# LEMURS: Learning Distributed Multi-Robot Interactions

arXiv: https://arxiv.org/abs/2209.09702 · HTML: https://mlsanity.com/paper/2209.09702/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Sep 2022.

## Built on by (most cited first, 4 of 4)

- [Graph learning in robotics: a survey](https://mlsanity.com/paper/2310.04294/) (2023)
- [Learning to Identify Graphs from Node Trajectories in Multi-Robot Networks](https://mlsanity.com/paper/2307.04374/) (2023)
- [Curriculum Imitation Learning of Distributed Multi-Robot Policies](https://mlsanity.com/paper/2509.25097/) (2025)
- [Physics-Informed Neural Controlled Differential Equations for Scalable Long Horizon Multi-Agent Motion Forecasting](https://mlsanity.com/paper/2510.00401/) (2025)

## Abstract (arXiv)

This paper presents LEMURS, an algorithm for learning scalable multi-robot control policies from cooperative task demonstrations. We propose a port-Hamiltonian description of the multi-robot system to exploit universal physical constraints in interconnected systems and achieve closed-loop stability. We represent a multi-robot control policy using an architecture that combines self-attention mechanisms and neural ordinary differential equations. The former handles time-varying communication in the robot team, while the latter respects the continuous-time robot dynamics. Our representation is distributed by construction, enabling the learned control policies to be deployed in robot teams of different sizes. We demonstrate that LEMURS can learn interactions and cooperative behaviors from demonstrations of multi-agent navigation and flocking tasks.