Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer

Transcription

1 Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer Luís Paulo Reis Member of the Directive Board of LIACC Artificial Intelligence and Computer Science Lab. Of the University of Porto, Portugal Associate Professor at School of Engineering, University of Minho, Portugal Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 1 Presentation Outline Artificial Intelligence, Robotics and Simulation RoboCup and Our Teams RoboCup Challenges and Leagues Portuguese Teams: FCPortugal, 5DPO, Cambada and PT Team Flexible Strategy for Robotic Teams Strategy and Formations/SBSP DPRE - Dynamic Positioning and Role Exchange SetPlays and Graphical Setplay Definition Generic Optimization of Skills/Decisions Applications and Projects at Portugal Agent Based Simulation: EcoSimNet Educational/Assistive Robotics: Intellwheels, Robot Dancing Strategic Reasoning: Poker Agents Real Sports: Soccer, Indoor Sports (Handball) Conclusions and Future Work Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 2

2 Artificial Intelligence Intelligence Capacity tosolve new problems through the use of knowledge Artificial Intelligence Science concerned with building intelligent machines, that is, machines that perform tasks that when performed by humans require intelligence Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 3 Autonomous Agents and Multi-Agent Systems Agent Traditional Definition: Computational System, situated in a given environment, that has the ability to perceivethat environment using sensorsand act, in an autonomous way, in that environment using its actuators to fulfill a given function. sensors percepts? environment agent actions effectors From Russel and Norvig, AI: A Modern Approach, 1995 Multi-Agent System: Agents exhibit autonomous behavior Interact with other agents in the system Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 4

3 Agents and Multi-Agent Systems To build individual autonomous intelligent agents is important, however: Agents don t live alone Necessary to work in group Multi-Agent Applications Coordination : to work in harmony in a group Dependencies in agent actions Need to respect global constraints No agent, individually has enough resources, information or capacity to execute the task or solve the problem Efficiency: Information exchange or tasks division Prevent anarchy and chaos: Partial vision, lack of authority, conflicts, agent s interactions Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 5 Intelligent Robotics Robotics Science and technology for projecting, building, programming and using Robots Study of Robotic Agents (with body) Increased Complexity: Environments:Dynamic, Inaccessible, Continuous and Non Deterministic! Perception: Vision, Sensor Fusion Action: Robot Control (humanoids!) Robot Architecture (Physical / Control) Navigation in unknown environments Interaction with other robots/humans Multi-Robot Systems Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 6

4 Current State of Robotics Used to Perform: Dangerous or difficult tasks to be performed directly by humans Repetitive tasks that may be performed more efficiently (or cheap) than when performed by humans Robots have moved from manufacturing, industrial applications to: Domestic robots(pets AIBO, vacuum cleaners) Entertainment robots(social robots) Medical and personal service robots Military and surveillance robots Educational robots Intelligent buildings Intelligent vehicles (cars, submarines, airplanes) New industrial applications (mining, fishing, agriculture) Hazardous applications (space exploration, military apps, toxic cleanup, construction, underwater apps) Multi-Robot Applications and Human-Robot Teams! Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 7 Agent-Based Simulation Simulation: Imitation of some real thing, state of affairs, or process, over time, representing certain key characteristics or behavioursof the physical or abstract system Applications: Understand system functioning Performance optimization Testing and validation Decision making Training and education Applied to complex systems impossible to solve mathematically Traditional Simulation Drawbacks: Systems are getting more complex and difficult to model as a whole Higher level tools available Human behaviour is often neglected or over simplified Agent Based Modeling and Simulation: Entities represented by Agents with Autonomous Behaviour Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 8

5 Robotic Competitions RoboCup Robotic Soccer Robotic Soccer FIRA DARPA Grand-Challenge Intelligent Ground Vehicle Competition European Land Robot Trial IEEE MicroMouse competition AAAI Grand Challenges First Competition (Lego-League) RoboGames(former RoboOlympics) Manitoba Robot Games LARC, SBR, OBR Robotic Fight: BattleBots, RobotWars, RobotSumo Underwater and aerial Robot Competitions Some Portuguese Competitions: Portuguese Robotics Open (including autonomous driving) Micro-Mouse/Ciber-Mouse Firefighting Robots Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 9 Robotic Competitions - RoboGames Videos: RoboGames Videos Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 10

6 Robotic Competitions - RoboCup Videos: RoboCup Videos Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 11 Robotic Competitions - Portugal SPR Sociedade Portuguesa de Robótica Festival Nacional de Robótica ( ) Festival Nacional de Robótica 2013 Lisbon Robotic Soccer Autonomous Driving Freebots(Free Robots Competition: Scientific, Juri Demo, Public Demo) Robot@Factory RoboCup Junior Demonstrations International Conference on Autonomous Robot Systems and Competitions, April 2012, Lisbon, Portugal Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 12

7 Robotic Competitions Benefits Research inspiration Hard deadline for creating fully functional system Common platform/problem for exchanging research ideas/solutions Continually improving solutions Excitement for students/researchers at all levels Large number of teams/solutions created Encouragement for flexible software/hardware Dangers Obsession with winning Domain dependent/hacked solutions Cost escalation Difficulty in entering at competitive level Restrictive rules Invalid evaluation conclusions based on Peter Stone, 2002 Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 13 Research Question How to Coordinate heterogeneous Multi-Robot Teams executing flexible tasks in a dynamic, adversarial environment? Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 14

