BRN Discussion Ongoing

[Sirod69]

BMW joins forces with Valeo to release an autonomous parking system

MADRID, 14 Feb. (EUROPA PRESS) - BMW and the manufacturer of components for vehicles Valeo have subscribed to a certificate of cooperation to unwind together with a system of independent labeling of level 4, it is decided that no supervision is necessary for part of the driver, and that it will be implemented in the new generation of coaches of the German brand, denominated 'Neue Klasse'. The automated parking lot offers drivers the possibility that the vehicle has the same tareas as the b ...


For his part, the president of Valeo's driving assistance systems area, Marc Vrecko, has indicated that this cooperation will take advantage of his company's knowledge and technologies, as well as "advanced computer vision algorithms based on artificial intelligence AI ".

BMW se alía con Valeo para desarrollar un sistema de aparcamiento autónomo

BMW y el fabricante de componentes para vehículos Valeo han suscrito un acuerdo de cooperación para...

www.europapress.es

 

[Sirod69]

VALEO AND BMW TOGETHER ON PARKING SOLUTIONS
February 14, 2023 Emil Peters 42 views
Following the strategic partnership on ADAS entered into by BMW and Valeo in mid-2022, both parties signed a partnership in January 2023 focused on the development of automated parking solutions.

There is a possibility that other car manufacturers will join this platform.

It is a form of Level 4 autonomous driving, without driver supervision. At a drop-off zone, the driver exits the car and the vehicle takes on tasks such as autonomously finding a parking space, making the necessary maneuvers to get in and out of a parking space, and can also drive back to a pick-up zone to return the vehicle to the driver. In order to make optimal use of the parking time, additional services such as fully automatic loading or fully automatic washing can be used.

Two types
The automated parking solutions are divided into two main categories, Type 1 and Type 2 systems. A Type 1 system has the necessary technologies running on the vehicle, while a Type 2 system has the necessary technologies installed in the appropriate infrastructure, such as a parking garage, and the vehicle is controlled by the infrastructure.

Valeo en BMW samen in parkeeroplossingen

Na de strategische samenwerking op het gebied van ADAS die BMW en Valeo medio 2022 zijn aangegaan, hebben beide partijen in januari 2023 een samenwerking ondertekend die zich richt op de ontwikkeling van geautomatiseerde parkeeroplossingen.

aftersalesmagazine.nl

 

[Diogenese]

VALEO AND BMW TOGETHER ON PARKING SOLUTIONS
February 14, 2023 Emil Peters 42 views
Following the strategic partnership on ADAS entered into by BMW and Valeo in mid-2022, both parties signed a partnership in January 2023 focused on the development of automated parking solutions.

There is a possibility that other car manufacturers will join this platform.

It is a form of Level 4 autonomous driving, without driver supervision. At a drop-off zone, the driver exits the car and the vehicle takes on tasks such as autonomously finding a parking space, making the necessary maneuvers to get in and out of a parking space, and can also drive back to a pick-up zone to return the vehicle to the driver. In order to make optimal use of the parking time, additional services such as fully automatic loading or fully automatic washing can be used.

Two types
The automated parking solutions are divided into two main categories, Type 1 and Type 2 systems. A Type 1 system has the necessary technologies running on the vehicle, while a Type 2 system has the necessary technologies installed in the appropriate infrastructure, such as a parking garage, and the vehicle is controlled by the infrastructure.

