Swarm
Unmanned Aerial System (UAS) operations by sophisticated state and even
non-state actors are a cause for concern to the U.S. Navy partly because
the threat potential is not fully known. Some military theorists assert
that “swarming” could be the Third Offset Strategy in military thinking and
the basis for possible wide-scale impacts on military operations and
tactics (e.g., [i]).
Swarming is “a tactic that employs multiple Unmanned Aerial Vehicles (UAV)
[often small UAV or sUAV] to overwhelm targets by using mass and attrition
in combination with decentralized maneuvers or combined fires from multiple
directions.”[ii]
Swarms may be used to disrupt ship deck or
aircraft flight operations, confuse the tactical picture and situational
awareness, precipitate inefficient or pre-mature expenditure of defensive
weapons, conduct reconnaissance and intelligence gathering, obscure or mask
high-threat units, overwhelm defenses, or themselves deliver
micro-munitions including chemical or biologic using coordinated ambush,
circling, or multi-axis attacks. Swarms can be trained to exhibit intricate
and difficult-to-predict animal or biological behaviors[iii].
Detection,
identification, and tracking of UAS sUAV swarms
is challenging because of deformability, low sUAV
Signal to Noise Ratio (SNR), large numbers of units, and elements of
tactics such as ambush. Irregular grouping and ungrouping dynamics
complicate the swarm picture, as the arrangement can change fluidly.
Detection, identification, and tracking are functions of data fusion (DF).
A specialized DF function is the identification (including classification)
of hard to detect and recognize objects, e.g., swarms, for which Deep
Learning (DL) has in recent years shown to be a good solution. MSDIT’s
innovations to this DF problem include:
Resolve
Multiple Targets in a Single Return Pulse. For long to mid-range
swarms, Detection and Identification (D&I) as an Unresolved Group
Target (UGT) by radar intrapulse
modulations using DL trained on synthetically superposed sUAV inverse backscattering and sUAV
propeller Doppler signatures.
Volumetric
Spatial Frequencies Analysis. For mid to short-range swarms, D&I as
a Partially-resolved / Resolved Group Target (P/RGT) using a novel spectral
frequency technique using DL trained on volumetric Fourier transforms of
swarm formations.
These two
innovations provide a seamless solution to sensor target resolution wherein
the UGT continuously give way to P/RGT detections as swarm range closes.
Optimizing
Linear Assignment for Multi-modal Fusion. Radar and IR sensing are made
complimentary, as the signal and 3-D characteristics of the radar inform
swarm detections and IR detections refine identification / classification.
Both are used to form swarm tracks without ever having to track individual sUAVs. Associating and tracking at the swarm level
allows low visible, dim, and weakly resolved image detections to be merged
into the swarm track while discarding non-associated noise detections.
This blend of
sensors and swarm signature-based DL and DF has never been tried before but
is well-founded and solves many of the long-standing issues with swarm
tracking.
Approach:
Blend of
sensors and swarm signature-based DL and DF that is innovative but
well-founded and solves many of the long-standing issues with swarm
tracking and that integrates well with existing DoN
Sense-Command-Act architectures.
Anticipated
Phase I Results:
Provide, “a
clear, accurate, and actionable view of the sUAV
swarm, improving classification confidence, and enabling effective
decision-making.”
Anticipated
Customers:
DoD:
Counter-Small Unmanned Aircraft Systems (C-sUAS) ; Joint Counter-small
Unmanned Aircraft Systems (C-sUAS) Capability
Commercial:
monitoring agricultural drone crop spraying; wildlife surveys; congested
waterways safety; detection of dangerous flocks to aircraft; riot and crowd
management; space debris cloud tracking
i Korpela, C., & Caton, J. L. (2015). Swarms in the
Third Offset. ed. White, SR, Closer than you think: The implications
of the Third Offset Strategy for the US Army, US Army Command and General
Staff College, Fort Leavenworth, KS, US. Liang, Q & Xiangsui,
W.
ii
UAS Technical Exploitation Lexicon, 2nd Edition, 16 August 2019
iii China:
Digital Pheromones and Wolf Packs, Swarm Intelligence for UAVs; 547
Intelligence Squadron; 16 October 2019
|