Fast Simulation of Crowd Collision Avoidance

TL;DR

This paper presents a GPU-based implementation of the ORCA crowd simulation model, achieving up to 30 times faster performance and enabling real-time simulation of over 100,000 agents for large-scale crowd behavior analysis.

Contribution

It introduces a novel GPU-accelerated linear program solver and spatial partitioning techniques for crowd simulation, significantly improving performance over CPU methods.

Findings

Up to 30x performance improvement over CPU models

Real-time simulation of over 100,000 agents

Effective GPU-based linear program solver

Abstract

Real-time large-scale crowd simulations with realistic behavior, are important for many application areas. On CPUs, the ORCA pedestrian steering model is often used for agent-based pedestrian simulations. This paper introduces a technique for running the ORCA pedestrian steering model on the GPU. Performance improvements of up to 30 times greater than a multi-core CPU model are demonstrated. This improvement is achieved through a specialized linear program solver on the GPU and spatial partitioning of information sharing. This allows over 100,000 people to be simulated in real time (60 frames per second).