A Learning Framework For Cooperative Collision Avoidance of UAV Swarms Leveraging Domain Knowledge

TL;DR

This paper introduces a MARL framework for UAV swarm collision avoidance that leverages domain knowledge from image processing to improve efficiency and scalability, enabling UAVs to adapt to complex environments.

Contribution

The framework integrates domain knowledge-driven rewards into MARL, reducing interaction complexity and enabling large swarm training without complex credit assignment.

Findings

Outperforms state-of-the-art MARL algorithms in collision avoidance tasks.

Enables large-scale UAV swarm training with minimal interaction.

UAVs adapt effectively to complex and non-ideal environments.

Abstract

This paper presents a multi-agent reinforcement learning (MARL) framework for cooperative collision avoidance of UAV swarms leveraging domain knowledge-driven reward. The reward is derived from knowledge in the domain of image processing, approximating contours on a two-dimensional field. By modeling obstacles as maxima on the field, collisions are inherently avoided as contours never go through peaks or intersect. Additionally, counters are smooth and energy-efficient. Our framework enables training with large swarm sizes as the agent interaction is minimized and the need for complex credit assignment schemes or observation sharing mechanisms in state-of-the-art MARL approaches are eliminated. Moreover, UAVs obtain the ability to adapt to complex environments where contours may be non-viable or non-existent through intensive training. Extensive experiments are conducted to evaluate the performances of our framework against state-of-the-art MARL algorithms.