# Collective Behavior Clone with Visual Attention via Neural Interaction Graph Prediction

arXiv: https://arxiv.org/abs/2503.06869 · HTML: https://mlsanity.com/paper/2503.06869/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data.
- First posted on arXiv 10 Mar 2025.

## Placed in

- Offline RL and imitation learning from data / [Imitation learning methods](https://mlsanity.com/offlinerl/imitation-learning-methods/)

## Built on by (most cited first, 2 of 2)

- [R2BC: Multi-Agent Imitation Learning from Single-Agent Demonstrations](https://mlsanity.com/paper/2510.18085/) (2025)
- [SIR: Structured Image Representations for Explainable Robot Learning](https://mlsanity.com/paper/2606.30101/) (2026)

## Abstract (arXiv)

In this paper, we propose a framework, collective behavioral cloning (CBC), to learn the underlying interaction mechanism and control policy of a swarm system. Given the trajectory data of a swarm system, we propose a graph variational autoencoder (GVAE) to learn the local interaction graph. Based on the interaction graph and swarm trajectory, we use behavioral cloning to learn the control policy of the swarm system. To demonstrate the practicality of CBC, we deploy it on a real-world decentralized vision-based robot swarm system. A visual attention network is trained based on the learned interaction graph for online neighbor selection. Experimental results show that our method outperforms previous approaches in predicting both the interaction graph and swarm actions with higher accuracy. This work offers a promising approach for understanding interaction mechanisms and swarm dynamics in future swarm robotics research. Code and data are available.