Learning Collective Dynamics of Multi-Agent Systems using Event-based Vision
It addresses the challenge of real-time perception for multi-agent systems in robotics or surveillance, though it is incremental as it builds on existing flocking simulators and deep learning.
This paper tackles the problem of predicting collective dynamics like interaction strength and convergence time in multi-agent systems from visual data, showing that event-based vision methods outperform frame-based approaches in accuracy and efficiency.
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.