RoboCup: The Robot World Cup Initiative

1
RoboCupThe Robot World Cup Initiative

• By Mariya Miteva

2
What is RoboCup?

• Soccer world cup for robots
• An attempt to foster AI and intelligent robotics
  research by providing a standard problem where
  wide range of technologies can be integrated and
  examined
• The ultimate goal is a team of fully autonomous
  humanoid robots that can win against the human
  world soccer champion team to be developed by
  2050!
• Sample Game Video

3
The Different Competitions

• RoboCup Soccer
• Small size
• Middle size
• Four-legged
• Humanoid
• Simulation
• RoboCup Rescue
• RoboCup Junior

4
RoboCup as a Standard AI Problem

• Standard problems are the driving force of AI
  research. For example, research on chess lead to
  the discovery of powerful search algorithms.
• After Deep Blue defeated Garry Kasparov in chess,
  AI needs a new challenge.
• AI research groups should be focused on solving
  real life problems, but often face social or
  economic constraints.
• A realistic, but affordable for many research
  groups problem is necessary.
• RoboCup is designed to meet the need of handling
  real world complexity, though in a limited
  environment, while maintaining an affordable
  problem size and research cost..

5
Why is soccer a good option?

• Soccer challenges
• dynamic environment
• real-time decision making and action
• high level of uncertainty and incomplete
  information
• sensor-acquired information
• distributed control and cooperation
• Areas of research include real-time sensor
  fusion, reactive behavior, strategy acquisition,
  learning, real-time planning, multi-agent
  systems, context recognition, vision, strategic
  decision making, motor control, intelligent robot
  control, etc.

6
Rules

• There are real robot, special skill, and
  simulation competitions, each having different
  rules usually controlled by human referees.
• In real robot competitions attributes of the
  environment such as the size of the field and the
  goal, the colors of the field, balls and robots,
  the maximum number of robots in a team, etc. are
  predetermined and differ from league to league.
• Most physical fouls are considered unintentional
  and ignored.

7
More Rules

• In simulation RoboCup a Soccer Server provides
  the virtual environment and controls the
  communication between the virtual robots and
  their control programs.
• Robots do not know their exact position, but only
  their position relative to landmarks
• Simulation allows development of advanced
  coordination systems without the physical
  constraints of real robots

8
Research Issues

• The goal of the competitions is to stimulate
  research and advancement in both designing and
  programming robots.
• The major areas of interest according to the
  article are
• Collaboration in a multi-agent environment
• Design and control
• Vision and sensor fusion
• Learning

9
Collaboration

• Each team has
• common goal (to win the game) , incompatible
  with the goal of the opponent team, and several
  subgoals (scoring)
• team-wide strategies to fulfill the common goal
  and local and global tactics to achieve subgoals
• Complications
• Dynamic environment
• Locally limited perception
• Different roles of team players
• Limited communication among players
• Trade-off between communication cost and accuracy
  of the global plan
• Final goal - promising local plans at each agent
  and coordination of these local plans

10
Sample Team Strategy
11
Design and Control

• Existing robots have been designed to perform
  mostly single behavior actions
• A RoboCup player needs to perform multiple
  subtasks( shooting, passing, heading, throwing,
  etc.) and meanwhile avoid opponents
• Two approaches in building a RoboCup player
• A combination of many specialized components
• One or two multitasking components
• The first approach is easier to design, while the
  second is easier to build
• The second approach is preferable since a RoboCup
  robot should be compact and quick
• The final goal of building a successful Humanoid
  Soccer Player currently appears to be unfeasible

12
Vision and Sensor Fusion

• Computer Vision researchers have been seeking for
  3D reconstruction of 2D visual information
• 3D reconstruction is too time-consuming for a
  RoboCup player to react in real time, so a
  simpler, faster and reliable vision system needs
  to be developed
• Other sensors (sonar, touch and force) need to be
  incorporated to provide further information,
  which can not be acquired by vision
• A method of sensor fusion/integration is
  necessary
• Robot Vision Video
• Robot Vision Video 2

13
Learning

• Because of the dynamic and uncertainty of the
  RoboCup environment, programming robot behaviors
  for all possible situations is impossible.
• Reinforcement learning is promising in RoboCup,
  since it allows acquisition of advanced behaviors
  with little prior knowledge.
• Almost all existing reinforcement learning has
  been used in computer simulation, but not in
  physical applications.

14
Learning

• Robots first learn skills in one to one
  competitions, which are still complex because of
  the motion of the opponent.
• To simplify the process, task decomposition is
  implemented
• two skills are independently acquired and then
  coordinated through learning

• Later on, many-to-many competitions are
  considered.
• Its hard to find a simple method for learning
  collective behavior
• Pattern finding methods or coordination by
  imitation are used
• The most difficult task is integration of
  the learning methods in a physical environment.

15
Current Champions (Osaka 2005)

• Soccer
• Small Sized Fu-Fighters (German)
• Middle Sized EIGEN Keio Univ (Japan)
• 4 Legged German Team (German)
• Humanoid 2-on-2 Team Osaka (Japan)
• 2D Simulation Brainstormers 2D (Germany)
• 3D Simulation Aria (Iran)
• Rescue
• Simulation Impossibles (Iran)
• Robot Toin Pelican (Japan)