Changes to Models S and X allow them to travel longer without larger batteries

You need less qualified people, less time, less parts, less often for repairs that a handy person can often do themselves and save on labor and parts. Significant sources of income are therefore shrunk for dealerships.

- How can I ensure I waste as little range as possible on heating, so that I don't risk having to make e.g. 2 stops instead of one?

- More critically, if I get stuck in traffic for several hours because of an accident, I need some way to ensure I don't freeze to death in my EV as I'm standing still and the battery runs out.

It seems these two things should be solvable with a single solution: a plug-in space heater to be used in emergencies and for maximizing cold weather range. The space heater could be e.g. a kerosene burner or similar. But for best effect it should of course "plug in" to the car vents.

Is this a thing? Or is heating the passenger compartment such a trivial use of energy anyway if the car is insulated, that it doesn't make a difference? In a concrete scenario: If I drive a model 3 and have 100km battery left, and I have 20km to my planned charging stop half way through my journey. Suddenly traffic stands still because of an accident and it's freezing outside. How long will the "100km" charge maintain the 30K temperature difference while still having 20km left?

Surely you don't want people to drive 200km to the nearest service station, no matter if that's once a year or once every 3 years? Maybe that's the difference - customers expect EVs to be bleeding edge, so the service can be a hassle, and you can still get away with it?

Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving https://arxiv.org/abs/1812.07179

3D object detection is an essential task in autonomous driving. Recent techniques excel with highly accurate detection rates, provided the 3D input data is obtained from precise but expensive LiDAR technology. Approaches based on cheaper monocular or stereo imagery data have, until now, resulted in drastically lower accuracies --- a gap that is commonly attributed to poor image-based depth estimation. However, in this paper we argue that data representation (rather than its quality) accounts for the majority of the difference. Taking the inner workings of convolutional neural networks into consideration, we propose to convert image-based depth maps to pseudo-LiDAR representations --- essentially mimicking LiDAR signal. With this representation we can apply different existing LiDAR-based detection algorithms. On the popular KITTI benchmark, our approach achieves impressive improvements over the existing state-of-the-art in image-based performance --- raising the detection accuracy of objects within 30m range from the previous state-of-the-art of 22% to an unprecedented 74%. At the time of submission our algorithm holds the highest entry on the KITTI 3D object detection leaderboard for stereo image based approaches.

Karpathy was also pointing to:

Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras https://arxiv.org/abs/1904.04998

We present a novel method for simultaneous learning of depth, egomotion, object motion, and camera intrinsics from monocular videos, using only consistency across neighboring video frames as supervision signal. Similarly to prior work, our method learns by applying differentiable warping to frames and comparing the result to adjacent ones, but it provides several improvements: We address occlusions geometrically and differentiably, directly using the depth maps as predicted during training. We introduce randomized layer normalization, a novel powerful regularizer, and we account for object motion relative to the scene. To the best of our knowledge, our work is the first to learn the camera intrinsic parameters, including lens distortion, from video in an unsupervised manner, thereby allowing us to extract accurate depth and motion from arbitrary videos of unknown origin at scale. We evaluate our results on the Cityscapes, KITTI and EuRoC datasets, establishing new state of the art on depth prediction and odometry, and demonstrate qualitatively that depth prediction can be learned from a collection of YouTube videos.

Tesla has also advantage of having radars and is able to do supervised learning of depth estimates for moving objects from video.

I was also skeptical of Tesla self-driving capability, because they had some stupid ideas, like ignoring radar data based on GPS tagging from fleet behavior. But lack of LIDAR will not be the issue. Not even close.

It seems like they are focusing on building proper pipeline for training neural networks. The question is whether neural networks as a technology can handle self driving. Reasoning based on "human brain can do it, so artificial neural networks can do it" is wrong. Natural neural networks and artificial neural networks, besides name share only very, very rough low level conceptual ideas. Moreover, our ANN architectures are probably missing most of what brains do on high level. So, I think this is still an open question - can ANN do it? If not, then nobody will have full self driving capability widely deployed any time soon. Because, even tough neural networks are not perfect, everything else is super brittle in comparison.

LIDAR and hires maps are technologies that give working short-term solution, are sort of local minimum. LIDAR is super expensive and already proven to be not necessary. While, hires maps are super brittle and too capital intensive to be widely deployed.

But if neural networks are sufficient Tesla will leave everyone in dust. There will be literally no competition. They do not need to learn electric cars manufacturing in order to deploy their technology widely, they are doing that already. They will not need to backtrack on LIDAR and hires maps solutions. Also, their decision to deploy self driving hardware to every car means that they have access to stupidly big amount of real world data from all varieties of environments all around the world.

BTW - Extrapolating based what Tesla was doing before Karpathy joined is probably misguided. I was afraid that he will get lost in a big corporation, but he seems to be doing great job there. In my opinion technology that build with his supervision will be significantly better than what Tesla was doing before. But Karpathy is not a magician.

So, Tesla has the biggest potential and the big question is: Are neural networks sufficient for self driving?

There is a reason that some oils are far more expensive than others. Oil change shops have an incentive to make you come back soon, so you will be told there is no need for the more expensive oil. The composition of the oil and the quality of the engine and its parts will of course influence the build up of slug.