8 Presentation Outline Artificial Intelligence and Robotics RoboCup and Our Teams RoboCup Challenges RoboCup Leagues: Simulation (2D, 3D, MR, Rescue), SSL, MSL and SPL Portuguese Teams: FCPortugal, 5DPO, Cambada and PT Team Flexible Strategy for Robotic Teams Application in other Projects at Portugal Conclusions and Future Work Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 15 Joint International Project: RoboCup: Objectives (Distributed) Artificial Intelligence Intelligent Robotics Soccer Central Research Topic: Very complex collective game Huge amount of technologies involved: Autonomous Agents, Multi-Agent/Multi-Robot Systems, Cooperation, Communication, Strategic Reasoning, Robotics, Sensor Fusion, Real-Time Reasoning, Machine Learning, etc Main Goal of the RoboCup Initiative: By 2050, develop a team of fully autonomous humanoid robots that may win against the human world champion team in soccer! Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 16

9 RoboCup: Official Competitions 1997 Nagoya (Japan) 1998 Paris (France) 1999 Stockholm (Sweden) 2000 Melbourne (Australia) 2001 Seattle (USA) 2002 Fukuoka(Japan) 2003 Padua(Italy) 2004 Lisbon(Portugal) 2005 Osaka(Japan) 2006 Bremen (Germany) 2007 Atlanta (USA) 2008 Suzuhu(China) 2009 Graz(Austria) 2010 Singapore(Singapore) 2011 Istanbul(Turkey) 2012 Mexico City(Mexico) 2013 Eindhoven (Holland) 2014 João Pessoa (Brazil) Local Championships: GermanOpen (European), JapaneseOpen, AustralianOpen, AmericanOpen, Portuguese Open, Dutch Open Iranian Open, China Open, Participant/Awarded Countries: Germany, USA, Japan, Iran, China, Australia, Portugal, Holland, Brazil, Singapore Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 17 RoboCup: Global Perspective Soccer Leagues Simulation: Sim2D, Sim3D (Humanoids), Coach, MR League Robots Small-Size Robots Middle-Size Standard Platform(Aibo; NAO) Humanoid Robots RoboCup Rescue Simulation, Virtual, Robotic RoboCup Júnior Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 18

10 RoboCup Leagues: Simulation 2D Virtual Robots 105*68m Virtual Field Agents controlled by different computers (or processes) Simulator sends perception and receives actions from agents Teams of 11 players plus a coach Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 19 RoboCup Leagues: Simulation 2D 2D Simulator Client-Server System Agents (player s brains) control a single player: UDP sockets/linux Server: Receives agent commands Simulatesmovementof objects Sends perceptions to the agents Two teams with 11 players + coach, try to score goals! Simulation Characteristics Real-Time - Human Distributed 24 Processes Inaccessible (hidden), Continuous and Dynamic World Errors in: Perception, Movement and Action Limited Resources and Communication Multi-Objective, Cooperative and Adverse Environment Server Architecture Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 20

11 RoboCup Leagues: Simulation 2D 1997: League Start-> Simple Play 1998: Simple Passing and Good Individual skills 2000: Formations and Soccer like Playing Videos: Simulation 2D League Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 21 RoboCup Leagues: Simulation 3D Third dimension adds complexity Complexities from real robots Realistic physics and Robot Model: Started with sphere in 2004 Humanoids in 2007 NAO Robot Model: 2008 Strong relation with SPL 6 vs6 games -> 9 vs9 -> 11 vs11 Heterogeneous Robots in 2012 Very difficult to create competitive skills by hand! Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 22

12 Humanoid Robot - Simspark Server (SimSpark) Manages the simulation process Updates world state Enforces soccer rules - referee Forces the laws of physics : collisions, drag, gravity,... Agent connections, Send sensor information (perceptors) Executes actions (effectors) Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 23 Simulation 3D Spheres model : Very Basic playing! 2006: Formations/High-level playing! Videos: Simulation 3D Spheres model Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 24

13 Simulation 3D Humanoid model : Very Basic playing! 2011: Formations/High-level playing! Videos Simulation3D: Humanoid Robots Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 25 Middle Size League Robots are completely autonomous 5 robots per team Robots around 50x50cm and 80cm height Field 18mx12m, green with white lines MSL rules based on official FIFA laws Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 26

14 Middle Size League : Very Basic playing! Individual Dribbling! 2008: Formations SBSP/High-level playing/setplays! Videos: Middle Size League Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 27 Flexible Strategy for RoboCup RoboCup Leagues: Simulation 2D, Simulation 3D, Small-Size, Middle- Size, SPL and Search and Rescue Applications in four distinct teams: FC Portugal (University of Porto/Aveiro/Minho) Simulation 2D, Simulation 3D, Coach, MR, Rescue, SPL CAMBADA(University of Aveiro) Prof. Nuno Lau Middle-Size League, 5DPO(University of Porto) Prof. A.P.Moreira Small-Size League, Middle-Size League Portuguese Team (University of Porto/Aveiro/Minho) SPL Standard Platform League More than 30 awards in International Competitions for these 4 Teams! Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 28

