# Graph Neural Networks for Decentralized Multi-Agent Perimeter Defense

arXiv: https://arxiv.org/abs/2301.09689 · HTML: https://mlsanity.com/paper/2301.09689/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 40 references that are in the map.
- First posted on arXiv 23 Jan 2023.

## Builds on (most cited first, 26 of 26)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Convolutional Neural Network Architectures for Signals Supported on Graphs](https://mlsanity.com/paper/1805.00165/) (2018)
- [Graph Neural Networks for Decentralized Multi-Robot Path Planning](https://mlsanity.com/paper/1912.06095/) (2019)
- [Graph Neural Networks: Architectures, Stability and Transferability](https://mlsanity.com/paper/2008.01767/) (2020)
- [Learning Decentralized Controllers for Robot Swarms with Graph Neural Networks](https://mlsanity.com/paper/1903.10527/) (2019)
- [Message-Aware Graph Attention Networks for Large-Scale Multi-Robot Path Planning](https://mlsanity.com/paper/2011.13219/) (2020)
- [A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning](https://mlsanity.com/paper/2011.00382/) (2020)
- [SLOAM: Semantic Lidar Odometry and Mapping for Forest Inventory](https://mlsanity.com/paper/1912.12726/) (2019)
- [It Takes Two: Learning to Plan for Human-Robot Cooperative Carrying](https://mlsanity.com/paper/2209.12890/) (2022)
- [MAVNet: an Effective Semantic Segmentation Micro-Network for MAV-based Tasks](https://mlsanity.com/paper/1904.01795/) (2019)
- [Mine Tunnel Exploration using Multiple Quadrupedal Robots](https://mlsanity.com/paper/1909.09662/) (2019)
- [Active Metric-Semantic Mapping by Multiple Aerial Robots](https://mlsanity.com/paper/2209.08465/) (2022)
- [Decentralization of Multiagent Policies by Learning What to Communicate](https://mlsanity.com/paper/1901.08490/) (2019)
- [Mobile Wireless Network Infrastructure on Demand](https://mlsanity.com/paper/2002.03026/) (2020)
- [Defending a Perimeter from a Ground Intruder Using an Aerial Defender: Theory and Practice](https://mlsanity.com/paper/2109.02852/) (2021)
- [Matching-Based Capture Strategies for 3D Heterogeneous Multiplayer Reach-Avoid Differential Games](https://mlsanity.com/paper/1909.11881/) (2019)
- [Perimeter-defense Game between Aerial Defender and Ground Intruder](https://mlsanity.com/paper/2012.14980/) (2020)
- [Construction of the Barrier for Reach-Avoid Differential Games in Three-Dimensional Space with Four Equal-Speed Players](https://mlsanity.com/paper/1904.02810/) (2019)
- [Guarding a Target Set from a Single Attacker in the Euclidean Space](https://mlsanity.com/paper/2109.07075/) (2021)
- [Competitive Perimeter Defense of Conical Environments](https://mlsanity.com/paper/2110.04667/) (2021)
- [D2CoPlan: A Differentiable Decentralized Planner for Multi-Robot Coverage](https://mlsanity.com/paper/2209.09292/) (2022)
- [Vision-based Relative Detection and Tracking for Teams of Micro Aerial Vehicles](https://mlsanity.com/paper/2207.08301/) (2022)
- [Vision-based Perimeter Defense via Multiview Pose Estimation](https://mlsanity.com/paper/2209.12136/) (2022)
- [Learning Decentralized Strategies for a Perimeter Defense Game with Graph Neural Networks](https://mlsanity.com/paper/2211.01757/) (2022)
- [Guarding a Subspace in High-Dimensional Space with Two Defenders and One Attacker](https://mlsanity.com/paper/1904.01113/) (2019)
- [Modular Multi-Rotors: From Quadrotors to Fully-Actuated Aerial Vehicles](https://mlsanity.com/paper/2202.00788/) (2022)

## Built on by (most cited first, 3 of 3)

- [LPAC: Learnable Perception-Action-Communication Loops with Applications to Coverage Control](https://mlsanity.com/paper/2401.04855/) (2024)
- [Learning Decentralized Flocking Controllers with Spatio-Temporal Graph Neural Network](https://mlsanity.com/paper/2309.17437/) (2023)
- [A Decentralized Spike-based Learning Framework for Sequential Capture in Discrete Perimeter Defense Problem](https://mlsanity.com/paper/2305.16748/) (2023)

## Abstract (arXiv)

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.