Hybrid Data-Driven Algorithms for Networked Multi-Agent Systems: Stability and Robustness

Abstract

The main goal of the proposed research is to develop analytical and constructivetools for the development of model-free and data-driven stochastic hybriddynamical systems in the context of multi-agent systems, with stability, convergence,and robustness guarantees. To achieve this objective, we will rely on and enhance thePI’s recent work on a general framework for stochastic hybrid dynamical systems andmodel-free hybrid control systems, which allows for non-unique solutions and thusthe interplay between randomness and independent decision making in multi-agentsystems. Our goal is to generate novel analytical tools for the analysis of data-drivenalgorithms in the context of stochastic hybrid dynamical systems, as well as constructiveprocedures for the design of robust model-free and data-driven algorithms,with performance guarantees, for networked multi-agent dynamical systems.

Document Details

Document Type
DoD Grant Award
Publication Date
Jun 11, 2018
Source ID
FA95501810246

Entities

People

  • Andrew R. Teel

Organizations

  • Air Force Office of Scientific Research
  • United States Air Force
  • University of California, Santa Barbara

Tags

Fields of Study

  • Computer science

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Data Mining and Knowledge Discovery.