15 Our Teams: University of Porto/Aveiro Simulation 2D: FC Portugal Best: Winners RoboCup2000, Winners Euro 2000, Euro 2001 Simulation 3D: FC Portugal Best: Winner RoboCup2006, Winners Euro 2006, Euro 2007 Simulation Coach: FC Portugal Best: Winner RoboCup2002, 2 nd RoboCup2003, 2004 Simulation MR League: FC Portugal Best: 2 nd RoboCup2007 Rescue Simulation: FC Portugal Best: Winner Euro 2006 Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 29 Our Teams: University of Porto/Aveiro Middle-Size: CAMBADA (Univ.Aveiro) Best: Winners RoboCup 2008 Small-Size: 5DPO (Univ.Porto) Best: 2 nd RoboCup2006, Winners Euro 2001, 2006, 2007 Middle-Size: 5DPO (Univ.Porto) Best: 3 rd Euro 2001 Standard Platform(Aibo): FC Portugal/FC Portus Best: 5 th RoboCup2003 Standard Platform(NAO): Portuguese Team Best: Starting in 2011 Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 30

16 Presentation Outline Artificial Intelligence, Robotics and Simulation RoboCup and Our Teams Flexible Strategy for Robotic Teams Strategy and Formations/SBSP DPRE - Dynamic Positioning and Role Exchange SetPlays and Graphical Setplay Definition Generic Optimization of Skills/Decisions Applications and other Projects at Portugal Conclusions and Future Work Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 31 The Coordination Problem Coordinate autonomous robots decisions to carry out team tasks as efficiently as possible Coordination challenges Strategy Role assignment Formation Plan execution Communication Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 32

17 Flexible Strategy for Robotic Teams Our Approach: Common Framework for Cooperative Robotics : Strategy- Strategical Coordination and Coaching SBSP Situation Based Strategic Positioning (Formations) DPRE Dynamic Position and Role Exchange SetPlay Framework and Graphical Definition Generic Optimizer of Skills/Decisions Bridging the Gap Between Simulation and Robotics Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 33 Formalization of a Team Strategy Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 34

18 Coaching Game Statistics and Opponent Modeling Information Time and Result Individual Action: Active/Passive (with/without ball) Transitions (Ball losses and Ball recoveries) Attacks and Assistances Assistant Coach Field Information Ball Possession By: Period Coach Region (from and to) Team Definitions Player Principal Coach etc. Opponent Modeling Game Statistics Instructions Field Actions Players Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 35 Base Concepts: Coach Unilang Time Periods, Regions, Tactics, Formations, Situations, Player Types Language Defined in BNF Examples: <MESSAGE> ::= (<TIME> <ID> <MESSAGE PART> {<MESSAGE PART>}) <MESSAGE PART> ::= <DEFINITION_MESS> <STATISTICS_MESS> <OPP_MOD_MESS> <INSTRUCTION_MESS> TACTIC_DEFINITION> ::= <TEAM_MENTALITY> <GAME_PACE> <TEAM_PRESSURE> <FIELD_USE> <PLAYING_STYLE> <RISK_TAKEN> <OFFSIDE_TACTIC> <POSITIONING_EXCHANGE_USE> <FORMATIONS_USED> <FORMATION> ::= <PREDEFINDED_FORMATION> <FORMATION_NAME> <FORMATION_DEFINITION> <PREDEFINED_FORMATION> ::= att <FORMATION_DEFINITION>::= {(<PLAYER> <POS_NUMBER> <PLAYER_POSITIONING> <PLAYER_TYPE>)} <PLAYER_POSITIONING> ::= <VERTICAL_POSITIONING> <HORIZONTAL_POSITIONING> Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 36

19 Formations in Robotic Soccer Formations are an essential concept in multi-robot teams: Provide a coordination framework: tasks/role assignment Real impact on team performance Can/should be adapted to team and opponent capabilities Common concept with military units coordinated movements or real soccer formations Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 37 Role based models Formation Models Ex: Striker, Supporter, Defender, Goalie SPAR Strategic Positioning with Attraction and Repulsion Locker-Room agreement SBSP Situation Based Strategic Positioning Distinction between active and passive situations Distinct team movements for different situations Strategic position based on global information(such as current ball position) keeps the team in the selected formation SBSP/DT Situation Based SP with Delaunay Triangulation Added flexibility in the definition of positionings Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 38

20 SBSP - Situation Based Strategic Positioning Strategic Situation: SBSP Strategic Positioning Active Situation (with/without Ball): Active Behavior Definition based on: Situation and Shared info(ball Position) Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 39 SBSP vsspar Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 40

21 SBSP with Delaunay Triangulation Based on Akiyama, 2007 Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 41 SBSP with Delaunay Triangulation Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 42

22 Formations in the MSL Videos: Formations in the MSL Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 43 SBSP with Flux Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 44

23 SBSP with Flux Calculates Flux, Safety and Easiness of all possible points considering the tactic in use! Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 45 DPRE - Dynamic Positioning and Role Exchange Dynamic Exchange of Positioningsand Behaviorsbased on utility: Distances from players positions to their strategic positions Positioning importance and adequacy of agents DPRE improves the robotic team collective performance Important against opponents with similar collective capabilities Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 46

