On the Evolutionary Co-Adaptation of Morphology and Distributed Neural Controllers in Adaptive Agents
MetadataShow full item record
The attempt to evolve complete embodied and situated artiﬁcial creatures in which both morphological and control characteristics are adapted during the evolutionary process has been and still represents a long term goal key for the artiﬁcial life and the evolutionary robotics community. Loosely inspired by ancient biological organisms which are not provided with a central nervous system and by simple organisms such as stick insects, this thesis proposes a new genotype encoding which allows development and evolution of mor- phology and neural controller in artiﬁcial agents provided with a distributed neural network. In order to understand if this kind of network is appropriate for the evolution of non trivial behaviours in artiﬁcial agents, two experiments (description and results will be shown in chapter 3) in which evolution was applied only to the controller’s parameters were performed. The results obtained in the ﬁrst experiment demonstrated how distributed neural networks can achieve a good level of organization by synchronizing the output of oscillatory elements exploiting acceleration/deceleration mechanisms based on local interactions. In the second experiment few variants on the topology of neural architecture were introduced. Results showed how this new control system was able to coordinate the legs of a simulated hexapod robot on two diﬀerent gaits on the basis of the external circumstances. After this preliminary and successful investigation, a new genotype encoding able to develop and evolve artiﬁcial agents with no ﬁxed morphology and with a distributed neural controller was proposed. A second set of experiments was thus performed and the results obtained conﬁrmed both the eﬀectiveness of genotype encoding and the ability of distributed neural network to perform the given task. The results have also shown the strength of genotype both in generating a wide range of diﬀerent morphological structures and in favouring a direct co-adaptation between neural controller and morphology during the evolutionary process. Furthermore the simplicity of the proposed model has showed the eﬀective role of speciﬁc elements in evolutionary experiments. In particular it has demonstrated the importance of the environment and its complexity in evolving non-trivial behaviours and also how adding an independent component to the ﬁtness function could help the evolutionary process exploring a larger space solutions avoiding a premature convergence towards suboptimal solutions.
The following license files are associated with this item: