitor a RoboCup Middle Size League (MSL) soccer match. The use of drones was a first though towards achieving the goal. While drone can certainly play a part in the system, we must not limit ourselves to them. To better understand how the system should look like, a systems engineering approach should be taken during the design. From the start, this project was part of the PDEng MSD curriculum. The PDEng trainees were tasked with the development of the system architecture and implementation. Parallel to this, a team of students from the TU/e Honors programme High Tech Systems are tasked with the control of the drones. One of these teams have continued their efforts in drone-control by creating the Firefly-project.

The projects described are often of short duration. Moreover, every year the projects are done with new teams, which have their own ideas and approaches. These teams create their own documentation to show what they have done, such that they can be graded. Sometimes they use previous work as inspiration, but often they start from scratch with their own ideas. While this can give new perspectives on the system, it slows down the progress of creation. Instead of going progressing through the entire V-Model with each new group, we keep repeating the Project Definition (left side of the V).

This wiki-page is created in order to centralize the efforts made by several different students and teams. This page will act as the central backbone of the system. All decisions, requirements, functionalities etc. will be explained here. Since we are building ONE system, we should only need ONE backbone. This approach can lead to difficulties in grading the students/teams, since it might not be clear what part exactly they have contributed to. Therefore a separate page is made for each team. Here they can explain their contributions to the system (see navigation box).

Illustration by Peter van Dooren, BSc student at Mechanical Engineering, TU Eindhoven, November 2016.