24 DPRE - Dynamic Positioning and Role Exchange ALGORITHM DynamicPositioningExchange(WorldState, Situation, Positionings) RETURNS Positionings(TeamSize) PARAMETERS WorldState, Positionings[TeamSize], Situation { FOR PL1 = 2 TO TeamSize-1 DO FOR PL2 = PL1+1 TO TeamSize DO IF PositionValid(PL1) AND PositionValid(PL2) THEN { Dist11 = Distance(Position(Pl1),SBSPPosition(Pl1)) Dist22 = Distance(Position(Pl2),SBSPPosition(Pl2)) Dist12 = Distance(Position(Pl1),SBSPPosition(Pl2)) Dist21 = Distance(Position(Pl2),SBSPPosition(Pl1)) Adeq11 = PosAdequacy(Pl1, Positioning[Pl1]) Adeq22 = PosAdequacy(Pl2, Positioning[Pl2]) Adeq12 = PosAdequacy(Pl1, Positioning[Pl2]) Adeq21 = PosAdequacy(Pl2, Positioning[Pl1]) Util = ExchangePositions(DPREMode, Situation, Dist11, Dist22, Dist12, Dist21, Adeq11, Adeq22, Adeq12, Adeq21, PosImp(Positioning[Pl1]), PosImp(Positioning([Pl2]) IF Util > ThresUtil(Situation) THEN exchange(positionings[pl1], Positionings[Pl2]) } RETURN Positionings } Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 47 ADVCOM Intelligent Communication Challenges: What and When to communicate? What to Communicate? Individual World State to improve world state accuracy Useful Events for coordination When to Communicate? Communication utilityisvery high or is greater then communication utility (modeled) of teammates! Creation of a Communicated World State! Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 48

25 Motivation and principle: MM - Mutual Modeling Use Teammate and Opponent Models! Estimate their positions and actions! Fuse this information with visual, sensorial, aural information Enables more accurate world states Very useful when vision and sensors are not of good quality Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 49 Setplays: Concept and Definition Simple, pre-defined but flexible plans, which describe cooperation and coordination between agents/robots Defined before the game by a domain expert Easy to define and change Human readable language(high abstraction level) Selected, Instantiated and executed at run-time (text file) Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 50

26 Setplay Definition (setplay :name simplecorner :players (list (playerrole :rolename CornerP) (playerrole :rolename receiver) (playerrole :rolename shooter)) :steps (seq (step :id 0 :waittime 15 :aborttime 70 :participants (list (at CornerP (pt :x 52 :y 34)) (at receiver (pt :x 40 :y 25)) (at shooter (pt :x 36 :y 2))) :condition (playm fk_our) :leadplayer CornerP :transitions (list (nextstep :id 1:condition (canpasspl :from CornerP :to receiver) :directives (list (do :players CornerP :actions (bto :players receiver)) (do :players receiver :actions (receivepass)))))) Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 51 Setplay Definition (step :id 1 :waittime 5 :aborttime 70 :participants (list (at CornerP (pt :x 52 :y 34)) (at receiver (pt :x 40 :y 25)) (at shooter (pt :x 36 :y 2)) ) :condition (and (bowner :players receiver) (playm play_on)) :leadplayer receiver :transitions (list (nextstep :id 2 :condition (canpasspl :from receiver :to shooter) :directives (list (do :players receiver :actions (bto :players shooter)) (do :players shooter :actions (receivepass)))))) (step :id 2 :aborttime 70 :participants (list (at CornerP (pt :x 52 :y 34)) (at receiver (pt :x 40 :y 25)) (at shooter (pt :x 36 :y 2)) ) :condition (and (bowner :players shooter) (playm play_on) ) :leadplayer shooter :transitions (list (nextstep :id 3 :condition (canshoot :players shooter) :directives (list (do :players shooter :actions (shoot)))))) Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 52

27 Setplays- Structure Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 53 Setplays Actions and Conditions Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 54

28 Usage/Interest of Setplay Library Setplay Definition/Graphical application Implement Conditions and Actions Deal with low level Communication Decide Setplay start, eventually CBR/ML Great flexibility: Application to all RoboCupleagues: Simulation 2D, Simulation 3D, Middle Size, MR League, SPL) Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 55 Setplays: Graphical Definition Import Formal Definition(Setplay framework) Export SPlanner RCSSMonitor FCPortugal Debug LogPlayer RCSSLogPlayer included on SPlanner Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 56

29 SetPlays in the Simulation 2D League Videos: Setplay Graphical Definition Videos: Setplays in the Simulation 2D League 57/23 Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 57 SetPlays in the MSL Passes Essential for teamplay 3 phases Preparation/Alignment Pass Catch ball Used by CAMBADA in Playoff Free Challenge 2008 Also on Playon! RolePasser PassFlag TRYING_TO_PASS Align to receiver Kick the ball PassFlag BALL_PASSED Move to next position RoleReceiver Align to Passer PassFlag READY Catch ball Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 58

30 SetPlays in the MSL Videos: Setplays in the MSL Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 59 Flexible Strategy for Robotic Teams Simple Example (from FCPortugal 3D): STWorldState<-FillInWSforStrategy(); Actions<-CallStrategy(STWorldState); ExecuteActions(Actions); void FCPAgentH::FillInWSforStrategy() { WorldState& world = SWorldState::getInstance(); strategy->ws_gametime = world.gtime; strategy->ws_result = world.game->ourgoals- world.game->opponentgoals; strategy->ws_ballpos = world.ball->position.to2d(); / strategy->ws_ballowner = world.->ball_owner; strategy->ws_ballintpos = world.ball->finalpos.to2d(); strategy->ws_mynumber = world.me->unum; strategy->ws_mydir = world.me->orientation; for (intt = 1; t <= strategy->st_num_players; t++) { strategy->ws_teampos[t]= world.getfcportugalplayer(t)->position.to2d(); strategy->ws_opppos[t] = world.getopponentplayer(t)->position.to2d(); strategy->ws_teamconf[t] = world.getfcportugalplayer(t)->conf; strategy->ws_oppconf[t] = world.getopponentplayer(t)->conf; } strategy->ws_playmode = world.game->playmode; } Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 60

