Bridging the Model-Reality Gap With Lipschitz Network Adaptation

As robots venture into the real world, they are subject to unmodeled dynamics and disturbances. Traditional model-based control approaches have been proven successful in relatively static and known operating environments. However, when an accurate model of the robot is not available, model-based des...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE robotics and automation letters Ročník 7; číslo 1; s. 642 - 649
Hlavní autoři: Zhou, Siqi, Pereida, Karime, Zhao, Wenda, Schoellig, Angela P.
Médium: Journal Article
Jazyk:angličtina
Vydáno: Piscataway IEEE 01.01.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Adaptation
Adaptation models
Aerodynamics
Computational modeling
Control systems design
deep learning methods
Dynamic stability
Dynamical systems
Hovering
Lipschitz condition
Machine learning for robot control
Model reference adaptive control
Neural networks
Nonlinear control
Nonlinear dynamical systems
Nonlinear dynamics
Nonlinear systems
Pendulums
Predictive models
Robots
robust/adaptive control
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:As robots venture into the real world, they are subject to unmodeled dynamics and disturbances. Traditional model-based control approaches have been proven successful in relatively static and known operating environments. However, when an accurate model of the robot is not available, model-based design can lead to suboptimal and even unsafe behaviour. In this work, we propose a method that bridges the model-reality gap and enables the application of model-based approaches even if dynamic uncertainties are present. In particular, we present a learning-based model reference adaptation approach that makes a robot system, with possibly uncertain dynamics, behave as a predefined reference model. In turn, the reference model can be used for model-based controller design. In contrast to typical model reference adaptation control approaches, we leverage the representative power of neural networks to capture highly nonlinear dynamics uncertainties and guarantee stability by encoding a certifying Lipschitz condition in the architectural design of a special type of neural network called the Lipschitz network. Our approach applies to a general class of nonlinear control-affine systems even when our prior knowledge about the true robot system is limited. We demonstrate our approach in flying inverted pendulum experiments, where an off-the-shelf quadrotor is challenged to balance an inverted pendulum while hovering or tracking circular trajectories.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2377-3766
2377-3766
DOI:10.1109/LRA.2021.3131698