BRN Discussion Ongoing

[Bravo]

NASA+Google “Space Doctor”.

This is pretty interesting.

I wasn't able to locate any public documentation specifically describing how this NASA–Google “Space Doctor” AI assistant actually works.

AI assistants in space operate locally, not over the internet, so you would have to think that this assistant would be an onboard AI model optimized for the edge.

If this space doctor assistant is deployed onboard, it would be a compelling fit IMO for AKida's low-power, low-latency decision-making (e.i., real-time vital sign monitoring or anomaly detection).

NASA and Google Launch Space Doctor AI Assistant​

What happens if you run into medical issues in space and can’t get in touch with Houston? NASA and Google say their new artificial intelligence system might help the next time you’re stuck in Earth’s orbit and need some help.
Dubbed the Crew Medical Officer Digital Assistant – or CMO-DA – the new AI system is a multi-modal interface that uses natural language processing and machine learning to provide real-time analyses of crew health and performance, Google said.
The tool is meant to support a designated crew medical officer or flight surgeon in making medical decisions and maintaining crew health.
“As NASA embarks on a new era of human spaceflight, beginning with the Artemis campaign’s aim to return to the Moon, preparations are underway to ensure crew health and wellness,” says a release from Google. “This includes exploring whether remote care capabilities can deliver detailed diagnoses and treatment options if a physician is not onboard or if real-time communication with Earth-based medical experts is limited.”
CMO-DA could help support human exploration of the Moon, Mars, “and beyond,” according to the release, which said the care the system provides “could become increasingly important as NASA missions venture deeper into space.”
Google said that trials applying AI on a range of medical scenarios showed “promise for reliable diagnoses based on reported symptoms,” and that it will continue testing alongside NASA and medical doctors to further refine the model with the aim of enhancing autonomous crew health and performance.
The AI tool was co-developed by Google Cloud, NASA’s Lunar Command and Control Interoperability project, and NASA’s Human Research Program.
“This tool represents an important milestone for AI technology, medical care, and our continued exploration of the cosmos,” said Google. “Not only does this innovation hold potential for advancing space missions, but it could also benefit people here on Earth by providing early access to quality medical care in remote areas.”

NASA and Google Launch Space Doctor AI Assistant

What happens if you run into medical issues in space and can’t get in touch with Houston? NASA and Google say their new artificial intelligence system might help the next time you’re stuck in Earth’s orbit and need some help.

meritalk.com

OpenAI launched the latest version ChatGPT 5.0 today, so I thought I would test it by asking it about NASA+Google “Space Doctor”.




My Question:
Can you please provide a potential system architecture for the Space Doctor incorporating BrainChip's AKIDA?


ChatGPT 5.0's reponse:
Here’s a speculative system architecture for a “space-doctor” assistant and where BrainChip’s Akida could add real value. I’ve split it into layers so it’s easy to map to flight hardware.

1) Mission goals (what the system must do)​

• Onboard, offline care: triage, checklists, vitals monitoring, procedure guidance without ground link.
• Ultra-low power + high reliability: runs for months/years; graceful under comms blackouts.
• Radiation tolerance & safety: fail-safe behaviors; no single point of failure.

2) High-level stack (two compute paths working together)​

• Cognitive path (LLM/clinical engine): runs medical dialog, protocols, decision support (x86/ARM/RISC-V flight CPU or space-graded AI SoC).
• Reflex path (Akida neuromorphic): event-driven, always-on perception + anomaly detection (sub-watt), feeding signals to the cognitive path only when needed.

3) Where Akida fits (neuromorphic “reflex” services)​

1. Vitals watcher (always-on)
   • Inputs: ECG/PPG, respiration mic, IMU, skin temp.
   • Akida tasks: edge denoising, heartbeat/arrhythmia detection, apnea events, fall detection.
   • Why Akida: event-based spikes → microjoule-level monitoring, near-zero false wakeups.
2. Procedural vision assistant
   • Inputs: head-cam / bay camera (event camera or low-FPS vision).
   • Akida tasks: instrument recognition, hand-pose/step confirmation, sterile-field breach alerts.
   • Output: lightweight “OK/alert/next-step” tokens to the LLM UI.
3. Acoustic anomaly guard
   • Inputs: cabin mics, equipment mics.
   • Akida tasks: detect cough patterns, distress calls, equipment bearing changes.
   • Benefit: sub-watt continuous acoustic sentry without streaming audio to the main CPU.
4. Intent & workload classifier
   • Inputs: glance/head motion, short speech cues, task context.
   • Akida tasks: infer “crew busy/stressed,” gate LLM verbosity, prioritize alerts.
5. Safety watchdog
   • Monitors the cognitive stack; if the big model stalls, Akida triggers safe checklists/alerts.

4) Data flow (simplified)​

Sensors → Akida micro-models (event detectors) → tokens/flags → Cognitive engine (LLM/clinical rules) → Crew UI (audio AR prompts, tablet HUD)
↳ During comms windows: compressed summaries to ground (DTN); otherwise full autonomy.

5) Hardware sketch​

• Compute:
  • Rad-tolerant CPU/SoC (e.g., NOEL-V, Rad-ARM) for OS, UI, LLM inference (quantized).
  • Akida IP/SoC (or space-qualified board) for always-on neuromorphic tasks.
• Sensors: ECG/PPG patch, IMU, event-camera or low-light camera, boundary mics, skin-temp, SpO₂.
• Storage: local model zoo (LLM + Akida SNNs), medical protocols, offline pharmacopoeia.
• Comms: DTN stack; store-and-forward to ground.

6) Fault tolerance & safety​

• Triple-mode alerts: visual + haptic + audio.
• Graceful degradation: if LLM is unavailable, Akida still runs vitals/fall detection + “hard rules” (CPR checklist, EpiPen guidance).
• Radiation strategy: Akida models are small; use TMR/EDAC on weights, periodic checksum & refresh from golden image.
• Human-in-the-loop: confirmations before any high-risk recommendation.

