Intercepting an Agile Target with Net-Carrying Drones using Competitive Multi-Agent Reinforcement Learning
This work addresses the practical problem of drone interception for security applications, showing that MARL with self-play can learn effective pursuit-evasion strategies in high-fidelity simulation.
The authors formulate the problem of intercepting an agile drone with net-carrying drones as a competitive MARL task and train pursuers and evader using MAPPO with PFSP. Their solution outperforms heuristic baselines in catch rate, time to catch, and crash rates, with PFSP yielding more robust policies.
This article presents a solution to intercept an agile drone by a team of agile drone carrying catching nets. We formulate the problem as a competitive Multi-Agent Reinforcement Learning (MARL) task. To address the problem of nonstationarity and catastrophic forgetting of agents overfitting to the current opponent strategy, we train the pursuers and the evader using Multi-Agent Proximal Policy Optimization (MAPPO) with Prioritized Fictitious Self Play (PFSP). We train the agents in a high-fidelity simulator using low-level control commands, collective thrust and body rates (CTBR), to achieve agile flights for both the pursuers and the evader. We compare the performance of the trained policies in terms of catch rate, time to catch and crash rates, against heuristic baselines and show that our solution outperforms them. Ablation studies show that PFSP lead to more robust policies that can adapt to different opponent strategies, and that a low-level control commands are crucial for learning performing strategies in the pursuit-evasion task. Finally, a qualitative analysis of the learned behaviours highlights the emergence of cooperative tactics among the pursuers.