[jmkerr]

In 8:39 - 8:42, there's a group (three people with a dog and stroller) crossing the street left to right.

Here's what the Tesla recognises on the screen:

  One person
  Nothing
  Motorcycle
  Nothing
  Motorcycle
  Nothing
  Car
  Nothing
  One person
  Two persons
  One person
  One person and a motorcycle
  One person
  Nothing
  Motorcycle
  One person
  One person and two motorcycles
  Two persons
  One person
  One person and a motorcycle
  Two persons
  One person

It seems to me you wouldn't really need public testing yet at this early stage of development. At a minimum, I would expect it to count the people correctly and get rid of the motorcycles, i.e. basic perception.

[lupire]

Is it critical to know whether it's a stroller or a motorcycle? It's an obstacle either way.

[Traster]

Absolutely, an essential part of driving is predicting how the state of the world will change in the future - and the behaviour of a motorcycle is vastly different from the behaviour of a stroller.

[jmkerr]

In this case it doesn't matter, because there's a car in front anyway.

I don't know how much the system can ignore or mislabel people and still drive safely, but right now it's not really safe and it's not necessary to have the car drive while improving object recognition.

[ekster]

Presumably strollers and motorcycles have very different behaviors to predict.

[avereveard]

generally speaking the cloud of future position where a person or a bike can be is wildly different