Neural-Swarm2: Planning and Control of Heterogeneous Multirotor Swarms using Learned Interactions

TL;DR

Neural-Swarm2 introduces a learning-based approach combining physics models and neural networks to enable safe, close-proximity flight of heterogeneous drone swarms by accurately modeling aerodynamic interactions.

Contribution

It presents a novel method integrating spectral normalization and heterogeneous deep sets for interaction-aware planning and control of drone swarms, improving accuracy and scalability.

Findings

Generalizes to larger swarms beyond training data

Reduces worst-case tracking errors by up to three times

Outperforms baseline nonlinear controllers in experiments

Abstract

We present Neural-Swarm2, a learning-based method for motion planning and control that allows heterogeneous multirotors in a swarm to safely fly in close proximity. Such operation for drones is challenging due to complex aerodynamic interaction forces, such as downwash generated by nearby drones and ground effect. Conventional planning and control methods neglect capturing these interaction forces, resulting in sparse swarm configuration during flight. Our approach combines a physics-based nominal dynamics model with learned Deep Neural Networks (DNNs) with strong Lipschitz properties. We make use of two techniques to accurately predict the aerodynamic interactions between heterogeneous multirotors: i) spectral normalization for stability and generalization guarantees of unseen data and ii) heterogeneous deep sets for supporting any number of heterogeneous neighbors in a permutation-invariant manner without reducing expressiveness. The learned residual dynamics benefit both the proposed interaction-aware multi-robot motion planning and the nonlinear tracking control design because the learned interaction forces reduce the modelling errors. Experimental results demonstrate that Neural-Swarm2 is able to generalize to larger swarms beyond training cases and significantly outperforms a baseline nonlinear tracking controller with up to three times reduction in worst-case tracking errors.