Real time Decision Making for Autonomous Systems using AI Methods

Abstract

Efficient cooperation of swarm systems is a vital part for their successful operations and effective real time decision making is the key enabler of such cooperation. This is because the strength of a swarm hinges on the distributed nature of the sensing resources available and proper decision making for the utilisation of these resources is key to maximise its operational advantages. This proposal addresses two key areas for swarm systems using AI methods: (i) decision making (ii) communications frequency assignment. There have been extensive studies on decision making for many different operations. Despite many studies, there are certain challenging issues and capability gaps to operate swarms of unmanned systems. The main technological challenge is to develop a rigorous approach for designing and analysing cooperative, dynamic decision making for unmanned systems in swarms so that they will complete the required tasks, recover safely from faults and emergencies, and respond predictably to instructions. Especially, this issue becomes more significant as the size of the unmanned swarm systems increases. The mathematic properties of decision making indicate that obtaining an optimal solution is usually impossible, and the near optimal solution is sought. There have been efforts to resolve the challenges caused by these mathematical characteristics in decision making, but most solutions are ‘customised’ for specific scenarios. Mitigating this issue, this project aims to develop a modular, flexible and robust decision making algorithm that can handle the representative mathematical properties of the decision making problem for autonomous systems. The algorithm(s) to be developed will leverage recent breakthroughs of artificial intelligent technologies.

Document Details

Document Type
DoD Grant Award
Publication Date
Jan 14, 2022
Source ID
FA95501917032

Entities

People

  • Hyo-Sang Shin

Organizations

  • Air Force Office of Scientific Research
  • Cranfield University
  • United States Air Force

Tags

Fields of Study

  • Computer science

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Aerial Unmanned Vehicle Swarm Micro Periodontal Dentistry.
  • Systems Analysis and Design

Technology Areas

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