Nonlinear MPC for Quadrotors in Close-Proximity Flight with Neural Network Downwash Prediction

TL;DR

This paper presents a novel control approach combining neural network-based downwash prediction with nonlinear model predictive control to improve close-proximity quadrotor swarm flight safety and accuracy.

Contribution

It introduces a neural network predictor trained with spectral normalization integrated into NMPC for proactive disturbance handling in quadrotor swarms.

Findings

75.37% reduction in height tracking error

Validated safety and effectiveness of the neural network predictor

Successful real-time trajectory tracking in experiments

Abstract

Swarm aerial robots are required to maintain close proximity to successfully traverse narrow areas in cluttered environments. However, this movement is affected by the downwash effect generated from other quadrotors in the swarm. This aerodynamic effect is highly nonlinear and hard to describe through mathematical modeling. Additionally, the existence of the downwash disturbance can be predicted based on the states of neighboring quadrotors. If this prediction is considered, the control loop can proactively handle the disturbance, resulting in improved performance. To address these challenges, we propose an approach that integrates a Neural network Downwash Predictor with Nonlinear Model Predictive Control (NDP-NMPC). The neural network is trained with spectral normalization to ensure robustness and safety in uncollected cases. The predicted disturbances are then incorporated into the optimization scheme in NMPC, which enforces constraints to ensure that states and inputs remain within safe limits. We also design a quadrotor system, identify its parameters, and implement the proposed method on board. Finally, we conduct a prediction experiment to validate the safety and effectiveness of the network. In addition, a real-time trajectory tracking experiment is performed with the entire system, demonstrating a 75.37% reduction in tracking error in height under the downwash effect.