7) Security & privacy​

• Edge-only PII processing.
• No raw audio/video offboard; only encrypted summaries/metrics sent during comms windows.
• Model integrity checks before activation; signed updates only.

8) Two deployment profiles​

• Near-Earth (ISS/Gateway): bigger LLM possible; more frequent syncs; Akida still handles 24/7 sensing cheaply.
• Deep-space (Moon/Mars): heavier reliance on Akida gatekeeping + smaller, quantized LLM; aggressive power caps; longer offline windows.

9) MVP build plan (practical steps)​

1. Sim lab prototype (Earth):
   • Sensor kit + Akida dev board + SBC (e.g., Jetson/ARM) with a small local LLM (e.g., 3–7B quantized).
   • Implement 3 Akida micro-models: arrhythmia, fall detection, instrument recognition.
2. Edge-first orchestration:
   • Only wake the LLM when Akida raises a “meaningful event.”
3. Latency & power budget:
   • Target: Akida services <300 mW continuous; LLM duty-cycled to <10% uptime.
4. Ops drills:
   • Run scripted med scenarios (burns, lacerations, chest pain, EVA fatigue), evaluate false-alarm rate and response timing.
5. Hardening path:
   • Port to rad-tolerant CPU; add EDAC/TMR; test with injected bit-flips and sensor dropouts.

10) Why this helps the mission​

• Power: continuous monitoring without draining batteries.
• Responsiveness: sub-100 ms reflexes for critical events.
• Bandwidth: local understanding; only brief summaries to Earth.
• Reliability: Akida as a low-power safety net even if the “big brain” naps.

 

[keyeat]

I’ll just go ahead and say it:

Today feels like a perfect day for a price-sensitive announcement – nothing exaggerated, just something realistic that puts recurring revenue on the horizon.

Not a one-off payment, but a long-term agreement that contributes meaningfully to the company’s sustainable growth over time.

Just one such signal would already go a long way in restoring confidence and making a lot of us pretty happy.

 

[Deleted member 3781]

 

[Diogenese]

I see they are conducting casting call for the sequel "Kiddy-Fiddler on the Roof".

NASA+Google “Space Doctor”.

This is pretty interesting.

I wasn't able to locate any public documentation specifically describing how this NASA–Google “Space Doctor” AI assistant actually works.

AI assistants in space operate locally, not over the internet, so you would have to think that this assistant would be an onboard AI model optimized for the edge.

If this space doctor assistant is deployed onboard, it would be a compelling fit IMO for AKida's low-power, low-latency decision-making (e.i., real-time vital sign monitoring or anomaly detection).

NASA and Google Launch Space Doctor AI Assistant​

What happens if you run into medical issues in space and can’t get in touch with Houston? NASA and Google say their new artificial intelligence system might help the next time you’re stuck in Earth’s orbit and need some help.
Dubbed the Crew Medical Officer Digital Assistant – or CMO-DA – the new AI system is a multi-modal interface that uses natural language processing and machine learning to provide real-time analyses of crew health and performance, Google said.
The tool is meant to support a designated crew medical officer or flight surgeon in making medical decisions and maintaining crew health.
“As NASA embarks on a new era of human spaceflight, beginning with the Artemis campaign’s aim to return to the Moon, preparations are underway to ensure crew health and wellness,” says a release from Google. “This includes exploring whether remote care capabilities can deliver detailed diagnoses and treatment options if a physician is not onboard or if real-time communication with Earth-based medical experts is limited.”
CMO-DA could help support human exploration of the Moon, Mars, “and beyond,” according to the release, which said the care the system provides “could become increasingly important as NASA missions venture deeper into space.”
Google said that trials applying AI on a range of medical scenarios showed “promise for reliable diagnoses based on reported symptoms,” and that it will continue testing alongside NASA and medical doctors to further refine the model with the aim of enhancing autonomous crew health and performance.
The AI tool was co-developed by Google Cloud, NASA’s Lunar Command and Control Interoperability project, and NASA’s Human Research Program.
“This tool represents an important milestone for AI technology, medical care, and our continued exploration of the cosmos,” said Google. “Not only does this innovation hold potential for advancing space missions, but it could also benefit people here on Earth by providing early access to quality medical care in remote areas.”

NASA and Google Launch Space Doctor AI Assistant

What happens if you run into medical issues in space and can’t get in touch with Houston? NASA and Google say their new artificial intelligence system might help the next time you’re stuck in Earth’s orbit and need some help.

meritalk.com

Hi Bravo,

AkidaNet/TENN Automatic Speech Recognition model and AkidaNet/LLM + RAG would be useful in NLP for health analysis.

https://brainchip.com/ready-to-use-akida-neural-network-models/

AkidaNet/TENN Automatic Speech Recognition Model​

Our TENNs model approach is applied to Automatic Speech Recognition for compact accurate voice to text applications.

AkidaNet/TENN Large Language Model (LLM+RAG)​

Our TENNs model approach is applied to an LLM model with Retrieval Augmented Generation to provide intelligent access to documentation for those end use cases looking to embed an LLM for their products user interface.

RAG permits the use of very large databases to be store information to be loaded into Akida in blocks relevant to selected topics.

TENN models can be loaded into some of the NPUs (NPEs) of nodes as required. TENN models are very compact, but I don't know the conditions and limitations for loading them into Akida. If I had a dollar ... (Hint: goto Diogenese GoFundMe).

 

[Diogenese]

My Question:
In what ways would the neuromorphic Akida “Space Doctor” system differ from traditional approaches?

ChatGPT 5.0's respone:
The neuromorphic Akida “Space Doctor” system would differ from a traditional CPU/GPU-based approach in some really important ways — and in a space environment, those differences become mission-critical.

