Learning Altruistic Collaboration in Heterogeneous Multi-Team Systems

TL;DR

This paper introduces a graph neural network-based framework for scalable, altruistic multi-team robot collaboration using Hamilton's rule, validated in firefighting simulations.

Contribution

It proposes a novel GNN policy for dynamic, altruistic robot allocation in heterogeneous multi-team systems, addressing NP-hardness and scalability challenges.

Findings

The GNN policy achieves near-optimal performance in simulations.

The approach scales effectively to larger multi-team systems.

Validation in firefighting scenarios demonstrates practical applicability.

Abstract

This paper studies heterogeneous multi-team collaboration through dynamic robot allocation, where robots are treated as transferable resources. Leveraging Hamilton's rule from ecology as an altruistic decision-making mechanism, we propose a multi-team collaborative resource allocation framework with heterogeneous capabilities, transfer costs, and capability-dependent contributions. The resulting allocation problem is combinatorial and is shown to be NP-hard. To address scalability, we develop a graph neural network policy under centralized training and decentralized execution that approximates the altruistic allocations based on Hamilton's rule. The model operates over the team interaction graph and predicts robot-level transfer decisions and next robot-to-team assignments. The proposed approach is validated in a firefighting scenario through simulations and experiments, demonstrating that the learned policy achieves near-optimal performance while scaling to larger systems.