Following the ''modularity'' orthodoxy of some years ago, it has tradi
tionally been assumed that there is a clear and obvious separation bet
ween perception and cognition. Close examination of this concept, howe
ver, fails to reveal the join. Ballard et al.'s contention that the tw
o ''cannot be easily separated'' is consistent with nonmodular views o
f the way that symbol grounding might be achieved in situated systems.
Indeed, the traditional separation is viewed as unhelpful.