Welcome to the Angry Birds AI Competition Website
NEW (November 28, 2016): The next AIBIRDS competition will be held at IJCAI 2017 in Melbourne, Australia.
NEW (September 23, 2016): The results of our first Level Generation Competition are out!
NEW (July 19, 2016): Humans won the 2016 Man vs Machine Challenge. Now that Go is solved, Angry Birds is the next big AI Challenge!
NEW (July 15, 2016): We have a winner! Team BamBirds is the AIBIRDS 2016 Champion. See the detailed results.
Here you will find all the information about upcoming and previous Angry Birds AI Competitions. The task of this competition is to develop a computer program that can successfully play Angry Birds. The long term goal is to build an intelligent Angry Birds playing agent that can play new levels better than the best human players. This is a very difficult problem as it requires agents to predict the outcome of physical actions without having complete knowledge of the world, and then to select a good action out of infinitely many possible actions. This is an essential capability of future AI systems that interact with the physical world. The Angry Birds AI competition provides a simplified and controlled environment for developing and testing these capabilities.
The next Angry Birds AI competition will be held at IJCAI 2017 in Melbourne, Australia, August 24-25, 2017. For more details please refer to the Call for Participation and the detailed Competition Rules. This year we will again have two competition tracks, the standard track and a competitive track where two AI agents try to solve the same level with alternating shots. Previous Angry Birds AI competitions were held in Sydney in December 2012 during the Australasian AI conference, in Beijing in August 2013 during the IJCAI conference, in Prague in August 2014 at the ECAI conference, in Buenos Aires in July 2015 at the IJCAI conference, and most recently at the IJCAI 2016 conference in New York. Further details about these past competitions can be found here.
We provide a basic game playing software that includes a computer vision module, a trajectory planning module, and the game interface that works with the Chrome version of Angry Birds. The image you see above is a typical output of our computer vision module that detects and categorises the relevant objects and places a bounding box around them. Alternatively, you can download the source code of previous successful participants.
We also have a discussion forum where you can discuss issues and exchange ideas with us and with other participants. On the forum we will also post the latest news and answers to some common questions. You can also leave a comment or like us on our Facebook page where we post latest news and announcements. You can also follow us on Twitter.
There are typically two further events during a competition. One is the Symposium on AI in Angry Birds which gives the opportunity to present original scientific work related to the problems of developing intelligent Angry Birds playing agents. Please refer to the Call for Papers for more details on the Symposium. The other event is the popular Angry Birds: Man vs Machine Challenge where we test if the best AI agents can already beat humans at playing Angry Birds.
Jochen Renz, XiaoYu (Gary) Ge, Peng Zhang and Matthew Stephenson
Australian National University