BRN Discussion Ongoing

inston

Emerged
Oh boy - I wish I had the money to buy more right now!
 

Attitude estimation system and attitude estimation method​


Current Assignee: MegaChips Corp

Abstract​

To estimate a user's posture, including a direction of the user's body, using a small number of sensors.SOLUTION: A posture estimation system comprises a measurement member 1 located at any part of four limbs of a user, and a posture acquisition part 520 for acquiring the posture of the measurement member. The measurement member includes an acceleration sensor 14 and a gyro sensor 15. The posture acquisition part 520 includes a reference coordinate determination part 521 for setting a reference coordinate system of the measurement member based on the user's operation of making the measurement member face a target 3, and an attitude estimation part 522 for estimating an attitude of the measurement member relative to the target by acquiring detection values Da and Dr output from the acceleration sensor and the gyro sensor in response to the user's operation of changing the attitude of the measurement member.

View attachment 77936

View attachment 77937

GPT analysis:


This patent describes a posture estimation system that determines a user's body orientation using a minimal number of sensors. It is primarily designed for gaming, VR, fitness tracking, and motion-based interaction systems.




1. Purpose & Use


The system aims to estimate the posture and orientation of a user’s body efficiently, using a small number of sensors instead of a full-body motion capture setup. This is particularly useful for:


  • Gaming – Motion-based gameplay using handheld controllers.
  • Virtual Reality (VR) & Augmented Reality (AR) – Enhancing user movement tracking.
  • Fitness & Rehabilitation – Monitoring body movement for training or therapy.
  • Human-Computer Interaction – Intuitive gesture-based controls.



2. Sensor Technologies


The system uses two key inertial sensors, embedded in a measuring device (such as a handheld controller or a wearable limb sensor):


  1. Acceleration Sensor (Accelerometer)
    • Measures movement acceleration in three axes (X, Y, Z).
    • Helps determine tilt and linear motion.
  2. Gyro Sensor (Gyroscope)
    • Measures rotational velocity in three axes (yaw, pitch, roll).
    • Tracks rotational movement and orientation changes over time.

These sensors are typically placed in:


  • Handheld controllers (left and right hands).
  • Wearable devices (e.g., strapped to feet or arms).
  • Potential expansion to lower body tracking (e.g., sensors on both hands and feet).



3. Processing Technologies & Processor Locations


The system processes sensor data at multiple levels, using different processors located in the controllers and the game console.


A. Processing at the Controller Level (Embedded Processors)


Each controller (or wearable sensor) contains an onboard processor that performs initial data collection and preprocessing:


  • Location: Inside each controller (or wearable sensor).
  • Functions:
    • Collects acceleration and gyroscope data.
    • Filters raw data to reduce noise.
    • Performs preliminary sensor fusion to combine acceleration and rotational data.
    • Communicates with the game console via wireless or wired connection.

B. Processing at the Game Console Level (Central Processing)


The main computational processing happens inside the game console:


  • Location: The game console’s central processor (CPU).
  • Functions:
    1. Reference Coordinate System Setup
      • The user performs a calibration motion, aligning the controllers to a fixed target (e.g., display screen).
      • This sets a baseline reference coordinate system.
    2. Posture Estimation
      • The console’s processor integrates accelerometer and gyroscope data from the controllers.
      • Uses sensor fusion algorithms to track movement and correct drift.
    3. Common Coordinate Conversion
      • Since each controller has an independent coordinate system, the console converts them into a unified coordinate system for consistent tracking.
    4. Machine Learning-Based Full Body Estimation
      • The console’s processor runs a machine learning model to estimate full-body posture based on limited sensor data.
      • The model is trained to predict shoulder, arm, and torso positions from hand-held controllers alone.
    5. Adaptive Motion Correction for Different Users
      • The system adjusts for different body sizes by applying acceleration correction algorithms.
      • Example: A child's arm will have different acceleration characteristics than an adult's, so the system scales acceleration values based on user height.



