Journal article
Graph neural networks for decentralized multi-agent perimeter defense
Frontiers in control engineering, v 4, 1104745
13 Jan 2023
Abstract
In this work, we study the problem of decentralized multi-agent perimeter defense that asks for computing actions for defenders with local perceptions and communications to maximize the capture of intruders. One major challenge for practical implementations is to make perimeter defense strategies scalable for large-scale problem instances. To this end, we leverage graph neural networks (GNNs) to develop an imitation learning framework that learns a mapping from defenders’ local perceptions and their communication graph to their actions. The proposed GNN-based learning network is trained by imitating a centralized expert algorithm such that the learned actions are close to that generated by the expert algorithm. We demonstrate that our proposed network performs closer to the expert algorithm and is superior to other baseline algorithms by capturing more intruders. Our GNN-based network is trained at a small scale and can be generalized to large-scale cases. We run perimeter defense games in scenarios with different team sizes and configurations to demonstrate the performance of the learned network.
Metrics
9 Record Views
Details
- Title
- Graph neural networks for decentralized multi-agent perimeter defense
- Creators
- Elijah S. Lee - University of PennsylvaniaLifeng Zhou - Drexel UniversityAlejandro Ribeiro - University of PennsylvaniaVijay Kumar - University of Pennsylvania
- Publication Details
- Frontiers in control engineering, v 4, 1104745
- Publisher
- Frontiers
- Resource Type
- Journal article
- Language
- English
- Academic Unit
- Electrical and Computer Engineering
- Other Identifier
- 991021945766104721