Learning in MPC Research

This set of of papers shows repetitively learning cost-to go and safe invariant sets for systems with known models.

Publications:

• U. Rosolia and F. Borrelli, "Learning Model Predictive Control for Iterative Tasks. A Data-Driven Control Framework," in IEEE Transactions on Automatic Control, vol. 63, no. 7, pp. 1883-1896, July 2018.

• U. Rosolia and F. Borrelli. "Learning model predictive control for iterative tasks: A computationally efficient approach for linear system." IFAC-PapersOnLine 50.1 (2017): 3142-3147. 

• U. Rosolia, X. Zhang and F. Borrelli, "Simple Policy Evaluation for Data-Rich Iterative Tasks," 2019 American Control Conference (ACC), Philadelphia, PA, USA, 2019, pp. 2855-2860. 

• H. Xue, E. Zhu, J. M. Dolan, and F. Borrelli, "Learning Model Predictive Control with Error Dynamics Regression for Autonomous Racing", 2024 IEEE International Conference on Robotics and Automation (ICRA), Yokohama, Japan, May 2024.

GitHub repositories:

• LMPC GitHub 

• LMPC Racing

• LMPC ROS2

Video of experimental tests

• LMPC on the Berkeley Autonomous Race Car (BARC) Platform 

• LMPC for Autonomous Racing on Hyundai Genesis (Track Test) 

• LMPC on the Indy Dallara Light (Track Test)

This set of of papers shows a computationally efficient extension of LMPC for nonlinear systems with known models.

Publications:

• U. Rosolia and F. Borrelli, "Learning How to Autonomously Race a Car: A Predictive Control Approach," in IEEE Transactions on Control Systems Technology.

• Rosolia, U., & Borrelli, F. (2019). Minimum Time Learning Model Predictive Control. ArXiv, abs/1911.09239. 

• Nair, S.H., Rosolia, U., & Borrelli, F. (2020). Output-Lifted Learning Model Predictive Control for Flat Systems. ArXiv, abs/2004.05173. 

This set of of papers shows extension of LMPC to systems under stochastic, state-dependent model disturbances. 

Publications:

• U. Rosolia, X. Zhang, and F. Borrelli, (2019). Robust Learning Model Predictive Control for Linear Systems. ArXiv, abs/1911.09234.

• U. Rosolia, X. Zhang and F. Borrelli, "Robust learning model predictive control for iterative tasks: Learning from experience," 2017 IEEE 56th Annual Conference on Decision and Control (CDC), Melbourne, VIC, 2017, pp. 1157-1162. 

• U. Rosolia and F. Borrelli, "Sample-Based Learning Model Predictive Control for Linear Uncertain Systems," 2019 IEEE 58th Conference on Decision and Control (CDC), Nice, France, 2019, pp. 2702-2707. 

• U. Rosolia, X. Zhang and F. Borrelli, "A Stochastic MPC Approach with Application to Iterative Learning," 2018 IEEE Conference on Decision and Control (CDC), Miami Beach, FL, 2018, pp. 5152-5157. 

• S. H. Nair and F. Borrelli, (2023). Robust Output-Lifted Learning Model Predictive Control. arXiv preprint arXiv:2303.12127. 

This set of of papers shows learning of uncertain model parameters in robust/stochastic MPC. Disturbance supports are known

Publications:

• M. Bujarbaruah, X. Zhang and F. Borrelli, "Adaptive MPC with Chance Constraints for FIR Systems," 2018 Annual American Control Conference (ACC), Milwaukee, WI, 2018, pp. 2312-2317.

• M. Bujarbaruah, X. Zhang, U. Rosolia and F. Borrelli, "Adaptive MPC for Iterative Tasks," 2018 IEEE Conference on Decision and Control (CDC), Miami Beach, FL, 2018, pp. 6322-6327. 

