🤖 AI Summary
This paper addresses the decentralized target localization task assignment problem for heterogeneous UGV/UAV systems under dynamic scalability—where both robot and task counts vary over time. We propose GATAR, a novel graph neural operator–driven decentralized assignment framework. GATAR introduces a graph attention mechanism for neighborhood-aware information aggregation and incorporates a heterogeneity-aware preprocessing module to explicitly model platform-specific characteristics. A single trained model generalizes across systems of 2–12 heterogeneous robots. In extensive multi-scenario simulations, GATAR consistently outperforms state-of-the-art baseline methods in assignment quality, convergence speed, and robustness to communication failures and topology changes. The framework achieves near-global optimality while maintaining strong scalability and decentralization guarantees—enabling real-time, adaptive coordination without centralized supervision or retraining.
📝 Abstract
We introduce a new graph neural operator-based approach for task allocation in a system of heterogeneous robots composed of Unmanned Ground Vehicles (UGVs) and Unmanned Aerial Vehicles (UAVs). The proposed model, GATAR, or Graph Attention Task AllocatoR aggregates information from neighbors in the multi-robot system, with the aim of achieving globally optimal target localization. Being decentralized, our method is highly robust and adaptable to situations where the number of robots and the number of tasks may change over time. We also propose a heterogeneity-aware preprocessing technique to model the heterogeneity of the system. The experimental results demonstrate the effectiveness and scalability of the proposed approach in a range of simulated scenarios generated by varying the number of UGVs and UAVs and the number and location of the targets. We show that a single model can handle a heterogeneous robot team with a number of robots ranging between 2 and 12 while outperforming the baseline architectures.
