Robots that <i>have</i> emotions
Domenico Parisi, Giancarlo Petrosino
- Year
- 2010
- Citations
- 93
Abstract
Animals have many different motivations and they must decide which of their different motivations they should try at any given time to satisfy with their behavior. Emotions are states of an individual’s body and brain that allow the motivational decision mechanism of the individual to function more properly, that is, in ways that increase the individual’s survival and reproductive chances. The article describes five different simulated robots which, unlike current ‘‘emotional’’ robots, can be said to have emotions. The robots may need to eat and drink, eat and fly away from a predator, eat and find a mating partner, eat and take care of their offspring, or eat and rest in order to heal from physical damage. We show that adding a special emotional circuit to the neural network controlling the robots’ behavior leads to better motivational decisions, and therefore to higher fitness, and we describe how in many circumstances the robots endowed with an emotional circuit behave differently than those lacking the circuit. We conclude by indicating various directions of future research.
Keywords
Related papers
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991
A new optimizer using particle swarm theory
R.C. Eberhart, James Kennedy
2002