Online Flocking Control of UAVs with Mean-Field Approximation

TL;DR

This paper introduces a distributed flocking control method for UAV swarms using mean-field approximation, ensuring smooth, collision-free formation and velocity consensus through an inference-based approach validated by real-world experiments.

Contribution

It presents a novel inference-based, distributed flocking control algorithm for UAVs that incorporates mean-field approximation and feasible action spaces, improving coordination and collision avoidance.

Findings

Successfully controls UAV swarms to formation and velocity consensus

Achieves real-time collision avoidance in physical and simulated environments

Validates effectiveness through experiments with physical UAVs

Abstract

This work presents a novel, inference-based approach to the distributed and cooperative flocking control of aerial robot swarms. The proposed method stems from the Unmanned Aerial Vehicle (UAV) dynamics by limiting the latent set to the robots' feasible action space, thus preventing any unattainable control inputs from being produced and leading to smooth flocking behavior. By modeling the inter-agent relationships using a pairwise energy function, we show that interacting robot swarms constitute a Markov Random Field. Our algorithm builds on the Mean-Field Approximation and incorporates the collective behavioral rules: cohesion, separation, and velocity alignment. We follow a distributed control scheme and show that our method can control a swarm of UAVs to a formation and velocity consensus with real-time collision avoidance. We validate the proposed method with physical UAVs and high-fidelity simulation experiments.