Latent Linear Quadratic Regulator for Robotic Control Tasks

Yuan Zhang, Shaohui Yang, Toshiyuki Ohtsuka, Colin Jones, Joschka Boedecker
Proceedings of The 8th Annual Learning for Dynamics and Control Conference, PMLR 331:1620-1637, 2026.

Abstract

Model predictive control (MPC) offers high-performance control but remains computationally expensive for nonlinear dynamics, hindering its real-time deployment in robotic tasks. Inspired by the Koopman operator, we propose the $\textbf{la}$tent $\textbf{l}$inear $\textbf{q}$uadratic $\textbf{r}$egulator (LaLQR) framework, which learns an alternative latent linear-quadratic structure enabling efficient LQR-based control for nonlinear systems. LaLQR enforces the fixed Brunovsky canonical form on the latent linear dynamics to ensure controllability and numerical stability, while jointly learning a nonlinear embedding and cost function under latent state and cost prediction objectives. Experiments on diverse MuJoCo simulated robotic tasks show that LaLQR achieves comparable control quality to expensive gradient-based optimization methods while offering superior computational efficiency and superior generalization over learning-based baselines.

Cite this Paper

BibTeX
@InProceedings{pmlr-v331-zhang26b, title = {Latent Linear Quadratic Regulator for Robotic Control Tasks}, author = {Zhang, Yuan and Yang, Shaohui and Ohtsuka, Toshiyuki and Jones, Colin and Boedecker, Joschka}, booktitle = {Proceedings of The 8th Annual Learning for Dynamics and Control Conference}, pages = {1620--1637}, year = {2026}, editor = {Sukhatme, Gaurav and Lindemann, Lars and Tu, Stephen and Wierman, Adam and Atanasov, Nikolay}, volume = {331}, series = {Proceedings of Machine Learning Research}, month = {17--19 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v331/main/assets/zhang26b/zhang26b.pdf}, url = {https://proceedings.mlr.press/v331/zhang26b.html}, abstract = {Model predictive control (MPC) offers high-performance control but remains computationally expensive for nonlinear dynamics, hindering its real-time deployment in robotic tasks. Inspired by the Koopman operator, we propose the $\textbf{la}$tent $\textbf{l}$inear $\textbf{q}$uadratic $\textbf{r}$egulator (LaLQR) framework, which learns an alternative latent linear-quadratic structure enabling efficient LQR-based control for nonlinear systems. LaLQR enforces the fixed Brunovsky canonical form on the latent linear dynamics to ensure controllability and numerical stability, while jointly learning a nonlinear embedding and cost function under latent state and cost prediction objectives. Experiments on diverse MuJoCo simulated robotic tasks show that LaLQR achieves comparable control quality to expensive gradient-based optimization methods while offering superior computational efficiency and superior generalization over learning-based baselines.} }
Endnote
%0 Conference Paper %T Latent Linear Quadratic Regulator for Robotic Control Tasks %A Yuan Zhang %A Shaohui Yang %A Toshiyuki Ohtsuka %A Colin Jones %A Joschka Boedecker %B Proceedings of The 8th Annual Learning for Dynamics and Control Conference %C Proceedings of Machine Learning Research %D 2026 %E Gaurav Sukhatme %E Lars Lindemann %E Stephen Tu %E Adam Wierman %E Nikolay Atanasov %F pmlr-v331-zhang26b %I PMLR %P 1620--1637 %U https://proceedings.mlr.press/v331/zhang26b.html %V 331 %X Model predictive control (MPC) offers high-performance control but remains computationally expensive for nonlinear dynamics, hindering its real-time deployment in robotic tasks. Inspired by the Koopman operator, we propose the $\textbf{la}$tent $\textbf{l}$inear $\textbf{q}$uadratic $\textbf{r}$egulator (LaLQR) framework, which learns an alternative latent linear-quadratic structure enabling efficient LQR-based control for nonlinear systems. LaLQR enforces the fixed Brunovsky canonical form on the latent linear dynamics to ensure controllability and numerical stability, while jointly learning a nonlinear embedding and cost function under latent state and cost prediction objectives. Experiments on diverse MuJoCo simulated robotic tasks show that LaLQR achieves comparable control quality to expensive gradient-based optimization methods while offering superior computational efficiency and superior generalization over learning-based baselines.
APA
Zhang, Y., Yang, S., Ohtsuka, T., Jones, C. & Boedecker, J.. (2026). Latent Linear Quadratic Regulator for Robotic Control Tasks. Proceedings of The 8th Annual Learning for Dynamics and Control Conference, in Proceedings of Machine Learning Research 331:1620-1637 Available from https://proceedings.mlr.press/v331/zhang26b.html.

Related Material