News for hackers. Stuff that matters.
Re:Andrej Karpathy: Why Tesla Removed Radar and Ultrasonic S... by snovv_crash on Sunday October 30, 2022 @04:27PM (#33398301)
The amount of compute that sensor fusion uses is miniscule compared to running a NN or computing stereo depth maps. Sensor fusion runs in the background of your phone the whole time to power things like [0] for example.

0. https://sensor-js.xyz/demo.html

Re:Andrej Karpathy: Why Tesla Removed Radar and Ultrasonic S... by Nomentatus on Sunday October 30, 2022 @05:30PM (#33398942)
Well, yes and no. Integrating the data and adjudicating conflicts between sensors is a real task, too. Also having just two opinions doesn't necessarily help if they conflict, and the lidar is the thinnest source of data. How do you coin flip that? You likely end up just discarding the Lidar's conflicting opinion.
Re:Andrej Karpathy: Why Tesla Removed Radar and Ultrasonic S... by snovv_crash on Friday November 04, 2022 @09:04AM (#33465932)
LIDAR data might be more sparse but it is also more reliable, being an active sensor so it isn't affected by night.

The real way is to use the LIDAR to add to the depth probability distribution in the stereo depth estimation. This way you aren't throwing any data away. LIDAR often gives probabilities as well, for example, and this can be used to eliminate reflections.

Re:Andrej Karpathy: Why Tesla Removed Radar and Ultrasonic S... by 01100011 on Sunday October 30, 2022 @06:11PM (#33399393)
You are confused my friend.

Reading sensor data is not the same as feeding that data to a neural network and asking it to form a worldview composed of possibly conflicting sensor data streams(i.e. lidar vs vision vs ultrasonic).

You are somewhat correct that it is quite trivial to read sensor data. For many sensors, there is some work which needs to be done to denoise or cleanup the input data. That's not where the story ends, however.

Re:Andrej Karpathy: Why Tesla Removed Radar and Ultrasonic S... by snovv_crash on Monday October 31, 2022 @02:54AM (#33402745)
In order to display the gravity-aligned acceleration, sensor fusion between gyro and accelerometer has to occur. This is typically done with a Kalman filter, and runs on 1960s levels of hardware. If you look at something like a drone autopilot, eg. Ardupilot, the sensor fusion is soo cheap that they even extended the Kalman filter to also estimate things like the sensor bias offsets and earth's magnetic field vectors.

Sensor fusion is computationally cheap. It's just a lot of R&D to do it in a way that leads to a net gain in precision and robustness.

Re:Andrej Karpathy: Why Tesla Removed Radar and Ultrasonic S... by 01100011 on Wednesday November 02, 2022 @08:22PM (#33444912)
We're talking about radar and ultrasonic sensors here, not accelerometers. We're also talking about feeding them to a deep neural network. Not the same thing. Sensor fusion is not being done with a Kalman filter in this case.
Re:Andrej Karpathy: Why Tesla Removed Radar and Ultrasonic S... by snovv_crash on Friday November 04, 2022 @08:59AM (#33465843)
Radar and ultrasound both give drastically less data than a simple 720p webcam. After postprocessing their output bandwidth is more similar to a 9-axis IMU than a camera.
Re:Andrej Karpathy: Why Tesla Removed Radar and Ultrasonic S... by 01100011 on Sunday November 06, 2022 @01:39PM (#33495691)
Yes and each time you process the incoming camera data in the neural network you have extra calculations due to the sensor fusion with another data source, regardless of its bitrate. Have you worked with deep learning much?