Defense Advanced Research Projects AgencyTagged Content List

Supervised Autonomy

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

Showing 24 results for Autonomy + Complexity RSS
01/29/2015
Robots can learn to recognize objects and patterns fairly well, but to interpret and be able to act on visual input is much more difficult.  Researchers at the University of Maryland, funded by DARPA’s Mathematics of Sensing, Exploitation and Execution (MSEE) program, recently developed a system that enabled robots to process visual data from a series of “how to” cooking videos on YouTube. Based on what was shown on a video, robots were able to recognize, grab and manipulate the correct kitchen utensil or object and perform the demonstrated task with high accuracy—without additional human input or programming.  
06/25/2015
DARPA’s Defense Sciences Office (DSO) is sponsoring a two-day Proposers Day event to provide information to potential proposers on the objectives of an anticipated DSO Office-wide Broad Agency Announcement (BAA) solicitation. The event will be held on Tuesday and Wednesday, July 21-22, 2015, at the DARPA Conference Center (675 North Randolph Street, Arlington, VA 22203) and will be webcast for potential proposers who would like to participate remotely.
05/18/2016
DARPA’s Defense Sciences Office (DSO) is sponsoring a two-day Proposers Day, June 22-23, to provide information to potential proposers on the objectives of the DSO Office-wide Broad Agency Announcement (BAA): http://go.usa.gov/cStaQ. Attendees may register to attend in person or via webinar.
04/28/2017
DARPA’s Defense Sciences Office (DSO), which identifies and pursues high-risk, high-payoff research initiatives across a broad spectrum of science and engineering disciplines, will host Discover DSO Day (D3) on June 15, in Arlington, Virginia. The event is designed to familiarize potential proposers with the mission, research areas of interest, and business processes pursued by the DSO, a fundamental research office with a history of not only reshaping existing technical fields but also creating entirely new disciplines—and of transforming bold, paradigm-challenging initiatives into game-changing technologies for U.S. national security.
05/31/2017
Advances in artificial intelligence (AI) are making virtual and robotic assistants increasingly capable in performing complex tasks. For these “smart” machines to be considered safe and trustworthy collaborators with human partners, however, robots must be able to quickly assess a given situation and apply human social norms. Such norms are intuitively obvious to most people—for example, the result of growing up in a society where subtle or not-so-subtle cues are provided from childhood about how to appropriately behave in a group setting or respond to interpersonal situations. But teaching those rules to robots is a novel challenge.