An Automatic Race Track Generating System

Abstract

AbstractIn this paper, we propose an automatic race track generating system based on difficulty evaluation and feature turns detection for providing users skill-matched contents. Given a start point, a goal point, and a difficulty expectation chart, our system ranks all candidate race tracks according to the similarity with respect to the given difficulty curve. Then, user can choose a satisfied track and export it into a racing car simulator to play.The system automatically creates the racing line for the input race track. Then, the line is used to segment turns in the race track, and the corresponding ideal maximum speed variation is exploited to evaluate the difficulty by our proposed Turnscore formula. Also, the corresponding curvature chart of the racing line is encoded as a string and the characterized regular expression for feature turns is being matched in the string for identifying feature turns.As the experimental results show, the feature turns detection is of high accuracy and the difficulty evaluation is reliable so that our system is effective to provide skill-matched race tracks for users.KeywordsDifficulty EvaluationRace Track GenerationRacing LineString SearchingProcedural Content GenerationFeature Detection