Empirical evaluation of a Q-Learning Algorithm for Model-free Autonomous Soaring

TL;DR

This paper presents a real-time, model-free Q-learning algorithm for autonomous glider soaring, demonstrating improved endurance by adapting to atmospheric conditions without relying on detailed models.

Contribution

It introduces a Q-learning based control method for autonomous soaring that is online, data-driven, and computationally efficient, suitable for real-time deployment.

Findings

Q-learning effectively controls the glider in non-stationary conditions

The approach enhances mission endurance by exploiting thermal updrafts

The method operates with low computational requirements

Abstract

Autonomous unpowered flight is a challenge for control and guidance systems: all the energy the aircraft might use during flight has to be harvested directly from the atmosphere. We investigate the design of an algorithm that optimizes the closed-loop control of a glider's bank and sideslip angles, while flying in the lower convective layer of the atmosphere in order to increase its mission endurance. Using a Reinforcement Learning approach, we demonstrate the possibility for real-time adaptation of the glider's behaviour to the time-varying and noisy conditions associated with thermal soaring flight. Our approach is online, data-based and model-free, hence avoids the pitfalls of aerological and aircraft modelling and allow us to deal with uncertainties and non-stationarity. Additionally, we put a particular emphasis on keeping low computational requirements in order to make on-board execution feasible. This article presents the stochastic, time-dependent aerological model used for simulation, together with a standard aircraft model. Then we introduce an adaptation of a Q-learning algorithm and demonstrate its ability to control the aircraft and improve its endurance by exploiting updrafts in non-stationary scenarios.