TACO: Trajectory-Aware Controller Optimization for Quadrotors

TL;DR

TACO is a real-time, trajectory-aware controller optimization framework for quadrotors that adapts control parameters online to improve tracking accuracy and dynamic feasibility across diverse trajectories.

Contribution

The paper introduces TACO, a novel online optimization method that adapts quadrotor controller parameters based on trajectory predictions, enabling faster and more effective control.

Findings

TACO outperforms static tuning in trajectory tracking accuracy.

TACO operates significantly faster than black-box optimization methods.

Trajectory adaptation with TACO reduces tracking error.

Abstract

Controller performance in quadrotor trajectory tracking depends heavily on parameter tuning, yet standard approaches often rely on fixed, manually tuned parameters that sacrifice task-specific performance. We present Trajectory-Aware Controller Optimization (TACO), a framework that adapts controller parameters online based on the upcoming reference trajectory and current quadrotor state. TACO employs a learned predictive model and a lightweight optimization scheme to optimize controller gains in real time with respect to a broad class of trajectories, and can also be used to adapt trajectories to improve dynamic feasibility while respecting smoothness constraints. To enable large-scale training, we also introduce a parallelized quadrotor simulator supporting fast data collection on diverse trajectories. Experiments on a variety of trajectory types show that TACO outperforms conventional, static parameter tuning while operating orders of magnitude faster than black-box optimization baselines, enabling practical real-time deployment on a physical quadrotor. Furthermore, we show that adapting trajectories using TACO significantly reduces the tracking error obtained by the quadrotor.