Valeo en BMW samen in parkeeroplossingen

Na de strategische samenwerking op het gebied van ADAS die BMW en Valeo medio 2022 zijn aangegaan, hebben beide partijen in januari 2023 een samenwerking ondertekend die zich richt op de ontwikkeling van geautomatiseerde parkeeroplossingen.

aftersalesmagazine.nl

Valeo patent application:

WO2023280574A1 METHOD FOR OPERATING A PARKING ASSISTANCE SYSTEM, COMPUTER PROGRAM PRODUCT, AND PARKING ASSISTANCE SYSTEM

A method for operating a parking assistance system (100) is proposed. The parking assistance system (100) comprises a number (102) of sensors (102A – 102F) which are arranged in a predetermined region (110) and are each configured to detect a vehicle (200) present in the predetermined region (110) and to output a respective sensor signal. The method comprises the steps of: a) detecting (S1) a number of specific features (201 - 203) of the vehicle (200), b) determining (S2) a specific vehicle model (MSPEC) for the vehicle (200) on the basis of the detected specific features (201 - 203), c) receiving (S3) a sensor signal from at least one sensor (102A – 102F) of the number (102), d) determining (S4) a pose (POS) of the vehicle (200) on the basis of the received sensor signal using the determined specific vehicle model (MSPEC), and e) controlling (S5) the vehicle (200) on the basis of the determined pose (POS).

After training, the detector is set up to determine the pose of the vehicle on the basis of the sensor signals.
The detector is designed in particular as an artificial intelligence, such as a neural network, in particular a CNN (convolutional neural network).

[0043]​

In particular, the detector is already pre-trained on the basis of general characteristics that vehicles typically have. This means that the detector already includes a general vehicle model, for example, and that it can be suitable for determining the pose of a vehicle even before training with the specific features. However a confidence of the determined pose of the detector is significantly lower before this training than afterwards.

[0044]​

The structure of a neural network is shown, for example, as follows.
The neural network can be divided into three layers or sections, an input layer, one or more hidden layers, and an output layer. Each of the layers includes a plurality of individual neurons, it also being possible for different layers to have a different number of neurons. The amount of neurons in the input layer depends, for example, on the amount and the format of the data to be processed by the neural network, which can also be referred to as the dimensionality of the data. For example, the amount of neurons in the output layer depends on the dimensionality of the output vector.

[0045]​

The input layer forms the input of the neural network, to which the input vector is fed. The neurons of the input layer accept the information contained in the input vector and pass it on to the neurons of the first hidden layer in a weighted form. The neurons of the first hidden layer receive the weighted signals from the input layer and pass them on to the following hidden layer in a weighted form. The signals are passed through the neural network from layer to layer in this way until the output layer is reached. The output vector is tapped off at the neurons of the output layer. The amount of hidden layers is basically unlimited, however the computing power required to operate the neural network scales with the amount of hidden layers. The more layers a neural network includes, the more complex tasks the neural network can solve, but the training effort, i.e. the size of the training data set, increases accordingly. It is therefore advantageous to use only as many hidden layers as are necessary for the task at hand.

[0046] ​

In addition to the training data used, the topology of the neural network has a major influence on how well a respective neural network is able to solve a particular problem. A suitable topology depends on the available sensors and/or the type of input data. A suitable topology can be determined for specific sensors, for example by trying out a number of different topologies. By using the specific features as training data, the neural network is optimally adapted to determine the pose of the respective vehicle. The pre-trained neural network can be stored like a computer program and serves as a template for the specific neural network. In particular, the training of the neural network with the specific features takes place without a great expenditure of time, since the training data is limited. One can also say that a fine-tuning of the pre-trained neural network is carried out.
...
[0059]
According to a second aspect, a computer program product is proposed which comprises instructions which, when the program is executed by a computer, cause the latter to execute the method according to
a method for operating a parking assistance including a number of sensors arranged in a predetermined area, which are each set up to detect a vehicle present in the predetermined area and to output a respective sensor signal, comprising the steps of:
a) detecting a number of specific features of the vehicle,
b) determining a specific vehicle model for the vehicle based on the detected specific features,
c) receiving a sensor signal from at least one sensor,
d) determining a pose of the vehicle depending on the received sensor signal using the determined specific vehicle model, and
e) controlling the vehicle depending on the determined pose.