Here’s the breakdown:

1. Processing philosophy — events vs. frames​

Traditional processors

• Work in frame-based mode — constantly process entire streams of data at fixed intervals (e.g., every camera frame, every ECG reading).
• Even if nothing changes in the input, they still burn the same compute cycles and power.
• Good for heavy numerical tasks but wasteful for long periods of “no activity.”

Akida neuromorphic processor

• Works in event-driven mode — only processes when something changes (spike in heart rate, hand movement in the fridge, sudden camera motion, new sound).
• If nothing changes, power draw is near-zero.
• Perfect for long-duration idle-but-listening health monitoring in space.

---

2. Power & thermal management​

Traditional processors

• Continuous high-power draw for AI inference (LLMs, CNNs, signal processing).
• On the ISS or deep space, every watt matters, and waste heat is hard to radiate away.
• You’d need more batteries, cooling systems, and scheduling to avoid overheating.

Akida neuromorphic

• Can run always-on sensing at hundreds of microwatts to a few milliwatts.
• Frees up the main CPU/GPU to sleep most of the time and only wake on Akida’s signal.
• Less heat generated → easier thermal management in microgravity.

---

3. Latency​

Traditional processors

• A “big” AI model might have 200–500 ms delay before producing an inference, especially if it needs to boot from idle.
• That’s fine for chatting, but not for “astronaut collapsed” scenarios.

Akida neuromorphic

• Sub-10 ms reaction for known patterns (fall detection, arrhythmia, abnormal breathing).
• Immediate trigger to wake the main medical assistant model.

---

4. Radiation resilience​

Traditional processors

• Complex DRAM/GPU architectures → more susceptible to single-event upsets (SEUs) from cosmic radiation.
• Needs heavier error correction and redundancy → more mass.

Akida neuromorphic

• Smaller memory footprint, simpler weight storage → easier to harden and triple-modular-redundancy (TMR).
• Small models mean it’s easier to store multiple golden copies to refresh after bit flips.

---

5. Autonomy & communication load​

Traditional processors

• Without optimization, they might require sending large raw datasets to Earth for analysis.
• Deep-space missions (Mars) can have 20+ min one-way comms delays — not suitable for urgent triage.

Akida neuromorphic

• Runs pre-trained detection locally → sends only compressed “event summaries” to main CPU/LLM.
• Cuts down on both comms bandwidth and storage requirements.
• Enables true edge autonomy when comms are down or delayed.

---

6. AI model footprint​

Traditional processors

• Often require hundreds of MB or even GB of weights for AI models.
• Onboard storage and loading times become significant.
• Updates in space are slower and riskier.

Akida neuromorphic

• Uses ultra-compact spiking neural network (SNN) models — often 1–10 MB for a detection task.
• Faster to load, update, and validate.
• Can carry dozens of task-specific models in memory (e.g., different medical conditions) and swap on demand.

---

7. Mission risk profile​

Traditional-only system

• If main CPU/GPU locks up or fails, all AI functionality is gone.
• Crew has to revert to manual procedures until system reboot.

Akida + traditional hybrid

• Akida operates independently as a “medical watchdog” — still running core health monitoring even if the big system crashes.
• Can even trigger an emergency call or alert without CPU intervention.

---

Bottom line:
In space, idle listening, ultra-low power, ultra-low latency, and radiation resilience are more important than raw TOPS.
Akida’s neuromorphic design means:

• It “listens” almost for free and only wakes the big systems when necessary.
• It’s far less fragile in radiation-heavy environments.
• It enables autonomous, safe operation without constant ground support.

That’s why NASA-style projects like the “Space Doctor” could lean on neuromorphic processors — because in deep space, the less you waste and the faster you react, the longer you survive.

https://www.bing.com/videos/rivervi...5161FD6AF48CC178BC3F5161FD6AF48CC&FORM=VAMGZC

 

[Deleted member 3781]

time to just dive into the weekend!
See you next week guys!

 

[HopalongPetrovski]

Just popped over to the crapper cause it's so bloody boring atm and snagged this typical titbit from their convo. Enjoy!

 

[Boab]

Proposed new data centre vetoed by council due to water and energy concerns. Good for us

Arizona city defeats massive data center project over water, energy concerns

Tucson stops work on 290-acre Project Blue data center north of Pima County Fairgrounds due to community concerns about water use and energy consumption.

www.foxbusiness.com

 

[LongTermInvestor]

time to just dive into the weekend!
See you next week guys!

View attachment 89407

In my opinion, BrainChip is performing well this week - it’s closing well above $0.20 despite several attempts by shorters to push it below that level. Promising times ahead!

 

[manny100]

https://www.bing.com/videos/rivervi...5161FD6AF48CC178BC3F5161FD6AF48CC&FORM=VAMGZC

I would not be surprised to see a number of companies trialing with AKIDA1000 chips test in parallel with Gen 2 on AKIDA cloud.
Efficiency and performance gains to good to ignore. Those really intent on adopting AKIDA will get credit towards hardware purchases.
Arquimea are on to it quick smart. Cannot help suspecting that apart from lifesaving they are testing for their defense products.
" Hélder Rodríguez López, Embedded Software Research Engineer at Arquimea Research said, “The Akida Cloud’s ability to provide us advanced access to the latest features of Akida and easily test our neuromorphic model innovations remotely is a real advantage for progressing our advanced model development programs.”"
I can see companies like Tata parallel testing. Bascom Hunter? etc.
This is way more than just a tech upgrade this is a real pivot and push for Gen 2 adoption.

