Intelligence has been science's subject of study as a result of biological evolution.
In the last hundred million years, intelligence has evolved together with biology. One
may get to this conclusion by analyzing the behavior of creatures that have surged as
well as their ability to store and process information. Evolution has generated creatures
having brains with great adaptive capacity. Assuming that human intelligence has evolved
through a long and slow process that took place along several million years, it would
make sense to try and replicate artificially the same steps taken in this process. Evolution
shows us a path that goes from the simplest to the most complex minds presenting the
features and abilities that have evolved along time. On the present work, it is believed that
the way evolution goes is a good source of inspiration to artificial intelligence. According
to Dennett, a kind of mind that appeared along evolution is the Popperian mind capable
of imagining, planning future states and learning from environment presenting great
capacity to adapt to new and unexpected situations. A Popperian agent is modeled and
implemented to learn from environment rules and to plan future actions based on self
knowledge. Finally, two prototypes of Popperian agents are implemented to solve
distinct problems and it can be observed the capacity of the Popperian agents to adapt to
environment conditions in order to accomplish own objectives.
Although substantial progress has been made on the question of the origin of life, less progress can be seen concerning the origins of intelligence. There is not even general agreement of what intelligence is. The paper proposes a deenition of intelligence grounded in biology, w h i c h m a k es the question of the origins of intelligence seem more approachable. It then identiies two major transitions that must have been crucial in the development of intelligence: the origins ogeneral purpose' neural networks and the origins of language. Some experimental work is reported that tries to recapitulate these major transitions using an artiicial life perspective.
A key concern in genetic programming (GP)is the size of the state--space which must besearched for large and complex problem domains.One method to reduce the state--spacesize is by using Strongly Typed Genetic Programming(STGP). We applied both GP andSTGP to construct cooperation strategies tobe used by multiple predator agents to pursueand capture a prey agent on a grid--world.This domain has been extensively studied inDistributed Artificial Intelligence (DAI) asan...
A new architecture for controlling mobile robots is described. Layers of control system are built to let the robot operate at increasing levels of competence. Layers are made up of asynchronous modules that communicate over low-bandwidth channels. Each module is an instance of a fairly simple computational machine. Higher-level layers can subsume the roles of lower levels by suppressing their outputs. However, lower levels continue to function as higher levels are added. The result is a robust and flexible robot control system. The system has been used to control a mobile robot wandering around unconstrained laboratory areas and computer machine rooms. Eventually it is intended to control a robot that wanders the office areas of our laboratory, building maps of its surroundings using an onboard arm to perform simple tasks.
Coevolution (i.e., the evolution of two or more competing populations with coupled fitness) has several features that may potentially enhance the power of adaptation of artificial evolution. In particular, as discussed by Dawkins and Krebs [3], competing populations may reciprocally drive one another to increasing levels of complexity by producing an evolutionary "arms race." In this article we will investigate the role of coevolution in the context of evolutionary robotics. In particular, we will try to understand in what conditions coevolution can lead to "arms races." Moreover, we will show that in some cases artificial coevolution has a higher adaptive power than simple evolution. Finally, by analyzing the dynamics of coevolved populations, we will show that in some circumstances well-adapted individuals would be better advised to adopt simple but easily modifiable strategies suited for the current competitor strategies rather than incorporate complex and general strategies that may be effective against a wide range of opposing counter-strategies.