31 Generic Optimization of Skills/Decisions A skill consists in a purposeful, repeatable action taken by the executing agent, such as: - Walk (forward/backward/side) -Turn around -Rotate around a point -Kick the ball -Catch the ball (fall down) - Get up (front/back)... These can be specified once and executed as many times as necessary Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 61 Humanoid Robot XML File Parameters Agent Code Specification Model Angle Values sent to the server at each cycle Joint Values Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 62

32 FCP Types of Skills Slot Behaviors CPG Behaviors TFS Walk Skills definition: XML File Flexible Humanoid Robot Skills Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 63 Generic Optimization Find the best configuration of a set of parameters to achieve a goal The goal is to minimize or maximize a quantity -the value of the objective function The independent variables that can change while trying to achieve the goal are known as decision variables Decision variables can only take certain values - variable domains Decision variables can be subject to further constraints kick the ball maximize distance travelled by the ball Joint angles at certain time intervals,... - specification model parameters knee joints cannot bend forward left & right arm joints must have the same values Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 64

33 Generic Optimization Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 65 Get Up Front Skill Get the robot up after it fell down on the ground to its front Skill Specification Model: Slot Behavior, Sine interpolation Selectmetaheuristic: Hill climbing, simulatedannealing, tabu search, PSO, ACO, genetic algorithms 39 decision variables after enforcing left & right side equality Objectives: Speed Stability Effectiveness Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 66

34 Get Up Front Skill Videos: Skill s Optimization Process Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 67 Results: Fast Stable Skills Videos: Getup, kick and walk skills Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 68

35 Results 20 m Kick!!! Optimization increased Kick length from 9m to aprox 20m! More than the double of the best Simulation3D teams Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 69 PT Teams: Portuguese Team Videos: Portuguese Team andapplicationto Real Humanoid Robots Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 70

36 Selected Results: FC Portugal Competition Results: FCPortugal st place in the 2D Simulation League, European st place in the 2D Simulation League, RoboCup rd place in the 2D Simulation League, RoboCup st place in the 2D Simulation League, European (GO) st place in the Coach Competition, RoboCup nd place in the Coach Competition, RoboCup nd place in the Coach Competition, RoboCup st place in the 3D Simulation League, RoboCup nd place in the Small-Size League, RoboCup st place in the 3D Simulation League, European st place in the Rescue Sim League, European nd place in the 2D Simulation League, European st place in the 3D Simulation League, European nd place in the 2D Simulation League, European nd place in the Physical Visual. League, RoboCup rd place in the 3D Simulation League, European rd place in the 2D Simulation League, European rd place in the 3D Simulation League, European rd place in the 2D Simulation League, European 2010 Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 71 Selected Results: CAMBADA, 5DPO Competition Results: FC Portugal nd place in the 3D Simulation League, European 2011 (GO) 2 nd place in the 2D Simulation League, European 2011 (GO) st place in the 3D Simulation League, European 2012 (DO) 3 rd place in the 2D Simulation League, European 2012 (DO) 2 nd place in the Rescue Simulation League, European 2012 (DO) Competition Results: CAMBADA and 5DPO DPO: 3 rd place in the SSL League, RoboCup DPO: 1 st place in the SSL League League, European (GO) DPO: 3 rd place in the MSL League League, European (GO) DPO: 2 nd place in the SSL League, European (GO) DPO: 2 nd place in the SSL League, European (GO) DPO: 1 st place in the SSL League, European (GO) DPO: 1st place in the SSL League, European DPO: 2nd place in the SSL League, RoboCup CAMBADA: 1 st place in the MSL League, RoboCup CAMBADA: 3 rd place in the MSL League, RoboCup CAMBADA: 2 nd place in the MSL League, European 2010 CAMBADA: 3 rd place in the MSL League, RoboCup CAMBADA: 3 rd place in the MSL League, RoboCup2011 Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 72

37 Presentation Outline Artificial Intelligence and Robotics RoboCup and Our Teams Flexible Strategy for Robotic Teams Applications and other Projects at Univ. of Porto and Minho Agent Based Simulation: EcoSimNet, FlightSimNet Educational/Assistive Robotics: Intellwheels, Robot Dancing Strategic Reasoning: Poker Agents Real Sports: Soccer, Indoor Sports(Handball) Conclusions and Future Work Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 73 EcoSimNet: Agent-Based Ecologic Simulation Realistic simulation of ecological models Difficult task Mixing complex biological, chemical and physical processes Slowness associated to each simulation Integrate human factor/decisions in the simulation Provide flexible services to help sustainable management of aquatic ecosystems Custom solutions to any aquatic ecosystem Environmental impact studies/water framework directive Aquaculture optimization/carrying capacity Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 74

