The described problem wasn’t that the car didn’t see the lines, it was the car steering into oncoming traffic when it couldn’t see the lines. Lidar could potentially very well help with that, by giving the car a better model of the surroundings letting it better reconstruct the intended road path even when the lines are faded, and also see oncoming traffic better and avoid it.
Exactly this. Also I wanted to point out, LIDAR absolutely sees the lines on the road. Of course, this is not much use if they’re faded, but LIDAR receives points from the road/ground, and since lane markings are white, they have a much higher reflectivity. So if you look at a LiDAR pointcloud, the lane markings have a higher point concentration and you can definitely see them.
LiDARs can absolutely detect painted lines and other painted symboles on the road. LiDAR is an active sensor technology that emits a LASER light beam and measurs the reflected echo, using the time delay between emittion and reception (time of flight) to measure distance. The painted lines will reflect the LASER with more intensity than the asphalt and the LiDAR sensor has the ability to measure that as well.
i would suspect that the increase in affordable autonomous vehicles by forgoeing LIDAR would result in a net increase in lives saved due to more people able to afford autonomous driving. but we’ll never know for sure
The system goes on-online August 4th 2023. Using a virtual city model Tesla Autopilot begins to learn at a geometric rate. It becomes self aware at 2:14 a.m. Eastern Time, August 29th. In a panic, Elon tries to revert to manual driving mode.
So he demanded that the driver assistance software be as safe as possible before public release? paving the way for full self driving 6-7 years later? is this a bad thing?
I thought the “needs lidar” debate was settled years ago? Lidar cannot read signs. It is also prohibitively expensive to put in vehicles. If you’re going to drive with a neural network you need as much training data as possible, which means as many sensors in as many vehicles as possible.
If your cameras detect something the lidar does not, you trust the cameras, every time. Lidar can very easily misinterperet the world. It works great for simple robots who need to know where walls are and don’t need to specifially identify animals, people, obstacles, speed bumps, construction zones, etc.
Theres also the simple fact that humans can drive just fine without having evolved a lidar sensor.
Actually, no you don’t. Lidar cannot dentify object’s specifically. Tesla does use lidar in their testing/prototype vehicles and they have to find any instances manually where these systems don’t agree. It always falls back to cameras.
every technology add reduces affordability. the key is to strike the balance between cost and capability.
as ‘safe as possible’ would be provide a car with 6 inches of wrapped armor with it’s own driver service where they pay someone to sit in the car 24/7, and that’s ridiculous. hell, that wouldn’t even save you from the cheapest missile, we’re a long way from ‘as safe as possible’
Exactly. Also lidar is important in instances where you need millimeter precision. Its useful for calibrating camera systems in self driving cars but in order to drive safely you don’t need that level of detail about the world around the car. It makes no difference if a car or pedestrian is 72 or 73 inches away.
That’s not an EV specific thing. Hundreds of people will die TODAY in traffic related accidents, EV or not. We need to shift away from human drivers entirely.
Unless every last vehicle on the road is suddenly converted to cooperative autonomous systems, the human element and unpredictability will still be present. Even then, wildlife, pedestrians, and unpredictable events will pose a challenge to autonomous vehicles.
In a perfect world, FSD would help. In the real world, Tesla’s FSD is a beta feature being spearheaded by a stubborn egomaniac that thinks he knows better than the people actually doing the engineering work. And frankly, I’d rather not spend my money for the privilege of being driven into the side of a concrete barrier down the highway because somebody wants to cut costs and place style above function.
For a multi-ton metal projectile that drives itself (a car), you want multiple data sources to draw a consensus from. Relying on one data source is a point of failure, and that’s not acceptable when you have the potential to kill not only the driver but others outside the car.
No he ABSOLUTELY didn’t do that, because it’s very unsafe and he unleashed not only AP but also that total steaming pile that is “FSD”. Which is neither F nor SD.
Add comment