Defense Advanced Research Projects AgencyTagged Content List

Supervised Autonomy

Automated capabilities with human supervision; "human in the loop"

Showing 11 results for Autonomy + Analytics RSS
Department of Defense (DoD) operators and analysts collect and process copious amounts of data from a wide range of sources to create and assess plans and execute missions. However, depending on context, much of the information that could support DoD missions may be implicit rather than explicitly expressed. Having the capability to automatically extract operationally relevant information that is only referenced indirectly would greatly assist analysts in efficiently processing data.
Dramatic success in machine learning has led to a torrent of Artificial Intelligence (AI) applications. Continued advances promise to produce autonomous systems that will perceive, learn, decide, and act on their own. However, the effectiveness of these systems is limited by the machine’s current inability to explain their decisions and actions to human users (Figure 1). The Department of Defense (DoD) is facing challenges that demand more intelligent, autonomous, and symbiotic systems. Explainable AI—especially explainable machine learning—will be essential if future warfighters are to understand, appropriately trust, and effectively manage an emerging generation of artificially intelligent machine partners.
The U.S. Government operates globally and frequently encounters so-called “low-resource” languages for which no automated human language technology capability exists. Historically, development of technology for automated exploitation of foreign language materials has required protracted effort and a large data investment. Current methods can require multiple years and tens of millions of dollars per language—mostly to construct translated or transcribed corpora.
Urban Reconnaissance through Supervised Autonomy (URSA) is a DARPA program to enable improved techniques for rapidly discriminating hostile intent and filtering out threats in complex urban environments.
Program Manager
Dr. Bartlett Russell joined DARPA as a program manager in April of 2019. Her work focuses on understanding the variability of human cognitive and social behavior to enable the decision-maker, improve analytics, and generate autonomous and AI systems that enable human adaptability. Prior to joining DARPA, Russell was a senior program manager and lead of the human systems and autonomy research area in Lockheed Martin’s Advanced Technology Laboratories.