38 EcoSimNet: Agent-Based Ecologic Simulation EcoDynamo Simulator for aquatic ecosystems Intelligent Agents Include the human rationality in the scenarios generation and decisions ECOLANG Communication language for simulations of complex ecological systems EcoSimNet Platform that integrates all the previous Enables parallel simulations - clusters Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 75 Intellwheels: Intelligent Wheelchair Limited mobility: Increment of the elderly population Physical disabilities: Cerebral Palsy, Tetraplegia Inability to control electric wheelchairs Year 2020 Intelligent Wheelchair: Robotic device provided with sensorial and actuation systems and processing capabilities: (Semi)Autonomous behavior Obstacle avoidance, navigation and planning Flexible Human-Machine interaction Cooperation with other IW/devices World elderly pop. Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 76

39 Intellwheels: Intelligent Wheelchair IW useful in practice: Very low cost and ergonomic impact Simulation/mixed reality Flexible multi-modal interface IW development platform... Joystick / Buttons Facial Expressions Voice Commands Head Gestures Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 77 Intellwheels: Intelligent Wheelchair... Joystick / Buttons Facial Expressions Voice Commands Head Gestures Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 78

40 Robot Dancing based on RTBT Motivation: Improve human-robot social interaction: by means of bodily communication Improve robotic expressiveness: By imitation of human motion Dance as a rich case study Goals: Map human movement periodic patterns onto humanoid robots Model and generate humanoid dance Samba dance style as first case study Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 79 Robot Dancing based on RTBT Dance Motion Analysis Dance Motion Generation Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 80

41 Robot Dancing based on RTBT Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 81 Sports Analysis: Handball and Soccer Artificial Intelligence x Computer Vision x Intelligent Simulation Detection and Tracking of Ball and Players Intelligent Game Analysis: Coach Reports (Data Mining) Creation of Players and Team Models (High-level models + Data mining) Realistic Simulation of Soccer/Handball Games Colour Calib. Back/Forg Detect Forg Categ. Colour Update Pixel Aggr. Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 82

42 Indoor Sports Analysis: Handball Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 83 Poker Strategy with Online Opp. Modeling Poker is a game humans find fascinating Huge and growing market: Casinos, tournaments, online, television Challenge of Poker for DAI: Many new and interesting problems not faced in Chess, Go, or Backgammon: Random, hidden information, bluffing and trapping, need for opponent modeling Poker is a simple game that demands for complex strategies Project General Objective: Develop an agent capable of beating the best human players in No Limit, Multi-Player, Texas Hold em, Poker Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 84

43 Poker Strategy with Online Opp. Modeling LIACC Poker Simulator Human Interface POKERLANG <STRATEGY>::= Agent {<ACTIVATION_CONDITION> 1 <TACTIC>} <ACTIVATION_CONDITION>::= {<EVALUATOR>} AAAI Poker <TACTIC>::= <PREDEFINED_TACTIC> <TACTIC_NAME><TACTIC_DEFINITION> <PREDEFINED_TACTIC>::= Agent 2 loose_agressive loose_passive Competition tight_agressive tight_passive Server <TACTIC_NAME>::= Agent [string] 3 <TACTIC_DEFINITION>::={<BEHAVIOUR> <VALUE>} <BEHAVIOUR>::= {<RULE>} <RULE>::= {<EVALUATOR> Agent n <PREDICTOR>} <ACTION> <EVALUATOR>::= St <NUMBER_OF_PLAYERS> OM <STACK> <POT_ODDS> <HAND_REGION> <POSITION_AT_TABLE> <PREDICTOR>::= <IMPLIED_ODDS> <OPPONENT_HAND> <OPPONENT_IN_GAME> <STEAL_BET> Opp. <IMAGE_AT_TABLE> Opp.Modelling <ACTION>::= Strategy{<PREDEFINED_ACTION><PERC> Model <DEFINED_ACTION><PERC>} Agent <PREDEFINED_ACTION>::= <STEAL_THE_POT> <SEMI_BLUFF> <CHECK_RAISE_BLUFF> <SQUEEZE_PLAY> <CHECK_CALL_TRAP> <CHECK_RAISE_TRAP> <POST_OAK_BLUFF> Human Player Poker Builder Online Poker Server 1 Online Poker Server n Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 85 Research Team Finished Students Former Phd Students (finish date) 1. Pedro M. V. Moreira(PRODEP/IPVC, Mar2009) 2. Vasco H. Vinhas G. Moreira(FCT, Oct2010) 3. Francisco A. F. Reinaldo(FCT/Brasil, Nov2010) 4. Rodrigo A. M. Braga (Capes/Brasil, Nov2010) 5. António M. C. Pereira (FCT/FEUP, Dec2010) 6. Pedro M. H. C. Abreu(FCT, Mar2011) 7. Daniel C. Silva (FCT, Nov2011) 8. António Pedro Costa (FCT/U.Aveiro, Mar2012) 9. Luís H. R. Mota(FCT/ISCTE, Apr2012) 10. Pedro Valente(Univ. South. Denmark, Aug2012) Former MSc Students (finish date) 1. Pedro Miguel Teixeira Faria, Nov Pedro Nuno Macedo Leite da Silva, Dec Sérgio Fernando Grilate Louro, Sep Paulo César Basto Cardoso, July André Monteiro Oliveira Restivo, Oct Darya Alexandrovna Barteneva, Apr Marcelo Roberto Petry, Feb Jorge Filipe de Ribeiro Teixeira, Mar João Pedro Bugalho Certo, Mar João Manuel Marques de Oliveira, Mar Dinis Alexandre Marialva Felix, Mar Péricles Filomeno Monteiro Pinto, May António Pedro da Silva Mota, May João Carlos Leite Ferreira, Jun João Manuel Lobato Oliveira, Jul Pedro Miguel de Castro Malheiro, Jul Márcio Miguel Couto de Sousa, Jul Marco Filipe Chaves Pinto da Silva, Jul José Miguel Neves Leão de Campos, Jul Ricardo Nuno Nóbrega Silva, Jul Daniel Tiago de Jesus Coutinho, Jul André Miguel de Oliveira Rodrigues, Jul Pedro Melo Campos, Jul Rui André Teixeira de Sousa Sêca, Jul Pedro Daniel da Cunha Mendes, Jul Duarte Miguel Faria Ferreira Cabral, Jul João Nuno Boavista Taborda, Jul Luís Ângelo de Sá Barbosa, Jul Filipe Manuel Miranda da Cruz, Nov2008 Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 86

