Re:NTSB: Autopilot steered Tesla car toward traffic barrier ...
by jeffreygoesto on Thursday June 07, 2018 @02:23PM
(#17258648)
It is a ROC curve/precision-recall issue basically. Radar has a terrible lateral and even worse to non-existing elevation measurement. Potholes, man holes, Coke cans and ground clutter look all alike and can in fact be detected as "having the negative relative velocity as my car's own velocity". You want to stop for only very few of all those stationary objects, otherwise you won't drive at all. The problem is you can't classify the relevant ones with radar. Which is why the camera helps, but obviously (for false positive suppression and a high availability of the autopilot) only if it positively classifies a car's rear.
[ Parent
| on HN ]
Re:NTSB: Autopilot steered Tesla car toward traffic barrier ...
by greedo on Thursday June 07, 2018 @02:52PM
(#17258950)
The military does it with SAR (synthetic aperture radar). Is something like that feasible for self-driving cars?
Re:NTSB: Autopilot steered Tesla car toward traffic barrier ...
by WrtCdEvrydy on Thursday June 07, 2018 @04:20PM
(#17259872)
Consider price point implications.
Re:NTSB: Autopilot steered Tesla car toward traffic barrier ...
by greedo on Thursday June 07, 2018 @04:34PM
(#17260002)
Well, if SDVs take off as advocates espouse, the volume (plus Moore's Law) will make costs drop.
Re:NTSB: Autopilot steered Tesla car toward traffic barrier ...
by jacquesm on Friday June 08, 2018 @07:33AM
(#17264322)
Volume maybe, but Moore's Law definitely not.