iceblink7
Member
I agree: NN seems like overkill for something that's been solved very effectively with less engineering on other cars. It's difficult to imagine why this is so difficult for Tesla. Anxiously awaiting 2019.40.
You can install our site as a web app on your iOS device by utilizing the Add to Home Screen feature in Safari. Please see this thread for more details on this.
Note: This feature may not be available in some browsers.
I am reminded of the space race. The US spent $millions (allegedly) developing a pen which would write in zero gravity. The Russians spent $1 on a pencil.
$5 sensors work on every other car, why on earth spend money on a NN to figure out it is raining.
The wide angle lens is used for detecting rain. The wide angle lens focal length is zero, like a fish eye lens, so yes it can focus on the windscreen fine.No, it has 3 forward-facing cameras but none focussed on the windscreen. It is almost impossible to notice drops on these cameras due to this focal length. Now rain NN must understand how things look correct and what is "distorted" as it isn't seeing drops.
I'm encouraged by the suggestion that the wiper software will learn from my experiences. Most of my complaints about automatic wiper function could be improved by an option to adjust the sensitivity to my preferences.
"If automatic wipers is not performing to your preference, any manual adjustment to wiper speed will be captured to further train and improve the network in future software updates."
The wide angle lens is used for detecting rain. The wide angle lens focal length is zero, like a fish eye lens, so yes it can focus on the windscreen fine.
Though I am very new to the Tesla model 3 I do know about neural networks. The training is done on a big computer somewhere. The error backpropagation algorithm for a deep NN is computationally intensive. But, once trained, the neural network can be deployed on low processing power devices, such as our Tesla 3 computer.
This assumes the rain in Spain is the same as the rain everywhere else, I suppose.
There seems to be some value judgement here but perhaps you have access to more information about this than is available on the forum? Could you share it please?
For fartkaraoke yes, for wiper function, maybe not the best choice. Ifs not life or death since the manual override is there, but just a bad place for annoyance. Perhaps you should consider the implementation to be somewhat of a beta like some of the other aspects of the Tesla.
Or sleet, or volcanic ash etc.? Yes, this is the philosophy behind simple hardware and sophisticated software. We are the beta testers and trainers, though we have to wait for software updates to reap the fruits.
We have one set of eyes on our mammalian heads. They are not the best optical design. At the back is neuronal tissue which grew out on the optic nerve from the brain in our embryonic development and it does the first layers of processing of the signal. It's called the retina. Then the signal goes through other bits of the brain and ends up in the visual cortex. That learns by example and training starting straight after birth. Simple hardware, sophisticated software. The system ends up, at least the Inuits' does, allegedly, being able to distinguish between 12 kinds of snow.