Re:Tesla's self driving algorithm's overlay [video]
by jedberg on Monday February 03, 2020 @03:40PM
(#22228773)
Probably is. The computer power necessary to go higher would use all the battery and take up a ton of space.
If you've seen other self driving cars, they usually have no trunk because the entire thing is server racks.
Re:Tesla's self driving algorithm's overlay [video]
by jamestimmins on Monday February 03, 2020 @03:46PM
(#22228850)
Maybe this is ridiculous, but is it feasible that Tesla plans to use the SpaceX Starlink satellites to offload data for processing remotely?
Re:Tesla's self driving algorithm's overlay [video]
by jedberg on Monday February 03, 2020 @03:48PM
(#22228869)
Unlikely, too risky. Even the slightest glitch in the network could be disastrous. The car has to be at least smart enough to pull over and stop safely.
Re:Tesla's self driving algorithm's overlay [video]
by mAritz on Monday February 03, 2020 @05:05PM
(#22229758)
When talking about computation being a power drain, one could imagine a scenario where certain computations that can deal with the latency of starlink internet could be offloaded by default to the cloud. When a network failure is detected or results take too long to come in, the on-board computer could still take over the same computations, resulting in more power drain for a short moment.
Re:Tesla's self driving algorithm's overlay [video]
by gzer0 on Monday February 03, 2020 @09:17PM
(#22231719)
There are 4,000+ planned starlink satellites that are planning to be deployed in total. This, in addition to backup with cell towers in case starlink goes down really makes this scenario risk-free.
Re:Tesla's self driving algorithm's overlay [video]
by daniel2x on Monday February 03, 2020 @04:18PM
(#22229223)
Have you ever filled out a Captcha identifying roadsigns?
Re:Tesla's self driving algorithm's overlay [video]
by jamestimmins on Monday February 03, 2020 @06:18PM
(#22230460)
I'm not sure I follow? I'm just asking whether it's possible that the underlying processing could take place in a remote server, rather than an onboard computer in the car.
Re:Tesla's self driving algorithm's overlay [video]
by daniel2x on Tuesday February 04, 2020 @03:20PM
(#22240484)
I was making a subtle joke that filling out a captcha identifying roadsigns could be the remote server that drives someone's car.
Re:Tesla's self driving algorithm's overlay [video]
by maccam94 on Monday February 03, 2020 @04:04PM
(#22229071)
The cameras are running at higher fps, but the processed outputs don't need to go that fast. At 65MPH, 18fps is one frame for every 5 feet of travel.
Re:Tesla's self driving algorithm's overlay [video]
by kevin_thibedeau on Monday February 03, 2020 @04:38PM
(#22229455)
Not fast enough to react to someone swerving into your lane.
Re:Tesla's self driving algorithm's overlay [video]
by ygra on Monday February 03, 2020 @05:05PM
(#22229765)
Cars don't tend to jump sideways all of a sudden (and if they do, then usually by outside force, which tends to be hard to avoid). There's plenty of frames to detect that (note that the view shown is not the only camera, otherwise making a turn safely would be fairly impossible).
Re:Tesla's self driving algorithm's overlay [video]
by kevin_thibedeau on Monday February 03, 2020 @05:17PM
(#22229900)
They don't have to "jump" sideways. All it takes is someone assuming you aren't there and moving into the space you occupy.
Re:Tesla's self driving algorithm's overlay [video]
by kickopotomus on Monday February 03, 2020 @05:15PM
(#22229885)
Much faster than a human would react. Acutely focused humans generally take at least 1 second to hit the brakes in an emergency. Longer if distracted or tired[1].
[1]: https://www.researchgate.net/publication/233039156_Brake_Rea...
Re:Tesla's self driving algorithm's overlay [video]
by kevin_thibedeau on Monday February 03, 2020 @05:18PM
(#22229912)
Braking is slowed by the limitations of nerve conduction down to the legs. You can swerve away from danger with faster reaction time.
Re:Tesla's self driving algorithm's overlay [video]
by kickopotomus on Monday February 03, 2020 @05:22PM
(#22229955)
The same nerve conduction latency exists for your arms. The computer will beat you every time.
Re:Tesla's self driving algorithm's overlay [video]
by chillacy on Monday February 03, 2020 @05:35PM
(#22230089)
Perhaps a humorous example of this: a robot that always wins at rock paper scissors: https://www.youtube.com/watch?v=3nxjjztQKtY
There's a fun parlor trick which takes advantage of human reaction time too: place a hundred dollar bill on the table, let the other party place their hand a few inches away, start your hand a foot above theirs; the first person to place their hand on the money wins, and the other party can start moving as soon as you start moving. Turns out you can easily go around their hand and grab the bill before they're able to react.
Re:Tesla's self driving algorithm's overlay [video]
by kevin_thibedeau on Monday February 03, 2020 @05:56PM
(#22230292)
It's a shorter distance.
Re:Tesla's self driving algorithm's overlay [video]
by kickopotomus on Monday February 03, 2020 @06:13PM
(#22230431)
The distance is beside the point. The amount of time it takes for your brain to parse visual stimuli, then propagate a signal to your arms, and finally for the muscles in your arm to contract will be much slower than a computer parsing a sequence of images and then actuating the steering column. The computer is faster both at understanding it needs to respond and at signaling driving systems to respond.
Surely that can't be right