The symbol-grounding problem concerns how symbols relate to the real world. The symbol-grounding problem becomes obvious if the human observer is taken out of the loop and the System must interact on ist own with the environment. It is a characteristic of symbolic approaches; nonsymbolic approaches do not have a symbol-grounding problem.

Using symbols in a computer system is no problem as long as there is a human interpreter who can be safely expected to be capable of establishing the appropriate relations to some outside world: the mapping is "grounded" in the human's experience of his or her interaction with the real world. However, once we remove the human interpreter from the loop, as in the case of autonomous agents, we have to take into account that the system needs to interact with the environment on ist own. Thus, the meaning of the symbols must be grounded in the system's own interaction with the real world, [...]. Symbol systems, such as computer programs, in which symbols refer only to other symbols they employ to the outside world. The symbols have meaning only to a designer or a user, not to the system itself. The