BRN Discussion Ongoing

[Fact Finder]

Interestingly, Valeo are at pains to explain that they had developed the algorithms in-house. Well this is a patent they developed for ADAS/AV.

But, and this is a very big butt, they do not claim to have invented the NNs, to the extent that they treat the NNs as "black boxes".

US2021166090A1 DRIVING ASSISTANCE FOR THE LONGITUDINAL AND/OR LATERAL CONTROL OF A MOTOR VEHICLE
VALEO:

Figs 1 to 3 show prior art (known) ADAS arrangements, and the patent then goes on to describe the deficiencies of these systems before describing the invention with reference to Figures 4 to 6.

View attachment 8303


View attachment 8304

[0008] The “online” operation of one known system 3 of this type is shown schematically in FIG. 2. The system 3 comprises a neural network 31 , for example a deep neural network or DNN, and optionally a module 30 for redimensioning the images in order to generate an input image Im′ for the neural network, the dimensions of which are compatible with the network, from an image Im provided by a camera 2 . The neural network forming the image processing device 31 has been trained beforehand and configured so as to generate, at output, a control instruction Scom , for example a (positive or negative) setpoint acceleration or speed for the vehicle when it is desired to exert longitudinal control of the motor vehicle, or a setpoint steering angle of the steering wheel when it is desired to exert lateral control of the vehicle, or even a combination of these two types of instruction if it is desired to exert longitudinal and lateral control.

[0009] In another known implementation of an artificial-intelligence driving assistance system, shown schematically in FIG. 3, the image Im captured by the camera 2 , possibly redimensioned to form an image Im′, is processed in parallel by a plurality of neural networks in a module 310 , each of the networks having been trained for a specific task. Three neural networks have been shown in FIG. 3, each generating an instruction P1 , P2 or P3 for the longitudinal and/or lateral control of the vehicle, from one and the same input image Im′. The instructions are then fused in a digital module 311 so as to deliver a resultant longitudinal and/or lateral control instruction Scom .

[0010] In both cases, the neural networks have been trained based on a large number of image records corresponding to real driving situations of various vehicles involving various humans, and have thus learned to recognize a scene and to generate a control instruction close to human behaviour.

[0011] The benefit of artificial-intelligence systems such as the neural networks described above lies in the fact that these systems will be able to simultaneously apprehend a large number of parameters in a road scene (for example a decrease in brightness, the presence of several obstacles of several kinds, the presence of a car in front of the vehicle and whose rear lights are turned on, curved and/or fading marking lines on the road, etc.) and respond in the same way as a human driver would. However, unlike object detection systems, artificial-intelligence systems do not necessarily classify or detect objects, and therefore do not necessarily estimate information on the distance between the vehicle and a potential hazard.

#####################################################

Figs 4 to 6 relate to zooming in on an item of interest in the field of view and analysing the unzoomed and zoomed images using parallel NNs.

######################################################

[0037] The image processing device 31 a comprises for example a deep neural network.

[0038] The image processing device 31 a is considered here to be a black box, in the sense that the invention proposes to improve the responsiveness of the algorithm that it implements without acting on its internal operation.

[0039] To this end, the invention makes provision to perform, in parallel with the processing performed by the device 31 a, at least one additional processing operation using the same algorithm as the one implemented by the device 31 a, on an additional image formulated from the image Im1 .

[0040] To this end, according to one possible embodiment of the invention, the system 3 comprises a digital image processing module 32 configured so as to provide at least one additional image Im2 at input of an additional image processing device 31 b, identical to the device 31 a and accordingly implementing the same processing algorithm, this additional image Im2 resulting from at least one geometric and/or radiometric transformation performed on the image [#### ie, ZOOM! ####] Im1 initially captured by the camera 2 . In this case too, the system 3 may comprise a redimensioning module 30 b similar to the redimensioning module 30 a, in order to provide an image Im2 ′ compatible with the input of the additional device 31 b.

The algorithm has the effect that the zoomed image can cause the ADAS to apply the brakes earlier than it would in response to the unzoomed image if the leading vehicle applies its brakes.

Well don't aske me - I just live here ...