44 Research Team Finished Students Former MSc Students (finish date) 31. Hugo Rafael de Brito Picado, Dec Nuno Filipe dos Reis Almeida, Dec Pedro César Fonseca Gonçalves Alves, Jan Rui Manuel Figueiredo de Almeida, Mar Pedro Ricardo da Nova Valente, Mar Luís Pedro Brandão Martinho, Mar Rui Filipe Lourenço Guedes, May Luís Filipe Gonçalves Lemos, May José Maria Mendonça e Moura, Jul Mário Joaquim Firmino Leite Faria, Jul Antero Guimarães Pacheco da Silva, Jul Rui Manuel Fernando Lopes, Jul Catarina M. B. N. Santiago, Jul Nuno Pedro Silva da Cruz, Jul Ricardo João Teixeira Santos Mestre, Jul José Carlos Pinto Miranda, Dec Frederico Manuel S. C. B. Cunha, Mar Vitor Hugo da Silva Pereira, Mar Carlos Jorge Lemos Nunes, Mar Filipe Teixeira Marques, Jul Abel Fernando Neto M. Santos, Jul Pedro Daniel Pereira Alves de Sousa, Jul João Paulo Santos Portela, Jul Luis Filipe GuimarãesTeófilo, Jul Hugo Miguel Pereira Peixoto, Jul Pedro Miguel Amorim Gomes, Jul Hugo Filipe P. A. S. Mendes, Jul Miguel Augusto Pereira de Oliveira, Dec José Luís Machado Rei, Feb Ivo Miguel da Paz dos Reis Gomes, Feb Sérgio Miguel Fontes de Vasconcelos, Feb André Almeida Vidal, Feb Paulo Sérgio Ribeiro Martins, Feb Maria João Tavares Barbosa Jul André Susano Pinto Jul António Jorge Alpedrinha Ramos, Jul João Guilherme Cravo, Jul Luís Miranda Cruz, Jul Nuno Miguel da Silva Passos, Jul Paulo Alexandre Alves de Sousa, Jul José Eduardo Castro Xavier, Jul Marco André Silva, Jul2011 Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 87 Current Research Team Current PhD Students (pred finish dates) 1. Roberto Rodrigues(FEUP/PRODEI, E.S.F.V., Dec2012) 2. João Lobato Oliveira (FEUP/PRODEI, FCT, Dec2012) 3. Dulce Mota(FEUP/PRODEI, ISEP/PROTEC, Dec2012) 4. Marcelo Petry(FEUP/PRODEI, FCT/Brasil, 2013) 5. Catarina Santiago (FEUP/PRODEI, F.Gulbenkian, 2013) 6. Nima Shafii(FEUP/PRODEI, FCT/Iran, 2013) 7. Paula Rego(FEUP/PRODEI, IPVC/PROTEC, 2013) 8. Fernando Almeida (MAPI, FCT/IPV, 2013) 9. Marco Guimarães (FADEUP, Sports, 2013) 10. Liliana Mendes (FPCUP, Psychology, 2014) 11. Luis Teófilo(FEUP/PRODEI, FCT, 2014) 12. Rui Chirlo(FEUP/PRODEI, FCNAUP, 2014) 13. Daniel Constantino (FEUP/PRODEI, ESVC, 2014) 14. Paulo Trigueiros (UMinho/DEI, 2014) 15. Abbas Abdlomeki(MAPI, FCT/Iran, 2015) Current PostDoc Students 1. Bruno Pimentel (FCT/ PhD UA, ) PhD Researchers 1. Pedro M. V. Moreira(IPVC) 2. Rodrigo A. M. Braga (Univ. Fed. Sta Catarina) 3. António M. C. Pereira (FEUP) 4. Pedro M. H. C. Abreu(DEI/UC) 5. Daniel C. Silva (DEI/UC) 6. Luís H. R. Mota(ISCTE) 7. António Pedro Costa (Loudomedia) Current MScStudents Students (pred finish dates) 1. Bruno Vaz Queiroga Alves, 13 Feb Seraphin Miranda, 13 Feb João Couto Soares, 13 Feb Romina Neves, 13 Feb Rui Pedro Gomes Ferreira, 20 Feb Nuno Resende, Jul Cesar, Brandão, Jul Rui Monteiro, Jul Gil J. Silva, Jul Carlos Eduardo Ermida Santos, Jul2012 Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 88

