Selectively Reactive Coordination for a Team of Robot Soccer Champions

CMDragons 2015 is the champion of the RoboCup Small Size League of autonomous robot soccer. The team won all of its six games, scoring a total of 48 goals and conceding 0. This unprecedented dominant performance is the result of various features, but we particularly credit our novel offense multi-robot coordination. This paper thus presents our Selectively Reactive Coordination (SRC) algorithm, consisting of two layers: A coordinated opponent-agnostic layer enables the team to create its own plans, setting the pace of the game in offense. An individual opponent-reactive action selection layer enables the robots to maintain reactivity to different opponents. We demonstrate the effectiveness of our coordination through results from RoboCup 2015, and through controlled experiments using a physics-based simulator and an automated referee.

[1]  Kanjanapan Sukvichai,et al.  Robot Hardware, Software, and Technologies behind the SKUBA Robot Team , 2012, RoboCup.

[2]  David L. Westbrook,et al.  Capture the Flag: Military Simulation Meets Computer Games , 1999 .

[3]  Mehmet Akar,et al.  RoboCup Small-Size League: Past, Present and Future , 2014, RoboCup.

[4]  Manuela M. Veloso,et al.  The CMUnited-97 robotic soccer team: perception and multiagent control , 1998, AGENTS '98.

[5]  Manuela M. Veloso,et al.  CMDragons 2015: Coordinated Offense and Defense of the SSL Champions , 2015, RoboCup.

[6]  Manuela M. Veloso,et al.  Safe Multirobot Navigation Within Dynamics Constraints , 2006, Proceedings of the IEEE.

[7]  Manuela M. Veloso,et al.  Fast and accurate vision-based pattern detection and identification , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[8]  Manuela M. Veloso,et al.  CMDragons: Dynamic passing and strategy on a champion robot soccer team , 2008, 2008 IEEE International Conference on Robotics and Automation.

[9]  Manuela M. Veloso,et al.  Opponent-driven planning and execution for pass, attack, and defense in a multi-robot soccer team , 2014, AAMAS.

[10]  Sven Behnke,et al.  Predicting Away Robot Control Latency , 2003, RoboCup.

[11]  Manuela M. Veloso,et al.  Efficient physics-based planning: sampling search via non-deterministic tactics and skills , 2009, AAMAS.

[12]  Manuela M. Veloso,et al.  Variable Level-Of-Detail Motion Planning in Environments with Poorly Predictable Bodies , 2010, ECAI.

[13]  Manuela M. Veloso,et al.  Task Decomposition, Dynamic Role Assignment, and Low-Bandwidth Communication for Real-Time Strategic Teamwork , 1999, Artif. Intell..

[14]  Dimitri P. Bertsekas,et al.  A new algorithm for the assignment problem , 1981, Math. Program..

[15]  Yue Zhao,et al.  ZJUNlict: RoboCup 2013 Small Size League Champion , 2013, RoboCup.

[16]  Manuela M. Veloso,et al.  The CMUnited-98 champion small-robot team , 1998, Adv. Robotics.

[17]  G. Whelan,et al.  Cooperative search and rescue with a team of mobile robots , 1997, 1997 8th International Conference on Advanced Robotics. Proceedings. ICAR'97.

[18]  Manuela M. Veloso,et al.  SSL-Vision: The Shared Vision System for the RoboCup Small Size League , 2009, RoboCup.

[19]  Raffaello D'Andrea.  The Cornell RoboCup Robot Soccer Team: 1999-2003 , 2005, Handbook of Networked and Embedded Control Systems.

[20]  Brett Browning,et al.  STP: Skills, tactics, and plays for multi-robot control in adversarial environments , 2005 .

[21]  Manuela M. Veloso,et al.  AutoRef: Towards Real-Robot Soccer Complete Automated Refereeing , 2014, RoboCup.

[22]  Sarit Kraus,et al.  Multi-robot perimeter patrol in adversarial settings , 2008, 2008 IEEE International Conference on Robotics and Automation.

[23]  Yue Zhao,et al.  ZJUNlict: RoboCup 2014 Small Size League Champion , 2014, RoboCup.

[24]  Manuela M. Veloso,et al.  Trajectory-Based Short-Sighted Probabilistic Planning , 2012, NIPS.

[25]  Peter Stone,et al.  Keepaway Soccer: From Machine Learning Testbed to Benchmark , 2005, RoboCup.