Enabling Robust Persistent Autonomy in Robots

Abstract

This project investigates the science of persistent autonomy for robotic systems, towards the goal of enhanced machine intelligence. In order to achieve persistent autonomy, a robot must be able to operate for long periods without the aid of human intervention. Persistent autonomy is characterized by the abilities to: (a) continually progress with mission objectives (sense or effect the world state); (b) apply generally-stated human preferences appropriately in specific situations; (c) adapt to novel circumstances; (d) avoid hazards; and (e) resolve failures. The challenges of persistent autonomy include limited or denied communication with humans, unknown and changing environments, hazardous conditions, and software failures. This project focuses specifically on the problems of structural adaptation to the unknown and resolution of unanticipated failures.

Document Details

Document Type
DoD Grant Award
Publication Date
Feb 06, 2017
Source ID
FA95501710109

Entities

People

  • Ross Knepper

Organizations

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

Tags

Readers

  • Economics
  • Robotics and Automation.
  • Unmanned Aerial System (UAS) Autonomous Capabilities and Mission Reconnaissance.

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • AI & ML - DoD AI Strategy
  • Autonomy
  • Autonomy - Autonomous System Control
  • Autonomy - Human-Robot Interaction
  • Autonomy - UAVs