45 Collaborations - Conferences 16th EPIA 2013 (Portuguese Conf. on Artificial Intelligence),Azores, Portugal, September Propose a Thematic Track(Deadline December 2012) Submit Papers to EPIA Portuguese Conference on Artificial Intelligence(Deadline March 2013) 13th Portuguese RoboticsOpen 2013 (Festival Nacional de Robótica), Lisbon, April (webpage 2013 not yet available) Participate in the Competitions(Deadline March 2013) SubmitPapersto theinternational Conference on Autonomous Robot Systems and Competitions (Deadline January 2013) 8th CISTI 2013 (IberianConf. oninfsystemsna Technologies), Lisbon, June Propose a Workshop (Deadline November 2012) SubmitPapersto WISA@CISTI Workshop onintelligentsystemsandapplications(deadline March 2013) PhD in Portugal (or Sandwich Portugal/Brasil) Joint Participation in RoboCup SPR Portuguese Robotics Society Joint Research Projects LIACC, Porto University of Minho, University of Porto, University of Aveiro INESC Brasil Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 89 Conclusions Coordinationof Teams in Adversarial Environments: Strategy, Formations (SBSP/DT), DPRE, Setplays Complete Tactical/Formation Framework including graphical interface Complete Setplay Framework including graphical interface Generic Coordination Framework/Library: May be used for coordinating any team: World State -> High-Level Decision! Useful for researching on low-level Robotics! Several MAS/MRT coordination methodologies developed with competition success Applications to different robots for distinct cooperative robotic tasks and also to other domains: Rescue, surveillance, military apps Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 90

46 Future Work Strategy based on Tactics, Formations, Flux and Setplays: Formations: flexible use of global vs local info Apply and test in other leagues Test Strategy definition by domain experts(using graphical application) Heterogeneous Robot Teams and Human-Robot Teams Setplays Framework Learning/optimizing setplays using ML Apply and test in other leagues Test Setplay definition by domain experts(using graphical application) Heterogeneous Robot Teams and Human-Robot Teams Release Strategy and Setplay Frameworks for the community OtherCurrentWork: Bridging the Gap between Simulation and Real Robotics: MSL Simulation, SPL League (3D Sim), Real Sports Apply Strategy to other domains: Computer Poker Real Soccer/Sports Research: Individual/team decision, game analysis, and realistic players/game simulation Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 91 Related Publications (1) Luis Mota, LuísPaulo Reis and NunoLau, Multi-Robot Coordination using Setplaysin the Middle-size and Simulation Leagues, Mechatronics, Elsevier, Vol. 21, Issue 2, pp , March 2011, ISSN: , DOI: /j.mechatronics ) (IF: 0.94; SCImagoQ2) Rodrigo A.M. Braga, Marcelo Petry, Luís Paulo Reis, A. Paulo.Moreira, IntellWheels: A Modular Development Platformfor IntelligentWheelchairs. JRRD -Journal of Rehabilitation Research and Development, Dep. of Veterans Affairs, USA, Vol. 48, Issue 9, pp , Dec2011, ISSN: , (IF: 1.71; SCImago Q1) Pedro H. Abreu, J.Moura, Daniel C. Silva, LuísPaulo Reis, JúlioGarganta, Performance Analysis in Soccer: a Cartesian Coordinates based Approach using RoboCupData, Soft Computing -A Fusion of Foundations, Methodologies and Applications, Springer Verlag, Germany, Vol. 16, pp , ISSN: , January 2012 (IF: 1.51; SCImago Q2) Pedro Abreu, JoãoMoreira, Israel Costa, Daniel Castelão, JoãoMoreira, LuísPaulo Reis, JúlioGarganta, Human vs. Virtual Robotic Soccer: A Technical Analysis about Two Realities, European Journal of Sport Science, Taylor & Francis, Vol. 12, Issue 1, pp.26-35, January 2012, ISSN: (IF: 0.89; SCImago Q2). Daniel Silva, Rodrigo A.M. Braga, Luís Paulo Reis, Eugénio Oliveira. Designing a Meta-Model for a Generic Robotic Agent System using GAIA Methodology. Information Sciences, Volume 195, pp , July 2012, Elsevier, ISSN: , (IF:2.84; SCImago Q1) (online first, to appear) João Lobato Oliveira, Luiz Naveda, FabienGouyon, Luís Paulo Reis, Paulo Sousa, MarcLeman. A Parameterizable Spatiotemporal Representation of Popular Dance Styles for Humanoid Dancing Characters. EURASIP Journal on Audio, Speech, and Music Processing, Hindawi Publishing Corporation, USA, ISSN: , (IF: 0.34; SCImago Q3) (to appear) B.M.Faria, G.Castillo, N.Lau, L.P.Reis, Classification of FC Portugal Robotic Soccer Formations: A Comparative Study of Machine Learning Algorithms, Robotica Journal, n. 82, 1st Trim., pp. 4-9, 2011, ISSN: Flexible Coordination of Multi-Robot Teams: Applications in Robotic Soccer, Luis Paulo Reis, LARS/SBR 2012, Fortaleza, Brazil, 92