Single-Shot Learning of Multirotor Controller Gains: A Data-Driven Approach with Experimental Validation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Mirtaba, Mohammad, Oveissi, Parham, Salaza, Juan Augusto Paredes, Goel, Ankit
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908397006225408
author Mirtaba, Mohammad
Oveissi, Parham
Salaza, Juan Augusto Paredes
Goel, Ankit
author_facet Mirtaba, Mohammad
Oveissi, Parham
Salaza, Juan Augusto Paredes
Goel, Ankit
contents This paper demonstrates the single-shot learning capabilities of retrospective cost optimization based data-driven control applied to learning multirotor controller gains for trajectory tracking. In particular, the proposed control approach is first used within a simple multirotor simulation environment to learn appropriate multirotor controller gains to follow a trajectory. Then, the gains resulting from a single simulation run are used in a more complex multirotor simulation environment based on Simulink for performance verification. Finally, the resulting gains are implemented in a physical quadrotor and the results for waypoint and trajectory tracking are reported in this paper. The proposed control approach is the continuous-time version of the widely used discrete-time retrospective control adaptive control algorithm, which is simpler to implement within continuous-time simulation environments and whose performance does not depend on appropriate sampling time choice.
format Preprint
id arxiv_https___arxiv_org_abs_2410_03815
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Single-Shot Learning of Multirotor Controller Gains: A Data-Driven Approach with Experimental Validation
Mirtaba, Mohammad
Oveissi, Parham
Salaza, Juan Augusto Paredes
Goel, Ankit
Systems and Control
This paper demonstrates the single-shot learning capabilities of retrospective cost optimization based data-driven control applied to learning multirotor controller gains for trajectory tracking. In particular, the proposed control approach is first used within a simple multirotor simulation environment to learn appropriate multirotor controller gains to follow a trajectory. Then, the gains resulting from a single simulation run are used in a more complex multirotor simulation environment based on Simulink for performance verification. Finally, the resulting gains are implemented in a physical quadrotor and the results for waypoint and trajectory tracking are reported in this paper. The proposed control approach is the continuous-time version of the widely used discrete-time retrospective control adaptive control algorithm, which is simpler to implement within continuous-time simulation environments and whose performance does not depend on appropriate sampling time choice.
title Single-Shot Learning of Multirotor Controller Gains: A Data-Driven Approach with Experimental Validation
topic Systems and Control
url https://arxiv.org/abs/2410.03815