Hi
@Frangipani ,
The excerpt I posted immediately below the post from which you inferred a suggested Akida link refers to an algorithm.
Further on, that article continues:
I
n artificial intelligence, machine learning is a way that computers learn from data—lots of data—to identify patterns and make decisions or draw conclusions.
This automated process can be powerful when the patterns might not be obvious to human researchers looking at the same data, which is typical for large, complex data sets such as those involved in imaging and spectral analysis.
In MOMA's case, researchers have been collecting laboratory data for more than a decade, according to Victoria Da Poian, a data scientist at NASA Goddard who co-leads development of the machine learning algorithm. The scientists train the algorithm by feeding it examples of substances that may be found on Mars and labeling what they are. The algorithm will then use the MOMA data as input and output predictions of the chemical composition of the studied sample, based on its training.
"The more we do to optimize the data analysis, the more information and time scientists will have to interpret the data," Da Poian said. "This way, we can react quickly to results and plan next steps as if we are there with the rover, much faster than we previously would have."
The collected data will be used in building various AI models which can be used by the AI algorithm for classification or "labelling" as well as for navigation. If NASA are using a conventional CNN algorithm, this will be a significant drain on their elctricity supply.
BRN has been engaged with NASA for some years. It would be surprising if Victoria Da Poian were to be unaware of Akida. In particular NASA would have been aware of TeNNs for a couple of years.
The rover must navigate autonomously, and Akida has famously been found to enable an increase in cruising speed of such rovers due to its real time processing capabilities. The rover is said to have a range of several km.
While Akida has been radhardened by Vorago, there is nothing to suggest the Akida SoC is incorporated in the rover. Indeed, as you point out, time would be against this possibility ... but next time?
Sean Hehir recently acknowledged that BRN now has an additional product line for algorithms.
Rosalind is not due to be launched til 2028, so there is time to incorporate TeNNs/Akida 2 algorithms in the Mars rover. But who knows? It may already be there.
FN:
https://www.esa.int/Science_Explora...th_of_ESA_s_ExoMars_Rosalind_Franklin_mission
FAQ: The ‘rebirth’ of ESA’s ExoMars Rosalind Franklin mission
13/03/2023
...
T
here is a plan to re-use in the new Lander the qualified onboard computer, the radar doppler altimeter and the parachute system that had been developed for the previous version of the mission.
...
This refers to the lander module, but the rover will also have a "qualified" processor which will not be readily replaced. However:
A
ny obsolescence of parts will be taken care of with appropriate refurbishments during the development of the ExoMars Rosalind Franklin Mission.
Hi Diogenese,
Victoria da Poian is a NASA Visiting Scientist, whose actual employer is a company called Microtel LLC, specialising in software and systems engineering applications for Earth science and space missions, that was acquired by Tyto Athene in April.
https://science.gsfc.nasa.gov/sci/bio/victoria.dapoian
Tyto Athene Acquires Microtel to Expand Space System Capabilities
www.govconwire.com
The new ML algorithm you referred to was developed specifically for data collected, analysed and sent back to Earth (!) by an instrument aboard the Rosalind Franklin rover, the Mars Organic Molecule Analyzer (MOMA) - said algorithm will be used
by researchers on Earth to study the data and decide about the next steps,
not by the instrument autonomously.
And it has nothing to do with Rosalind Franklin’s autonomous navigation system at all.
When a robotic rover lands on another world, scientists have a limited amount of time to collect data from the troves of explorable material, because of short
www.nasa.gov
Besides, there is no indication that Victoria Da Poian has been working with SNNs and/or TENNs in recent years.
You should also ask yourself the following: If she had been blown away by Akida technology or TENNs, why would she and her colleagues have set up two open-science ML challenges in 2022 and published a paper about the results in 2023 (published in early 2024), declaring CNN solutions the winning entries in both cases?
