DARPA selects SRI to develop VIGIL for Mind's Eye

SRI International is leading a team to design a visual intelligence system, known as VIGIL (Visual Intelligence Grounded in Learning), to enable a new era in unmanned robotic surveillance.

The SRI team is being funded through the US Defense Advanced Research Projects Agency's (DARPA's) Mind's Eye program. VIGIL will be integrated with other components of the Mind's Eye program that are being developed by research teams around the globe. The result will be a smart camera system that needs minimal human supervision, can be deployed rapidly and cost effectively in unmanned vehicles (UVs) stationed in areas under automatic surveillance, and can interpret behavior and identify potential threats from video data.

"Surveillance in dangerous areas is currently performed by remote reconnaissance teams and advanced scouting patrols, who are often risking their lives," said Hung Bui, Ph.D., senior computer scientist at SRI International. "While their efforts can be supplemented through the use of cameras on unmanned vehicles, such devices still require constant human monitoring to analyze ongoing activities. SRI's VIGIL system combines automatic reasoning and machine perception to automatically analyze areas of interest while keeping members of the armed forces out of harm's way."

For this project, SRI and its partners, the University of Leeds and the University of Maryland, are currently working to solve the following challenges:

-- Generate consistent interpretations based on adequate background
knowledge about the structure of observed actions and objects
-- Recognize potential threats despite incomplete or missing perceptual
input
-- Learn new patterns and situation indicators with minimal human
supervision

In related projects for DARPA, SRI's Artificial Intelligence Center has been involved with the Personalized Assistant that Learns (PAL) program. As part of this program, SRI and team members worked to develop a next-generation Cognitive Agent that Learns and Organizes (CALO). Other projects for DARPA include LAGR, a project to develop autonomous off-road navigation, using techniques based on real-time vision and learning.

Source: SRI