The AKIDA on the BRN website is black. Not sure if it’s the black box you were looking for but I think someone sat on it cause it’s kinda flat. FF


AKIDA BALLISTA

 

[Wags]

I'm with you macca,,, Please divulge your shares? I'm about to do the same

Geez Chook, that's a bit personal, but what the hell.
Between the Leader of Opposition and self, we have just under 400K. In our simple world, thats a chunk of skin. Some is at an average late 40's, some a bit higher.
We actually had more than that, but thanks to me and some crappy decisions, thinking I was clever, I burnt a few. I posted at the time that I had learnt my lesson and from now on, its the deck chair for me.
BTW, we had a baked dinner tonight, and my favourite colour is green.
Hope this helps


Oooohhhhh shoot, please divulge your shares,. penny just dropped, the other holdings. Ok. SYA, PLL, PLS, ZIP (ouch), AXE and Im sweet on NMT. and I don't wear jarmies,

 

[Diogenese]

The AKIDA on the BRN website is black. Not sure if it’s the black box you were looking for but I think someone sat on it cause it’s kinda flat. FF


AKIDA BALLISTA

If it was still in its bubble wrap, that would have been machinegun flatus.

 

[alwaysgreen]

But what a trick.

May West had one trick.

Groucho Marx’s had one trick.

Charlie Chaplin had one trick.

Marilyn Munro had one trick.

Sir Edmund Hilary had one trick.

If the one trick is good enough you can dine out on it forever.

FF

AKIDA BALLISTA

My wife is a teacher and said she hates it when parents ask her to concentrate more on their child's weak subjects. No, concentrate on what they are good at and what they like and put every ounce of their being into it. Imagine if Tiger Woods turned around when he was 14 and said, "I'm pretty good at golf. I should probably try and improve my basketball".

Nothing wrong with a one trick pony!

 

[MDhere]

After we are all billionaires we could take up a collection for the tech analyst who wrote that Valeo was going to be consigned to history by Velodyne and it’s revolutionary Lidar. We could buy him a stamp for the envelope to send a job application to MF.

My opinion only DYOR
FF

AKIDA BALLISTA

after we are all billionaires? lol love yr confidence and i thought I was an optimist

 

[Fact Finder]

after we are all billionaires? lol love yr confidence and i thought I was an optimist

Nup. Didn’t you listen to the politicians during the election we are about to suffer rampant inflation and a postage stamp is going cost a billion dollar bucks soon. FF

AKIDA BALLISTA

 

[Violin1]

Geez Chook, that's a bit personal, but what the hell.
Between the Leader of Opposition and self, we have just under 400K. In our simple world, thats a chunk of skin. Some is at an average late 40's, some a bit higher.
We actually had more than that, but thanks to me and some crappy decisions, thinking I was clever, I burnt a few. I posted at the time that I had learnt my lesson and from now on, its the deck chair for me.
BTW, we had a baked dinner tonight, and my favourite colour is green.
Hope this helps


Oooohhhhh shoot, please divulge your shares,. penny just dropped, the other holdings. Ok. SYA, PLL, PLS, ZIP (ouch), AXE and Im sweet on NMT. and I don't wear jarmies,

Ok Macca - you're not staying at my place.....

 

[Violin1]

Hi all. Tony Dawe has kindly responded and confirmed that Antonio was referring to a total of 4 to 5 directors not an additional 4 to 5 directors. In effect, that would see one new non exec director coming onto the board in the short-term, and another NED coming on in the medium term. That would ensure the board maintained a majority of independent NED’s.
V

 

[Wags]

Ok Macca - you're not staying at my place.....

Oh V, Ive got a good gown, and Im shy. Your safe.
or was it my holdings that upset you?
Thankyou mate, you made me laugh, cheers

 

[Violin1]

Oh V, Ive got a good gown, and Im shy. Your safe.
or was it my holdings that upset you?
Thankyou mate, you made me laugh, cheers

was scared you'd come down and while we were talking trading you'd show me a parcel.......

 

[BaconLover]

Oh V, Ive got a good gown, and Im shy. Your safe.
or was it my holdings that upset you?
Thankyou mate, you made me laugh, cheers

More likely your non-holdings.

 

[Deleted member 118]

I'm sorely tempted to get my leprechaun boots out of the closet and pop open a magnum of champers!

 

[Bravo]

I like it!

NVIDIA DRIVE Hyperion Combines Orin With Best-in-Class Sensor Architecture for Production-Ready Platform​

Continental, Hella, Luminar, Sony and Valeo integrate sensors into DRIVE Hyperion 8 platform.


