no code implementations • 30 Apr 2024 • Rayan Mazouz, John Skovbekk, Frederik Baymler Mathiesen, Eric Frew, Luca Laurenti, Morteza Lahijanian
This paper introduces a method of identifying a maximal set of safe strategies from data for stochastic systems with unknown dynamics using barrier certificates.
no code implementations • 22 Mar 2024 • Eduardo Figueiredo, Andrea Patane, Morteza Lahijanian, Luca Laurenti
Uncertainty propagation in non-linear dynamical systems has become a key problem in various fields including control theory and machine learning.
no code implementations • 8 Mar 2024 • Robert Reed, Hanspeter Schaub, Morteza Lahijanian
Autonomous spacecraft control via Shielded Deep Reinforcement Learning (SDRL) has become a rapidly growing research area.
no code implementations • 8 Jan 2024 • Frederik Baymler Mathiesen, Morteza Lahijanian, Luca Laurenti
In this paper, we present IntervalMDP. jl, a Julia package for probabilistic analysis of interval Markov Decision Processes (IMDPs).
no code implementations • 15 Oct 2023 • Qi Heng Ho, Tyler Becker, Benjamin Kraske, Zakariya Laouar, Martin S. Feather, Federico Rossi, Morteza Lahijanian, Zachary N. Sunberg
Evaluations on a set of benchmark problems demonstrate the efficacy of our algorithm and show that policies for RC-POMDPs produce more desirable behaviors than policies for C-POMDPs.
no code implementations • 3 Oct 2023 • Luca Laurenti, Morteza Lahijanian
Providing safety guarantees for stochastic dynamical systems has become a central problem in many fields, including control theory, machine learning, and robotics.
no code implementations • 19 Sep 2023 • John Skovbekk, Luca Laurenti, Eric Frew, Morteza Lahijanian
We introduce a general procedure for the finite abstraction of nonlinear stochastic systems with non-standard (e. g., non-affine, non-symmetric, non-unimodal) noise distributions for verification purposes.
no code implementations • 12 Sep 2023 • Robert Reed, Luca Laurenti, Morteza Lahijanian
Deep Kernel Learning (DKL) combines the representational power of neural networks with the uncertainty quantification of Gaussian Processes.
no code implementations • 22 Jun 2023 • Peter Amorese, Morteza Lahijanian
Further, we show a method of computing the entire Pareto front (the set of all optimal trade-offs) via an adaptation of a multi-objective A* algorithm.
1 code implementation • 19 Jun 2023 • Steven Adams, Andrea Patane, Morteza Lahijanian, Luca Laurenti
In this paper, we introduce BNN-DP, an efficient algorithmic framework for analysis of adversarial robustness of Bayesian Neural Networks (BNNs).
no code implementations • 14 Apr 2023 • Qi Heng Ho, Zachary N. Sunberg, Morteza Lahijanian
This paper introduces a sampling-based strategy synthesis algorithm for nondeterministic hybrid systems with complex continuous dynamics under temporal and reachability constraints.
no code implementations • 29 Dec 2022 • Ibon Gracia, Dimitris Boskos, Morteza Lahijanian, Luca Laurenti, Manuel Mazo Jr
First, we construct a finite abstraction of the switched stochastic system as a \emph{robust Markov decision process} (robust MDP) that encompasses both the stochasticity of the system and the uncertainty in the noise distribution.
no code implementations • 2 Nov 2022 • Giannis Delimpaltadakis, Morteza Lahijanian, Manuel Mazo Jr., Luca Laurenti
Interval Markov Decision Processes (IMDPs) are finite-state uncertain Markov models, where the transition probabilities belong to intervals.
no code implementations • 18 Jul 2022 • Anne Theurkauf, Nisar Ahmed, Morteza Lahijanian
A well understood technique for trading off communication costs with estimation accuracy is event triggering (ET), where measurements are only communicated when useful, e. g., when Kalman filter innovations exceed some threshold.
no code implementations • 8 Jul 2022 • Qi Heng Ho, Roland B. Ilyes, Zachary N. Sunberg, Morteza Lahijanian
This paper presents an algorithmic framework for control synthesis of continuous dynamical systems subject to signal temporal logic (STL) specifications.
1 code implementation • 15 Jun 2022 • Rayan Mazouz, Karan Muvvala, Akash Ratheesh, Luca Laurenti, Morteza Lahijanian
A key step in our method is the employment of the recent convex approximation results for NNs to find piece-wise linear bounds, which allow the formulation of the barrier function synthesis problem as a sum-of-squares optimization program.
no code implementations • 11 Mar 2022 • Steven Adams, Morteza Lahijanian, Luca Laurenti
Neural networks (NNs) are emerging as powerful tools to represent the dynamics of control systems with complicated physics or black-box components.
no code implementations • 20 Feb 2022 • Justin Kottinger, Shaull Almagor, Morteza Lahijanian
In the Multi-Agent Path Finding (MAPF) problem, the goal is to find non-colliding paths for agents in an environment, such that each agent reaches its goal from its initial location.
no code implementations • 31 Dec 2021 • John Jackson, Luca Laurenti, Eric Frew, Morteza Lahijanian
In this article, we develop a framework for verifying partially-observable, discrete-time dynamical systems with unmodelled dynamics against temporal logic specifications from a given input-output dataset.
no code implementations • 11 Oct 2021 • John Jackson, Luca Laurenti, Eric Frew, Morteza Lahijanian
The online controller may improve the baseline guarantees since it avoids the discretization error and reduces regression error as new data is collected.
no code implementations • 5 Apr 2021 • John Jackson, Luca Laurenti, Eric Frew, Morteza Lahijanian
We present a data-driven framework for strategy synthesis for partially-known switched stochastic systems.
no code implementations • 23 Sep 2020 • Andrew M. Wells, Morteza Lahijanian, Lydia E. Kavraki, Moshe Y. Vardi
Linear Temporal Logic over finite traces (LTLf) has been used to express such properties, but no tools exist to solve policy synthesis for MDP behaviors given finite-trace properties.
no code implementations • 26 Apr 2020 • Èric Pairet, Juan David Hernández, Marc Carreras, Yvan Petillot, Morteza Lahijanian
The proposed approach deals with the motion, probabilistic safety, and online computation constraints by: (i) incrementally mapping the surroundings to build an uncertainty-aware representation of the environment, and (ii) iteratively (re)planning trajectories to goal that are kinodynamically feasible and probabilistically safe through a multi-layered sampling-based planner in the belief space.