BrainChip + Information Systems Laboratories (AFWERX Agility Prime)

uiux

Regular

AFWERX Agility Prime – A New Era of Aerospace

ARLINGTON, Texas (AFRL) – AFWERX Agility Prime, launched in April 2020, is the Air Force’s collaborative initiative to work with the industrial base on testing and experimentation, accelerating development of the commercial electric vertical takeoff and landing (eVTOL) aircraft industry, enabling resilient distributed logistics and sustainable mobility.

Agility Prime is a Department of the Air Force program and also includes collaboration with the Army for developing transformative vertical lift capabilities. In an effort to build upon collaboration and teamwork, AFWERX Agility Prime representatives made an appearance at the Air Force versus Army football game on November 6 at Globe Life Field in Arlington, Texas. With fans on both sides interested in the innovative efforts of both the Army and Air Force, this game offered the perfect stage for this shared ingenuity.

---


BrainChip Holdings Ltd (ASX: BRN, OTCQX: BRCHF, ADR: BCHPY), a leading provider of ultra-low power, high performance artificial intelligence technology and the world’s first commercial producer of neuromorphic AI chips and IP, today announced that Information Systems Laboratories, Inc. (ISL) is developing an AI-based radar research solution for the Air Force Research Laboratory (AFRL) based on its Akida™ neural networking processor.

“ISL has decided to use Akida and Edge-based learning as a tool to incorporate into their portfolio of research engineering and engineering solutions in large part due to our innovative capabilities and production-ready status that provides go-to-market advantages,” said Sean Hehir, BrainChip CEO. “We are pleased to be included as the AI- and Edge-based learning component of ISL’s research sponsored by AFRL. We feel that the combination of technologies will help expediate its deployment into the field.”

About AFRL and AFWERXAFRL and AFWERXhave partnered to streamline the Small Business Innovation Research process in an attempt to speed up the experience, broaden the pool of potential applicants and decrease bureaucratic overhead. Beginning in SBIR 18.2, and now in J203-CS01, the Air Force has begun offering ‘The Open Topic’ SBIR/STTR program that is faster, leaner and open to a broader range of innovations.

---


Deep Learning Sensor Technology for Safe Flying Car Operations

Sensor technology that enables safe takeoff, landing, navigation, and Sense & Avoid (SAA) flight is paramount for Urban Air Mobility (UAM). The approach must be all-weather, day-night, low C-SWaP, and identify obstacles during flight (aircraft, UAS, birds) as well as during takeoff/landing (cables, buildings). The FAA advises that an air vehicle be able to Detect, Sense, and Avoid (DSA) other aircraft with detection ranges of 3 nmi or more. We are proposing an Artificial Intelligence Radar (AIR) solution that is all-weather, extremely lightweight and cost effective. It leverages a novel sensor technology, ISL’s state-of-the-art M&S tool RFView®, and the Simlat flight environment. RFView® was recently highlighted as an AFRL SBIR Success Story for its ability to dramatically reduce the need for expensive flight testing



https://www.ohiofrn.org/sites/ofrn/files/attachments/cms_page/ISL - AI Sensor Technology for Safe UAM.pdf


1644454680785.png



---



US Air Force showcases 35 high-speed VTOL aircraft concepts

The US Air Force wants to take things up a notch with a new generation of high-speed vertical takeoff and landing aircraft. Thirty five designs have been selected, here's a peek at just a few to catch our eye.


---



US11256988 - PROCESS AND METHOD FOR REAL-TIME SENSOR NEUROMORPHIC PROCESSING

Applicants
Joseph R. Guerci
Information Systems Laboratories, Inc.
Jameson Bergin
Brian Watson
Sandeep Gogineni
Colton Smith
Gavin McGee

Abstract
A novel system and method are described that allows for implementation of compact and efficient deep learning AI solutions to advanced sensor signal processing functions. The process includes the following stages: (1) A method for generating requisite annotated training data in sufficient quantity to ensure convergence of a deep learning neural network (DNN); (2) A method for implementing the resulting DNN onto a Spiking Neural Network (SNN) architecture amenable to efficient neuromorphic integrated circuit (IC) architectures; (3) A method for implementing the solution onto a neuromorphic IC; and (4) A statistical method for ensuring reliable performance.

vSK-vPz8Ak9SWSN8DqZC2w-JMvVLJTMxpguKpfWSY5EIt2mBJ6xaruIwylU0t6OGsYNAd0lHaMabRfcMKB-0K1THP8LEepYNNKCorw6hT0zNNRZaXZQObrP_V4TMhbQrfu9GUX4ga9332iaEbq-fbgc_5TcAjTrKfLuDX18c1feinbatqjxiGf2zN2flTR02
 