November 9, 2021 by Gary Hicok




Safe, robust autonomous vehicles require a foundation that’s just as dependable.
NVIDIA DRIVE Hyperion 8 is a computer architecture and sensor set for full self-driving systems. This latest generation technology is designed for the highest levels of functional safety and cybersecurity, and is supported by sensors from a wide range of leading suppliers including Continental, Hella, Luminar, Sony and Valeo. DRIVE Hyperion is available today for 2024 vehicle models, NVIDIA founder and CEO Jensen Huang announced at GTC.
The production platform is designed to be open and modular, so customers can easily use what they need — from core compute and middleware all the way to NCAP, level 3 driving, level 4 parking and AI cockpit capabilities.
During the GTC keynote, Huang showed a DRIVE Hyperion 8 vehicle drive autonomously from the NVIDIA headquarters in Santa Clara, Calif., to Rivermark Plaza in San Jose.



DRIVE Hyperion is also scalable, with the current standard DRIVE Orin platform designed to be upgradeable with NVIDIA DRIVE Atlan and DriveWorks APIs that are compatible across generations.

Architected for Safety​

With a functionally safe AI compute platform at its core, DRIVE Hyperion provides a secure base for autonomous vehicle development.
Two NVIDIA DRIVE Orin systems-on-a-chip provide redundancy and fail-over safety, as well as ample compute for level 4 self-driving and intelligent cockpit capabilities.
The DRIVE Hyperion 8 developer kit also includes NVIDIA Ampere architecture GPUs. This high-performance compute delivers ample headroom for developers to test and validate new software capabilities.
The NVIDIA DriveWorks Sensor Abstraction Layer streamlines sensor setup with easy-to-use plugins, while DRIVE AV Software contains the deep neural networks for perception, mapping, planning and control.

Sensing New Possibilities​

By including a complete sensor setup on top of centralized compute and AI software, DRIVE Hyperion provides everything needed to validate an intelligent vehicle’s hardware on the road.
Its sensor suite encompasses 12 cameras, nine radars, 12 ultrasonics and one front-facing lidar sensor. And with the adoption of best-in-class sensor suppliers coupled with sensor abstraction tools, autonomous vehicle manufacturers can customize the platform to their individual self-driving solutions.
This open, flexible ecosystem ensures developers can test and validate their technology on the exact hardware that will be on the vehicle.
The long-range Luminar Iris sensor will perform front-facing lidar capabilities, using a custom architecture to meet the most stringent performance, safety and automotive-grade requirements.
“NVIDIA has led the modern compute revolution, and the industry sees them as doing the same with autonomous driving,” said Austin Russell, Founder and CEO of Luminar. “The common thread between our two companies is that our technologies are becoming the de facto solution for major automakers to enable next-generation safety and autonomy. By taking advantage of our respective strengths, automakers have access to the most advanced autonomous vehicle development platform.”
The radar suite includes Hella short-range and Continental long-range and imaging radars for redundant sensing. Sony and Valeo cameras provide the cutting edge in visual sensing, in addition to ultrasonic sensors from Valeo for measuring object distance.
“NVIDIA DRIVE Hyperion is a complete platform for developing autonomous vehicles, which is why Sony has integrated its sensors to give our customers the most effective transition from prototype to production vehicles,” said Marius Evensen, Head of Automotive Marketing at Sony.
DRIVE Hyperion is open and can accelerate the AV industry’s time to market by giving manufacturers the ability to leverage NVIDIA’s own development work. It includes all the tools NVIDIA engineers use to record, capture and process all the data from these sensors in real time.
And this entire toolset is synchronized and calibrated precisely for 4D data collection, giving developers valuable time back in deploying safe and robust autonomous vehicles. DRIVE Hyperion is the ideal platform for anyone developing autonomous vehicles.
Catch up on the full GTC keynote:

NVIDIA DRIVE Hyperion Combines Orin With Best-in-Class Sensor Architecture for Production-Ready Platform

DRIVE Hyperion is a computer architecture and sensor set for self-driving systems, designed for functional safety and cybersecurity.

blogs.nvidia.com

 

[Diogenese]

I like it!

NVIDIA DRIVE Hyperion Combines Orin With Best-in-Class Sensor Architecture for Production-Ready Platform​

Continental, Hella, Luminar, Sony and Valeo integrate sensors into DRIVE Hyperion 8 platform.


