Skip to main content

A Hybrid Reinforcement Learning and Cellular Automata Model for Crowd Simulation on the GPU

by Sergio Ruiz, Benjamin Hernandez Arreguin
Publication Type
Conference Paper
Book Title
High Performance Computing: 5th Latin American Conference, CARLA 2018
Publication Date
Page Numbers
59 to 74
Publisher Location
Singapore, Singapore
Conference Name
Latin American High Performance Computing Conference (CARLA 2018)
Conference Location
Bucaramanga, Colombia
Conference Sponsor
Universidad Industrial de Santander
Conference Date

We present a GPU-based hybrid model for crowd simulations. The model uses reinforcement learning to guide groups of pedestrians towards a goal while adapting to environmental dynamics, and a cellular automaton to describe individual pedestrians’ interactions. In contrast to traditional multi-agent reinforcement learning methods, our model encodes the learned navigation policy into a navigation map, which is used by the cellular automaton’s update rule to calculate the next simulation step. As a result, reinforcement learning is independent of the number of agents, allowing the simulation of large crowds. Implementation of this model on the GPU allows interactive simulations of several hundreds of pedestrians.