Efficient multi-agent deep reinforcement learning algorithm for multi UAV collision avoidance

Mohammad Reza Rezaee

doi:10.1016/j.asoc.2026.115145

Efficient multi-agent deep reinforcement learning algorithm for multi UAV collision avoidance

2026-03-30

0

OA

AI

M

Mohammad Reza Rezaee

N

Nor Asilah Wati Abdul Hamid *

M

Masnida Hussin

Z

Zuriati Ahmad Zukarnain

DOI：10.1016/j.asoc.2026.115145

Original

Save

View PDF

Abstract

En 中文

• Suggest an efficient multi-agent deep reinforcement learning algorithm for UAV collision avoidance in dynamic environments. • Propose an efficient graph attention network architecture for modeling UAV interactions. • Demonstrate improved scalability with increasing numbers of UAVs based on the suggested architecture and curriculum learning.

Keywords:

Unmanned aerial vehicle

Collision avoidance

Multi-agent learning

Deep reinforcement learning

Graph attention network

Efficient multi-agent deep reinforcement learning algorithm for multi UAV collision avoidance

Abstract

AI Summary

Journal

Organization