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

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.

arXiv commentAccepted by IEEE Transactions on Robotics (T-RO), 2021. Video is available at https://youtu.be/Y02juH6BDxo

References in corpus (7)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Neural Lander: Stable Drone Landing Control using Learned Dynamics
• Trajectory Generation for Multiagent Point-To-Point Transitions via Distributed Model Predictive Control
• Control Regularization for Reduced Variance Reinforcement Learning
• Smooth Imitation Learning for Online Sequence Prediction
• Meta-Learning-Based Robust Adaptive Flight Control Under Uncertain Wind Conditions
• Numerical Predictive Control for Delay Compensation

Cited by in corpus (2)

• Perturbation-based Regret Analysis of Predictive Control in Linear Time Varying Systems
• Decentralized Control of Quadrotor Swarms with End-to-end Deep Reinforcement Learning