BrainChip Launches Akida Cloud for Instant Neuromorphic Access

BrainChip launches Akida Cloud, providing instant access to the latest neuromorphic technology for developers and edge AI innovators.

brainchip.com

 

[Diogenese]

I would not be surprised to see a number of companies trialing with AKIDA1000 chips test in parallel with Gen 2 on AKIDA cloud.
Efficiency and performance gains to good to ignore. Those really intent on adopting AKIDA will get credit towards hardware purchases.
Arquimea are on to it quick smart. Cannot help suspecting that apart from lifesaving they are testing for their defense products.
" Hélder Rodríguez López, Embedded Software Research Engineer at Arquimea Research said, “The Akida Cloud’s ability to provide us advanced access to the latest features of Akida and easily test our neuromorphic model innovations remotely is a real advantage for progressing our advanced model development programs.”"
I can see companies like Tata parallel. Bascom Hunter? etc.

BrainChip Launches Akida Cloud for Instant Neuromorphic Access

BrainChip launches Akida Cloud, providing instant access to the latest neuromorphic technology for developers and edge AI innovators.

brainchip.com

I have the exact same thought about Arquimea and defence.

They can do field trials on their sharkwatch drone, but it is clear that they are in the queue for the Akida cloud with a lot of other early adopters.

There is a great urgency to develop autonomous drones. I can see them having a drone with a km of optical fibre trailing out the back
for target designation, or maybe even laser comms, to avoid electronic countermeasures.

I wonder what cybersecurity measures Akida cloud has, because it will all be commercially sensitive and above. There will need to be firewalls between different customer data.

 

[TheDrooben]

While Larry agrees with all the frustration about the lack of ASX announcements and the effect on the SP as a result and also the shorters doing their faecal trades...Larry has never sold and keeps on buying as he did again today....so thank you to everyone who is keeping the SP at this level.....Larry loves you

Really Happy as Larry

 

[IloveLamp]

@Neuromorphia i was doing some back research on o.h.b hellas, and wow......what a great post

Thread 'The Growing Brainchip Akida Ecosystem' https://thestockexchange.com.au/threads/the-growing-brainchip-akida-ecosystem.63596/

OHB Hellas onboard satellite fire detection solution | OHB Hellas

🚀 Introducing Our Onboard Satellite Fire Detection Algorithm 🔥 We’re excited to share our progress in satellite technology that enhances early fire detection and monitoring. Our new onboard algorithm quickly identifies signs of fire from space, enabling faster response times and potentially...

www.linkedin.com

 

[Diogenese]

Hi @manny100 ,

I guess the fact that the Akida 2 FPGA has only 6 nodes (24 NPUs) is due to the limitation of FPGA technology, in that the FPGA chip only has sufficient circuit elements (logic gates, memory, ...) to build 24 NPUs.

Did you happen to notice whether the Akida 2 cloud FPGA includes VIT? The original announcement from a couple of years ago mentioned that VIT would only be available with the top of the range version, but a lot of water has flowed under the bridge since than.

The Akida 2 IP allows for up to 128 nodes (512 NPUs):

https://www.hackster.io/news/brainc...-vision-transformer-acceleration-5fc2d2db9d65

The company has confirmed that it will be licensing the Akida IP in three product classes: Akida-E will focus on high energy efficiency with a view to being embedded alongside, or as close as possible, to sensors and offering up to 200 giga-operations per second (GOPS) across one to four nodes; Akida-S will be for integration into microcontroller units and systems-on-chip (SoCs), hitting up to 1 tera-operations per second (TOPS) across two to eight nodes; and Akida-P will target the mid- to high-end, and will be the only tier to offer the optional vision transformer acceleration, scaling between eight and 128 nodes with a total performance of up to 50 TOPS.

 

[Frangipani]

BrainChip's Akida Cloud: A Game Changer for Edge AI Developers | BrainChip posted on the topic | LinkedIn

Our latest blog takes a deep dive into the advantages of Akida Cloud! BrainChip now offers instant, hardware-free access to the Akida 2 neuromorphic platform right in the cloud. With Akida Cloud, you can: · Test and benchmark low-power AI models · Run real-time inferences with live data ·...

www.linkedin.com

Unlock Your AI Potential: A Deep Dive into BrainChip's Akida™ Cloud

Unlock Your AI Potential: A Deep Dive into BrainChip's Akida™ Cloud In the rapidly

brainchip.com

Unlock Your AI Potential: A Deep Dive into BrainChip’sAkida™ Cloud​

In the rapidly evolving landscape of Artificial Intelligence, having immediate access to the most powerful and efficient tools is paramount. BrainChip is revolutionizing AI development with its innovative Akida Cloud, a platform designed to provide developers with seamless access to the latest neuromorphic processor technology. This cloud initiative focuses on significantly shortening development cycles and empowering creators to bring their AI visions to life faster than ever before.

The core mission of the Akida Cloud is to remove barriers and accelerate innovation. By providing a direct line to the latest Akida technology, developers can program and execute neural networks for immediate results, streamlining the path from concept to product.

​

The Strategic Advantage of Akida Cloud​

Leveraging the Akida Cloud offers a multitude of strategic benefits for developers, partners, and businesses alike:

• Accelerated Prototyping: Dive into Akida’s most advanced features and begin prototyping instantly, without waiting for physical hardware.
• Continuous Innovation: The platform is extensible, meaning as new versions and configurations of Akida are available, they become download and run options on the Akida Cloud.
• Empowering Partnerships:Partners can effectively demonstrate working models and prototypes to customers, enabling parallel development workflows before hardware is even on-site.
• Flexible and Accessible: A versatile business model includes options for limited free access and usage-based pricing, with credits applicable to future hardware purchases. An on-premises Akida FPGA Developer Platform is also available for dedicated use.

​

How to Get Access​

• Getting started with the Akida Cloud and its “limited free access” is a straightforward process. To begin your journey, you will need to formally request access through the BrainChip website. You can navigate to the “Developer Hub” or the Akida Cloud information page to get access. You will be prompted to provide your contact information and details about your project or interest in the technology. Once submitted, the BrainChip team will respond with the next steps to get you connected to the platform.

