Without LIDAR, this is a fool’s endeavor.
I wish this was talked about every single time the subject came up.
Responsible, technologically progressive companies have been developing excellent, safe, self-driving car technology for decades now.
Elon Musk is eviscerating the reputation of automated vehicles with his idiocy and arrogance. They don’t all suck, but Tesla sure sucks.
Even with LIDAR there are just too many edge cases for me to ever trust a self driving car that uses current-day computing technology. Just a few situations I’ve been in that I think a FSD system would have trouble with:
-
I pulled up at a red light where a construction crew was working on the side of the road. They had a police detail with them. As I was was watching the red light the cop walked up to my passenger side and yelled “Go!” at me. Since I was looking at the light I didn’t see him trying to wave me through the intersection. How would a car know to drive through a red light if a cop was there telling you to?
-
I’ve seen cars drive the wrong way down a one way street because the far end was blocked due to construction and backtracking was the only way out. (Residents were told to drive out the wrong way) Would a self driving car just drive down to the construction site and wait for hours for them to finish?
-
I’ve seen more than one GPS want to route cars improperly. In some cases it thinks a practically impassible dirt track is a paved road. In other cases I’ve seen chains and concrete barriers block intersections that cities/towns have determined traffic shouldn’t be going through.
-
Temporary detour or road closure signs?
-
We are having record amounts of rain where I live and we’ve seen roads covered by significant flooding that makes them unsafe to drive on. Often there aren’t any warning signs or barricades for a day or so after the rain stops. Would an FSD car recognize a flooded out road and turn around, or drive into the water at full speed?
In my opinion, FSD isn’t attempting to solve any of those problems. Those will require human intervention for the foreseeable future.
Musk’s vision is (was?) to eventually turn Tesla’s into driverless robo-taxis. At one point he even said he could see regular Tesla owners letting their cars drive around like automated Ubers, making money for them, instead of sitting idle in garages.
Well FSD is supposed to be Level 5 according to the marketing and description when it went on sale. Of course, we know Tesla’s lawyers told California that they have nothing more than Level 2, have not timeline to begin building anything beyond Level 2, and that the entire house of cards hinges on courts and regulators continuing to turn a blind eye.
Or there are better other ways to tell a FSD car that the road is closed. We could use QR code or something like that which includes info about blockade, where you can drive around it, and how long it will stay blocked. A FSD should be connected enough to call home and give info to the servers, those then update the other FSD cars, et voila tadaa.
I don’t know why people are so quick to defend the need of LIDAR when it’s clear the challenges in self driving are not with data acquisition.
Sure, there are a few corner cases that it would perform better than visual cameras, but a new array of sensors won’t solve self driving. Similarly, the lack of LIDAR does not forbid self driving, otherwise we wouldn’t be able to drive either.
challenges in self driving are not with data acquisition.
What?!?! Of course it is.
We can already run all this shit through a simulator and it works great, but that’s because the computer knows the exact position, orientation, velocity of every object in a scene.
In the real world, the underlying problem is the computer doesn’t know what’s around it, and what those things around doing or going to do.
It’s 100% a data acquisition problem.
Source? I do autonomous vehicle control for a living. In environments much more complicated than a paved road with accepted set rules.
You’re confusing data acquisition with interpretation. A LIDAR won’t label the data for your AD system and won’t add much to an existing array of visible spectrum cameras.
You say the underlying problem is that the computer doesn’t know what’s around it. But its surroundings are reliably captured by functional sensors. Therefore it’s not a matter of acquisition, but processing of the data.
Dont let them know about that I don’t want my radar detector flipping out for laser lol
K and KA band are used for blind spot monitoring and would make radar detectors go nuts until filtering got worked out, cars that use Lidar will set them off as well though they’re more rare still
Do you have lidar on your head? No, yet you’re able to drive with just two cameras on your face. So no lidar isn’t required. Not that driving in a very dynamic world isn’t very difficult for computers to do, it’s not a matter of if, it’s just a matter of time.
Would lidar allow “super human” driving abilities? Like seeing through fog and in every direction in the dark, sure. But it’s not required for the job at hand.
You have eyes that are way more amazing than any cameras that are used in self driving, with stereoscopic vision, on a movable platform, and most importantly, controlled via a biological brain with millions of years of evolution behind it.
I’m sorry, you can’t attach a couple cameras to a processor, add some neural nets, and think it’s anything close to your brain and eyes.
Do you have lidar on your head?
Nope,
And that’s exactly why humans crash. Constantly.
Even when paying attention.
They don’t have resolution in depth perception, nor the FOV.
I remember watching a video talking about is there a camera that can see as well as a human eye. The resolution was there are cameras that see close but not as well and they are very big and expensive and the human brain filters much of it without you realizing. I think it could be done with a camera or two but I think we are not close to the technology for the near future.
A lot of LIDAR fans here for some reason, but you’re absolutely right.
There’s just not a good amount of evidence pointing that accurate depth perception only obtained through LIDAR is required for self driving, and it also won’t solve the complex navigation of a real world scenario. A set of visible spectrum cameras over time can reconstruct a 3D environment well enough for navigation and it’s quite literally what Tesla’s FSD does.
I don’t know why someone would still say it’s not possible when we already have an example running in production.
“But Tesla FSD has a high disengagement rate” - for now, yes. But these scenarios are more often possible to be solved by high definition maps than by LIDAR. For anyone that disagrees, go to youtube, choose a recent video of Tesla’s FSD and try to find a scenario where a disengagement would have been avoided by LIDAR only.
There are many parts missing for a complete autonomous driving experience. LIDAR is not one of them.
