The name is absent

ASM	Disciplines	Architecture	Combination of stimuli	Learning schemes
Tinbergen	ethology	hierarchical network of nodes, where each node represents a kind of behaviour	summed	none
Lorenz	ethology, psychology and hydraulic engineering	psycho-hydraulic model	summed	none
Baerends	ethology	hierarchical network of nodes, where each node represents a kind of behaviour	unstated	none
Brooks	robotic	distributed network of finite state machines	unstated	none
Rosenblatt and Payton	robotic and artificial neural networks	connectionist, feed-forward network. Behaviours are defined by connections among processing elements	can be any function of weighted inputs	none
Maes	ethology and behaviour-based systems	non-hierarchical, distributed network, where each node represents a type of behaviour	summed	none
Beer	ethology, neuroethology and artificial neural networks	semi-hierarchical network, where each node is a neural network implementing a particular kind of behaviour	summed	none
Halpe rin	ethology and artificial neural networks	non-supervised, hierarchical, feed-forward network	summed	classical, secondary, and postponed conditioning
Negrete	neurophysiology ethology	non-hierarchical, distributed network of neuro-humoral neurons	summed	none
Goetz	artificial neural networks and attractors theory	recurrent distributed network	summed	none

Table 1. Different action selection mechanisms.

We can see that ASMs have been inspired in many different areas, and that they present
many diverse properties. There has not been proposed a “best” ASM, since different systems
have different requirements. We can say that each ASM is the best for what it was created for:
for controlling an artificial creature in the context it was proposed.

CorPapers

The name is absent

More intriguing information