BRN 2.22% 22.0¢ brainchip holdings ltd

Anyonre else remember Rob Telson recently speaking about...

  1. 9,738 Posts.
    lightbulb Created with Sketch. 25487
    Anyonre else remember Rob Telson recently speaking about increasing the range of EV's and Autonomous Vehicles towards 1000 kilometres. If you did this article in particular the comments from FORD make interesting reading:

    "Autonomous Driving SystemsSlash EV Driving Range by 25 Percent

    Waymo

    The powerful computer and sensorsnecessary for autonomy draw a surprising amount of energy.

    DanCarney | Apr 25, 2021

    The microprocessors, cameras, lidars, and radarsneeded to let cars drive themselves consume so much electric power that theycan trim the driving range by one-fourth.

    “The compute [power] just to run the algorithms tomake all the decisions to drive the car could take 25 percent of the electricrange off an electric car,” stated Ford Motor Co. CEO Jim Farley during an interview posted on Hagerty’s YouTube channel. “That’s how power-hungry the human-equivalent of our brain decision-making is,” he said. “Humans are amazing! To try to beat a human, which is basically the intent, it’s a really hard problem.”


    Human sensors like eyes and ears are passive,so they add relatively little to the power draw, but autonomous vehicles useactively energetic sensors in the form of radar and lidar, which contributes tothe total system consumption topping that of a human pilot.

    “Total system power consumption for most AVstypically runs somewhere between 1.5-3 kW,” noted Sam Abuelsamid, PrincipalAnalyst for e-mobility ecosystems, Guidehouse Insights. “That includes thepower for all the sensors and the compute. Compute alone is probably about500-1,000W depending on the specific configuration.”

    “From our perspective, this is certainly not asustainable model for consumers nor our environment as CO2 emissions continueto skyrocket — and begs the question of whether autonomous vehicles will trulybe able to deliver on the promise of greener transportation,” observed RobertBielby, Senior Director of Automotive System Architecture and Segment Marketing,Embedded Business Unit, at Micron. “To put those earlier power figures intoperspective, the industry would ideally like to target 75-200 watts maximum forthe compute power for autonomous vehicles, so I believe the industry has a longway to go.”

    In recognition of this challenge to EV range, theindustry is developing guidelines to help gauge autonomous vehicle processorenergy consumption. "AVCC members feel that improving the power efficiencyof compute systems is important and we have recently launched aMicro-benchmarks Working Group to investigate this and other topics,” said TimWong, chairman of the Autonomous Vehicle Computing Consortium. “Benchmarksoffer valuable industry insight about workloads that are likely to be executed.This information will help automotive compute designers to improve theperformance and power efficiency of their products.”

    The difficulty of saving energy is apparent whenconsidering the size of the processing task. “Autonomous vehicles need to makeimportant decisions in real-time, and all of that requires processing a massiveamount of data from the fusion of multiple sensors including radar, lidar,and high-resolution cameras,” explained Bielby. “As a testament to thesheer quantity of data that autonomous vehicles process, they are expected togenerate an average of 20 terabytes of data per day. Combine that with the AI(like gesture recognition, natural language processing, computer vision, andmachine learning) needed to piece together and analyze that data in splitseconds—on top of in-vehicle infotainment, HD displays, and other digitalcockpit features—and we’re seeing an exponential increase in memory and computedemands.”

    Just look at the complexity of their software toaccomplish these tasks. “The modern luxury vehicle now runs over 100 millionlines of code, more than Facebook, Windows Vista, Google Chrome,Boeing 787, the Space Shuttle, and the Hubble Space Telescope,” Bielbyreported. “This could grow to 200-300 million lines of code in thenear future. To achieve Level 4 to Level 5 autonomous capabilities, computeperformance at the level of 600 tera operations per second isrequired, rivaling what you can find in data centers and servers.”

    Micron is working to reel in the power consumptionby the autonomy systems with the goal of preserving EV power. “To get back someof that driving range, automotive OEMs and suppliers can look to use low-power,energy-efficient memory and storage created using the most advanced processtechnology nodes (aka more advanced semiconductor process nodes based onstate-of-the-art manufacturing techniques),” Bielby said.

    There is also room for improvement when it comes tooptimizing these systems for use in autonomous vehicles. “The energy problem isalso reflective of the fact that today’s circuits and solutions are not yetfully optimized for the autonomous space,” Bielby stated. “For example, AIcomputation requires a lot of back and forth between external memory and thecomputer chip. Every time the car reads or writes to external memory, the poweris more than 100X what it would be if the processing could be done locallywithin the chip.

    Cars can also wring improvements from theirelectric architecture, according to Bielby. “Another way automotive players arelooking to improve energy efficiency and extend driving range is a fundamentalrethink and redesign of the underlying electrical system architecture,” hesaid.

    “As the number of electronic control units andsensors has continued to increase dramatically with each generationof vehicle, the associated wiring has grown considerably to the point where itcan represent almost 5 percent of the vehicles’ weight, Bielbycontinued. “And it’s no wonder — today’s high-end vehicle cancontain more than 100 ECUs and 500 LEDs with an ever-growing number ofsensors. Interconnecting this large number of ECUs and sensors canrequire up to 5000 meters of wiring.”

    Considering the increasing demands for processingpower, it will be interesting to see how successful carmakers are at reducingpower consumption for autonomous driving computer systems and sensors, butknowing that industry groups are already targeting this concern suggests thepotential for progress by the time cars really are able to chauffeur us to ourdestinations."

    My opinion only DYOR
    FF

    AKIDA BALLISTA

 
watchlist Created with Sketch. Add BRN (ASX) to my watchlist
(20min delay)
Last
22.0¢
Change
-0.005(2.22%)
Mkt cap ! $408.3M
Open High Low Value Volume
22.5¢ 22.5¢ 21.8¢ $1.107M 5.019M

Buyers (Bids)

No. Vol. Price($)
6 110458 22.0¢
 

Sellers (Offers)

Price($) Vol. No.
22.5¢ 355185 24
View Market Depth
Last trade - 16.10pm 28/06/2024 (20 minute delay) ?
BRN (ASX) Chart
arrow-down-2 Created with Sketch. arrow-down-2 Created with Sketch.