Reinforcement learning with formal performance metrics for quadcopter attitude control under non-nominal contexts

Nicola Bernini , Mikhail Bessa , Rémi Delmas , Arthur Gold , Eric Goubault (1) , Romain Pennec , Sylvie Putot (1) , François Sillion

1 LIX - Laboratoire d'informatique de l'École polytechnique [Palaiseau]

We explore the reinforcement learning approach to designing controllers by extensively discussing the case of a quadcopter attitude controller. We provide all details allowing to reproduce our approach, starting with a model of the dynamics of a crazyflie 2.0 under various nominal and non-nominal conditions, including partial motor failures and wind gusts. We develop a robust form of a signal temporal logic to quantitatively evaluate the vehicle's behavior and measure the performance of controllers. The paper thoroughly describes the choices in training algorithms, neural net architecture, hyperparameters, observation space in view of the different performance metrics we have introduced. We discuss the robustness of the obtained controllers, both to partial loss of power for one rotor and to wind gusts and finish by drawing conclusions on practical controller design by reinforcement learning.

Mots clés: Control Systems [C3210P] Aerospace Control [C3360L] Reinforcement learning [C6264] Formal Logic [C4210] Reinforcement learning Control Quadcopter dynamics Performance metrics Temporal logics; Reinforcement learning control quadcopter dynamics performance metrics temporal logics; Reinforcement learning; control; quadcopter dynamics; performance metrics; temporal logics

Domaines: Informatique [cs]

Nicola Bernini, Mikhail Bessa, Rémi Delmas, Arthur Gold, Eric Goubault, et al.. Reinforcement learning with formal performance metrics for quadcopter attitude control under non-nominal contexts. Engineering Applications of Artificial Intelligence, 2023, 127, ⟨10.1016/j.engappai.2023.107090⟩. ⟨hal-04336289⟩