Silicon Investor (SI) -- The First Internet Community

STOCKTALK

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor. We ask that you disable ad blocking while on Silicon Investor in the best interests of our community. If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.

Technology Stocks : Qualcomm Moderated Thread - please read rules before posting -- Ignore unavailable to you. Want to Upgrade?

To: Art Bechhoefer who wrote (176486)	12/5/2022 1:34:56 PM
From: engineer	Read Replies (1) \| Respond to of 196451

the CONCEPT might be ok, but the actual corner cases to be solved have yet to be done. All these autonomous cars are running into strange places and things that they cannot predict. I have one road that I drive in San Diego alot near my home. My mercedes has alot of the autonomous stuff in it, but every time I pass one little spot, all the crash warning sensors go off for no reason, car tries to correct something, but I have never figured out what it doesn't like. just starts beeping and red lights come on and it does this thump thing that usually shows me I crossed over a line at the edge of the road. I have had this happen perhaps 50 or more times in the last 3 years. Little things like this make fully autononous driving cars a myth yet to be solved. I don't see everyone reaching the point where we just let them out on the roads without drivers for many years. They do not have enough AI processing power in the cars as of yet, and they definitely do not have the corner case training sets to learn from yet. It may take millions of more events to setup learning cases for the AI to get to where the system can be trusted in 99.9% of the time. If the automakers wanted to move the stuff forward, it would be much better if they all contributed common corner case training data to an industry base so that they can gain the training sets faster.