Bioinspired Physical Deep Learning Paradigm for Sonar Sensing in Cluttered Environments

Abstract

The research will address the problem of sonar sensing in cluttered environments. It will develop a virtual environment to train a miniature dynamic sonar system inspired by bat biosonar performing navigation and target identification in dense foliage. The virtual environment will be constructed with generative deep neural networks to represent natural foliage echoes and the functional characteristics of the biomimetic sonar head. The outcome will be an optimized miniature cyber-physical sonar.

Document Details

Document Type
DoD Grant Award
Publication Date
Jul 27, 2020
Source ID
N001741910001

Entities

People

  • Rolf Meuller

Organizations

  • United States Navy
  • Virginia Tech

Tags

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Neural Network Machine Learning.
  • Robotics and Automation.

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • AI & ML - Neural Networks
  • Biotechnology
  • Cyber