Is it possible to see microwave ovens on the ground with a Rydberg antenna array for in-cockpit drone Remote ID signal location?
Recently I heard about an approach where they train a model to behave as a Lidar, using only camera inputs. Sounds like a cool, modular approach, but not sure about safety.
You can train those models all you want, the sensors still have some physical limitations. A regular camera operating in the visible spectrum won't be able to penetrate dense fog, where lidar or radar may still work.
True, but it's the same for a human driver.
Sure, but we should aim for superhuman driving capabilities, especially in conditions humans struggle.
Maybe, but the car can also simply refuse to drive if the conditions are bad.
Of course it can refuse (and should do so if it's unsafe), but that's not the goal, is it?
Of course, but Lidar is more expensive.
Meh, i believe Tesla will be wrong on this one. Yes, they will achieve good autonomous cars without lidar and radar, but someone else will build a slightly safer autonomous driving experience with those added modalities. The costs will plummet as the sensors become ubiquitous and eventually they will be required by legislation.
Yup, I strongly agree with you too. Infact In fact I mentioned that in my interview for the Tesla Autopilot team lol I guess that’s why they didn’t move me forward in the process.
haha, bold move.
EV grade LiDAR is now under $1000 a pop. In retail. For car manufacturers it must be under half of that.
Driving in conditions unsafe for humans is not a current goal of anyone I'm aware of.
Tesla FSD used to do this with occupancy networks [0]. It's basically a "software lidar". Afaik they don't use it any more in their newest FSD stack, expect for visualizations maybe.