TR2021-126
Learning Disagreement Regions with Deep Neural Networks to Reduce Practical Complexity of Mixed-Integer MPC
-
- "Learning Disagreement Regions with Deep Neural Networks to Reduce Practical Complexity of Mixed-Integer MPC", IEEE International Conference on Systems, Man, and Cybernetics, DOI: 10.1109/SMC52423.2021.9659186, October 2021, pp. 3238-3244.BibTeX TR2021-126 PDF Video
- @inproceedings{Chakrabarty2021oct,
- author = {Chakrabarty, Ankush and Quirynen, Rien and Romeres, Diego and Di Cairano, Stefano},
- title = {Learning Disagreement Regions with Deep Neural Networks to Reduce Practical Complexity of Mixed-Integer MPC},
- booktitle = {IEEE International Conference on Systems, Man, and Cybernetics},
- year = 2021,
- pages = {3238--3244},
- month = oct,
- doi = {10.1109/SMC52423.2021.9659186},
- url = {https://www.merl.com/publications/TR2021-126}
- }
,
- "Learning Disagreement Regions with Deep Neural Networks to Reduce Practical Complexity of Mixed-Integer MPC", IEEE International Conference on Systems, Man, and Cybernetics, DOI: 10.1109/SMC52423.2021.9659186, October 2021, pp. 3238-3244.
-
MERL Contacts:
-
Research Areas:
Abstract:
Efficiently computing solutions to mixed-integer optimization-based control problems, such as in model predictive control (MPC) of hybrid systems, is extremely challenging due to the exponential worst-case complexity. The practical time-complexity of computing good control actions can be reduced by using a combination of two solvers: a strong solver that generates optimal or near-optimal closed-loop solutions with a large number of iterations, and a weak solver that converges quickly to suboptimal closed-loop solutions. In this paper, we propose the use of deep neural networks to learn sub-regions of the admissible state-space where replacing the strong solver with the weak solver maintains constraint satisfaction properties and does not result in a significant deterioration of performance. We illustrate the practical time-complexity reduction of the proposed solver selection mechanism on a station-keeping problem for a satellite.