Surveillance that spots suspicious behavior
- By Susan Miller
- May 23, 2018
To help warfighters distinguish between threats and noncombatants, the Defense Advanced Research Projects Agency is looking for new ways to use drones and sensors to analyze human behaviors that indicate hostile intent.
Current technology cannot effectively find snipers or hidden combatants, leaving the military to rely on dismounted warfighters to patrol urban areas. To limit the danger to warfighters and reduce the manpower used in patrols, DAPRA wants autonomous systems that detect and positively identify hostile agents before any troops come in contact with them.
Like current surveillance systems, the Urban Reconnaissance through Supervised Autonomy program would use drones, integrated sensors and advanced algorithms to distinguish between threats and noncombatants. However, URSA would also measure responses to natural or created stimuli and analyze those behaviors to help deduce the intent of persons of interest.
DARPA provided an example of how URSA would work:
A static sensor located near an overseas military installation detects an individual moving across an urban intersection and towards the installation outside of normal pedestrian pathways. An unmanned aerial system (UAS) equipped with a loudspeaker delivers a warning message. The person is then observed running into a neighboring building. Later, URSA detects an individual emerging from a different door at the opposite end of the building, but confirms it is the same person and sends a different UAS to investigate. This second UAS determines that the individual has resumed movement toward a restricted area. It releases a nonlethal flash-bang device at a safe distance to ensure the individual attends to the second message and delivers a sterner warning. This second UAS takes video of the subject and determines that the person’s gait and direction are unchanged even when a third UAS flies directly in front of the person and illuminates him with an eye-safe laser dot. URSA then alerts the human supervisor and provides a summary of these observations, warning actions, and the person’s responses and current location.
The agency is asking proposers to also consider advantages of different types of autonomous vehicles, as well as various actions to illicit responses from observed individuals, but it maintained URSA will require significant advances in active sensing, behavior understanding and autonomous decision-making to determine intent. Therefore, DARPA wants proposals that focus on "new algorithms and techniques to rapidly discriminate between threats and noncombatants, as opposed to sensor, effector and platform development."
Other key features on the wish list include:
- Accumulating and integrating evidence over time and from multiple sources.
- Processing the data fast enough to be useful for dismounted soldiers.
- Enabling the appropriate amount of human intervention.
- Tracking and re-identifying targets accurately enough to qualify as actionable intelligence.
- Using existing hardware, software, simulation infrastructure and physical interfaces to limit costs.
The URSA program is a two-phase, 36-month development effort. Up to $22 million is available for multiple awards in Phase 1. More information is available here.
Susan Miller is executive editor at GCN.
Over a career spent in tech media, Miller has worked in editorial, print production and online, starting on the copy desk at IDG’s ComputerWorld, moving to print production for Federal Computer Week and later helping launch websites and email newsletter delivery for FCW. After a turn at Virginia’s Center for Innovative Technology, where she worked to promote technology-based economic development, she rejoined what was to become 1105 Media in 2004, eventually managing content and production for all the company's government-focused websites. Miller shifted back to editorial in 2012, when she began working with GCN.
Miller has a BA and MA from West Chester University and did Ph.D. work in English at the University of Delaware.
Connect with Susan at firstname.lastname@example.org or @sjaymiller.