10. Uniform and Gaussian Distributions
Nd787 C4 L1 A07 Uniform And Gaussian Distributions V1
What about flying cars?
What does all of this have to do with flying cars? A lot!
Sensors, for example, are imperfect. If I am 1 meter away from a wall and I point my range finder at that wall, I'm likely to get measurements that are slightly different than 1 meter. I might get 0.992… then 1.001… etc…
These measurements are generally centered on the true value of the distance (in this case 1 meter) but they have "Gaussian Noise" added on as well. As you just saw, a Gaussian random variable is parameterized by the mean, \mu, and variance \sigma^2.
A good sensor will have a small variance. A bad sensor will have a large variance. Either way, before we put a sensor on our drone we need to know, actually we need to estimate, what this variance is.