4. Advantages Over Traditional Systems


  • Fewer sensors required (no need for full-body tracking suits).
  • No waist-mounted sensors needed (orientation is inferred from hand-held devices).
  • Cost-effective and power-efficient (less hardware, lower processing demands).
  • Machine learning integration allows accurate full-body tracking with limited data.
  • Adaptable for different users via automated motion scaling.



Number 1 post for me this year

1740366799411.gif
 
  • Like
  • Haha
  • Fire
Reactions: 9 users

TECH

Regular
View attachment 77971


EXTRACT



View attachment 77983






View attachment 77978


View attachment 77979
View attachment 77980

View attachment 77981






Here is a snippet from a podcast published online on the 7 August 2024, where Satalia's CEO & WPP Chief AI Officer, Daniel Hulme, talks about neuromorphic computing and Spiking Neural Networks.






Hi Bravo...some nice posts over the last few days, great work...after your very convincing post/s highlighting a possible solid connection to Veritone with it's aiWARE product/s.

I went back through my Linkedin conversations with Chad Steelberg, who at the time was the CEO and Chair of the Board of Directors, before handing off both titles during 2023 and 2024 to his brother Ryan.

My few conversations with Chad were in 2019/2020 and in September 2020 when I asked about our potential of being embedded within Veritone aiWare product/s he said at the time......
Chad Steelberg 11:12 PM
  • 👏
  • 👍
  • 😊

"Thanks for the note. Not much engagement at this time, but congrats on the progress"

We had issues with Studio and I'm reasonably comfortable in saying that, I think we aren't involved with Veritone in anyway.

BUT I HOPE I'M 100% WRONG, AS HAPPENS OFF AND ON :ROFLMAO:

Another interesting point is that with our 2024 Annual Report due out any day now, I just wonder if the Top 20 maybe coupled
with the report....hopefully there is nothing to rock the boat, we need surprises on the revenue front.

Tech (I know nothing) (y)
 
  • Like
Reactions: 9 users

MegaportX

Regular
Anyone have an idea when NVIDIA and Intel with be reporting next.
 

Iseki

Regular
Looks like MB.OS is a rebranding of QNX out of Waterloo uni.

QNX is already in use in all the major car makers vehicles - BMW, Bosch, Continental, Dongfeng Motor, Geely, Ford, Honda, Subaru, Toyota, Volkswagen, Volvo, and more.

So, it looks to me that we've been used by MB in a slimy sort of way.

In fact QNX is an Unix-like, real-time operating system that is embedded in not only cars, but medical devices, machinery, and other devices.So I wonder if BRN will produce drivers for QNX as well as linux?

 
  • Sad
Reactions: 1 users
Anyone have an idea when NVIDIA and Intel with be reporting next.
I believe that NVIDIA report is out on Thursday USA time according to comm bank report
 
  • Like
  • Fire
Reactions: 2 users

uiux

Regular
Looks like MB.OS is a rebranding of QNX out of Waterloo uni.

QNX is already in use in all the major car makers vehicles - BMW, Bosch, Continental, Dongfeng Motor, Geely, Ford, Honda, Subaru, Toyota, Volkswagen, Volvo, and more.

So, it looks to me that we've been used by MB in a slimy sort of way.

In fact QNX is an Unix-like, real-time operating system that is embedded in not only cars, but medical devices, machinery, and other devices.So I wonder if BRN will produce drivers for QNX as well as linux?



"Looks like MB.OS is a rebranding of QNX out of Waterloo uni."




Where is this info from
 
  • Like
Reactions: 1 users

uiux

Regular
Looks like MB.OS is a rebranding of QNX out of Waterloo uni.

QNX is already in use in all the major car makers vehicles - BMW, Bosch, Continental, Dongfeng Motor, Geely, Ford, Honda, Subaru, Toyota, Volkswagen, Volvo, and more.

So, it looks to me that we've been used by MB in a slimy sort of way.

In fact QNX is an Unix-like, real-time operating system that is embedded in not only cars, but medical devices, machinery, and other devices.So I wonder if BRN will produce drivers for QNX as well as linux?



Found something all good

 
  • Like
  • Fire
  • Love
Reactions: 11 users

Iseki

Regular
"Looks like MB.OS is a rebranding of QNX out of Waterloo uni."




