Learning Multi-Pursuit Evasion for Safe Targeted Navigation of Drones

Abstract

Safe navigation of drones in the presence of adversarial physical attacks from multiple pursuers is a challenging task. This paper proposes a novel approach, asynchronous multi-stage deep reinforcement learning (AMS-DRL), to train adversarial neural networks that can learn from the actions of multiple evolved pursuers and adapt quickly to their behavior, enabling the drone to avoid attacks and reach its target. Specifically, AMS-DRL evolves adversarial agents in a pursuit-evasion game where the pursuers and the evader are asynchronously trained in a bipartite graph way during multiple stages. Our approach guarantees convergence by ensuring Nash equilibrium among agents from the game-theory analysis. We evaluate our method in extensive simulations and show that it outperforms baselines with higher navigation success rates. We also analyze how parameters such as the relative maximum speed affect navigation performance. Furthermore, we have conducted physical experiments and validated the effectiveness of the trained policies in real-time flights. A success rate heatmap is introduced to elucidate how spatial geometry influences navigation outcomes. Project website: https://github.com/NTU-ICG/AMS-DRL-for-Pursuit-Evasion.

arXiv commentAccepted by IEEE Transactions on Artificial Intelligence

References in corpus (5)

• Learning High-Speed Flight in the Wild
• Neural-Fly Enables Rapid Learning for Agile Flight in Strong Winds
• Decentralized Multi-Agent Pursuit using Deep Reinforcement Learning
• Cooperative Pursuit with Multi-Pursuer and One Faster Free-moving Evader
• Collaborative Target Search with a Visual Drone Swarm: An Adaptive Curriculum Embedded Multistage Reinforcement Learning Approach

Cited by in corpus (2)

• Vision-based Learning for Drones: A Survey
• Target Search and Navigation in Heterogeneous Robot Systems with Deep Reinforcement Learning