Correct-by-Construction Controller Synthesis using Gaussian Process Transfer Learning

This project investigates a novel correct-by-construction controller synthesis scheme for these systems by embracing ideas from Gaussian processes and control Barrier functions. If successful, this could allow safety controllers developed for one type of autonomous vehicle to be transferred to another of a wholly new type – or for use in a new environment all together – while still ensuring the original safety guarantee. This would enable safe deployment of multiple (similar) systems using the same control architecture specifically designed for only one of them; hence, a significant increase in efficiency in the design process. The resulting algorithms of this project will be tested on underwater and aerial vehicles with an eye to future applications to other CPS domains.

2024

  1. R. Reed, H. Schaub, and M. Lahijanian, “Shielded Deep Reinforcement Learning for Complex Spacecraft Specifications,” in American Control Conference (ACC), Toronto, Canada, 2024. (accepted)

2023

  1. J. Skovbekk, L. Laurenti, E. Frew, and M. Lahijanian, “Formal Abstraction of General Stochastic Systems via Noise Partitioning,” IEEE Control Systems Letters, pp. 1–1, Dec. 2023.

  2. R. Reed, L. Laurenti, and M. Lahijanian, “Promises of Deep Kernel Learning for Control Synthesis,” IEEE Control Systems Letters, pp. 1–1, Dec. 2023.

  3. S. Adams, A. Patane, M. Lahijanian, and L. Laurenti, “BNN-DP: Robustness Certification of Bayesian Neural Networks via Dynamic Programming,” in International Conference on Machine Learning (ICML), Honolulu, HI, USA, 2023, pp. 133–151.

  4. G. Delimpaltadakis, M. Lahijanian, M. Mazo Jr., and L. Laurenti, “Interval Markov Decision Processes with Continuous Action-Spaces,” in International Conference on Hybrid Systems: Computation and Control (HSCC), San Antonio, TX, USA, 2023.

2022

  1. R. Mazouz, K. Muvvala, A. Ratheesh Babu, L. Laurenti, and M. Lahijanian, “Safety Guarantees for Neural Network Dynamic Systems via Stochastic Barrier Functions,” in Advances in Neural Information Processing Systems (NeurIPS), New Orleans, Louisiana, USA, 2022, vol. 35, pp. 9672–9686.

  2. S. A. Adams, M. Lahijanian, and L. Laurenti, “Formal Control Synthesis for Stochastic Neural Network Dynamic Models,” IEEE Control Systems Letters (L-CSS), 2022.

2021

  1. J. Jackson, L. Laurenti, E. Frew, and M. Lahijanian, “Synergistic Offline-Online Control Synthesis via Local Gaussian Process Regression,” in IEEE Conference on Decision and Control (CDC), 2021.

  2. J. Jackson, L. Laurenti, E. Frew, and M. Lahijanian, “Towards Safe, Abstraction-based Online Learning and Synthesis for Unknown Systems,” in Workshop on Integrating Planning and Learning, 2021.

  3. J. Jackson, L. Laurenti, E. Frew, and M. Lahijanian, “Strategy synthesis for partially-known switched stochastic systems,” in Conference on Hybrid Systems: Computation and Control (HSCC), 2021, pp. 1–11.

2020

  1. J. Jackson, L. Laurenti, E. Frew, and M. Lahijanian, “Towards Data-driven Verification of Unknown Dynamical Systems,” in Workshop on Robust Autonomy: Tools for Safety in Real-World Uncertain Environments, 2020.

  2. J. Jackson, L. Laurenti, E. Frew, and M. Lahijanian, “Safety verification of unknown dynamical systems via gaussian process regression,” in 2020 IEEE 59th Conference on Decision and Control (CDC), 2020.