Parking assistance system (100) with a number (102) of sensors (102A - 102F) arranged in a predetermined area (110) for detecting a vehicle (200) present in the predetermined area (110) and for outputting a respective sensor signal, and with :
a detection unit (122) for detecting a number of specific features (201 - 203) of the vehicle (200),
a determination unit (124) for determining a specific vehicle model (MSPEC) for the vehicle (200) on the basis of the specific features (201 - 203),
a receiving unit (126) for receiving a sensor signal from at least one sensor (102A - 102F) of the number (102), the determination unit (124) for determining a pose (POS) of the vehicle (200) depending on the received sensor signal using the determined specific vehicle model (MSPEC) is set up, and
a control unit (128) for controlling the vehicle (200) depending on the determined posed pose (POS).

Akida could perform the function of the detection unit and determination unit.

 

[GStocks123]

Hmm..

Book a meeting | PROPHESEE | Luca Verre

We are back at #MWC this year! Secure your meeting with us at our private suite We will be at MWC 2023 in Barcelona from February 27 to March 2 in suite 418, Alexandre Hotel Fira Congress. Experience never-seen-before event-based Metavision® demonstrations such as next-generation smartphone...

www.linkedin.com

 

[_Nordi_]

BMW and Valeo engage in a strategic cooperation to co-develop next-generation Level 4 automated parking experience

The BMW Group and Valeo announced their cooperation for the co-development of fully automated parking technologies up to Level 4

www.valeo.com

 

[_Nordi_]

BMW und Valeo beschließen eine strategische Partnerschaft zur gemeinsamen Entwicklung automatisierter Level-4-Parklösungen der nächsten Generation.

Die BMW Group und Valeo intensivieren ihre langjährige Partnerschaft mit einer neuen Kooperation. Nach Bekanntgabe einer umfangreichen Zusammenarbeit bei ADAS-Domain-Controllern, Sensoren und Software für das Parken und Manövrieren für die künftige Plattformgeneration „Neue Klasse“* haben die...

www.press.bmwgroup.com

 

[Sirod69]

Plumerai

Plumerai People Detection AI enables you to mask people in your camera feed in real-time. As the AI runs on the edge, the footage leaving the camera is anonymized, helping you to comply with privacy laws such as GDPR and CCPA.
Find out more at https://lnkd.in/eAGuaPkh

 

[Rise from the ashes]

Sorry wrong video.

Well turns out it's not fake but the miscreant who tweeted it has a link to one that does not perform like the one he advertised.

Oh thoughts and prayers for those living in Ohio that's totally screwed up what's transpired over there. Absolutely frightening.

Two more trains derail weeks after Ohio chemical spill

Nearly two weeks after an Ohio train derailment resulted in dangerous chemicals being released into air, two more trains derailed back-to-back on Monday. On Mo

www.westernstandard.news

 

[Deleted member 118]

The millions of shorts are the problem. Not a few on here having a whinge about the share price and lack of sales!

I noticed the shorts have increased to 7% in a short period of time, wouldn’t be surprised if we are over 8% now. Hoping the shorts can get it to 10% for me under my circumstances. But they are wankers.

 

[Sirod69]

Now I really have to see if the course(=share price) is already in the basement?

 

[Rise from the ashes]

I noticed the shorts have increased to 7% in a short period of time, wouldn’t be surprised if we are over 8% now. Hoping the shorts can get it to 10% for me under my circumstances. But they are wankers.

Not sure why a lot of people blame the shorts for where the price is surely most rational people think other factors are involved?
@Sirod69 you mean curse?

And what's with all this UFO bullshit going on around the world. We getting invaded by aliens

 

[Deleted member 118]

Not sure why a lot of people blame the shorts for where the price is surely most rational people think other factors are involved?
@Sirod69 you mean curse?

