Learning Collective Dynamics of Multi-Agent Systems using Event-based Vision

TL;DR

This paper introduces evMAP, a deep learning approach using event-based vision data to predict collective dynamics in multi-agent systems, demonstrating improved accuracy over traditional methods.

Contribution

It presents a novel problem setting, creates a new dataset with event-based visual data, and develops evMAP for real-time prediction of multi-agent behaviors.

Findings

Event-based representation outperforms frame-based methods in predicting collective dynamics.

evMAP achieves real-time, accurate predictions of interaction strength and convergence time.

Created a new simulated dataset for multi-agent vision-based perception.

Abstract

This paper proposes a novel problem: vision-based perception to learn and predict the collective dynamics of multi-agent systems, specifically focusing on interaction strength and convergence time. Multi-agent systems are defined as collections of more than ten interacting agents that exhibit complex group behaviors. Unlike prior studies that assume knowledge of agent positions, we focus on deep learning models to directly predict collective dynamics from visual data, captured as frames or events. Due to the lack of relevant datasets, we create a simulated dataset using a state-of-the-art flocking simulator, coupled with a vision-to-event conversion framework. We empirically demonstrate the effectiveness of event-based representation over traditional frame-based methods in predicting these collective behaviors. Based on our analysis, we present event-based vision for Multi-Agent dynamic Prediction (evMAP), a deep learning architecture designed for real-time, accurate understanding of interaction strength and collective behavior emergence in multi-agent systems.