Simultaneous learning of state-to-state minimum-time planning and control

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F25%3A00387208" target="_blank" >RIV/68407700:21230/25:00387208 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.5220/0013716800003982" target="_blank" >https://doi.org/10.5220/0013716800003982</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.5220/0013716800003982" target="_blank" >10.5220/0013716800003982</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Simultaneous learning of state-to-state minimum-time planning and control

Popis výsledku v původním jazyce

This paper tackles the challenge of learning a generalizable minimum-time flight policy for UAVs, capable of navigating between arbitrary start and goal states while balancing agile flight and stable hovering. Traditional approaches, particularly in autonomous drone racing, achieve impressive speeds and agility but are constrained to predefined track layouts, limiting real-world applicability. To address this, we propose a reinforcement learning-based framework that simultaneously learns state-to-state minimum-time planning and control and generalizes to arbitrary state-to-state flights. Our approach leverages Point Mass Model (PMM) trajectories as proxy rewards to approximate the true optimal flight objective and employs curriculum learning to scale the training process efficiently and to achieve generalization. We validate our method through simulation experiments, comparing it against Nonlinear Model Predictive Control (NMPC) tracking PMM-generated trajectories and conducting abla tion studies to assess the impact of curriculum learning. Finally, real-world experiments confirm the robustness of our learned policy in outdoor environments, demonstrating its ability to generalize and operate on a small ARM-based single-board computer.

Název v anglickém jazyce

Simultaneous learning of state-to-state minimum-time planning and control

Popis výsledku anglicky

This paper tackles the challenge of learning a generalizable minimum-time flight policy for UAVs, capable of navigating between arbitrary start and goal states while balancing agile flight and stable hovering. Traditional approaches, particularly in autonomous drone racing, achieve impressive speeds and agility but are constrained to predefined track layouts, limiting real-world applicability. To address this, we propose a reinforcement learning-based framework that simultaneously learns state-to-state minimum-time planning and control and generalizes to arbitrary state-to-state flights. Our approach leverages Point Mass Model (PMM) trajectories as proxy rewards to approximate the true optimal flight objective and employs curriculum learning to scale the training process efficiently and to achieve generalization. We validate our method through simulation experiments, comparing it against Nonlinear Model Predictive Control (NMPC) tracking PMM-generated trajectories and conducting abla tion studies to assess the impact of curriculum learning. Finally, real-world experiments confirm the robustness of our learned policy in outdoor environments, demonstrating its ability to generalize and operate on a small ARM-based single-board computer.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20205 - Automation and control systems

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

22nd International Conference on Informatics in Control, Automation and Robotics - Volume 2

ISBN

978-989-758-770-2

ISSN

2184-2809

e-ISSN

—

Počet stran výsledku

9

Strana od-do

283-291

Název nakladatele

SciTePress - Science and Technology Publications

Místo vydání

Porto

Místo konání akce

Marbella

Datum konání akce

20. 10. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—