The ADEPT Framework for Intelligent Autonomy

Abstract

This paper describes the design and implementation of Draper Laboratory's All-Domain Execution and Planning Technology (ADEPT) architecture for intelligent autonomy. Intelligent autonomy is the ability to plan and execute complex activities in a manner that provides rapid, effective response to stochastic and dynamic mission events. Thus, intelligent autonomy enables the high-level reasoning and adaptive behavior for an unmanned vehicle that is provided by an operator in man-in-the-loop systems. Draper's intelligent autonomy has architecture evolved over a decade and a half beginning in the mid 1980s [3, 4, 6 and 12] culminating in an operational experiment funded under DARPA's Autonomous Minehunting and Mapping Technologies (AMMT) unmanned undersea vehicle program [15]. ADEPT continues to be refined through its application to current programs that involve air vehicles, satellites and higher-level planning used to direct multiple vehicles. The objective of ADEPT is to solidify a proven, dependable software approach that can be quickly applied to new vehicles and domains. The architecture can be viewed as a hierarchical extension of the sense-think-act paradigm of intelligence and has strong parallels with the military's Observe-Orient-Decide-Act (OODA) loop [14]. The key elements of the architecture are planning and decision-making nodes comprising modules for situation assessment, plan generation, plan implementation and coordination. A reusable, object-oriented software framework has been developed that implements these functions. As the architecture is applied to new areas, only the application specific software needs to be developed. This paper describes the core architecture in detail and discusses how this has been applied in the undersea, air, ground and space domains.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 2003
Accession Number
ADA484778

Entities

People

  • Michael Ricard
  • Stephan Kolitz

Organizations

  • Charles Stark Draper Laboratory

Tags

Communities of Interest

  • Air Platforms
  • Autonomy
  • Ground and Sea Platforms
  • Space
  • Weapons Technologies

DTIC Thesaurus Topics

  • Air Traffic
  • Aircrafts
  • Artificial Satellites
  • Autonomous Systems
  • Autonomous Vehicles
  • Autonomy
  • Cognitive Systems Engineering
  • Collision Avoidance
  • Control Systems
  • Guidance
  • Navigation
  • Payload
  • Situational Awareness
  • Target Recognition
  • Unmanned Aerial Vehicles
  • Unmanned Ground Vehicles
  • Unmanned Underwater Vehicles

Fields of Study

  • Computer science

Readers

  • Software Engineering.
  • Systems Analysis and Design
  • Unmanned Aerial System (UAS) Autonomous Capabilities and Mission Reconnaissance.

Technology Areas

  • Autonomy
  • Autonomy - Human-Robot Interaction
  • Space
  • Space - Spacecraft Maneuvers