BRN Discussion Ongoing

[FJ-215]

Morning FJ-215 ,

Google Image Result for https://chain.com.au/cdn/shop/products/67ddd576bbba42e78c27424a19298a34.thumbnail.0000000000_600x600.jpg?v=1681723222

Regards,
Esq.

I do prefer the golf kind.

 

[Esq.111]

Indeed,

Lad opens champagne bottle using golf ball. Via: Josh Kelley Golf | SPORTbible | Facebook https://share.google/nnbEd6UtN2p8lyDRX

Esq.

 

[charles2]

Persistent and disciplined buying of both BRCHF and BCHPY today both closing at their highs.

Over 1.1m shares traded of BRCHF....three times normal volume.

Usually trading in the US is quite haphazard.....not today. Draw your own conclusions after yesterday's ASX trading tsunami....interrupted by ASX functionaries.

 

[Tothemoon24]

Traditional LiDAR systems depend on the cloud, creating delays that limit how fast machines can respond. Akida PointNet++ brings AI processing directly to the edge, reducing latency by up to 80% and operating on just a few milliwatts of power.

This means faster perception, safer navigation, and smarter automation for vehicles, drones, robots, and intelligent infrastructure.

With Akida’s efficient on-chip design, devices can interpret complex 3D environments instantly without relying on cloud connectivity.

Learn how BrainChip’s Akida PointNet++ is shaping the future of spatial AI.
https://lnkd.in/gzbyf9Kv

LiDAR Point Cloud_LP

Leverage BrainChip’s advanced Lidar & point-cloud solutions for real-time edge perception with efficient neuromorphic processing.

brainchip.com

 

[7für7]

Traditional LiDAR systems depend on the cloud, creating delays that limit how fast machines can respond. Akida PointNet++ brings AI processing directly to the edge, reducing latency by up to 80% and operating on just a few milliwatts of power.

This means faster perception, safer navigation, and smarter automation for vehicles, drones, robots, and intelligent infrastructure.

With Akida’s efficient on-chip design, devices can interpret complex 3D environments instantly without relying on cloud connectivity.

Learn how BrainChip’s Akida PointNet++ is shaping the future of spatial AI.
https://lnkd.in/gzbyf9Kv
View attachment 91807

LiDAR Point Cloud_LP

Leverage BrainChip’s advanced Lidar & point-cloud solutions for real-time edge perception with efficient neuromorphic processing.

brainchip.com

Thanks for the post! I also was about to post the same and deleted it…..

I just have one question… When I post something, I usually write one or two sentences about what it’s about and then add the link.

I’ve noticed that you often also take a screenshot of the post’s header with the BrainChip logo, copy and paste the text separately, and then also include the link — all good, of course — but why the screenshot of the header with the BrainChip logo?

 

[7für7]

Sorry if already posted

“BrainChip experts host an interactive webinar showcasing the benefits of executing AI/ML inference models on BrainChip’s Akida 2 remotely using Akida Cloud.”

Akida Cloud Webinar

Join BrainChip's Akida Cloud webinar for a practical walkthrough and live demos on Akida 2, showcasing on-device AI capabilities without hardware requirements.

brainchip.com

 

[Taproot]

Home

Parsons is a digitally enabled solutions provider and a leader in many diversified markets with a focus on national security, defense, and global infrastructure.

www.parsons.com

 

[7für7]

It’s a long time ago since we talked about gaps… is……is there any gap to….is there any gap to close?

 

[Mccabe84]

Fingers crossed we get a short squeeze as they might not be the ones buying

 

[equanimous]

in response to the speeding ticket yesterday Brainchip has decided to go again....

 

[7für7]

Here is the LinkedIn post regarding Akida…LiDAR

Akida PointNet++: Edge AI for Faster LiDAR Processing | BrainChip posted on the topic | LinkedIn

raditional LiDAR systems depend on the cloud, creating delays that limit how fast machines can respond. Akida PointNet++ brings AI processing directly to the edge, cutting latency to under 10 milliseconds while consuming only a few milliwatts of power. This means faster perception, safer...

www.linkedin.com

 

[Bravo]

The partnership between Arduino and BrainChip was announced in October 2022

Just to clarify, BrainChip and Arduino have not formally announced a partnership to date. However there is a connection between Brainchip and Arduino via the Edge Impulse ecosystem.

• In May 2022, BrainChip and Edge Impulse officially announced a partnership to accelerate AI/ML deployments on BrainChip’s Akida platform.
• In October 2022, Arduino and Edge Impulse announced a white-label partnership, integrating Edge Impulse Studio directly into Arduino’s online tools.

