Learn-to-Fly (L2F) is a new framework that aims to replace the traditional iterative development paradigm for aerial vehicles with a combination of real-time aerodynamic modeling, guidance, and learning control. To ensure safe learning of the vehicle dynamics on the fly, this paper presents an adaptive control ()-based scheme, which actively estimates and compensates for the discrepancy between the intermediately learned dynamics and the actual dynamics. First, to incorporate the periodic update of the learned model within the L2F framework, this paper extends the architecture to handle a switched reference system subject to unknown time-varying parameters and disturbances. The paper also includes analysis of both transient and steady-state performance of the architecture in the presence of nonzero initialization error for the state predictor. Second, the paper presents how the proposed scheme is integrated into the L2F framework, including its interaction with the baseline controller and the real-time modeling module. Finally, flight tests on an unmanned aerial vehicle validate the efficacy of the proposed control and learning scheme.
Adaptive Control with Switched Reference Models: Application to Learn-to-Fly
Journal of Guidance, Control, and Dynamics ; 45 , 12 ; 2229-2242
2022-08-12
14 pages
Article (Journal)
Electronic Resource
English
Adaptive Control for Systems with Slow Reference Models
AIAA | 2010
|Adaptive Control for Systems with Slow Reference Models
British Library Conference Proceedings | 2010
|Adaptive control of flexible spacecraft using two reference models
British Library Conference Proceedings | 1996
|