​

Evaluating the Power of Akida: A Step-by-Step Guide​

The true power of the Akida Cloud lies in its hands-on evaluation capabilities. The platform offers a distinct advantage for R&D teams, allowing them to remotely test and refine advanced neuromorphic models. Here is how it works:

• Seamless Connection: Getting connected is straightforward. By adding a simple configuration to your local SSH file, you can create a secure and persistent “tunnel” to the Akida Cloud server. This works seamlessly across Windows, macOS, and Linux environments.
• Launch Your Workspace: Once connected, a single command initiates Jupyter Labs. This launches a pre-configured, browser-based environment loaded with all the necessary tools and Akida-specific libraries.
• Explore and Experiment: Within Jupyter Labs, you will find a comprehensive library of example notebooks. These examples are your gateway to understanding Akida’s capabilities. You can explore a range of applications, from image classification to complex object detection, and run them directly on the second-generation Akida architecture.
• Real-Time Data Streaming: A key innovation is the ability to stream your own real-time data to the Akida Cloud for inferencing from your local machine. The results can be streamed back to your local machine, providing immediate feedback. This full loop data acquisition, processing and display is demonstrated in applications like eye-tracking, where this rapid feedback loop allows for quick iteration and training, dramatically improving model accuracy under real-world conditions.

​

The Next Generation of Neuromorphic Power​

The Akida Cloud today runs on the second-generation Akida platform, which delivers a monumental leap in performance—offering up to four times the performance and efficiencyof the first generation. The architecture is also finely tuned to support state-space based Temporal Event-Based Neural Nets (TENNs), making it exceptionally proficient at processing raw, time-sensitive data from video, audio, and other sensors. This advanced capability simplifies model implementation, reduces model size, and speeds up development for a new generation of intelligent edge devices.

​

A Glimpse into the Future​

The Akida Cloud is not just about today’s technology; it is a platform for the future. BrainChip’s roadmap includes making future versions of Akida available through the cloud, providing access to different node configurations, enhanced memory, and significant architectural improvements. This will allow for custom configurations that enable customers to perfectly match their unique requirements for integration into an IC. Looking ahead, the Akida Cloud platform will support next-generation workloads, with future generations of Akida designed to manage the demands of future AI applications.

​

About BrainChip​

BrainChip is the worldwide leader in creating Edge AI on-chip processing and learning solutions. Its pioneering Akida™ processor is a fully digital, event-based AI engine that mimics the principles of the human brain. By analyzing only, the essential sensor inputs right at the point of acquisition, Akida delivers unmatched efficiency, precision, and energy economy. BrainChip is dedicated to advancing the future of intelligent computing, bringing AI closer to the sensor and closer to real-time.

 

[Frangipani]

Frontgrade Technologies, the US parent company of our Swedish partner Frontgrade Gaisler, is sponsoring an upcoming webinar titled “Golden Dome Architecture: Accelerating Multi-Domain Defense with FPGA Technology”.

Frontgrade Technologies will be represented by three of the five roundtable participants, including their CTO Lorne Graves:

Golden Dome Architecture: Accelerating Multi-Domain Defense with FPGA Technology

As the threat landscape shifts toward faster, more agile strike capabilities, so too must our defensive architectures. From traditional ballistic missiles to hypersonic glide vehicles and unmanned aerial systems (UAS), the spectrum of challenges is broad and intensifying. The Golden Dome...

resources.embeddedcomputing.com

 

[Deleted member 3781]

While Larry agrees with all the frustration about the lack of ASX announcements and the effect on the SP as a result and also the shorters doing their faecal trades...Larry has never sold and keeps on buying as he did again today....so thank you to everyone who is keeping the SP at this level.....Larry loves you

View attachment 89417

Really Happy as Larry

While 7 agrees with you about all the frustration caused by the lack of ASX announcements and the resulting effect on the SP …as well as the shorters doing their dirty trades… I also have never sold and keep on buying, as I did again two days ago.
But I still don’t want to thank those who are keeping the SP at this level… and that’s why I hate them!

 

[Frangipani]

The EDGX team recently presented their EDGX DPU to the Belgian Federal Minister for Public Enterprises, Civil Service, State Building Management, Digitalization and Science Policy & her entourage, which also included a Programme Manager from the Belgian Science Policy Office (BELSPO):

#sciencepolicy #ai #newspace #earthobservation #satcom #ssa #spaceinnovation #belspo #belgium #europe #obdp | EDGX

🇧🇪 We had the honour of welcoming Federal Minister Vanessa Matz responsible for Public Enterprises, Civil Service, State Building Management, Digitalization and #SciencePolicy, along with Matthias P. from BELSPO - Belgian Science Policy Office to the EDGX headquarters 🚀 It was a great...

www.linkedin.com

View attachment 84902

View attachment 84905


By the looks, EDGX are counting down to a launch in Q1/2026:

View attachment 84903


As LinkedIn doesn’t provide the exact date of the post, I checked out the Minister’s Instagram profile for any clues - et voilà!

Besides finding out that her visit in Ghent must have been on 16 April itself or a couple of days earlier at most (although the lack of time adverbs such as ‘yesterday‘ or ‘last week’ suggest it was likely a same-day post), I also spotted a BrainChip sticker at the EDGX headquarters in Ghent.

So the launch must be scheduled for no later than 1 March 2026, then.

