Improving Drone Racing Performance Through Iterative Learning MPC

TL;DR

This paper introduces an enhanced iterative learning MPC framework for autonomous drone racing, achieving significant improvements in lap times and safety through adaptive costs, safe sets, and Cartesian formulations, validated by extensive simulations and real-world tests.

Contribution

The paper presents three innovations—adaptive cost function, shifted local safe set, and Cartesian-based formulation—that improve iterative learning MPC for drone racing.

Findings

Up to 60.85% lap time reduction in simulations.

6.05% improvement on a real drone with a tuned controller.

Enhanced safety and robustness in real-world drone racing scenarios.

Abstract

Autonomous drone racing presents a challenging control problem, requiring real-time decision-making and robust handling of nonlinear system dynamics. While iterative learning model predictive control (LMPC) offers a promising framework for iterative performance improvement, its direct application to drone racing faces challenges like real-time compatibility or the trade-off between time-optimal and safe traversal. In this paper, we enhance LMPC with three key innovations: (1) an adaptive cost function that dynamically weights time-optimal tracking against centerline adherence, (2) a shifted local safe set to prevent excessive shortcutting and enable more robust iterative updates, and (3) a Cartesian-based formulation that accommodates safety constraints without the singularities or integration errors associated with Frenet-frame transformations. Results from extensive simulation and real-world experiments demonstrate that our improved algorithm can optimize initial trajectories generated by a wide range of controllers with varying levels of tuning for a maximum improvement in lap time by 60.85%. Even applied to the most aggressively tuned state-of-the-art model-based controller, MPCC++, on a real drone, a 6.05% improvement is still achieved. Overall, the proposed method pushes the drone toward faster traversal and avoids collisions in simulation and real-world experiments, making it a practical solution to improve the peak performance of drone racing.