Seamless Integration of Knowledge Acquisition for Autonomous Systems by Domain Users with Prudence Capability

Abstract

Knowledge-based systems are typically constrained by their ability to acquire new knowledge without the intercession of a technical knowledge engineer. This introduces a fundamental disconnect between the system and the domain expert - even if a knowledge acquisition interface is provided, the domain expert is usually highly constrained in their expressiveness and ability to train the system due to technology-specific implementation.Knowledge-based systems are also currently limited in their applicability to autonomous systems. The domain expert/knowledge acquisition bottleneck in this paradigm also poses a great challenge to effectively train an autonomous system with new or modified behaviours without considerable effort and implementation change. In the autonomous system-operating environment, there is no consistent model of abstraction (of services/behaviour, information and data) that can be leveraged across different systems and domains.

Document Details

Document Type
DoD Grant Award
Publication Date
Sep 21, 2018
Source ID
FA23861614045

Entities

People

  • Byeong Ho Kang

Organizations

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

Tags

Fields of Study

  • Computer science

Readers

  • Artificial Intelligence
  • Distributed Systems and Data Platform Development
  • Software Engineering.

Technology Areas

  • Autonomy