• Bujarbaruah, M., Zhang, X., Tanasković, M., & Borrelli, F. (2019). Adaptive MPC under Time Varying Uncertainty: Robust and Stochastic. ArXiv, abs/1909.13473. 

• Bujarbaruah, M., Nair, S.H., & Borrelli, F. (2019). A Semi-Definite Programming Approach to Robust Adaptive MPC under State Dependent Uncertainty. ArXiv, abs/1910.04378. 

• Nair, S.H., Bujarbaruah, M., & Borrelli, F. (2019). Modeling of Dynamical Systems via Successive Graph Approximations. ArXiv, abs/1910.03719. 

• Bujarbaruah, M., & Vallon, C. (2019). Exploiting Model Sparsity in Adaptive MPC: A Compressed Sensing Viewpoint. ArXiv, abs/1912.04408. 

• Papadimitriou, D.G., Rosolia, U., & Borrelli, F. (2020). Control of Unknown Nonlinear Systems with Linear Time-Varying MPC. ArXiv, abs/2004.03041. 

• Bujarbaruah, M., Zhang, X., Tseng, H.E., & Borrelli, F. (2018). Adaptive MPC for Autonomous Lane Keeping. ArXiv, abs/1806.04335. 

This set of of papers shows learning of unknown disturbance supports with known confidence. Safety during learning is ensured with a guaranteed probability.

Publications:

• Bujarbaruah, M., Shetty, A., Poolla, K., & Borrelli, F. (2019). Learning Robustness with Bounded Failure: An Iterative MPC Approach. ArXiv, abs/1911.09910.

GitHub repositories:

• coming soon

Video of experimental tests

• Catching on Kendama

This set of of papers shows learning of unknown safety constraints. True constraint satisfaction is ensured with a guaranteed probability 

Publications:

• Bujarbaruah, M., Vallon, C. & Borrelli, F.(2020).Learning to Satisfy Unknown Constraints in Iterative MPC. ArXiv, abs/2006.05054.

This set of papers shows the development of data-driven control policies for solving tasks in unknown environments, while being able to guarantee constraint satisfaction before beginning the task.

Publications:

• Vallon, C., & Borrelli, F. (2019). Task decomposition for iterative learning model predictive control. ArXiv, abs/1903.07003.

• Vallon, C., & Borrelli, F. (2020). Task Decomposition for MPC: A Computationally Efficient Approach for Linear Time-Varying Systems. ArXiv, abs/2005.01673. 

• Vallon, C., & Borrelli, F. (2020). Data-Driven Hierarchical Predictive Learning in Unknown Environments. ArXiv, abs/2005.05948. 

• Shen, X., Zhu, E. L., Stürz, Y. R., & Borrelli, F. (2021, May). Collision avoidance in tightly-constrained environments without coordination: a hierarchical control approach. In 2021 IEEE International Conference on Robotics and Automation (ICRA) (pp. 2674-2680). IEEE.

GitHub repositories:

• TDMPC GitHub

• Strategy-Guided Control GitHub - MATLAB, Python & ROS

This set of of papers shows fast implementation of  MPC using neural networks with online suboptimality check.

Publications:

• X. Zhang, M. Bujarbaruah and F. Borrelli, "Safe and Near-Optimal Policy Learning for Model Predictive Control using Primal-Dual Neural Networks," 2019 American Control Conference (ACC), Philadelphia, PA, USA, 2019, pp. 354-359.

• Zhang, X., Bujarbaruah, M., & Borrelli, F. (2019). Near-Optimal Rapid MPC using Neural Networks: A Primal-Dual Policy Learning Framework. ArXiv, abs/1912.04744. 

• Russo, L., Nair, S. H., Glielmo, L., & Borrelli, F. (2023). Learning for Online Mixed-Integer Model Predictive Control with Parametric Optimality Certificates. arXiv preprint arXiv:2303.12152.

GitHub repositories:

• Primal-Dual Policy Learning

• LAMPOS