Multi-UAV adaptive path planning using Deep Reinforcement Learning

Hafedh Jouini

doi:10.1016/j.robot.2026.105678

Multi-UAV adaptive path planning using Deep Reinforcement Learning

2026-09-07

0

PRE

AI

DOI：10.1016/j.robot.2026.105678

Original

Original request for help

Save

Abstract

En 中文

• Development of a DRL-based E-MAPPO-CTDE framework for multi-UAV trajectory optimization addressing energy, safety, and communication. • Demonstration of robust collision-free navigation and perfect mission completion across various swarm configurations in complex 3D environment. • Ensures collision-free and coordinated navigation in dynamic multi-agent environments. • Demonstrates scalability of the E-MAPPO-CTDE framework to larger UAV swarms while maintaining robust energy efficiency, coordination, and adaptability in dynamic environments.

Keywords:

Multi-UAV systems

Deep learning

DRL

MAPPO

Trajectory efficiency

Energy optimization

Multi-UAV adaptive path planning using Deep Reinforcement Learning

Abstract

Journal

Organization