Discovering Several Robot Behaviors through Speciation
This contribution studies speciation from the standpoint of evolutionary robotics (ER). A common approach to ER is to design a robot’s control system using neuro-evolution during training. An extension to this methodology is presented here, where speciati
- PDF / 2,659,100 Bytes
- 11 Pages / 430 x 660 pts Page_size
- 93 Downloads / 234 Views
EvoVisi´on Project, CICESE Research Center, Ensenada, B.C., M´exico [email protected], [email protected] 2 APIS Team, INRIA-Futurs, Parc Orsay Universit´e 4, ORSAY Cedex, France [email protected] 3 Grupo de Evoluci´on Artificial, Universidad de Extremadura, M´erida, Spain [email protected]
Abstract. This contribution studies speciation from the standpoint of evolutionary robotics (ER). A common approach to ER is to design a robot’s control system using neuro-evolution during training. An extension to this methodology is presented here, where speciation is incorporated to the evolution process in order to obtain a varied set of solutions for a robotics problem using a single algorithmic run. Although speciation is common in evolutionary computation, it has been less explored in behavior-based robotics. When employed, speciation usually relies on a distance measure that allows different individuals to be compared. The distance measure is normally computed in objective or phenotypic space. However, the speciation process presented here is intended to produce several distinct robot behaviors; hence, speciation is sought in behavioral space. Thence, individual neurocontrollers are described using behavior signatures, which represent the traversed path of the robot within the training environment and are encoded using a character string. With this representation, behavior signatures are compared using the normalized Levenshtein distance metric (N-GLD). Results indicate that speciation in behavioral space does indeed allow the ER system to obtain several navigation strategies for a common experimental setup. This is illustrated by comparing the best individual from each species with those obtained using the Neuro-Evolution of Augmenting Topologies (NEAT) method which speciates neural networks in topological space.
1 Introduction Evolutionary Robotics (ER) [1] can be seen as an extension to behavior-based robotics (BBR) [2,3]. In classic BBR behaviors are hand-designed by a human expert. On the other hand, in ER the sensory-motor mappings that control the way in which a robot interacts with its surroundings emerge from an artificial evolutionary process. Consequently, ER encourages robot behaviors to emerge from complex interactions between: 1) the autonomous agent; 2) the control mechanism; and 3) the physical environment. ER employs evolutionary computation (EC) methods in the design process of artificial neural networks (ANN) that provide the control mechanism for an autonomous robot. When using ER techniques, most researchers are only interested in finding a single solution for the problem at hand, e.g. a navigation strategy. However, using evolution M. Giacobini et al. (Eds.): EvoWorkshops 2008, LNCS 4974, pp. 164–174, 2008. c Springer-Verlag Berlin Heidelberg 2008
Discovering Several Robot Behaviors through Speciation
165
to find a single super individual can have several disadvantages [4]. For instance, a large amount of computational effort is not exploited because only one solution from the population i
Data Loading...
