A Machine Learning Enhanced Algorithm for the Optimal Landing Problem

Yaohua Zang, Jihao Long, Xuanxi Zhang, Wei Hu, Weinan E, Jiequn Han
Proceedings of Mathematical and Scientific Machine Learning, PMLR 190:319-334, 2022.

Abstract

We propose a machine learning enhanced algorithm for solving the optimal landing problem. Using Pontryagin’s minimum principle, we derive a two-point boundary value problem for the landing problem. The proposed algorithm uses deep learning to predict the optimal landing time and a space-marching technique to provide good initial guesses for the boundary value problem solver. The performance of the proposed method is studied using the quadrotor example, a reasonably high dimensional and strongly nonlinear system. Drastic improvement in reliability and efficiency is observed.

Cite this Paper

BibTeX
@InProceedings{pmlr-v190-zang22a, title = {A Machine Learning Enhanced Algorithm for the Optimal Landing Problem}, author = {Zang, Yaohua and Long, Jihao and Zhang, Xuanxi and Hu, Wei and E, Weinan and Han, Jiequn}, booktitle = {Proceedings of Mathematical and Scientific Machine Learning}, pages = {319--334}, year = {2022}, editor = {Dong, Bin and Li, Qianxiao and Wang, Lei and Xu, Zhi-Qin John}, volume = {190}, series = {Proceedings of Machine Learning Research}, month = {15--17 Aug}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v190/zang22a/zang22a.pdf}, url = {https://proceedings.mlr.press/v190/zang22a.html}, abstract = {We propose a machine learning enhanced algorithm for solving the optimal landing problem. Using Pontryagin’s minimum principle, we derive a two-point boundary value problem for the landing problem. The proposed algorithm uses deep learning to predict the optimal landing time and a space-marching technique to provide good initial guesses for the boundary value problem solver. The performance of the proposed method is studied using the quadrotor example, a reasonably high dimensional and strongly nonlinear system. Drastic improvement in reliability and efficiency is observed.} }
Endnote
%0 Conference Paper %T A Machine Learning Enhanced Algorithm for the Optimal Landing Problem %A Yaohua Zang %A Jihao Long %A Xuanxi Zhang %A Wei Hu %A Weinan E %A Jiequn Han %B Proceedings of Mathematical and Scientific Machine Learning %C Proceedings of Machine Learning Research %D 2022 %E Bin Dong %E Qianxiao Li %E Lei Wang %E Zhi-Qin John Xu %F pmlr-v190-zang22a %I PMLR %P 319--334 %U https://proceedings.mlr.press/v190/zang22a.html %V 190 %X We propose a machine learning enhanced algorithm for solving the optimal landing problem. Using Pontryagin’s minimum principle, we derive a two-point boundary value problem for the landing problem. The proposed algorithm uses deep learning to predict the optimal landing time and a space-marching technique to provide good initial guesses for the boundary value problem solver. The performance of the proposed method is studied using the quadrotor example, a reasonably high dimensional and strongly nonlinear system. Drastic improvement in reliability and efficiency is observed.
APA
Zang, Y., Long, J., Zhang, X., Hu, W., E, W. & Han, J.. (2022). A Machine Learning Enhanced Algorithm for the Optimal Landing Problem. Proceedings of Mathematical and Scientific Machine Learning, in Proceedings of Machine Learning Research 190:319-334 Available from https://proceedings.mlr.press/v190/zang22a.html.

Related Material