Graph Neural Networks for Decentralized Multi-Agent Perimeter Defense

The problem of perimeter defense games considers a scenario where the defenders are constrained to move along a perimeter and try to capture the intruders while the intruders aim to reach the perimeter without being captured by the defenders (Shishika and Kumar, 2020). A number of previous works have solved this problem with engagements on a planar game space (Shishika and Kumar, 2018; Chen et al., 2021). However, in the real world, the perimeter may be represented by a three-dimensional shape as the players (e.g., defenders and intruders) may have the ability to perform three-dimensional motions. For example, a perimeter of a building that defenders aim to protect can be enclosed by a hemisphere. As a result, the defender robots should be able to move in three-dimensional space. For example, aerial robots have been well studied in various settings (Chen et al., 2020; Nguyen et al., 2019; Lee et al., 2016, 2020a), and all these settings can be real-world use-cases for perimeter defense. For instance, intruders try to attack a military base in the forest and defenders aim to capture the intruders. In this work, we tackle the perimeter defense problem in a domain where multiple agents collaborate to accomplish a task. Multi-agent collaboration has been explored in many areas including environmental mapping (Liu et al., 2022; Thrun et al., 2000), search and rescue (Miller et al., 2020; Baxter et al., 2007),