Online Adaptation for Flying Quadrotors in Tight Formations

2025-06-20

AI Summary

To address instability in tightly coordinated multi-rotor UAV formations caused by strong nonlinear and fast time-varying aerodynamic wake interference, this paper proposes an online adaptive control framework. The method integrates L1 adaptive control with Koopman neural ordinary differential equation (KNODE)-based dynamics modeling to enable real-time compensation of unmodeled aerodynamic disturbances; it further combines dynamic-weighted model predictive control (DW-MPC) with multi-agent distributed optimization to jointly ensure high-precision individual trajectory tracking and collective formation stability. The core contribution is the novel L1 KNODE-DW MPC mixture-of-experts architecture. Experimental validation on a three-UAV vertical tight-formation setup demonstrates sustained centimeter-level inter-vehicle spacing throughout flight. The proposed framework exhibits significantly enhanced robustness and generalization capability compared to conventional MPC baselines.

Technology Category

• Multiagent Systems: Adversarial Agents
• Intelligent Robots: State Estimation
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

The task of flying in tight formations is challenging for teams of quadrotors because the complex aerodynamic wake interactions can destabilize individual team members as well as the team. Furthermore, these aerodynamic effects are highly nonlinear and fast-paced, making them difficult to model and predict. To overcome these challenges, we present L1 KNODE-DW MPC, an adaptive, mixed expert learning based control framework that allows individual quadrotors to accurately track trajectories while adapting to time-varying aerodynamic interactions during formation flights. We evaluate L1 KNODE-DW MPC in two different three-quadrotor formations and show that it outperforms several MPC baselines. Our results show that the proposed framework is capable of enabling the three-quadrotor team to remain vertically aligned in close proximity throughout the flight. These findings show that the L1 adaptive module compensates for unmodeled disturbances most effectively when paired with an accurate dynamics model. A video showcasing our framework and the physical experiments is available here: https://youtu.be/9QX1Q5Ut9Rs

Problem

• Addressing aerodynamic wake interactions in tight quadrotor formations
• Overcoming nonlinear, fast-paced aerodynamic modeling challenges
• Enabling accurate trajectory tracking amid time-varying aerodynamic effects

Innovation

• Adaptive mixed expert learning control
• L1 KNODE-DW MPC framework
• Compensates unmodeled aerodynamic disturbances