Our TORCS driving controller presented at EvoGAMES 2017

Last week, @jjmerelo presented at EvoGAMES 2017 (inside Evo* 2017) our work titled “Driving in TORCS using modular fuzzy controllers”.

This paper presents a novel car racing controller for TORCS (The Open Racing Car Simulator), which is based in the combination of two fuzzy subcontrollers, one for setting the speed, and one to control the steer angle. The obtained results are quite promissing, as the controller is quite competitive even against very tough TORCS teams.

The abstract of the paper is:

When driving a car it is essential to take into account all possible factors; even more so when, like in the TORCS simulated race game, the objective is not only to avoid collisions, but also to win the race within a limited budget. In this paper, we present the design of an autonomous driver for racing car in a simulated race. Unlike previous controllers, that only used fuzzy logic approaches for either acceleration or steering, the proposed driver uses simultaneously two fuzzy controllers for steering and computing the target speed of the car at every moment of the race. They use the track border sensors as inputs and besides, for enhanced safety, it has also taken into account the relative position of the other competitors. The proposed fuzzy driver is evaluated in practise and timed races giving good results across a wide variety of racing tracks, mainly those that have many turning points.

There was an interactive presentation at the conference, together with a poster:

The paper is available online from: https://link.springer.com/chapter/10.1007/978-3-319-55849-3_24

Enjoy (and cite) it! :D

 

Advertisements

Hackathon in Videogames at EVO* 2014

Imagen

Hi to all,

Finally, the EVOHackathon will be held in the Oficina de Software Libre on Tuesday 22 April (one day before EVOGames conference).

There are 5 projects confirmed right now,namely:

  • Creating autonomous agents for Super Mario Bros. game
  • Creating an AI engine for the game Wetland (Greyman Studios)
  • Creating bots for 1 vs 1 combats in the RTS Planet Wars
  • Procedural generation of stages for a new game (Greyman Studios)
  • Progamer: Code visualization tool based in Super Mario Bros. levels

As you can see, two of them are proposed and will be directed by a videogames company.

We invite you to join us. It is free! :D

Curso online en Diseño, Organización y Evaluación de videojuegos y gamificación

Se trata de un MOOC, Massive Open Online Course (Curso online masivo y abierto) organizado por la Universidad Europea de Madrid e impartido por Miríada X.

El curso tiene una duración de 6 semanas (5 horas de estudio semanales), comenzando el próximo 20 de Enero.

La descripción del mismo (extraída de la web del curso) es:
“El curso en Creación y Desarrollo de Videojuegos y Gamificación es un primer puente tendido hacia aquellas personas que desean embarcarse en la aventura del diseño y desarrollo de videojuegos, explicando cada aspecto de la industria, desde el diseño a la financiación pasando por el arte y la evaluación.

El curso no pretende abarcar ningún área de programación ni plástica, sino elaborar un sustrato de conocimientos enfocados a la preparación de futuros diseñadores a través de un mapa de conceptos clave y la experiencia compartida de profesionales del medio. Cada módulo tendrá una decena aproximada de breves video-conceptos que eclosionarán en una entrevista final con un profesional del sector que dará su opinión acerca de la situación y posible evolución de la misma.”

Descripción en vídeo:

Los interesados pueden registrarse aquí.

CEDI 2013. Programar no es un juego de niños… ¿o sí?

Dentro del Primer Simposio Español de Entretenimiento Digital (SEED) del CEDI 2013, presentamos una herramienta para visualizar código Java en forma de videojuego tipo Super Mario.  El artículo se llama “Code Reimagined: Gamificación a través de la visualización de código”.

La idea consiste en una representación tipo mapa (parecido a un treemap) del árbol sintáctico. Los bloques de código se representan mediante plataformas, las expresiones como cajas, los bucles con tuberías y el retorno como una puerta… la verdad es que esta representación da mucho juego.

Al ejecutar paso a paso el programa se visualiza a Secret Maryo (la versión libre de Super Mario) recorriendo el escenario del programa.

Aquí está el código y esta es la presentación:

Modelando el conocimiento de un experto en Unreal Tournament (CEDI 2013)

En concreto, hemos presentado el artículo “Modelling Human Expert Behaviour in an Unreal Tournament 2004 Bot” dentro del Primer Simposio Español en Entretenimiento Digital, incluido dentro del CEDI 2013.

Y vosotros diréis, ¿por qué un artículo en inglés en un congreso español?. Pues porque los artículos en inglés que sean seleccionados podrán enviarse a un número especial de la revista Entertainment Computing (Elsevier). A ver si hay suerte. :D

El trabajo presenta el diseño de un bot (jugador autónomo) para jugar a Unreal Tournament 2004 (UT2K4). Dicho bot ha sido creado por Francisco Aisa y Ricardo Caballero, modelando el conocimiento y comportamiento de un jugador experto en dicho juego (el primero de ellos ;D).

La presentación podéis verla en:

Que la disfrutéis (y nos citéis, claro). :D

Saludos.

Unreal Expert Bots at IWANN 2013

Last week there was held IWANN 2013 at Tenerife, an international conference mainly devoted to researches inside the neural networks scope. In it, Antonio Fernández Leiva, Raúl Lara and Me organized the Special Session on Artificial Intelligence and Games.

There were five works in the session, one of them “Designing and Evolving an Unreal Tournament— 2004 Expert Bot“.

It describes the designing and improvement, through off-line (not during the game) evolution, of an autonomous agent (or bot) for playing the game Unreal Tournament 2004. This was created by means of a finite state machine which models the expert behaviour of a human player in 1 vs 1 deathmatch mode, following the rules of the international competition.

Then, the bot was improved by means of a Genetic Algorithm, yielding an agent that is, in turn a very hard opponent for the medium-level human player and which can (easily) beat the default bots in the game, even in the maximum difficulty level.

The presentation can be seen at:

Moreover, you can watch one example of the evolution in the following video:

Finally, the Unreal Expert and Genetic bot’s source code are available at https://github.com/franaisa/ExpertAgent

Enjoy them. ;)

Is entropy good for solving the game of MasterMind?

Well, it does. In another paper published in the Evostar conference, we compare several methods for measuring how good a combination is when compared to the others that could possibly be the solution; so far we had mostly used most parts (counting the number of non-zero partitions), but, in this paper, that compares our previous Evo method with another created by the coauthors, Maestro-Montojo and Salcedo-Sanz, we find that Entropy, at least for these sizes, is the way to go. Here’s the poster


You can access the paper Comparing Evolutionary Algorithms to Solve the Game of MasterMind, by Javier Maestro-Montojo, Juan Julián Merelo and Sancho Salcedo-Sanz (first and last authors from the University of Alcalá de Henares) online or request a copy from the authors.