And what's with all this UFO bullshit going on around the world. We getting invaded by aliens

As long as the alien invasion causes our sp to fall im happy

 

[charles2]

Once one overlooks the source a very intriguing article about the ramifications of self driving vehicles:

This Industry Will Be Worth $14 Trillion by 2027, Says Ark Invest -- Here's the Stock to Buy Now | The Motley Fool

The future of ride-hailing is autonomous vehicles, and it's set for a growth explosion, according to the tech-focused firm.

www.fool.com

 

[Sirod69]

As long as the alien invasion causes our sp to fall im happy

i wasn't talking about a course (share price=course), that's what they call it in germany, if something is very low, then it's in the basement, i was thinking of the share price.

Oh man you broke my joke, who believes in aliens

I think I'll go to the corner where @Bravo usually sits

 

[Food4 thought]

i wasn't talking about a course (share price=course), that's what they call it in germany, if something is very low, then it's in the basement, i was thinking of the share price.

Oh man you broke my joke, who believes in aliens

I think I'll go to the corner where @Bravo usually sits

We ( the world ) needs Bruce Willis to save us

 

[Foxdog]

Valeo patent application:

WO2023280574A1 METHOD FOR OPERATING A PARKING ASSISTANCE SYSTEM, COMPUTER PROGRAM PRODUCT, AND PARKING ASSISTANCE SYSTEM

A method for operating a parking assistance system (100) is proposed. The parking assistance system (100) comprises a number (102) of sensors (102A – 102F) which are arranged in a predetermined region (110) and are each configured to detect a vehicle (200) present in the predetermined region (110) and to output a respective sensor signal. The method comprises the steps of: a) detecting (S1) a number of specific features (201 - 203) of the vehicle (200), b) determining (S2) a specific vehicle model (MSPEC) for the vehicle (200) on the basis of the detected specific features (201 - 203), c) receiving (S3) a sensor signal from at least one sensor (102A – 102F) of the number (102), d) determining (S4) a pose (POS) of the vehicle (200) on the basis of the received sensor signal using the determined specific vehicle model (MSPEC), and e) controlling (S5) the vehicle (200) on the basis of the determined pose (POS).

After training, the detector is set up to determine the pose of the vehicle on the basis of the sensor signals.
The detector is designed in particular as an artificial intelligence, such as a neural network, in particular a CNN (convolutional neural network).

[0043]​

In particular, the detector is already pre-trained on the basis of general characteristics that vehicles typically have. This means that the detector already includes a general vehicle model, for example, and that it can be suitable for determining the pose of a vehicle even before training with the specific features. However a confidence of the determined pose of the detector is significantly lower before this training than afterwards.

[0044]​

The structure of a neural network is shown, for example, as follows.
The neural network can be divided into three layers or sections, an input layer, one or more hidden layers, and an output layer. Each of the layers includes a plurality of individual neurons, it also being possible for different layers to have a different number of neurons. The amount of neurons in the input layer depends, for example, on the amount and the format of the data to be processed by the neural network, which can also be referred to as the dimensionality of the data. For example, the amount of neurons in the output layer depends on the dimensionality of the output vector.

[0045]​

The input layer forms the input of the neural network, to which the input vector is fed. The neurons of the input layer accept the information contained in the input vector and pass it on to the neurons of the first hidden layer in a weighted form. The neurons of the first hidden layer receive the weighted signals from the input layer and pass them on to the following hidden layer in a weighted form. The signals are passed through the neural network from layer to layer in this way until the output layer is reached. The output vector is tapped off at the neurons of the output layer. The amount of hidden layers is basically unlimited, however the computing power required to operate the neural network scales with the amount of hidden layers. The more layers a neural network includes, the more complex tasks the neural network can solve, but the training effort, i.e. the size of the training data set, increases accordingly. It is therefore advantageous to use only as many hidden layers as are necessary for the task at hand.