View attachment 84904

Our Belgian space-tech partner EDGX just unveiled their new logo with the catchphrase “Sky-high Intelligence” at SmallSat Europe 2025 in Amsterdam, where they’re showcasing their EDGX DPU that was “designed to enable real-time in-orbit edge computing for next-gen missions in Earth Observation, Satcom and In-Orbit Servicing”. It runs on an NVIDIA Jetson Orin NX and comes with an optional neuromorphic Akida module for ultra-low-power applications:

#edgx #smallsateurope #aiinspace #onboardprocessing #edgeai #satcom #earthobservation #newspace #nvidia #orin #spacehardware #inorbitcompute | EDGX

🚀 Heading off at SmallSat Europe 2025! 🇪🇺 EDGX will be exhibiting at SmallSat Europe next week in Amsterdam! Join us at our booth where we will showcase our AI-based data processing unit – designed to enable real-time in-orbit edge computing for next-gen missions in Earth Observation, Satcom and...

www.linkedin.com

View attachment 85680

#edgx #smallsateurope #amsterdam #aiinspace #edgecomputing #spacetech #nvidiaorin #newbranding #earthobservation #satcom #ssa #inorbitai #newspace | EDGX

🚀 Live from SmallSat Europe in Amsterdam! We’re on-site with our brand-new EDGX booth and for the first time, we’re revealing our new logo and visual identity to the world! 🔥 👀 Swing by if you’re around, we’re showing: 🚀 High-performance onboard AI with NVIDIA Orin 🚀 Real-world use cases for...

www.linkedin.com

View attachment 85672

View attachment 85679

They also appear to have freshened up their website (which still has the old logo, though): https://www.edgx.space/

View attachment 85676 View attachment 85677 View attachment 85678

The EDGX team will be presenting their NVIDIA Jetson Orin-based DPU designed for LEO (Low Earth Orbit) missions, which they have now officially named Sterna, at SmallSat (Small Satellite Conference) in Salt Lake City from 10-13 August. The EDGX DPU aka Sterna is being offered with an optional neuromorphic BrainChip Akida add-on (cf. https://satsearch.co/products/edgx-dpu), although strangely this option appears not to be mentioned anywhere on the revamped EDGX website so far.

#smallsat2025 #edgx #spacetech #satelliteai #obdp #inorbitprocessing #smallsatconference #sternadpu | EDGX

🚀 EDGX at Small Satellite Conference 2025 🚀 We’ll be present at this year’s Small Satellite Conference (SmallSat) in Salt Lake City. If you're attending and exploring how to push the boundaries of onboard data processing, let’s connect. We'll bring along the EDGX Sterna DPU, our...

www.linkedin.com

I took the following screenshots exactly a week ago, on 2 August. When I just revisited https://www.edgx.space/, the website shows up largely as black, so maybe they are currently working on it in preparation for SmallSat, which starts on Sunday.

Today’s countdown to the launch of what I presume to be the first of the three planned missions should accordingly read 193 days (instead of 200 days as per screenshot), which would give us 18 February 2026 as the scheduled launch date for Sterna first acquiring flight heritage…

 

[Frangipani]

Speaking of EDGX - they just closed a €2.3 million funding round:

EDGX sluit een financieringsronde van € 2,3 miljoen af om AI-computing aan boord van satellieten te stimuleren | PMV

In de categorie beloftevolle ondernemers zoomt De Tijd vandaag terecht in op Nick Destrycker en Wouter Benoot, de oprichters van de Gentse ruimtevaartstart-up EDGX. EDGX bouwt AI-computersystemen die aan boord van satellieten zeer veel data kunnen verwerken vooraleer naar de aarde te sturen en...

www.linkedin.com

EDGX sluit een financieringsronde van € 2,3 miljoen af om AI-computing aan boord van satellieten te stimuleren

www.pmv.eu

EDGX sluit een financieringsronde van € 2,3 miljoen af om AI-computing aan boord van satellieten te stimuleren​

8 aug 2025

• EQUITY INVESTMENTS
• RISICOKAPITAAL

De financiering zal de missie van EDGX versnellen om ’s werelds snelste AI-aangedreven edge-computers voor satellietconstellaties te leveren, waardoor snelle en efficiënte gegevensverwerking vanuit de ruimte mogelijk wordt.

De Belgische ruimtevaartstartup EDGX heeft een seed-financieringsronde van € 2,3 miljoen afgesloten om de commercialisering te versnellen van EDGX Sterna, de volgende generatie edge AI-computer voor satellieten.

De startup heeft ook een overeenkomst gesloten met een satellietoperator ter waarde van € 1,1 miljoen en kan nu al plannen aankondigen voor een demonstratie in de ruimte tijdens een SpaceX Falcon 9-missie in februari 2026.
De financieringsronde werd mee geleid door het imec.istart future fund, met deelname van het Flanders Future Tech Fund, dat wordt beheerd door de Vlaamse investeringsmaatschappij PMV. EDGX heeft ook verdere financiering aangetrokken van bestaande investeerder imec.istart, Europa’s best gerangschikte universiteitsgebonden accelerator.

De EDGX Sterna-computer is een krachtige gegevensverwerkingseenheid (DPU) die wordt aangedreven door NVIDIA-technologie. Deze biedt de rekenkracht en AI-versnelling die nodig zijn om snel en efficient data te verwerken aanboord van sattelieten. Dit maakt een einde aan de traditionele bottleneck waarbij enorme hoeveelheden ruwe gegevens naar de aarde moeten worden gestuurd voor verwerking, waardoor satellietoperatoren snellere, efficiëntere en datagestuurde diensten kunnen leveren.

De Sterna-computer van EDGX wordt aangedreven door hun SpaceFeather-softwarestack, die is gebouwd voor autonome, veerkrachtige en upgradebare satellietoperaties. Deze omvat een ruimtebestendig Linux-besturingssysteem met volledige traceerbaarheid, een speciaal toezichtsysteem voor autonome gezondheidsmonitoring, detectie en herstel van stralingsfouten, en een applicatieframework in een baan om de aarde voor het implementeren van nieuwe mogelijkheden na de lancering. Samen maken SpaceFeather en Sterna slimmere, flexibelere missies mogelijk met minder downtime, lagere kosten en snellere oplevering van data aan de eindgebruikers.

