UT Austin Villa RoboCup 3D simulation team base code release

This release is based off the UT Austin Villa RoboCup 3D simulation league team.

Video of default demo behavior: (YouTube, mp4)

• Omnidirectional walk engine based on a double inverted pendulum model
• A skill description language for specifying parameterized skills/behaviors
• Getup behaviors for all agent types
• A couple basic skills for kicking one of which uses inverse kinematics
• Sample demo dribble and kick behaviors for scoring a goal
• World model and particle filter for localization
• Kalman filter for tracking objects
• All necessary parsing code for sending/receiving messages from/to the server
• Code for drawing objects in the roboviz monitor
• Communication system previously provided for use in drop-in player challenges
• Example behaviors/tasks for optimizing a kick and forward walk
• Support for Gazebo RoboCup 3D simulation plugin (https://bitbucket.org/osrf/robocup3ds)
• Scripts and code for collecting game statistics

• The team's complete set of skills such as long kicks and goalie dives
• Optimized parameters for behaviors such as the team's fastest walks (slow and stable walk engine parameters are included, as well as optimized walk engine parameters for positioning/dribbling and approaching the ball to kick)
• High level strategy including formations and role assignment

• simspark and rcssserver3d
• Boost library
• Threads library

Instructions for installing simspark and rcssserver3d: https://gitlab.com/robocup-sim/SimSpark/wikis/Installation-on-Linux

It's optional (recommended) to install the roboviz monitor: https://github.com/magmaOffenburg/RoboViz

cmake . 

(If cmake can't find RCSSNET3D set the SPARK_DIR environmental variable to the path where you installed the server and then rerun cmake. Also, if you installed rcssserver3d from a package instead of building it from source, you might need to install the rcssserver3d-dev package.)

make

First be sure to start the simulation server running.

./start.sh <host>

./start_penalty_kicker.sh <host>

./start_penalty_goalie.sh <host>

./start_gazebo.sh <host>

  Video of default walking behavior in Gazebo: (YouTube, mp4)

./kill.sh

./agentspark --help

See DOCUMENTATION for some high level documentation about the codebase.

See the methods in selectSkill() in behaviors/strategy.cc for demo behaviors.

See the optimization directory.

(http://www.cs.utexas.edu/~AustinVilla/sim/3dsimulation/)

(http://www.cs.utexas.edu/~AustinVilla/sim/3dsimulation/publications.html)

If you use this code for research purposes, please consider citing one or more research papers listed at the above link which includes the following topics and papers:

Patrick MacAlpine and Peter Stone. UT Austin Villa RoboCup 3D Simulation Base Code Release. In Sven Behnke, Daniel D. Lee, Sanem Sariel, and Raymond Sheh, editors, RoboCup 2016: Robot Soccer World Cup XX, Lecture Notes in Artificial Intelligence, Springer Verlag, Berlin, 2016. (http://www.cs.utexas.edu/~pstone/Papers/bib2html/b2hd-LNAI16-MacAlpine2.html)

Patrick MacAlpine, Samuel Barrett, Daniel Urieli, Victor Vu, and Peter Stone. Design and Optimization of an Omnidirectional Humanoid Walk: A Winning Approach at the RoboCup 2011 3D Simulation Competition. In Proceedings of the Twenty-Sixth AAAI Conference on Artificial Intelligence (AAAI), July 2012. (http://www.cs.utexas.edu/~pstone/Papers/bib2html/b2hd-AAAI12-MacAlpine.html)

Patrick MacAlpine and Peter Stone. Overlapping Layered Learning. Artificial Intelligence (AIJ), 254:21-43, Elsevier, January 2018. (http://www.cs.utexas.edu/~pstone/Papers/bib2html/b2hd-AIJ18-MacAlpine.html)

Patrick MacAlpine, Josiah Hanna, Jason Liang, and Peter Stone. UT Austin Villa: RoboCup 2015 3D Simulation League Competition and Technical Challenges Champions. In Luis Almeida, Jianmin Ji, Gerald Steinbauer, and Sean Luke, editors, RoboCup-2015: Robot Soccer World Cup XIX, Lecture Notes in Artificial Intelligence, Springer Verlag, Berlin, 2016. (http://www.cs.utexas.edu/~pstone/Papers/bib2html/b2hd-LNAI15-MacAlpine.html)

Patrick MacAlpine ([email protected])

Peter Stone ([email protected])