Abstract. We set up two open-science machine learning (ML) challenges focusing on building models to automatically analyse mass spectrometry (MS) data for
academic.oup.com
Furthermore, here is a link to the agreement signed by ESA and NASA in May:
https://www.nasa.gov/news-release/nasa-european-space-agency-unite-to-land-europes-rover-on-mars/
“With this memorandum of understanding, the NASA Launch Services Program will procure a U.S. commercial launch provider for the Rosalind Franklin rover. The agency will also provide heater units and elements of the propulsion system needed to land on Mars.”
All available evidence points to NASA having nothing to do with the ESA Mars rover’s navigation system.
This would highly likely be in the sole hands of Airbus Defence & Space that designed and built the rover now known as the ExoMars Rosalind Franklin rover in a cleanroom at its UK facility in Stevenage, before it was transferred to Italy in preparation for its planned launch in September 2022 from Baikonur, the spaceport operated by Russia within Kazakhstan.
While the Airbus team from Stavanage recently tested two of their rovers in a nearby quarry, including one similar to Rosalind Franklin nicknamed Charlie that - according to the following ESA blog article - was used “to test a new navigation system that could speed up rover missions on the Moon and Mars. This capability could lead to improved performance for ESA’s ExoMars Rosalind Franklin’s rover mission, which is expected to launch in 2028.”
https://blogs.esa.int/to-mars-and-back/2024/09/06/rovers-lightsabres-and-a-piglet/
… I doubt we are involved here.
Listen to this June 2023 presentation by Airbus Space Robotics Tech Lead Piotr Weclewski from 20:50 min, when he mentions the effort of validating new approaches such as neuromorphic or bio-inspired computing (that are generally of great interest to Airbus): “We need to bring it slowly, we need to bring it step by step to the picture. Why? Because of the criticality of the missions."
He goes on to emphasise that sending something not only to low-Earth orbit, but to the Moon, dramatically increases the complexity and the risk of radiation mitigation, thermal aspects etc.
So disruptive approaches such as the implementation of neuromorphic technology need to be carefully validated first in order not to endanger critical missions. That definitely sounds to me as if a trip to the Moon will be a first step
only after successful validation of this new technology in Low-Earth orbit (LEO), and that a mission to Mars, which is even more complex, will remain a long-term goal for now.
Here is another article on the quarry testing conducted earlier this month that quotes Airbus rover program manager Chris Draper, confirming that the Moon is the initial target for their rovers being tested these days:
The step-by-step validation approach ties in with the new ESA R&T program referred to as NEURAVIS, which - as we found out in July - will be conducted by a consortium consisting of Airbus, BrainChip, Frontgrade Gaisler and Neurobus.
This must have been the relevant tender that was awarded to them, titled
EVALUATION OF NEUROMORPHIC COMPUTING TECHNOLOGIES FOR VERY LOW POWER AI/ML APPLICATIONS - EXPRO PLUS
https://esastar-publication-ext.sso.esa.int/ESATenderActions/details/60869+
All this information combined with last week’s LinkedIn comments by both Alf Kuchenbuch and Laurent Hili (that I had quoted in my previous post, but which you didn’t address at all) strongly suggest to me we are not/will not yet be involved in the Rosalind Franklin Rover Mars mission. And IMO that includes TENNs software as a separate offering. Why else would Alf Kuchenbuch have referred to his “dream” of Laurent Hili, Sandi Habinc and Sean Hehir collaborating on providing Rosalind’s “children” with “a neuromorphic brain for better perception and autonomy”? (“That is my dream.”)
As the BrainChip staff member primarily dealing with our company’s space industry partners, he’d know exactly whether or not TENNs were currently being tested by Airbus in order to improve Rosalind Franklin’s navigation system. If that were indeed the case, why would he then refer to a new generation of rovers only and not to the Rosalind Franklin rover itself?
TENNs will first need to be validated, too.
So to sum it up, I predict there will be validation of our technology in LEO satellites first, before ESA will consider implementing it on the more critical and complex Lunar or even Martian missions.
. Going to be huge. Those Indians know their Tech!