De techniek en het ontwerp van EDGX combineren commerciële AI-versnelling met betrouwbaarheid van ruimtevaartkwaliteit, waardoor exploitanten van satellietconstellaties kunnen beschikken over een niveau van rekenkracht aan boord dat voordien niet realiseerbaar was. Klanten gebruiken de Sterna DPU van EDGX en de bijbehorende SpaceFeather-software voor verschillende toepassingen.

Voor spectrum monitoring maakt Sterna krachtige verwerking in de ruimte mogelijk om radiosignalen te lokaliseren en te classificeren, en om dynamische spectrumkaarten te genereren. Dit is een essentiële capaciteit die satellietoperatoren helpt om in real-time te begrijpen hoe frequenties worden gebruikt, interferentie te vermijden en bandbreedte efficiënter toe te wijzen om optimale communicatiediensten te leveren.

Op het gebied van aardobservatie ondersteunt Sterna intelligente surveillance en verkenning (ISR) door rechtstreeks aan boord hoge-resolutiebeelden te analyseren. Dit betekent dat satellieten objecten zoals schepen, voertuigen of infrastructuur onmiddellijk kunnen detecteren en markeren, en kunnen reageren op tijdgevoelige gebeurtenissen zoals overstromingen, bosbranden of aardbevingen. Het resultaat: snellere beslissingen, efficiëntere missies en levensreddende informatie die passieve observatie omzet in realtime situationeel bewustzijn.

Sterna ondersteunt ook 5G en 6G vanuit de ruimte. Door de verwerkingscapaciteiten van basisstations naar de ruimte te verplaatsen kunnen satellieten rechtstreeks deelnemen aan mobiele netwerken van de volgende generatie. Dit maakt de weg vrij voor naadloze directe connectiviteit met apparaten en levert supersnel internet aan afgelegen, achtergestelde of door rampen getroffen gebieden waar traditionele infrastructuur tekortschiet.

Met een volledig lanceringsmanifest, gegarandeerde commerciële contracten en onze eerste missie aanboord van een Falcon 9 rakket van SpaceX, stelt deze financiering ons in staat om op te schalen om te voldoen aan de vraag naar realtime informatie vanuit de ruimte.
NICK DESTRYCKER, OPRICHTER EN CEO EDGX

Naast de demonstratie in een baan om de aarde in februari staan er al twee verdere vluchten gepland voor 2026 en EDGX positioneert zich snel als leider op het gebied van AI ruimte-infrastructuur.

In een reactie op het nieuws zei Nick Destrycker, oprichter en CEO: “Klanten wachten niet op vluchtvalidatie, ze tekenen nu al. Met een volledig lanceringsmanifest, gegarandeerde commerciële contracten en onze eerste missie aanboord van een Falcon 9 rakket van SpaceX, stelt deze financiering ons in staat om op te schalen om te voldoen aan de vraag naar realtime informatie vanuit de ruimte.”

Wouter Benoot, oprichter en CTO van EDGX, zei: “Van nul naar honderd gaan, all-in, bij een ruimtevaartstartup is ambitieus. Die mentaliteit meenemen in de ontwikkeling van Sterna betekende nieuwe uitdagingen, voortdurend leren, maar ook echte vooruitgang. Wat het laat slagen is het team. Elke ingenieur brengt nieuwe ideeën, een drang om de ruimte te begrijpen en een passie om het te realiseren. We bouwen een subsysteem dat de volgende generatie satellieten aandrijft.”

Roald Borré, hoofd Venture Capital en lid van het uitvoerend comité bij PMV, zei: “Deze financieringsronde stelt ons in staat om het sterke team van EDGX te ondersteunen bij het op de markt brengen en verder ontwikkelen van veelbelovende Vlaamse technologie. EDGX is een van de weinige Europese spelers die een product aanbiedt dat krachtig, toegankelijk en robuust is, waardoor het unieke voordelen biedt in de snelgroeiende markt voor edge computing in de ruimte, niet in het minst wat betreft het versterken van de technologische positie van Europa in een strategische sector als ruimtevaart.”

Kris Vandenberk, managing partner bij imec.istart future fund, zei: “EDGX vertegenwoordigt precies het soort transformatieve infrastructuur waarnaar we op zoek zijn. De ruimtevaartindustrie kampt met een fundamentele bottleneck: we genereren enorme hoeveelheden data in een baan om de aarde, maar gebruiken nog steeds verouderde ‘store and forward’-architecturen. EDGX lost dit op door AI-aangedreven edge computing rechtstreeks in de ruimte te brengen, waardoor satellieten gegevens in realtime kunnen analyseren en erop kunnen reageren in plaats van te wachten op verwerking op de grond.”

Over EDGX

EDGX is een Belgisch ruimtevaartbedrijf met als missie ’s werelds snelste edge computers voor satellieten te leveren. Het vlaggenschipproduct, EDGX Sterna, is een krachtige AI-gegevensverwerkingseenheid op basis van de NVIDIA Jetson Orin, die realtime gegevensverwerking aan boord in een baan om de aarde mogelijk maakt. EDGX bedient de markten voor satellietcommunicatie/telecommunicatie, aardobservatie en in-orbit servicing in commerciële, overheids- en defensiesegmenten, met een bijzondere focus op het mogelijk maken van AI en krachtige gegevensverwerking op schaal in satellietconstellaties. EDGX is opgericht in 2023, heeft zijn hoofdkantoor in Gent, België, en zal in februari 2026 zijn eerste demonstratie in een baan om de aarde lanceren met een SpaceX Falcon 9.

www.edgx.space

press@edgx.space

---

Translation into English by Google Translator:


EDGX closes €2.3 million funding round to boost AI computing onboard satellites

August 8, 2025
EQUITY INVESTMENTS
VENTURE CAPITAL

The funding will accelerate EDGX's mission to deliver the world's fastest AI-powered edge computers for satellite constellations, enabling fast and efficient data processing from space.

