Play patterns for path prediction in multiplayer online games

Abstract

Traditional dead reckoning schemes predict a player's position by assuming that players move with constant force or velocity. However, because player movement is rarely linear in nature, using linear prediction fails to produce an accurate result. Among existing dead reckoning methods, only few focus on improving prediction accuracy via genuinely nontraditional methods for predicting the path of a player. In this paper, we propose a new prediction method based on play patterns. We implemented a 2D top-down multiplayer online game to act as a test harness that we used to collect play data from 44 experienced players. From the data for half of these players, we extracted play patterns, which we used to create our dead reckoning algorithm. A comparative evaluation proceeding from an extensive set of simulations (using the other half of our play data) suggests that our EKB algorithm yields more accurate predictions than the IEEE standard dead reckoning algorithm and the recent "Interest Scheme" algorithm.