TR2019-149
Robust Data-Driven Neuro-Adaptive Observers With Lipschitz Activation Functions
-
- "Robust Data-Driven Neuro-Adaptive Observers With Lipschitz Activation Functions", IEEE Conference on Decision and Control (CDC), DOI: 10.1109/CDC40024.2019.9029394, December 2019, pp. 2862-2867.BibTeX TR2019-149 PDF
- @inproceedings{Chakrabarty2019dec,
- author = {Chakrabarty, Ankush and Zemouche, Ali and Rajamani, Rajesh and Benosman, Mouhacine},
- title = {Robust Data-Driven Neuro-Adaptive Observers With Lipschitz Activation Functions},
- booktitle = {IEEE Conference on Decision and Control (CDC)},
- year = 2019,
- pages = {2862--2867},
- month = dec,
- doi = {10.1109/CDC40024.2019.9029394},
- url = {https://www.merl.com/publications/TR2019-149}
- }
,
- "Robust Data-Driven Neuro-Adaptive Observers With Lipschitz Activation Functions", IEEE Conference on Decision and Control (CDC), DOI: 10.1109/CDC40024.2019.9029394, December 2019, pp. 2862-2867.
-
MERL Contacts:
-
Research Areas:
Abstract:
While the use of neural networks for learning has gained traction in control and system identification problems, their use in data-driven estimator design is not as prevalent. Prior art on neuro-adaptive observers limit the type of activation functions to radial basis function networks and provide conservative bounds on the resulting observer estimation error because they leverage boundedness of the activation functions rather than exploiting their underlying structure. This paper proposes the use of Lipschitz activation functions in the neuroadaptive observer: utilizing the Lipschitz constants of these activations simplifies the data-driven observer design procedure via recently discovered LMI conditions. Furthermore, in spite of measurement noise and approximation error, pre-computable robust stability guarantees are provided on the resulting state estimation error.
Related News & Events
-
NEWS MERL researchers presented 8 papers at Conference on Decision and Control (CDC) Date: December 11, 2019 - December 13, 2019
Where: Nice, France
MERL Contacts: Mouhacine Benosman; Scott A. Bortoff; Ankush Chakrabarty; Stefano Di Cairano
Research Areas: Control, Machine Learning, OptimizationBrief- At the Conference on Decision and Control, MERL presented 8 papers on subjects including estimation for thermal-fluid models and transportation networks, analysis of HVAC systems, extremum seeking for multi-agent systems, reinforcement learning for vehicle platoons, and learning with applications to autonomous vehicles.