I think the point was that lidar is too low resolution. You must have very high resolution (in both time and space) to achieve L4 or L5; to accurately determine if a pedestrian is not paying attention, or if a bicyclist is looking to cross the road.
Not that Tesla is doing any of that right now, they most likely are not. But a lidar is not going to, either. Not ever, which is the point.
I thought the fleet learning aspects Karpathy outlines came pretty damn close to the pixie dust.
Musk would have you think it's a Lidar vs. cameras debate. It's not. It's a Lidar + cameras vs. just cameras debate. Lidar has significant shortcomings. So do cameras. But together they make for a decent perception system.
With regards to fleet learning, Tesla has been going on about it for years, but more data is not better. Better data is better. Clifornia's disengagement reports have seen criticism because they place an emphasis on the number of overall miles driven as a useful measure of progress, when actually it doesn't mean much. Companies like Zoox, after spending years doing small-scale closed course testing hit the ground running, and with only 10 vehicles and a few months of driving around San Fransisco they were able to take reporters for autonomous rides, and they took a couple dozen journalists to various pre-designated spots around SF with only one disengagement the whole day.
The nice thing about the whole fleet learning narrative is that is makes Tesla drivers feel like they're helping just by driving around.
That's correct, it's lidar+cameras vs just cameras. But it should be RF + radar + sonar + lidar + cameras vs anything else. If the 737Max8 tells us anything, it's that one sensor just isn't enough.
EM radiation from UV down to radio has different propagation characteristics, and materials form different attenuators. Radio easily passes through most non-metals with less attenuation than 400-800 THz radiation (light). When I was at Tesla, I tried like heck to get people to internalize this, but the 'cameras + one forward-looking radar is enough' crowd has clearly won.
Heck, RF can shoot through mud, rain, sleet, and snow. Cameras? not so much. Although I agree that the number of 'RF pixels' one gets is nowhere near what a camera provides, it does provide some pixels when the cameras are covered in road muck.
And what about when it's dark? Are the headlights going to provide enough light for the cameras to function well in all road conditions?
Well technically it's Lidar + Cameras + inertial measurement units + GPS + ultrasonic proximity sensors + Radar vs. all those things minus that one sensor that costs too much.
I haven't seen any mentions of cheaper Lidars, like single axis scanning only, to get some sort of depth map without spinning mirrors or 360 degree positions that ruin aesthetics.
I feel like this would be able to detect trees in the distance and other objects to orient the road/lane detection. And keep it cheap. Possibly add on to existing cars.
You can achieve L4 before you can determine if a pedestrian is paying attention. Your car will be slowing down when it doesn't have to but it can work and work safely.
Well, it has to work well enough to be useful. When Waymo reports one disengagement every 11,000 miles, that's just the safety critical disengagements. The total disengagement rate is much higher than that. They are also relying on teleoperators who can help guide the vehicles out of tricky situations, which are myriad and it will take forever for Waymo to build features down to a granular enough level that they can operate reliably enough to compete with Uber.
Slowing down isn’t always an option and it’s not always safe. (What happens when all the human driven cars keep driving at normal speed? You’ve now created an unsafe traffic condition for everyone.)
Not that Tesla is doing any of that right now, they most likely are not. But a lidar is not going to, either. Not ever, which is the point.
I thought the fleet learning aspects Karpathy outlines came pretty damn close to the pixie dust.