November 9, 2021 by Gary Hicok




Safe, robust autonomous vehicles require a foundation that’s just as dependable.
NVIDIA DRIVE Hyperion 8 is a computer architecture and sensor set for full self-driving systems. This latest generation technology is designed for the highest levels of functional safety and cybersecurity, and is supported by sensors from a wide range of leading suppliers including Continental, Hella, Luminar, Sony and Valeo. DRIVE Hyperion is available today for 2024 vehicle models, NVIDIA founder and CEO Jensen Huang announced at GTC.
The production platform is designed to be open and modular, so customers can easily use what they need — from core compute and middleware all the way to NCAP, level 3 driving, level 4 parking and AI cockpit capabilities.
During the GTC keynote, Huang showed a DRIVE Hyperion 8 vehicle drive autonomously from the NVIDIA headquarters in Santa Clara, Calif., to Rivermark Plaza in San Jose.



DRIVE Hyperion is also scalable, with the current standard DRIVE Orin platform designed to be upgradeable with NVIDIA DRIVE Atlan and DriveWorks APIs that are compatible across generations.

Architected for Safety​

With a functionally safe AI compute platform at its core, DRIVE Hyperion provides a secure base for autonomous vehicle development.
Two NVIDIA DRIVE Orin systems-on-a-chip provide redundancy and fail-over safety, as well as ample compute for level 4 self-driving and intelligent cockpit capabilities.
The DRIVE Hyperion 8 developer kit also includes NVIDIA Ampere architecture GPUs. This high-performance compute delivers ample headroom for developers to test and validate new software capabilities.
The NVIDIA DriveWorks Sensor Abstraction Layer streamlines sensor setup with easy-to-use plugins, while DRIVE AV Software contains the deep neural networks for perception, mapping, planning and control.

Sensing New Possibilities​

By including a complete sensor setup on top of centralized compute and AI software, DRIVE Hyperion provides everything needed to validate an intelligent vehicle’s hardware on the road.
Its sensor suite encompasses 12 cameras, nine radars, 12 ultrasonics and one front-facing lidar sensor. And with the adoption of best-in-class sensor suppliers coupled with sensor abstraction tools, autonomous vehicle manufacturers can customize the platform to their individual self-driving solutions.
This open, flexible ecosystem ensures developers can test and validate their technology on the exact hardware that will be on the vehicle.
The long-range Luminar Iris sensor will perform front-facing lidar capabilities, using a custom architecture to meet the most stringent performance, safety and automotive-grade requirements.
“NVIDIA has led the modern compute revolution, and the industry sees them as doing the same with autonomous driving,” said Austin Russell, Founder and CEO of Luminar. “The common thread between our two companies is that our technologies are becoming the de facto solution for major automakers to enable next-generation safety and autonomy. By taking advantage of our respective strengths, automakers have access to the most advanced autonomous vehicle development platform.”
The radar suite includes Hella short-range and Continental long-range and imaging radars for redundant sensing. Sony and Valeo cameras provide the cutting edge in visual sensing, in addition to ultrasonic sensors from Valeo for measuring object distance.
“NVIDIA DRIVE Hyperion is a complete platform for developing autonomous vehicles, which is why Sony has integrated its sensors to give our customers the most effective transition from prototype to production vehicles,” said Marius Evensen, Head of Automotive Marketing at Sony.
DRIVE Hyperion is open and can accelerate the AV industry’s time to market by giving manufacturers the ability to leverage NVIDIA’s own development work. It includes all the tools NVIDIA engineers use to record, capture and process all the data from these sensors in real time.
And this entire toolset is synchronized and calibrated precisely for 4D data collection, giving developers valuable time back in deploying safe and robust autonomous vehicles. DRIVE Hyperion is the ideal platform for anyone developing autonomous vehicles.
Catch up on the full GTC keynote:

NVIDIA DRIVE Hyperion Combines Orin With Best-in-Class Sensor Architecture for Production-Ready Platform

DRIVE Hyperion is a computer architecture and sensor set for self-driving systems, designed for functional safety and cybersecurity.

blogs.nvidia.com

I wonder if the Valeo cameras have a black box inside them?

 

[Bravo]

I wonder if the Valeo cameras have a black box inside them?

Black boxes to be equiped in all EU cars, etc from July 2022. Talking about a BLACK BOXES, it may only be semi-relevant.. but I love this song!

