Technical Note: Generating Realistic Fighting Scenes by Game Tree

TL;DR

This paper introduces a novel approach for generating realistic multi-avatar fighting scenes by transforming continuous actions into a discrete causality space, enabling strategic planning with algorithms like Minimax.

Contribution

It presents the temporal expansion approach and an offense/defense table to incorporate tactical decision-making into simulated fighting scenes.

Findings

Successfully generated realistic multi-avatar fighting scenes

Enabled strategic planning using game tree algorithms

Applicable to other continuous strategic activities like sports

Abstract

Recently, there have been a lot of researches to synthesize / edit the motion of a single avatar in the virtual environment. However, there has not been so much work of simulating continuous interactions of multiple avatars such as fighting. In this paper, we propose a new method to generate a realistic fighting scene based on motion capture data. We propose a new algorithm called the temporal expansion approach which maps the continuous time action plan to a discrete causality space such that turn-based evaluation methods can be used. As a result, it is possible to use many mature algorithms available in strategy games such as the Minimax algorithm and $\alpha-\beta$ pruning. We also propose a method to generate and use an offense/defense table, which illustrates the spatial-temporal relationship of attacks and dodges, to incorporate tactical maneuvers of defense into the scene. Using our method, avatars will plan their strategies taking into account the reaction of the opponent. Fighting scenes with multiple avatars are generated to demonstrate the effectiveness of our algorithm. The proposed method can also be applied to other kinds of continuous activities that require strategy planning such as sport games.