Multi-UAV Navigation and Control

The field of multi-UAV navigation and control is moving towards the development of innovative methods for safe and efficient flight planning, formation control, and collision avoidance in complex environments. Recent research has focused on the use of reinforcement learning, decentralized control architectures, and sparse shepherding techniques to enable multiple UAVs to navigate and interact with each other and their environment in a robust and adaptable manner. Notable advancements include the development of lightweight and computationally efficient algorithms for multi-UAV navigation, as well as the application of machine learning techniques to improve the resilience and safety of UAV swarms. Noteworthy papers include: LEARN, which introduces a lightweight two-stage safety-guided reinforcement learning framework for multi-UAV navigation in cluttered spaces. Anti-Jamming based on Null-Steering Antennas and Intelligent UAV Swarm Behavior, which proposes a unified optimization framework combining Genetic Algorithms, Supervised Learning, and Reinforcement Learning to mitigate jamming in UAV swarms.

Sources

LEARN: Learning End-to-End Aerial Resource-Constrained Multi-Robot Navigation

Anti-Jamming based on Null-Steering Antennas and Intelligent UAV Swarm Behavior

Flow-Based Path Planning for Multiple Homogenous UAVs for Outdoor Formation-Flying

Multi-Agent gatekeeper: Safe Flight Planning and Formation Control for Urban Air Mobility

Sparse shepherding control of large-scale multi-agent systems via Reinforcement Learning

Decentralized Shepherding of Non-Cohesive Swarms Through Cluttered Environments via Deep Reinforcement Learning

Built with on top of