Good morning,Apologies if this has already been posted...

Good morning,

Apologies if this has already been posted previously.

There has been speculation that Boeing could be one of our potential customers.

if you were going to put out an "APB" on Akida this would be a pretty good description.

My only concern would be if we aren't helping them with this, then who is.



NASA SBIR 2020 Phase I Solicitation H6.22 Deep Neural Net and Neuromorphic Processors for In-Space Autonomy and Cognition Lead Center: GRC Participating Center(s): ARC Technology Area: TA11 Modeling, Simulation, Information Technology and ProcessingScope TitleNeuromorphic CapabilitiesScope DescriptionThe Neuromorphic Processors for In-Space Autonomy and Cognition subtopic specifically focuses on advances insignal and data processing. Neuromorphic processing will enable NASA to meet growing demands for applyingartificial intelligence and machine learning algorithms on-board a spacecraft to optimize and automate operations.This includes enabling cognitive systems to improve mission communication and data processing capabilities,enhance computing performance, and reduce memory requirements. Neuromorphic processors can enable aspacecraft to sense, adapt, act and learn from its experiences and from the unknown environment withoutnecessitating involvement from a mission operations team. Additionally, this processing architecture shows promisefor addressing the power requirements that traditional computing architectures now struggle to meet in spaceapplications.The goal of this program is to develop neuromorphic processing software, hardware, algorithms, architectures,simulators and techniques as enabling capability for autonomous space operations. Emerging memristor and otherradiation-tolerant devices, which shows potential for addressing the need for energy efficient neuromorphicprocessors and improved signal processing capability, is of particular interest due to its resistance to the effects ofradiation.Additional areas of interest for research and/or technology development include: a) spiking algorithms that learnfrom the environment and improve operations, b) neuromorphic processing approaches to enhance dataprocessing, computing performance, and memory conservation, and c) new brain-inspired chips and breakthroughsin machine understanding/intelligence. Novel memristor approaches which show promise for space applications arealso sought.This subtopic seeks innovations focusing on low size, weight and power (SWaP) applications suitable lunar orbitalor surface operations, enabling efficient on-board processing at lunar distances. Focusing on SWaP-constrainedplatforms opens up the potential for applying neuromorphic processors in spacecraft or robotic control situationstraditionally reserved for power-hungry general purpose processors. This technology will allow for increased speed,energy efficiency and higher performance for computing in unknown and un-characterized space environmentsincluding the Moon and Mars.Page 1 of 3

Phase I will emphasize research aspects for technical feasibility and show a path toward a Phase II proposal.Phase I deliverables include concept of operations of the research topic, simulations and preliminary results. Earlydevelopment and delivery of prototype hardware/software is encouraged.Phase II will emphasize hardware and/or software development with delivery of specific hardware and/or softwareproducts for NASA, targeting demonstration operations on a low-SWaP platform. Phase II deliverables include aworking prototype of the proposed product and/or software, along with documentation and tools necessary forNASA to use the product and/or modify and use the software. In order to enable mission deployment, proposedprototypes should include a path, preferably demonstrated, for fault tolerance and mission tolerance.ReferencesSeveral reference papers that have been published at the Cognitive Communications for Aerospace Applications(CCAA) workshop are available at: http://ieee-ccaa.com.Expected TRL or TRL range at completion of the project 4 to 6Desired Deliverables of Phase IIPrototype, Hardware, SoftwareDesired Deliverables DescriptionPhase 2 deliverables should include hardware/software necessary to show how the advances made in thedevelopment can be applied to a cubesat, small sat, and rover flight demonstration.State of the Art and Critical GapsThe current State-of-the-Art (SOA) for in-space processing is the High Performance Spaceflight Computing (HPSC)processor being developed by Boeing for NASA GSFC. The HPSC, called the Chiplet, contains 8 general purposeprocessing cores in a dual quad-core configuration. Delivery is expected by December 2022. In a submission to theSTMD Game Changing Development (GCD) program, the highest computational capability required by a typicalspace mission is 35-70 GFLOPS (million fast logical operations per second).The current SOA does not address the capabilities required for artificial intelligence and machine-learningapplications in the space environment. These applications require significant amounts of multiply and accumulateoperations, in addition to a substantial amount of memory to store data and retain intermediate states in a neuralnetwork computation. Terrestrially, these operations require General-Purpose Graphics Processing Units (GP-GPUs), which are capable of teraflops (TFLOPS) each -- approximately 3 orders of magnitude above theanticipated capabilities of the HPSC.Neuromorphic processing offers the potential to bridge this gap through a novel hardware approach. Existingresearch in the area shows neuromorphic processors to be up to 1000 times more energy efficient than GP-GPUsin artificial intelligence applications. Obviously the true performance depends on the application, but neverthelessthe architecture has demonstrated characteristics that make it well-adapted to the space environment.Relevance / Science TraceabilityThe Cognitive Communications Project, through the Human Exploration and Operations Mission Directorate(HEOMD) Space Communications and Navigation (SCaN) Program, is one potential customer of work from thissubtopic area. Neuromorphic processors are a key enabler to the cognitive radio and system architectureenvisioned by this project. As communications become more complex, cognition and automation will play a largerrole to mitigate complexity and reduce operations costs. Machine learning will choose radio configurations, adjustfor impairments and failures. Neuromorphic processors will address the power requirements that traditionalcomputing architectures now struggle to meet and are of relevance to lunar return and Mars for autonomousoperations, as well as of interest to HEOMD and SMD for in-situ avionics capabilities. Page 2 of 3

Unlike Tensor, who previously referenced an Akida COTS chip for a Cubesat this could potentially be in the IP space.

Timing appears conveniently convergent. Who knows.

DYODJ