Where is this info from
I think it is a valid question to ask: is MB really writing their own OS or is it a re-branding of an existing OS.
I haven't seen MB answer the question, but I do know that back in the day QNX was the OS for realtime data routing. It's from Waterloo Uni, and a quick google will show that it's already in about 300million vehicles plus medical devices, and lo and behold, the owners of QNX, Blackberry, are suddenly (last month) pushing its public awareness.

I don't have any proof other than the above, which seems to be logical, and if true, might mean that we should understand what it means.

There are people here on this forum who are currently writing AKD1000 drivers for Windows.

What do you think?
 

Iseki

Regular
Found something all good

Yes, well. As you are probably aware much of the performance saving may be the simple fact that they are running a form of QNX, a micro-kernel OS.

On the one hand MB.OS is just a rebranding of QNX, and so we shouldn't expect too much from them.
On the other hand if MB are smart enough to select QNX, they might be smart enough to select Akida.

Either way the question remains: Why no Akida driver for QNX?
 
  • Like
Reactions: 1 users

uiux

Regular
Yes, well. As you are probably aware much of the performance saving may be the simple fact that they are running a form of QNX, a micro-kernel OS.

On the one hand MB.OS is just a rebranding of QNX, and so we shouldn't expect too much from them.
On the other hand if MB are smart enough to select QNX, they might be smart enough to select Akida.

Either way the question remains: Why no Akida driver for QNX?


If they have based MB.OS off QNX they would just write their own proprietary driver.


Mercedes are designing MSOCs. They don't need drivers for pcie cards, they will likely be working with chips on their own interfaces
 
  • Like
Reactions: 8 users
1740386723720.png


 
  • Like
  • Fire
  • Wow
Reactions: 35 users

Team refinement ……

IMG_3849.jpeg
 
  • Like
  • Fire
Reactions: 23 users

Team refinement ……

View attachment 77998
I know someone perfect for the job, but I hear he just started a new position at some GPU mob..
 
  • Haha
  • Like
  • Fire
Reactions: 14 users

overpup

Regular
I know someone perfect for the job, but I hear he just started a new position at some GPU mob..
They don't mention 'loyalty' in the must-haves, so he might be able to get back in...
 
  • Like
  • Fire
Reactions: 3 users

Iseki

Regular
If they have based MB.OS off QNX they would just write their own proprietary driver.


Mercedes are designing MSOCs. They don't need drivers for pcie cards, they will likely be working with chips on their own interfaces
Yep, Those MSOC's 'll transform your plebean vehicle from thirsty gas guzzler to thrifty gaslighter. Good luck to them! My skyline had a minicomputer, and all MB's had was automatic fuel openers that opened when the level got low. Those feckers use to open all the time.
 

walderamaa

Emerged

🤔🤔🤔
 

Diogenese

Top 20
If anyone's curious about what francois Piednoel has been working on at Mercedes:

WO2024230948A1 AUTONOMOUS VEHICLE SYSTEM ON CHIP 20230510

Applicants: MERCEDES BENZ GROUP AG [DE]; Inventors: PIEDNOEL FRANCOIS [US]
1740410945313.png


[0047] In various examples, the system on chip 300 can further include a machine-learning (ML) accelerator chiplet 350 that is specialized for accelerating Al workloads, such as image inferences or other sensor inferences using machine learning, in order to achieve high performance and low power consumption for these workloads. The ML accelerator chiplet 350 can include an engine designed to efficiently process graph-based data structures, which are commonly used in Al workloads, and a highly parallel processor, allowing for efficient processing of large volumes of data. The ML accelerator chiplet 350 can also include specialized hardware accelerators for common Al operations such as matrix multiplication and convolution as well as a memory hierarchy designed to optimize memory access for Al workloads, which often have complex memory access patterns.

Now I'm sure Francois knows at least one ML accelerator which does not use matrix multiplication (MM), but TENNs does use MM.

