[LINK] itN: 'Third fatal Tesla Autopilot crash ...'

[Bernard Robertson-Dunn]

On 21/05/2019 10:58 am, Kim Holburn wrote:
> I would think that only 3 fatal autopilot crashes is probably a very small number.  To figure out how it compares to human driving, you'd probably have to work out how much it's being used and figure how many fatal crashes there would have been without autopilot. 
>
> It's pretty clear that Level 3 and 4 autodriving systems have the potential to be dangerous and we have to jump to level 5: full self-driving cars.  There will still be crashes. Certainly as long as humans and computers share the roads but probably after as well.

In my experience as an automation engineer, when you automate something
you have to be able to deal with all the exceptions that a human can
manage instinctively. Humans can usually tell that something is
unexpected and has a strategy to deal with it - stop, swerve etc. This
is not 100% fail safe but it has a reasonable track record. Machines
need to be proactively programmed. This is hard.

Autodriving/full self-driving cars need to be tested against exceptions,
not the norm. AFAIK that has never happened and may only happen over
time in use, not the lab.

-- 

Regards
brd

Bernard Robertson-Dunn
Canberra Australia
email: brd at iimetro.com.au