 

[Jumpchooks]

Geez Chook, that's a bit personal, but what the hell.
Between the Leader of Opposition and self, we have just under 400K. In our simple world, thats a chunk of skin. Some is at an average late 40's, some a bit higher.
We actually had more than that, but thanks to me and some crappy decisions, thinking I was clever, I burnt a few. I posted at the time that I had learnt my lesson and from now on, its the deck chair for me.
BTW, we had a baked dinner tonight, and my favourite colour is green.
Hope this helps


Oooohhhhh shoot, please divulge your shares,. penny just dropped, the other holdings. Ok. SYA, PLL, PLS, ZIP (ouch), AXE and Im sweet on NMT. and I don't wear jarmies,

BRAINCHIP_IOUS

THIS IS US

ASPIRING TO BE ADVENTUROUS

OUR INVESTMEST WAS AUDASCIUOS

WE REASONED THE BRN CREW WERE ADVENTUREOUS

AMBIGUOUS,, ADIKA_ AKIDA_ ? BOTH WAYS WITH US

IT’S IT AI WITH SNN IOUS

INNOQUIOUS,, NOT ON THIS BUS WITH US

NOT AT ALL SUPERFLUOUS,,,

TRECHEROUS OR INSIDIOUS,,,

RU SERIOUS?

THIS BUS IS GOING TO THE UNIVERSE

YES WE’RE ON THE BUS

INCLUSIVE INVESTORS, OF ALL OF US

SUPERFLAGERISTICOUS ? MARY POPPINS YES TO US !!!!!

UBIQUITOUS_U BEAUT IT’S US

PLEASE COME WITH US

GET ON THE BUS

AKIDA BALLISTA

OR BUS

T

 

[dippY22]

I never understand why people still trust GS, credit Suisse etc.
Trust is like time.
Once it's gone, it's gone.

I love this, BaconLover...."Trust is like time. Once it's gone, it's gone".

And that is why a marriage with infidelity can never really work ever again the way most people idealistically intend when on the altar. I guess many people don't care if they can be deemed trustworthy since the divorce rate is now so staggeringly high.

I trust others and I deem myself to be very trustworthy (a variation of the golden rule, "do unto others, ...etc"). But people who prove to me not to be trustworthy are usually unceremoniously cast out of my life, because life is too short to play mind games and such.

To trust or be trusted is that powerful to me, a guiding light of principle if you will.

Recently at the AGM, I believe our Brainchip management did everything they could do to say "trust us". And I do, .... which is a big reason I bought shares in the promise of what is to come, and have continued to add to that ownership as that promise moves ever closer to "explosive sales" reality.
In the brief 2 + years I have been associated with them, Brainchip has proven to me to be trustworthy and in so doing has also demonstrated integrity. How big is that in this day and age?

Regards, dippY (....happily married for 45 years)

 

[mkg6R]

top gear made a video of the new mercedes hypercar. heres the link.

 

[dippY22]

My wife is a teacher and said she hates it when parents ask her to concentrate more on their child's weak subjects. No, concentrate on what they are good at and what they like and put every ounce of their being into it. Imagine if Tiger Woods turned around when he was 14 and said, "I'm pretty good at golf. I should probably try and improve my basketball".

Nothing wrong with a one trick pony!

That reminds me of a great Tiger Woods story. I believe it to be true but I wasn't there so I cannot verify it. Not that Tiger was a one trick pony, but....

At one of The Open championships he won, in Scotland I think, everyone else was practicing their sand shots because the course had many, many perilous sand bunkers and if you got in one you were in BIG trouble. Tiger chose not to practice sand shots, but instead to practice his "stinger" shot,....or driving iron (1 or 2 iron) which he used frequently off the tee that week. Why? Because he was good at it. Others practiced their sand shots because they wanted to improve that skill in preparation for inevitably hitting into the sand. Why? Because they weren't so good at it, and like I said, those traps were to be feared.

The end result of all that preparation,.....Tiger won,.... and why? In large part because he didn't hit a single sand trap off the tee during that week's competition.

Incredible story, if true. The moral, ....know your strengths. Stay in your lane and hone the skills you excell at and you will succeed.

dippY

 

[AusEire]

I stand by my earlier call, $500T or we walk away.

Earlier call? I thought this was a genuine offer made to the company already