VERIFIABLE HIERARCHICAL SENSING, PLANNING, AND CONTROL

Abstract

We propose a multidisciplinary approach to verifiable behaviour design in multi-agent robotic systems. Namely, we consider verifiable behaviours comprised of control, decision making, symbolic planning, sensing and classification. A hierarchical and modular behaviour structure synthesis is proposed in order to achieve tractable verification and hard guarantees at various levels of abstraction, i.e., from discrete plans to low level robust control of dynamics. Moreover, we aim for a dynamic co-design of the system and control behaviour in which sensing and environment classification lead to efficient refinement of plans and control strategies. Inversely, planning and control is synthesised with a sub goal of elucidating more knowledge on the environment.

Document Details

Document Type
DoD Grant Award
Publication Date
Oct 20, 2022
Source ID
FA23861914073

Entities

People

  • Tyler Summers

Organizations

  • Air Force Office of Scientific Research
  • United States Air Force
  • University of Texas at Dallas

Tags

Fields of Study

  • Computer science

Readers

  • Distributed Systems and Data Platform Development
  • Neural Network Machine Learning.
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • AI & ML - Machine Learning Algorithms
  • Autonomy
  • Autonomy - Autonomous System Control