PRISM: Recurrent Neural Networks and Presolve Methods for Fast Mixed-integer Optimal Control

Abhishek Cauligi, Ankush Chakrabarty, Stefano Di Cairano, Rien Quirynen
Proceedings of The 4th Annual Learning for Dynamics and Control Conference, PMLR 168:34-46, 2022.

Abstract

While mixed-integer convex programs (MICPs) arise frequently in mixed-integer optimal control problems (MIOCPs), current state-of-the-art MICP solvers are often too slow for real-time applications, limiting the practicality of MICP-based controller design. Although supervised learning has been proposed to hasten the solution of MICPs via convex approximations, they are not designed to scale well to problems with >100 decision variables. In this paper, we present PRISM: Presolve and Recurrent network-based mixed-Integer Solution Method, to leverage deep recurrent neural network (RNN) architectures such as long short-term memory (LSTMs) networks, in conjunction with numerical optimization tools to enable scalable acceleration of MICPs arising in MIOCPs. Our key insight is to learn the underlying temporal structure of MIOCPs and to combine this with presolve routines employed in MICP solvers. We demonstrate how PRISM can lead to significant performance improvements, compared to branch-and-bound (B&B) methods and to existing supervised learning techniques, for stabilizing a cart-pole with contact dynamics, and a motion planning problem under obstacle avoidance constraints.

Cite this Paper

BibTeX
@InProceedings{pmlr-v168-cauligi22a, title = {PRISM: Recurrent Neural Networks and Presolve Methods for Fast Mixed-integer Optimal Control}, author = {Cauligi, Abhishek and Chakrabarty, Ankush and Cairano, Stefano Di and Quirynen, Rien}, booktitle = {Proceedings of The 4th Annual Learning for Dynamics and Control Conference}, pages = {34--46}, year = {2022}, editor = {Firoozi, Roya and Mehr, Negar and Yel, Esen and Antonova, Rika and Bohg, Jeannette and Schwager, Mac and Kochenderfer, Mykel}, volume = {168}, series = {Proceedings of Machine Learning Research}, month = {23--24 Jun}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v168/cauligi22a/cauligi22a.pdf}, url = {https://proceedings.mlr.press/v168/cauligi22a.html}, abstract = {While mixed-integer convex programs (MICPs) arise frequently in mixed-integer optimal control problems (MIOCPs), current state-of-the-art MICP solvers are often too slow for real-time applications, limiting the practicality of MICP-based controller design. Although supervised learning has been proposed to hasten the solution of MICPs via convex approximations, they are not designed to scale well to problems with >100 decision variables. In this paper, we present PRISM: Presolve and Recurrent network-based mixed-Integer Solution Method, to leverage deep recurrent neural network (RNN) architectures such as long short-term memory (LSTMs) networks, in conjunction with numerical optimization tools to enable scalable acceleration of MICPs arising in MIOCPs. Our key insight is to learn the underlying temporal structure of MIOCPs and to combine this with presolve routines employed in MICP solvers. We demonstrate how PRISM can lead to significant performance improvements, compared to branch-and-bound (B&B) methods and to existing supervised learning techniques, for stabilizing a cart-pole with contact dynamics, and a motion planning problem under obstacle avoidance constraints.} }
Endnote
%0 Conference Paper %T PRISM: Recurrent Neural Networks and Presolve Methods for Fast Mixed-integer Optimal Control %A Abhishek Cauligi %A Ankush Chakrabarty %A Stefano Di Cairano %A Rien Quirynen %B Proceedings of The 4th Annual Learning for Dynamics and Control Conference %C Proceedings of Machine Learning Research %D 2022 %E Roya Firoozi %E Negar Mehr %E Esen Yel %E Rika Antonova %E Jeannette Bohg %E Mac Schwager %E Mykel Kochenderfer %F pmlr-v168-cauligi22a %I PMLR %P 34--46 %U https://proceedings.mlr.press/v168/cauligi22a.html %V 168 %X While mixed-integer convex programs (MICPs) arise frequently in mixed-integer optimal control problems (MIOCPs), current state-of-the-art MICP solvers are often too slow for real-time applications, limiting the practicality of MICP-based controller design. Although supervised learning has been proposed to hasten the solution of MICPs via convex approximations, they are not designed to scale well to problems with >100 decision variables. In this paper, we present PRISM: Presolve and Recurrent network-based mixed-Integer Solution Method, to leverage deep recurrent neural network (RNN) architectures such as long short-term memory (LSTMs) networks, in conjunction with numerical optimization tools to enable scalable acceleration of MICPs arising in MIOCPs. Our key insight is to learn the underlying temporal structure of MIOCPs and to combine this with presolve routines employed in MICP solvers. We demonstrate how PRISM can lead to significant performance improvements, compared to branch-and-bound (B&B) methods and to existing supervised learning techniques, for stabilizing a cart-pole with contact dynamics, and a motion planning problem under obstacle avoidance constraints.
APA
Cauligi, A., Chakrabarty, A., Cairano, S.D. & Quirynen, R.. (2022). PRISM: Recurrent Neural Networks and Presolve Methods for Fast Mixed-integer Optimal Control. Proceedings of The 4th Annual Learning for Dynamics and Control Conference, in Proceedings of Machine Learning Research 168:34-46 Available from https://proceedings.mlr.press/v168/cauligi22a.html.

Related Material