>> of vision are not "AGI-hard". A key component of self-driving is something that can determine whether a volume of space is empty, occupied, or ambiguous.
> Isn't the latter part of vision the part that's "AGI" hard though
Those accidents with self driving where they ram stationary objects at full speed because they cheaped out on LIDARs and only have visual feeds shows that visuo-spatial ability seems to be AGI-hard.
> Isn't the latter part of vision the part that's "AGI" hard though
Those accidents with self driving where they ram stationary objects at full speed because they cheaped out on LIDARs and only have visual feeds shows that visuo-spatial ability seems to be AGI-hard.