Last edited:
  • Like
  • Fire
  • Love
Reactions: 39 users

uiux

Regular
Updated with a new patent from ISL featuring neuromorphic IC:


SUMMARY OF THE INVENTION

The system and method of the invention, as described herein addresses all of the above steps in a novel, integrated fashion. A novel and non-obvious system and method of the claimed invention are described herein. The novel and non-obvious process and method of the invention allows for implementation of compact and efficient deep learning AI solutions to advanced sensor signal processing functions. The process and method of the invention includes the following stages:
(1) a method for generating requisite annotated training data in sufficient quantity to ensure convergence of a DNN;
(2) a method for implementing which converts the resulting DNN onto an SNN architecture which is amenable to efficient neuromorphic (IC) architectures;
(3) a method for implementing the solution onto a neuromorphic IC; and
(4) a statistical method for ensuring reliable performance.
The invention includes both a “Training cycle” as well as a “Live Operation.” The sequence begins with a sensor application being selected, with associated performance specifications. The sensor could be a radar, sonar, lidar, etc. A high-fidelity (hi-fi) sensor model can be used to generate the requisite training data and/or training environment. The sensor model (in this case RFView®) (https://RFView.ISLinc.com is used to generate training data in sufficient quantity to ensure convergence of the DNN neuron weights. Thereafter, a suitable DNN interface is established wherein the raw sensor training cycle data is preprocessed into a format suitable for presentation to a DNN. In this step of the method, the DNN is converted to an SNN. Discussion regarding the conversion from DNN to SNN is found in the paper by M. Davies et al., “Advancing neuromorphic Computing with Loihi: A survey of results and outlook,” Proceedings of the IEEE, vol. 109, no. 5, pp. 911-934, 2021. The SSN is then implemented on a suitable neuromorphic architecture or IC to achieve requisite performance.
 
  • Like
  • Fire
  • Thinking
Reactions: 16 users

Neuromorphia

fact collector
I saw these videos and thought this must be similar to what Information System Labs is doing except they have the advantage of Akida.
ISL.JPG
Air_Force_Research_Laboratory.png
US_Air_Force_Logo_Solid_Colour.svg.png






https://thestockexchange.com.au/threads/brn-discussion-2022.1/post-32882

Cognitive Radar shares similarities to Neuromorphic Enhanced Cognitive Radio from Intellisense Systems in that both can recognize interference and change to alternative frequencies.


 
  • Like
  • Fire
Reactions: 7 users

Neuromorphia

fact collector
We don't know what is going on behind the scenes at Information Systems Laboratories, Inc. (ISL)
But it could be similar 64 gang setup like Blue Raven...

IBM TrueNorth specs equivalent of 64 million neurons and 16 billion synapses of processing power.

Akida specs in a gang of 64 equivalent of 76 million neurons and 64 billion synapses

AFRL, IBM unveil world's largest neuromorphic digital synaptic super computer
Published July 24, 2018



blue raven-.JPG
 
  • Like
  • Fire
Reactions: 4 users

Neuromorphia

fact collector
Q. So how is this information relevant to this Brainchip + AFWERX Agility Prime - A New Era of Aerospace thread?

A. While there is no direct link between Brainchip and Agile Condor...

Agile Condor does have confirmed link to Air Force Research Laboratory.

Air Force Research Laboratory does have confirmed link to Information System Labs.

Information System Labs does have confirmed link to Brainchip.

So I am pointing out where previous ISL Blue Raven IBM TrueNorth ecosystem neuromorphic radar was expected to be first used in unmanned drones.


Abstract: 2015
The Air Force Research Laboratory Information Directorate Advanced Computing and Communications Division is developing a new computing architecture, designed to provide high performance embedded computing (HPEC) pod solution to meet operational and tactical real-time processing intelligence surveillance and reconnaissance (ISR) missions. This newly designed system, Agile Condor, is a scalable and HPEC system based on open industry standards that will increase, far beyond the current state-of-the-art, computational capability within the restrictive size, weight and power constraints of unmanned aircraft systems' external “pod” payloads. The objective with such a system is to explore and develop innovative system solutions to meet future Air Force real-time HPEC; e.g., multi-mission, multi-function ISR processing and exploitation. While the core compute capability can be placed in various environments, our baseline design utilizes a 12-inch diameter flight-certified aeronautics pod that is scalable in length. Agile Condor can be connected to external data sources, or the nose and tail can be made of Radio Frequency (RF) transparent material, enabling the use of various RF sensing technologies within the same aeronautics enclosure. Inside this pod is a lightweight, thermally-efficient industry standard 3U VPX conduction cooled (with unconditioned ambient air) chassis that supports the required board and interface hardware. Agile Condor brings high-performance computing closer to sensors and immediately enables future research and development efforts in neuromorphic computing and autonomous system operations.
1599289521_screenshot_1345.jpg


