The Air Force Research Laboratory's Information Directorate has a rich history of developing advanced computing technology for the warfighter guiding emerging technologies from the laboratory to the field. Memristors, also known as resistive random-access memory, is one such computing technology. This paper details AFRL's technical maturation of memristors for neuromorphic computing from early concept through device fabrication and architectural implementation using a combination of in-house programs, contractual efforts, and collaborative partnerships. It additionally explores recent DoD architectural advancements to further enable low size, weight, and power computationally efficient intelligent computing at the edge.
Detecting and identifying targets in unmanned aerial vehicle (UAV) images and videos have been challenging problems due to various types of image distortion. Moreover, the significantly high processing overhead of existing image/video processing techniques and the limited computing resources available on UAVs force most of the processing tasks to be performed by the ground control station (GCS) in an off-line manner. In order to achieve fast and autonomous target identification on UAVs, it is thus imperative to investigate novel processing paradigms that can fulfill the real-time processing requirements, while fitting the size, weight, and power (SWaP) constrained environment. In this paper, we present a new autonomous target identification approach on UAVs, leveraging the emerging neuromorphic hardware which is capable of massively parallel pattern recognition processing and demands only a limited level of power consumption. A proof-of-concept prototype was developed based on a micro-UAV platform (Parrot AR Drone) and the CogniMemTMneural network chip, for processing the video data acquired from a UAV camera on the y. The aim of this study was to demonstrate the feasibility and potential of incorporating emerging neuromorphic hardware into next-generation UAVs and their superior performance and power advantages towards the real-time, autonomous target tracking.
A fully parallel, silicon-based artificial neural network (CM1K) built on zero instruction set computer (ZISC) technology
was used for change detection and object identification in video data. Fundamental pattern recognition capabilities were
demonstrated with reduced neuron numbers utilizing only a few, or in some cases one, neuron per category. This
simplified approach was used to validate the utility of few neuron networks for use in applications that necessitate severe
size, weight, and power (SWaP) restrictions. The limited resource requirements and massively parallel nature of
hardware-based artificial neural networks (ANNs) make them superior to many software approaches in resource limited
systems, such as micro-UAVs, mobile sensor platforms, and pocket-sized robots.
A monolithic two-section quantum dot semiconductor laser is differentially pumped to form non-uniform current
injection in the gain region. We show that the nature of the spectral content in the output signal is affected by this
differential pumping; despite the fact that the separately pumped gain regions are not electrically isolated in this device.
Both negative (red-shift) and positive (blue-shift) spectral chirps were observed during mode-locked operation. It is also
demonstrated that mode locked operation is achieved with a much larger set of injection current / absorber bias voltage
pairs than was previously possible with single-pad current injection.
Generation of stable pulses and a frequency stabilized optical comb are two key requirements for Fourier Based
Arbitrary Waveform Generation (AWG) techniques. The longitudinal mode spacing of the laser must remain as stable
as possible to permit effective isolation and processing of the modes for waveform synthesis. The short and long term
temporal stability ultimately limits the system's precision as well as its operability in fielded systems. A packaged
erbium-doped waveguide provided a highly compact gain medium for the harmonically mode-locked laser design.
Stability was achieved by use of an intracavity etalon for frequency stabilization of the optical comb, a Pound-Drever-
Hall (PDH) method, and an active bias feedback loop for low frequency noise suppression. The temperature was
controlled to limit cavity length variation, and the contribution to stability of each method is quantitatively assessed.
The system's stable operating time was increased from hours to greater than a day, and the timing jitter is demonstrated
to be lower than that of commercially available erbium-doped fiber laser (EDFL) systems. Applications to optical signal
synthesis and Laser Radar are briefly discussed.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.