This one is interseting in that it shows the use of redundant SoCs:

WO2024230971A1 MULTIPLE SYSTEM-ON-CHIP ARRANGEMENT FOR VEHICLE COMPUTING SYSTEM 20230510

1740411348710.png





An interesting unrelated development, not yet shown to be suitable for automotive, is replacable clip-in chiplets (a bit like a SIM card), as this would enable the upgrading of the physical chiplet. However, the technology would need to be proven in the hostile vibrational environment of a car.


Multi-Chiplet Implementation of a Replaceable Integrated Chiplet (PINCH) Assembly

With the continuous growth of disaggregated systems, a need for new modular platforms to facilitate integration arises. A rePlaceable INegrated CHiplet (PINCH) assembly technology with the capability for reassembly, upgradeability, testing, and prototyping systems of multiple chiplets at once is presented. PINCH consists of a socket platform, positive self-alignment structures (PSAS), compressible micro interconnects (CMIs), and an interposer for die-to-die connectivity. The substrate-agnostic PSAS-to-PSAS self-alignment technology allows us to achieve sub-micrometer alignment accuracy without the need for advanced alignment equipment. CMIs are nonpermanent compliant OFF-chip electrical interconnects with the capability of compensating for height differences and nonuniform assembly force. 2-D arrays of 33×33 150 μm pitch CMIs are tested using the PINCH assembly platform and four-wire resistance measurements are reported. The total I/O count comes to 1089 per die. Single-chiplet and multi-chiplet implementations of PINCH are discussed. The total average resistance between chiplets was 113.8 mΩ for the single-chiplet assembly and 127.7 mΩ for the multi-chiplet assembly.

In the vibratiing environment, the featherweight mass of a clip-in chiplet would be an advantage, as it would have low momentum and thus be less likely to be displaced. (See DToE)*.

* Diogenese Theory of Everything.
 
  • Like
  • Fire
  • Love
Reactions: 31 users

Frangipani

Top 20
Check out this wonderful new use case: 😍

A collaboration with Omani start-up Onsor on real-time epilepsy seizure prediction in innovative smart glasses, incorporating both EEG sensors and neuromorphic processing capabilities thanks to AKD1500!

“At Onsor, we believe technology should empower people, not just assist them. That’s why we set out to create something truly life changing. A device that predicts seizures before they happen using AI. By integrating BrainChip’s Akida technology, we’re giving people real-time alerts, the power to take control, and the freedom to live with confidence. Great partnerships create breakthroughs. By integrating BrainChip’s Akida technology, we’re pushing the boundaries of what’s possible in AI and IoT. This collaboration isn’t just about technology, it’s about creating real-world solutions, like our neuromorphic seizure prediction glasses, that make a meaningful impact,” said Maadh Al Hinaai, CEO of Onsor Technologies.

The Onsor solution consists of a pair of wearable glasses incorporating EEG sensors, neuromorphic processing capabilities, paired with a user-friendly alert system on a mobile device. The key innovation is a seizure prediction neural network running on BrainChip’s Akida architecture, trained using Onsor data sets to achieve more than 95% accuracy out of the box with incremental learning and personalization algorithms to continuously increase accuracy for the user.


“Wearable devices such as these are only possible due to the innovation of Akida’s neuromorphic approach to produce ultra-low power processing and its ability to optimize the development and deployment of AI applications for the Edge. We look forward to continuing to collaborate with Onsor to advance the capabilities of this revolutionary product throughout its development and introduction into the market.” said Sean Hehir, BrainChip CEO.




D6680EFE-3040-4CC1-8763-DE67C92163C8.jpeg




2F0294B4-8D7B-4AC4-9D30-13F454DCF9C2.jpeg




D7EB6901-A8F3-4129-A6D1-9D894BEA23B5.jpeg
E294940E-512E-4206-9C73-52F3B1361AD4.jpeg
42779D46-BC7D-4B8C-8DD4-4C69E4192EDB.jpeg



BrainChip Collaborates with Onsor Technologies To Power Epileptic Seizure-Detecting Glasses

February 24, 2025 11:00 AM Eastern Standard Time

LAGUNA HILLS, Calif.--(BUSINESS WIRE)--BrainChip Holdings Ltd (ASX: BRN, OTCQX: BRCHF, ADR: BCHPY), the world’s first commercial producer of ultra-low power, fully digital, event-based, neuromorphic AI, today announced a collaboration with Onsor Technologies to enable an innovative approach using neuromorphic computing to predict epileptic seizures utilizing the Akida™ Platform in a wearable design.

