A Learning-based Quadcopter Controller with Extreme Adaptation

TL;DR

This paper presents a learning-based quadcopter controller that adaptively manages significant variations in vehicle parameters using imitation and reinforcement learning, eliminating the need for precise modeling.

Contribution

The novel controller estimates system parameters from sensor data, enabling rapid adaptation to diverse quadcopter dynamics without manual tuning.

Findings

Generalizes to unseen quadcopter parameters with up to 16x broader range than training

Successfully deployed on real quadcopters with 3.7x mass variation and 100x propeller constant variation

Demonstrates rapid adaptation to disturbances like payloads and motor failures

Abstract

This paper introduces a learning-based low-level controller for quadcopters, which adaptively controls quadcopters with significant variations in mass, size, and actuator capabilities. Our approach leverages a combination of imitation learning and reinforcement learning, creating a fast-adapting and general control framework for quadcopters that eliminates the need for precise model estimation or manual tuning. The controller estimates a latent representation of the vehicle's system parameters from sensor-action history, enabling it to adapt swiftly to diverse dynamics. Extensive evaluations in simulation demonstrate the controller's ability to generalize to unseen quadcopter parameters, with an adaptation range up to 16 times broader than the training set. In real-world tests, the controller is successfully deployed on quadcopters with mass differences of 3.7 times and propeller constants varying by more than 100 times, while also showing rapid adaptation to disturbances such as off-center payloads and motor failures. These results highlight the potential of our controller in extreme adaptation to simplify the design process and enhance the reliability of autonomous drone operations in unpredictable environments. The video and code are at: https://github.com/muellerlab/xadapt_ctrl