Learning for Control

Learning for Control: An Inverse Optimization Approach

Akhtar, Syed Adnan (Student TU Delft)
Sharifi K., Arman (TU Delft Team Tamas Keviczky)
Mohajerin Esfahani, P. (TU Delft Team Tamas Keviczky)

2022

We present a learning method to learn the mapping from an input space to an action space, which is particularly suitable when the action is an optimal decision with respect to a certain unknown cost function. We use an inverse optimization approach to retrieve the cost function by introducing a new loss function and a new hypothesis class of mappings. A tractable convex reformulation of the learning problem is also presented. The method is effective for learning input-action mapping in continuous input-action space with input-output constraints, typically present in control systems. The learning approach can be effectively transformed to learn a Model Predictive Control (MPC) behaviour and a case study to mimic an MPC is presented, which is a rather computationally heavy control strategy. Simulation and experimental results show the effectiveness of the proposed approach.

Aerospace electronics
convex reformulation.
Cost function
inverse optimization
Learning-based control
Least mean squares methods
Linear programming
supervised learning
Supervised learning
Symmetric matrices
Training

http://resolver.tudelft.nl/uuid:dc9403a0-f62b-41b5-81af-daec5d5e807e

https://doi.org/10.1109/LCSYS.2021.3050305

2021-07-27

2475-1456

IEEE Control Systems Letters, 6, 187-192

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Institutional Repository

journal article

© 2022 Syed Adnan Akhtar, Arman Sharifi K., P. Mohajerin Esfahani