vpx.JPG

VPX Neuromorphic Hardware component
VPX
defined by Wikipedia https://en.wikipedia.org/wiki/VPX#:~:text=VPX, also known as VITA,a new high speed connector.
VPX computer bus standard - V -VME and P -PCI and X the extents for both buses standards.[citation needed]
The VMEbus International Trade Association (VITA) working group, formed in March 2003, was composed of companies such as ADLINK, Boeing, Curtiss-Wright, Elma Electronic, GE Intelligent Platforms, Kontron, Mercury Computer Systems, and Northrop Grumman, it was designed with defense applications in mind...

VPX Neuromorphic artificial intelligence platform for remotely piloted / autonomous aircraft...

 
Last edited:
  • Like
  • Fire
Reactions: 13 users

Perhaps

Regular
  • Like
  • Fire
Reactions: 6 users

Jasonk

Regular
I think this is an old news . They just published it today. I could be wrong.
Could be right, I did a quick forum search before posting. As I was out and about on my phone and not on the laptop it was only a quick check.

I am sure some will view it and would not have seen it before.
 
  • Like
Reactions: 5 users
Can you delete it, it's a trash news source and a waste of everyone's time
That's the site that keeps on changing the date to make it look like latest news right?
 
  • Like
  • Fire
Reactions: 2 users

TechGirl

Founding Member
  • Like
  • Love
  • Fire
Reactions: 19 users

buena suerte :-)

BOB Bank of Brainchip
  • Like
  • Love
  • Fire
Reactions: 8 users

Perhaps

Regular
This was a great find Perhaps, thanks so much.

I just created a tweet to get it out there.


Thanks. We also been busy yesterday and spread the word on Twitter and Facebook.
 
  • Like
  • Love
  • Fire
Reactions: 12 users
Hadn't come across this before. Not directly related to afwerx but thought I'd put it here as it is related to the Agility Prime project team.

"ISL’s Agility Prime project team submitted an innovative idea to the ATI Urban Air Mobility Innovation Challenge in July 2022. The ISL team was notified of selection to pitch the idea to a select panel of judges at the Defense TechConnect Innovation Summit & Expo in Washington D.C. on September 28th, 2022. The innovative idea was centered around providing neuromorphic radar capabilities to the urban air mobility community for safety and autonomous use.


The ISL team was one of 20 selected companies to pitch their autonomous and urban air mobility ideas to the panel. The top 5 pitches were selected to receive “no strings attached” funding. The pitch was limited to 5 minutes with a 3-minute Q&A after to help the judging panel better understand the technology’s use and project goals. The ISL pitch team received a fair number of questions from the panel, many of which were centered around our neuromorphic training capability and modeling and simulation tool RFview®. ISL’s pitch was selected as one of the winners of the innovation challenge and received an innovation award certificate and an innovation medal."

Has Akida possibly been implemented into ISL's RFview??

@uiux do you by any chance have any new info? Your research has been sorely missed.
 

Attachments

  • Untitled 2.png
    Untitled 2.png
    440.1 KB · Views: 71
  • Untitled 5.png
    Untitled 5.png
    287.8 KB · Views: 75
  • Like
  • Fire
  • Love
Reactions: 17 users

Perhaps

Regular
Hadn't come across this before. Not directly related to afwerx but thought I'd put it here as it is related to the Agility Prime project team.

"ISL’s Agility Prime project team submitted an innovative idea to the ATI Urban Air Mobility Innovation Challenge in July 2022. The ISL team was notified of selection to pitch the idea to a select panel of judges at the Defense TechConnect Innovation Summit & Expo in Washington D.C. on September 28th, 2022. The innovative idea was centered around providing neuromorphic radar capabilities to the urban air mobility community for safety and autonomous use.


The ISL team was one of 20 selected companies to pitch their autonomous and urban air mobility ideas to the panel. The top 5 pitches were selected to receive “no strings attached” funding. The pitch was limited to 5 minutes with a 3-minute Q&A after to help the judging panel better understand the technology’s use and project goals. The ISL pitch team received a fair number of questions from the panel, many of which were centered around our neuromorphic training capability and modeling and simulation tool RFview®. ISL’s pitch was selected as one of the winners of the innovation challenge and received an innovation award certificate and an innovation medal."

Has Akida possibly been implemented into ISL's RFview??

@uiux do you by any chance have any new info? Your research has been sorely missed.
Yes, Akida is in use at the new RFview line for a while now.


Patent from Feb 22, 2022


While this is pretty old news, the story continues.

 
  • Like
  • Love
  • Fire
Reactions: 10 users
Top Bottom