[0046] ​

In addition to the training data used, the topology of the neural network has a major influence on how well a respective neural network is able to solve a particular problem. A suitable topology depends on the available sensors and/or the type of input data. A suitable topology can be determined for specific sensors, for example by trying out a number of different topologies. By using the specific features as training data, the neural network is optimally adapted to determine the pose of the respective vehicle. The pre-trained neural network can be stored like a computer program and serves as a template for the specific neural network. In particular, the training of the neural network with the specific features takes place without a great expenditure of time, since the training data is limited. One can also say that a fine-tuning of the pre-trained neural network is carried out.
...
[0059]
According to a second aspect, a computer program product is proposed which comprises instructions which, when the program is executed by a computer, cause the latter to execute the method according to
a method for operating a parking assistance including a number of sensors arranged in a predetermined area, which are each set up to detect a vehicle present in the predetermined area and to output a respective sensor signal, comprising the steps of:
a) detecting a number of specific features of the vehicle,
b) determining a specific vehicle model for the vehicle based on the detected specific features,
c) receiving a sensor signal from at least one sensor,
d) determining a pose of the vehicle depending on the received sensor signal using the determined specific vehicle model, and
e) controlling the vehicle depending on the determined pose.


Parking assistance system (100) with a number (102) of sensors (102A - 102F) arranged in a predetermined area (110) for detecting a vehicle (200) present in the predetermined area (110) and for outputting a respective sensor signal, and with :
a detection unit (122) for detecting a number of specific features (201 - 203) of the vehicle (200),
a determination unit (124) for determining a specific vehicle model (MSPEC) for the vehicle (200) on the basis of the specific features (201 - 203),
a receiving unit (126) for receiving a sensor signal from at least one sensor (102A - 102F) of the number (102), the determination unit (124) for determining a pose (POS) of the vehicle (200) depending on the received sensor signal using the determined specific vehicle model (MSPEC) is set up, and
a control unit (128) for controlling the vehicle (200) depending on the determined posed pose (POS).

Akida could perform the function of the detection unit and determination unit.

So Dio, do you think it's safe to say AKIDA is in both BMW and Merc?

 

[Sirod69]

On today's news from Valeo and BMW, just a thought:

If we were included here, it would also mean that Qualcomm would be a long-time customer. I'm already convinced of that. What do you think about it?

INNOVATION / PRODUITS ET TECHNOLOGIE | 28 JUN, 2022 | 2 MIN

Valeo signs major contract with the BMW Group in advanced driving assistance systems​

Valeo will develop and produce the ADAS domain controller capable of managing all data flows from all ADAS sensors in BMW Group vehicles based on the “Neue Klasse” platform. All driving assistance functions will be hosted and processed by the Valeo ADAS domain controller, which will be powered by Qualcomm Snapdragon SoCs**. The ADAS domain controller will host Valeo’s software platform for low-speed maneuvering, as well as software assets from BMW and Qualcomm for driving automation.

Valeo signs major contract with the BMW Group in advanced driving assistance systems

Valeo and the BMW Group have entered into a major collaboration for which Valeo will provide the ADAS domain controller, sensors and software for parking and maneuvering for BMW's upcoming platform generation "Neue Klasse"*, due to launch in 2025.

www.valeo.com

 

[GStocks123]

Keen to see these Oculi demos! (Confirmed BRN parter) It is also very interesting seeing a senior director from Qualcomm commenting on a startup company’s post that only has 1k followers.. could also be mates, who knows haha

 

[Rise from the ashes]

Keen to see these Oculi demos! (Confirmed BRN parter) It is also very interesting seeing a senior director from Qualcomm commenting on a startup company’s post that only has 1k followers.. could also be mates, who knows haha

Hi mate can you link me to where it's confirmed that oculi is a partner. I must have missed it or have a really shite memory.
Thanks

 

[Esq.111]

Morning Chippers,

Massive deal signed overnight between Air India ( TATA owned ) , Airbus & Boeing for 470 jets.

Biggest deal in passenger aviation aircraft history.

Tata & Sons will buy 250 from Airbus and 220 from Boeing.

* From memory large jets have anywhere from 20,000 to 30,000 sensors spread throughout.

So...

25,000 sensors ave.
X 470 jets
= 11,750,000 sensors give or take.

Hopefully BRN gets a look in.

Regards,
Esq.