Benthic Autonomy Gaits to Identify Munitions With Dactyl Sensors

Abstract

We propose to develop autonomous detection algorithms for UXO, UneXploded Ordinance in environments where long range sensors are ineffective. Specifically, SERDP has identified a need in shallow waters, where our crab-like robots are capable of walking on benthicsurfaces and lifting up cylindrical objects. As we develop this platform, we see an opportunity to learn more about how to autonomously use leg sensors to map the position and orientation of key objects (UXO) relative to the robot. This proposal creates the essential tools for this by creating simulation environments and a robust interaction dataset. The dataset will consist of the sensor-embedded crab robot walking over inert rounds, aka Simulated UXO or SUXO. We will share this dataset with Co-PI in Singapore (co-PISartoretti will request support from his government after approval from ONR). Furthermore, we will compare behavior of crab robots with that of biological crabs observed by Co-PI Glenna Clifton. These datasets and simulation environments will enable developmentefficient munitions-finding gaits for walking robots. In addition, this can shed light on how both robotic and biological crabs use legs in marine environments.

Document Details

Document Type
DoD Grant Award
Publication Date
Nov 21, 2023
Source ID
N000142412022

Entities

People

  • Kathryn A Daltorio

Organizations

  • Case Western Reserve University
  • Office of Naval Research
  • United States Navy

Tags

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Nanocomposite Materials Science
  • Robotics and Automation.

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • Autonomy