Emergent effects in massive agent swarms in real-time game environments

Computational efficiency and hence the scale of agent-based swarm simulations is bound by the nearest neighbour computation for each agent. This article proposes the use of GPU texture memory to implement lookup tables for a spatial partitioning based k-Nearest Neighbours algorithm. These improvements allow simulation of swarms of 2²⁰ agents at higher rates than the current best alternative algorithms. This approach is incorporated into an existing framework for simulating steering behaviours allowing for a complete implementation of massive agent swarm simulations, with per agent behaviour preferences, on a Graphics Processing Unit. These simulations have enabled an investigation of the emergent dynamics that occur when massive swarms interact with a choke point in their environment. Various modes of sustained dynamics with temporal and spatial coherence are identified when a critical mass of agents is simulated and some elementary properties are presented. The algorithms presented in this article enable researchers and content designers in games and movies to implement truly massive agent swarms in real time and thus provide a basis for further identification and analysis of the emergent dynamics in these swarms. This will improve not only the scale of swarms used in commercial games and movies but will also improve the reliability of swarm behaviour with respect to content design goals.

I. Introduction

Agent swarms have been used in a variety of computer game and animation products, such as the penguins in “Batman 2” or the horde of Saruman in “Lord of the Rings: The Two Towers”. Collective behaviours of the swarm represent higher order system dynamics arising from the low level interactions of individual agents, both with their neighbours and with elements of the local environment. Emergent dynamics and the resulting swarm behaviours are becoming increasingly relevant as the number and density of agents increases and as environments are made more complex. An understanding of these emergent dynamics and the relationship to the underlying agent interaction model is necessary if truly massive swarms are to be simulated, with predictable behaviours that meet content design goals. However, to achieve this understanding, the computational bottlenecks that limit the scale and efficiency of swarm simulations must be overcome.