“At Onsor, we believe technology should empower people, not just assist them. That’s why we set out to create something truly life changing. A device that predicts seizures before they happen using AI. By integrating BrainChip’s Akida technology, we’re giving people real-time alerts, the power to take control, and the freedom to live with confidence. Great partnerships create breakthroughs. By integrating BrainChip’s Akida technology, we’re pushing the boundaries of what’s possible in AI and IoT. This collaboration isn’t just about technology, it’s about creating real-world solutions, like our neuromorphic seizure prediction glasses, that make a meaningful impact,” said Maadh Al Hinaai, CEO of Onsor Technologies.

The Onsor solution consists of a pair of wearable glasses incorporating EEG sensors, neuromorphic processing capabilities, paired with a user-friendly alert system on a mobile device. The key innovation is a seizure prediction neural network running on BrainChip’s Akida architecture, trained using Onsor data sets to achieve more than 95% accuracy out of the box with incremental learning and personalization algorithms to continuously increase accuracy for the user.


“Wearable devices such as these are only possible due to the innovation of Akida’s neuromorphic approach to produce ultra-low power processing and its ability to optimize the development and deployment of AI applications for the Edge. We look forward to continuing to collaborate with Onsor to advance the capabilities of this revolutionary product throughout its development and introduction into the market.” said Sean Hehir, BrainChip CEO.

About BrainChip Holdings Ltd (ASX: BRN, OTCQX: BRCHF, ADR: BCHPY)
BrainChip is the worldwide leader in Edge AI on-chip processing and learning. The company’s first-to-market, fully digital, event-based AI processor, Akida™, uses neuromorphic principles to mimic the human brain, analyzing only essential sensor inputs at the point of acquisition, processing data with unparalleled efficiency, precision, and economy of energy. Akida uniquely enables Edge learning on the chip, independent of the cloud, dramatically reducing latency while improving privacy and data security. Akida Neural processor IP, when integrated into SoCs on any process technology, has shown substantial benefits on today’s workloads and networks, and offers a platform for developers to create, tune and run their models using standard AI workflows like Tensorflow/Keras. In enabling effective Edge compute to be universally deployable across real world applications such as connected cars, consumer electronics, and industrial IoT, BrainChip is proving that on-chip AI, close to the sensor, is the future, for its customers’ products, as well as the planet. Explore the benefits of Essential AI at www.brainchip.com.

About Onsor
At Onsor, we take pride in being a prominent technological entity, deeply rooted in Omani culture and national pride, committed to placing the Sultanate at the forefront of the global technology arena with unparalleled expertise. Our core drivers of ideas, innovation, and inspiration empower us to deliver cutting edge technological solutions that elevate the lives of our users.
Go Beyond at Onsor.om.

Follow BrainChip on Twitter: https://www.twitter.com/BrainChip_inc
Follow BrainChip on LinkedIn: https://www.linkedin.com/company/7792006
 
Last edited:
  • Like
  • Love
  • Fire
Reactions: 86 users

Frangipani

Top 20
We get a couple of mentions in this article by AI Consultant and Venture Capitalist Seth Dobrin (IBM’s former Global Chief AI Officer) - here are some excerpts:


59024BAE-DAAF-4180-A929-97058C837FFC.jpeg


BFE91BB6-A351-4C3E-9D08-E944294B5EBA.jpeg


D207B265-1012-465A-AEB7-E95DEAEE2AC3.jpeg
EFAEF1FD-5BCF-4916-91F2-35ACEF0EC437.jpeg
C1026BD4-8C91-4F77-92EA-B83A276008F5.jpeg





00A30D0A-F146-4599-B43D-1BB08371EC71.jpeg
C0DBEED4-5083-4316-89A2-0CA722DEFB45.jpeg
 
  • Like
  • Love
  • Fire
Reactions: 59 users
Top Bottom