Belgian space startup EDGX has closed a €2.3 million seed funding round to accelerate the commercialization of EDGX Sterna, its next-generation edge AI computer for satellites.

The startup has also signed a €1.1 million deal with a satellite operator and can already announce plans for an in-space demonstration during a SpaceX Falcon 9 mission in February 2026.

The funding round was co-led by the imec.istart future fund, with participation from the Flanders Future Tech Fund, which is managed by the Flemish investment company PMV. EDGX has also attracted further funding from existing investor imec.istart, Europe’s top-ranked university-based accelerator.

The EDGX Sterna computer is a high-performance data processing unit (DPU) powered by NVIDIA technology. It provides the computing power and AI acceleration needed to quickly and efficiently process data onboard satellites. This eliminates the traditional bottleneck of sending massive amounts of raw data back to Earth for processing, enabling satellite operators to deliver faster, more efficient, and data-driven services.

EDGX's Sterna computer is powered by its SpaceFeather software stack, built for autonomous, resilient, and upgradeable satellite operations. This includes a space-hardened Linux operating system with full traceability, a dedicated monitoring system for autonomous health monitoring, radiation fault detection and recovery, and an in-orbit application framework for implementing new capabilities after launch. Together, SpaceFeather and Sterna enable smarter, more flexible missions with less downtime, lower costs, and faster data delivery to end users.

EDGX's engineering and design combine commercial AI acceleration with spacecraft-grade reliability, enabling satellite constellation operators to access previously unattainable levels of onboard computing power. Customers are using EDGX's Sterna DPU and its associated SpaceFeather software for a variety of applications.

For spectrum monitoring, Sterna enables powerful space-based processing to locate and classify radio signals and generate dynamic spectrum maps. This is a critical capability that helps satellite operators understand in real time how frequencies are being used, avoid interference, and allocate bandwidth more efficiently to deliver optimal communication services.

In Earth observation, Sterna supports intelligent surveillance and reconnaissance (ISR) by analyzing high-resolution imagery directly on board. This means satellites can immediately detect and tag objects such as ships, vehicles, or infrastructure, and respond to time-sensitive events like floods, wildfires, or earthquakes. The result: faster decisions, more efficient missions, and life-saving information that transforms passive observation into real-time situational awareness.

Sterna also supports 5G and 6G from space. By moving base station processing capabilities into space, satellites can participate directly in next-generation mobile networks. This paves the way for seamless direct connectivity to devices, delivering high-speed internet to remote, underserved or disaster-affected areas where traditional infrastructure falls short.

“With a full launch manifest, secured commercial contracts, and our first mission aboard a SpaceX Falcon 9 rocket, this funding allows us to scale to meet the demand for real-time information from space.”
NICK DESTRYCKER, FOUNDER AND CEO EDGX

In addition to the orbital demonstration in February, two further flights are already planned for 2026, and EDGX is quickly positioning itself as a leader in AI space infrastructure.

Commenting on the news, Nick Destrycker, founder and CEO, said: “Customers aren’t waiting for flight validation; they’re signing now. With a full launch manifest, secured commercial contracts, and our first mission aboard a SpaceX Falcon 9 rocket, this funding allows us to scale to meet the demand for real-time information from space.”

Wouter Benoot, founder and CTO of EDGX, said: “Going from zero to 100, all-in, at a space startup is ambitious. Bringing that mindset to Sterna’s development meant new challenges, continuous learning, but also real progress. What makes it work is the team. Each engineer brings new ideas, a drive to understand space, and a passion to make it a reality. We’re building a subsystem that will power the next generation of satellites.”

Borré, Head of Venture Capital and Member of the Executive Committee at PMV, said: “This funding round enables us to support EDGX’s strong team in bringing promising Flemish technology to market and further developing it. EDGX is one of the few European players offering a product that is powerful, accessible, and robust, giving it unique advantages in the rapidly growing space edge computing market, not least in terms of strengthening Europe’s technological position in a strategic sector like space.”

Kris Vandenberk, Managing Partner at imec.istart Future Fund, said: “EDGX represents exactly the kind of transformative infrastructure we are looking for. The space industry faces a fundamental bottleneck: we generate enormous amounts of data in orbit, yet still use outdated ‘store and forward’ architectures. EDGX solves this by bringing AI-powered edge computing directly into space, enabling satellites to analyze and act on data in real time, instead of waiting for processing on the ground.”

About EDGX

EDGX is a Belgian space company with a mission to deliver the world's fastest edge computers for satellites. Its flagship product, EDGX Sterna, is a powerful AI data processing unit based on the NVIDIA Jetson Orin, enabling real-time onboard data processing in orbit. EDGX serves the satellite communications/telecommunications, Earth observation, and in-orbit servicing markets across commercial, government, and defense segments, with a particular focus on enabling AI and high-performance data processing at scale in satellite constellations. Founded in 2023, EDGX is headquartered in Ghent, Belgium, and will launch its first in-orbit demonstration in February 2026 aboard a SpaceX Falcon 9.

www.edgx.space

press@edgx.space

 

[Frangipani]

OHB Hellas onboard satellite fire detection solution | OHB Hellas

🚀 Introducing Our Onboard Satellite Fire Detection Algorithm 🔥 We’re excited to share our progress in satellite technology that enhances early fire detection and monitoring. Our new onboard algorithm quickly identifies signs of fire from space, enabling faster response times and potentially...

www.linkedin.com

View attachment 89419

At this point in time, the AKIDA satellite with an AKD1000 PCIe Card onboard that OHB Hellas has been developing is not slated to handle “fire detection” - according to their concept website https://giasaas.eu/, this application is instead supposed to be performed by their two other satellites: KRIA (equipped with a Xilinx KRIA KV260 Vision AI Starter Kit) and CORAL (equipped with a Google Coral TPU Dev Board):

https://thestockexchange.com.au/threads/brn-discussion-ongoing.1/post-462394