KNODE-MPC: A Knowledge-Based Data-Driven Predictive Control Framework for Aerial Robots

In this letter, we consider the problem of deriving and incorporating accurate dynamic models for model predictive control (MPC) with an application to quadrotor control. MPC relies on precise dynamic models to achieve the desired closed-loop performance. However, the presence of uncertainties in co...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE robotics and automation letters Ročník 7; číslo 2; s. 2819 - 2826
Hlavní autoři: Chee, Kong Yao, Jiahao, Tom Z., Hsieh, M. Ani
Médium: Journal Article
Jazyk:angličtina
Vydáno: Piscataway IEEE 01.04.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Aerodynamics
Complex systems
Computational modeling
Data models
Differential equations
Dynamic models
First principles
Gaussian process
Machine learning for robot control
Mathematical models
model learning for control
model predictive control
Neural networks
Ordinary differential equations
Predictive control
Predictive models
Robot control
System dynamics
Uncertainty
ISSN:2377-3766, 2377-3766
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In this letter, we consider the problem of deriving and incorporating accurate dynamic models for model predictive control (MPC) with an application to quadrotor control. MPC relies on precise dynamic models to achieve the desired closed-loop performance. However, the presence of uncertainties in complex systems and the environments they operate in poses a challenge in obtaining sufficiently accurate representations of the system dynamics. In this letter, we make use of a deep learning tool, knowledge-based neural ordinary differential equations (KNODE), to augment a model obtained from first principles. The resulting hybrid model encompasses both a nominal first-principle model and a neural network learnt from simulated or real-world experimental data. Using a quadrotor, we benchmark our hybrid model against a state-of-the-art Gaussian Process (GP) model and show that the hybrid model provides more accurate predictions of the quadrotor dynamics and is able to generalize beyond the training data. To improve closed-loop performance, the hybrid model is integrated into a novel MPC framework, known as KNODE-MPC. Results show that the integrated framework achieves 60.2% improvement in simulations and more than 21% in physical experiments, in terms of trajectory tracking performance.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2377-3766
2377-3766
DOI:10.1109/LRA.2022.3144787