In a post dated 21 January 2024 (see below), Fact Finder highlighted a project by Christopher Mendez (PRO Content Creator at Arduino) that used BrainChip’s AKD1000 with Edge Impulse to control a TV, air conditioner, or light simply by pointing at them. Using the Akida Development Kit and a Logitech BRIO 4K Webcam, the model achieved excellent accuracy and ultra-low power consumption. Mendez concluded:

"This project leverages the Brainchip Akida Neuromorphic Hardware Accelerator to propose an innovative solution to home automation. It can be optimized to work as a daily used gadget that may be at everyone's house in the near future.”

Fast-forward to today and Qualcomm has now acquired both Arduino (this week) and Edge Impulse (earlier this year), bringing them under the same umbrella.

I believe this creates a very interesting pathway where BrainChip could possibly integrate through Edge Impulse’s existing Akida support into the Arduino ecosystem via Qualcomm’s new edge AI stack. Or Qualcomm may encourage developer cross-pollination among its new assets (Arduino + Edge Impulse + Snapdragon Spaces, etc).

So while there’s still no direct BrainChip / Arduino partnership, the ecosystem connections have become much closer and potentially far more strategic.

At least that's what I'm hoping.




Link here #74,284

 

[7für7]

in response to the speeding ticket yesterday Brainchip has decided to go again....

View attachment 91809

Let’s see where we end up on Friday… latest Monday… I think the shorter will take every cent no matter what…. I don’t trust that sh…

 

[Pom down under]

2025 A.I. Awards Finalists | Cloud Computing & SaaS Awards

www.cloud-awards.com

 

[Bravo]

Traditional LiDAR systems depend on the cloud, creating delays that limit how fast machines can respond. Akida PointNet++ brings AI processing directly to the edge, reducing latency by up to 80% and operating on just a few milliwatts of power.

This means faster perception, safer navigation, and smarter automation for vehicles, drones, robots, and intelligent infrastructure.

With Akida’s efficient on-chip design, devices can interpret complex 3D environments instantly without relying on cloud connectivity.

Learn how BrainChip’s Akida PointNet++ is shaping the future of spatial AI.
https://lnkd.in/gzbyf9Kv
View attachment 91807

LiDAR Point Cloud_LP

Leverage BrainChip’s advanced Lidar & point-cloud solutions for real-time edge perception with efficient neuromorphic processing.

brainchip.com

Quite the coincidence if you ask me.

I was just thinking that BrainChip’s new Akida PointNet++ may be the missing piece in that puzzle behind Qualcomm’s acquisition of Arduino, to accelerate its push into robotics and intelligent automation, as discussed a little earlier.

I don't believe that Qualcomm currently has any true equivalent to Akida PointNet++, especially when it comes to real-time, neuromorphic 3D point-cloud processing at the edge, which is a critical capability for next-generation robotics, drones, and autonomous systems.

By processing LiDAR and 3D spatial data directly at the edge, Akida PointNet++ delivers sub-10 ms spatial awareness while drawing only milliwatts of power, potentially giving Qualcomm exactly what its robotics roadmap needs - faster perception, longer battery life, and smarter autonomy.

Combined with Arduino + Edge Impulse (Qualcomm), this could finally democratize neuromorphic robotics, with Akida quietly powering the spatial intelligence beneath it all.

Here's hoping!

 

[smoothsailing18]

Traditional LiDAR systems depend on the cloud, creating delays that limit how fast machines can respond. Akida PointNet++ brings AI processing directly to the edge, reducing latency by up to 80% and operating on just a few milliwatts of power.

This means faster perception, safer navigation, and smarter automation for vehicles, drones, robots, and intelligent infrastructure.

With Akida’s efficient on-chip design, devices can interpret complex 3D environments instantly without relying on cloud connectivity.

Learn how BrainChip’s Akida PointNet++ is shaping the future of spatial AI.
https://lnkd.in/gzbyf9Kv
View attachment 91807

LiDAR Point Cloud_LP

Leverage BrainChip’s advanced Lidar & point-cloud solutions for real-time edge perception with efficient neuromorphic processing.

brainchip.com

AI Overview

+1

Over 1.6 million LiDAR units were shipped globally in 2024, a figure that is expected to quadruple by 2030, driven primarily by increasing adoption in passenger cars. The market's massive growth is a clear indicator of the increasing demand for LiDAR technology across various sectors, including autonomous vehicles and advanced driver-assistance systems (ADAS).

