Automatic Track Generation for High-End Racing Games Using Evolutionary Computation

Abstract

Abstract-We investigate the application of evolutionary computation to the automatic generation of tracks for high-end racing games. The idea underlying our approach is that diversity is a major source of challenge/interest for racing tracks and, eventually, might play a key role in contributing to the player's fun. In particular, we focus on the diversity of a track in terms of its shape (i.e., the number and the assortments of turns and straights it contains), and in terms of driving experience it provides (i.e., the range of speeds achievable while driving on the track). We define two fitness functions that capture our idea of diversity as the entropy of the track's curvature and speed profiles. We apply both a single-objective and a multi-objective real-coded genetic algorithm to evolve tracks involving both a wide variety of turns and straights and also a large range of driving speeds. The results we report show that both singleobjective and multi-objective approaches can successfully evolve tracks with a high degree of diversity both in terms of shape and achievable speeds.

Adaptive user modelling in car racing games using behavioural and physiological data

“…Pushing the car to the limits and handling tight turns at high speeds is what engages the users in that category of games. Loiacono et al (2011) derived an algorithm for generating new tracks in a car simulator using single and multi-objective genetic algorithms. Through certain constraints (e.g.…”

“…and the use of polar coordinates, their algorithm fills the path through particular "control" points that the road needs to cross. Cardamone et al (2011) proposed a framework for advancing the Loiacono et al (2011) algorithm through a human-assisted generation of tracks. Subjects voted for each generated track using scoring interfaces (5 Likert scale or Boolean type) that were influencing the algorithm over the next generations of tracks.…”

Personalised track design in car racing games

“…Taking the research to the next step, Loiacono et al [9] derived an algorithm for generating new tracks in a car simulator (TORCS) using single and multi-objective genetic algorithms. By maximising the entropy of certain criteria (e.g.…”

A Real Time Lighting Technique for Procedurally Generated 2D Isometric Game Terrains

“…In general, what mainly changes amongst several approaches is the chosen threshold of randomness and the way it is applied to the problem. Evolutionary algorithms, which involve random mutations, are often applied to the procedural generation of characters [8], terrains [9], tracks for racing games [10] and others. However, as previously addressed, deterministic algorithms can also be classified as procedural.…”