no code implementations • 11 Jan 2024 • Victoria M. Dax, Jiachen Li, Kevin Leahy, Mykel J. Kochenderfer
Graph-structured data is ubiquitous throughout natural and social sciences, and Graph Neural Networks (GNNs) have recently been shown to be effective at solving prediction and inference problems on graph data.
no code implementations • 29 Jun 2023 • Kevin Leahy, Makai Mann, Zachary Serlin
We advance the state of the art in Boolean composition of learned tasks with three contributions: i) introduce two distinct notions of safety in this framework; ii) show how to enforce either safety semantics, prove correctness (under some assumptions), and analyze the trade-offs between the two safety notions; and iii) extend Boolean composition from discrete action spaces to continuous action spaces.
no code implementations • 26 May 2023 • Ho Chit Siu, Kevin Leahy, Makai Mann
The ground-truth validity of a specification, subjects' familiarity with formal methods, and subjects' level of education were found to be significant factors in determining validation correctness.
no code implementations • 4 Apr 2023 • Max H. Cohen, Makai Mann, Kevin Leahy, Calin Belta
In this paper, we present a framework for online parameter estimation and uncertainty quantification in the context of adaptive safety-critical control.
no code implementations • 30 Nov 2022 • Wenliang Liu, Kevin Leahy, Zachary Serlin, Calin Belta
In this paper, we propose a learning-based framework to simultaneously learn the communication and distributed control policies for a heterogeneous multi-agent system (MAS) under complex mission requirements from Capability Temporal Logic plus (CaTL+) specifications.
no code implementations • 4 Oct 2022 • Wenliang Liu, Kevin Leahy, Zachary Serlin, Calin Belta
We consider the problem of controlling a heterogeneous multi-agent system required to satisfy temporal logic requirements.
no code implementations • 3 Oct 2022 • Mingyu Cai, Makai Mann, Zachary Serlin, Kevin Leahy, Cristian-Ioan Vasile
This is achieved by decomposing an infeasible LTL formula into several reach-avoid sub-tasks with shorter horizons, which can be trained in a modular DRL architecture.
no code implementations • 17 Mar 2022 • Nathan Vaska, Kevin Leahy, Victoria Helus
In this work, we leverage contextual awareness for the anomaly detection problem.
no code implementations • 30 Sep 2020 • Kevin Leahy, Austin Jones, Cristian-Ioan Vasile
In this work, we focus on decomposing large multi-agent path planning problems with global temporal logic goals (common to all agents) into smaller sub-problems that can be solved and executed independently.
no code implementations • 24 Jan 2018 • Colm V. Gallagher, Kevin Leahy, Peter O'Donovan, Ken Bruton, Dominic T. J. O'Sullivan
20 baseline energy models are developed using an exhaustive approach with the optimal model being used to quantify savings.