Robust, High-Rate Trajectory Tracking on Insect-Scale Soft-Actuated Aerial Robots with Deep-Learned Tube MPC

TL;DR

This paper introduces a computationally efficient, robust trajectory tracking method for insect-scale MAVs using a neural network policy trained to imitate a robust tube MPC, enabling high accuracy and disturbance robustness.

Contribution

The work presents a neural network-based control strategy that replicates a robust tube MPC for small MAVs, combining robustness with low computational cost.

Findings

Position RMSE below 1.8 cm in challenging maneuvers

60% reduction in maximum position error compared to previous methods

Demonstrated robustness to large external disturbances

Abstract

Accurate and agile trajectory tracking in sub-gram Micro Aerial Vehicles (MAVs) is challenging, as the small scale of the robot induces large model uncertainties, demanding robust feedback controllers, while the fast dynamics and computational constraints prevent the deployment of computationally expensive strategies. In this work, we present an approach for agile and computationally efficient trajectory tracking on the MIT SoftFly, a sub-gram MAV (0.7 grams). Our strategy employs a cascaded control scheme, where an adaptive attitude controller is combined with a neural network policy trained to imitate a trajectory tracking robust tube model predictive controller (RTMPC). The neural network policy is obtained using our recent work, which enables the policy to preserve the robustness of RTMPC, but at a fraction of its computational cost. We experimentally evaluate our approach, achieving position Root Mean Square Errors lower than 1.8 cm even in the more challenging maneuvers, obtaining a 60% reduction in maximum position error compared to our previous work, and demonstrating robustness to large external disturbances