Breaking News
News & Analysis

TI Launches Purpose-Built SoCs for Automotive Vision

10/16/2013 00:01 AM EDT
15 comments
NO RATINGS
1 saves
Page 1 / 2 Next >
More Related Links
View Comments: Newest First | Oldest First | Threaded View
Page 1 / 2   >   >>
TCHsieh
User Rank
Rookie
Are we barking the wrong tree?
TCHsieh   11/6/2013 1:12:04 PM
NO RATINGS
Just like what the author quoted the industry expert's own expereince, the algorithm seemed working fine on freeway but failed a lot off freeway.  NO surprises here, environments on freeway are more predictable so the "human developed" software would handle better.  Off freeway, the environment becomes un-predictable and random.  The task may be simply too large for any state-of-the-art processor to handle and too complex for any "algorithm developer" to consider them all.  Yes, we can condition the user not to rely on the "smart" installed on car when off freeway.  But, it might be a "marketing no no".  We can also make incremental improvement over time when the processor becomes more powerful and able to extract more intelligence timely.  If so, based upon my years' obervation of technological advancement, the technology could always become a niche play and the "potential market" would prove to be illusive and never come to fruits. 

I am posting this message to ask a dumb question to my fellow engineers, are we barking the wrong tree?  Should we change the paradigm, instead of making the car smarter, we would make the road smarter? Let the car be a dumb receiver and follow the instruction from the processors monitoring road/traffic condition.  Leave the heavy lifting to those processors at fixed locations along the road.  Of course, we would still install some "smart" on car to detect those functions dealing with environment more local, such as "child behind the car during backing off", "a car is approaching near you".  What do you think? 

sw guy
User Rank
Manager
Re: Why a proprietary RISC core inside EVE?
sw guy   10/24/2013 6:40:47 AM
NO RATINGS
I assume this:

As EVE is expected to cope with very domain specific algorithms, some exotic instructions and/or data types/sizes are present. Consequently, cannot be a general purpose CPU.

But being exotic does not prevent a CPU to keep a small (reduced) number of instructions.

elctrnx_lyf
User Rank
Manager
Future of adas
elctrnx_lyf   10/19/2013 8:49:48 AM
NO RATINGS
Vision processing would be a key part of any autonomous driving systems in the future. I think TI may not be the only one in the race for a such a huge volume requirements in the future. Invention and Freescale also will be working on latest innovations to play a major role.

daleste
User Rank
CEO
Re: Cool
daleste   10/18/2013 8:14:57 PM
NO RATINGS
Hi Junko.  I'm not sure what you mean by "all the automotive chips", but they have many automotive qualified devices.  Mostly analog and mixed signal.  I don't think their automotive market share is very large.

junko.yoshida
User Rank
Blogger
Why a proprietary RISC core inside EVE?
junko.yoshida   10/18/2013 1:38:06 AM
NO RATINGS
This may be a minor detail, but when I was chatting with Jeff Bier at BDTI, he mentioned that a RISC core inside the vision hardware accelerator EVE (integrated inside this SoC) is not ARM, but TI's proprietary RISC core.

I wonder why... I mean, why not ARM?

junko.yoshida
User Rank
Blogger
Re: Ties in nicely with the "freaking out" article
junko.yoshida   10/18/2013 1:33:51 AM
NO RATINGS
What causes the remaining seven percent of traffic accidents  is an interesting question I haven't given much thought about. I will find out the answer...

junko.yoshida
User Rank
Blogger
Re: Ties in nicely with the "freaking out" article
junko.yoshida   10/18/2013 1:19:41 AM
NO RATINGS
No doubt, this is a hot field that's growing fast, I think.

Until several years ago, a lot of machine vision stuff was done on a sheer compute power basis. Purpose-built ADAS SoCs by comanies like Cognive, TI, Freescale and ST will definitely change the landscape for automotive vision.

junko.yoshida
User Rank
Blogger
Re: Cool
junko.yoshida   10/18/2013 1:09:57 AM
NO RATINGS
@daleste, that's a good point. I know that qualification is really a huge deal in the automotive market. Does TI manufacture pretty much all the automotive chips, then?

rstjobs
User Rank
Rookie
Re: ease of programming
rstjobs   10/17/2013 10:29:57 PM
NO RATINGS
As vision algorithms need lot of computational power, as hardware getting smarter faster we will see lot of such smart applications in future

Bert22306
User Rank
CEO
Ties in nicely with the "freaking out" article
Bert22306   10/17/2013 9:15:14 PM
NO RATINGS
"Further, 93 percent of traffic accidents in the United States are estimated to be due to human error."

I would have thought that number to be closer to 100 percent. I wonder, for example, if that stat includes less than ideal response to a sudden contingency, where a more expert, or perhaps automated reponse, could have avoided an accident. Things like skidding on ice, sudden tire failure, that sort of thing, where the blame is usually put on the mechanical problem rather than the response.

Very timely article. And if these vision systems are going to be a major component of the V2I solution, scanning signs and so on, there's going to be even more demand on the algorithms. Pretty exciting stuff, I'd say.

Page 1 / 2   >   >>
Most Recent Comments
August Cartoon Caption Winner!
August Cartoon Caption Winner!
"All the King's horses and all the KIng's men gave up on Humpty, so they handed the problem off to Engineering."
5 comments
Top Comments of the Week
Like Us on Facebook

Datasheets.com Parts Search

185 million searchable parts
(please enter a part number or hit search to begin)
EE Times on Twitter
EE Times Twitter Feed
Flash Poll
Radio
NEXT UPCOMING BROADCAST
How to Cope with a Burpy Comet
October 17, 2pm EDT Friday
EE Times Editorial Director Karen Field interviews Andrea Accomazzo, Flight Director for the Rosetta Spacecraft.