 

[Bravo]

Nice to see the ol' share price continuing to head in the right direction!

Hot diggity dog!

 

[Pom down under]

Nice to see the ol' share price continuing to head in the right direction!

Hot diggity dog!



View attachment 91816

 

[miaeffect]

Nice to see the ol' share price continuing to head in the right direction!

Hot diggity dog!



View attachment 91816

Your tub time is coming

 

[smoothsailing18]

From the other site

Here are some benchmarks comparing PointNet++ running on Akida 2 vs NVIDIA Jetson Xavier NX and Orin NX for real-time LiDAR classification at the edge.

1. Benchmark Sources​

• Akida PointNet++: BrainChip LiDAR Point Cloud Model brochure (Oct 2025).
• Jetson Xavier NX / Orin NX: Derived from public PyTorch PointNet++ benchmarks on ModelNet40 and KITTI, using TensorRT-optimized inference (batch = 1).
  • Xavier NX: 384 CUDA cores, 21 TOPS INT8
  • Orin NX: 1024 CUDA cores, 100 TOPS INT8
• Power figures are measured in NVIDIA’s MaxN mode, which reflects real deployment on drones / robotics platforms.

2. PointNet++ Performance Comparison​

Metric	Akida 2	Jetson Xavier NX	Jetson Orin NX
FPS (ModelNet40)	183 FPS	65 – 85 FPS (FP16/INT8)	110 – 135 FPS (FP16/INT8)
Latency / Frame	5 – 6 ms	12 – 15 ms	7 – 9 ms
Power	50 mW	10 – 15 W	15 – 25 W
Energy / Inference	0.28 mJ	~150 – 200 mJ	~200 – 300 mJ
Model Size	1.07 MB	~10 – 12 MB	~10 – 12 MB
Accuracy (ModelNet40)	81.6 % (4-bit QAT)	89 – 90 % (FP32 baseline)	89 – 90 % (FP32 baseline)
Deployment Mode	Always-on, ultra-low power	Embedded GPU (fan/heat dissipation required)	High-end embedded GPU

3. What This Shows​

1. Throughput
   • Akida 2 actually outperforms Xavier and Orin NX on raw FPS, despite being neuromorphic and consuming three orders of magnitude less power.
   • Orin NX gets closer but still lags slightly at similar batch sizes.
2. Power & Energy
   • Akida’s ~50 mW is in a completely different regime than the 10–25 W Jetson modules.
   • That’s ~500×–1000× lower energy per inference, which is decisive for always-on payloads (e.g. drones, satellites, smart infrastructure).
3. Accuracy Trade-off
   • Akida’s quantized model (4-bit QAT) loses ~8 % absolute accuracy vs FP32, but this is expected and often acceptable for edge classification, especially if upstream sensor fusion provides redundancy.
4. Form Factor / Thermal
   • Jetsons need active cooling and steady power supply — not trivial on space or micro-UAV platforms.
   • Akida can operate fanless, battery-powered, or solar-powered.

4. Strategic Takeaway​

Use Case	Best Fit
Battery-powered always-on LiDAR classification (e.g., satellite autonomy, drones, infrastructure nodes)	Akida 2 — ultra-low power, high FPS, compact
Onboard AI co-processor with larger perception stack (e.g., autonomous cars, ground robots)	Jetson Orin NX — higher model flexibility, better FP32 accuracy, but power-hungry
Mixed sensor fusion payloads with strict SWaP (e.g., ESA cubesats, tactical drones)	Akida as front-end classifier + Jetson/FPGA for downstream fusion or planning

Summary Table​

Feature	Akida 2	Jetson Xavier NX	Jetson Orin NX
FPS	183	65–85	110–135
Power	0.05 W	10–15 W	15–25 W
Energy/Inference	0.28 mJ	150–200 mJ	200–300 mJ
Accuracy	81.6 %	≈ 90 %	≈ 90 %
Edge Suitability	Always-on	Thermally constrained	High-end only

Bottom line:​

For PointNet++ at the edge, Akida 2 outperforms Jetson Xavier NX and Orin NX on raw FPS, power, and energy efficiency, with a modest accuracy gap from quantization that can be narrowed through improved training and model updates. This is why BrainChip is targeting Akida PointNet++ for autonomous drones, satellites, and infrastructure nodes — it's built for tiny, always-on LiDAR intelligence rather than general AI workloads.

*GPT5