BRAIN: Bio-inspired Resource-aware Adaptive Intelligence and Teaming

Abstract

The need to obtain actionable mission-critical information with limited resources is one of themost challenging problems for the development of next-generation unmanned systems.Harnessing intelligence from the nature, especially biological systems, is important for thedevelopment of smart unmanned systems that can proactively manage limited resources forreal-time mission needs. Recent technological advances provide some foundational progresstowards the development of new sensors, actuators, and computation that mimic their biologicalcounterparts. These advances, however, mainly aim to provide more capable components ofunmanned systems without quantifying the value of these components for actual mission needs,leading to the lack of adaptivity that is popular in many biological systems. The lack of adaptionwill lead to redundant perception, communication, action which are some main challengestowards the development of next-generation smart unmanned systems. The goal of the project isto overcome both theoretical and algorithmic challenges in developing bio-inspiredresource-aware adaptive intelligence and teaming for unmanned systems. In pursuit of this goal,the project will focus on three essential thrusts: (1) Cognitively-inspired Perception: this thrustwill adaptively manage perception via quantifying perception values; (2) Learning-based TeamDecision: this thrust will create a new guidance-based reinforcement learning approach to learnbio-inspired adaptive communication, action, and teaming strategies; and, (3) Social-inspiredEnd-to-end Learning: this thrust will create new multi-policy multi-objective reinforcementlearning strategies for multi-objective co-optimization under different preferences/priorities withverbal explanation. The novelty of this interdisciplinary project is the synthesis of approachesfrom the biological, cognitive, computational and decision/control sciences to create a newbio-inspired adaptive resource-aware perception and decision architecture that offers adaptivity,proactivity and efficiency.Approved for Public Release

Document Details

Document Type
DoD Grant Award
Publication Date
Nov 08, 2024
Source ID
N000142412405

Entities

People

  • Yongcan Cao

Organizations

  • Office of Naval Research
  • United States Navy
  • University of Texas at San Antonio

Tags

Fields of Study

  • Computer science

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Distributed Systems and Data Platform Development
  • Neural Network Machine Learning.

Technology Areas

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