This work presents a joint project by the University of Calabria (UniCal) and the Vienna University of Technology (TU Vienna), aiming at developing an Intelligent Agent participating in the 2013 Angry Birds Artificial Intelligence Competition. Angry Birds is a very popular video game where the main goal is to shoot at some pigs by means of birds of different characteristics from a slingshot. The game field (which is static until the player moves) features some structures that shelter pigs. Structures can be very complicated and can involve a number of different object categories with different properties, like wood, ice, stone, etc. The game scenario evolves largely complying with physics laws on a bi-dimensional plane; thus, it is possible, in principle, to infer how a structure will change if hit at a certain position by a certain bird. The Angry Birds AI Competitions are designed to test the abilities of Angry Birds artificial agents, playing on a variety of levels, on the Google Chrome version of the game. The competition runs on a client/server architecture, where the server runs an instance of the game for each participating agent. Each agent runs on a client computer, and communicates with the server according with a given protocol that allows agents to fetch screenshots of their own game screen at any time. An artificial player can also obtain the current high scores for each level, and can prompt the server for executing a shot, which will in turn be performed in the corresponding game screen. The long term goal of the Competition is to foster the building of AI agents that can play any new level better than the best human players. In order to successfully solve this challenge, participants are solicited to combine different areas of AI such as computer vision, knowledge representation and reasoning, planning, heuristic search, and machine learning. Successfully integrating methods from these areas is indeed one of the great challenges of AI.

AngryHEX: an Artificial Player for Angry Birds Based on Declarative Knowledge Bases / Calimeri, Francesco; Fink, M; Germano, S; Ianni, Giovambattista; Redl, C; Wimmer, A.. - 1107(2013), pp. 29-35. ((Intervento presentato al convegno Popularize Artificial Intelligence (PAI@AI*IA) - PAI 2013 tenutosi a Torino nel 05/12/2013.

AngryHEX: an Artificial Player for Angry Birds Based on Declarative Knowledge Bases

CALIMERI, Francesco;GERMANO S;IANNI, Giovambattista;
2013

Abstract

This work presents a joint project by the University of Calabria (UniCal) and the Vienna University of Technology (TU Vienna), aiming at developing an Intelligent Agent participating in the 2013 Angry Birds Artificial Intelligence Competition. Angry Birds is a very popular video game where the main goal is to shoot at some pigs by means of birds of different characteristics from a slingshot. The game field (which is static until the player moves) features some structures that shelter pigs. Structures can be very complicated and can involve a number of different object categories with different properties, like wood, ice, stone, etc. The game scenario evolves largely complying with physics laws on a bi-dimensional plane; thus, it is possible, in principle, to infer how a structure will change if hit at a certain position by a certain bird. The Angry Birds AI Competitions are designed to test the abilities of Angry Birds artificial agents, playing on a variety of levels, on the Google Chrome version of the game. The competition runs on a client/server architecture, where the server runs an instance of the game for each participating agent. Each agent runs on a client computer, and communicates with the server according with a given protocol that allows agents to fetch screenshots of their own game screen at any time. An artificial player can also obtain the current high scores for each level, and can prompt the server for executing a shot, which will in turn be performed in the corresponding game screen. The long term goal of the Competition is to foster the building of AI agents that can play any new level better than the best human players. In order to successfully solve this challenge, participants are solicited to combine different areas of AI such as computer vision, knowledge representation and reasoning, planning, heuristic search, and machine learning. Successfully integrating methods from these areas is indeed one of the great challenges of AI.
artificial intelligence; games; Answer Set Programming
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11770/170132
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 7
  • ???jsp.display-item.citation.isi??? ND
social impact