A Robotic Scenario for Programmable Fixed-Weight Neural Networks Exhibiting Multiple Behaviors
Artificial neural network architectures are systems which usually exhibit a unique/special behavior on the basis of a fixed structure expressed in terms of parameters computed by a training phase. In contrast with this approach, we present a robotic scenario in which an artificial neural network architecture, the Multiple Behavior Network (MBN), is proposed as a robotic controller in a simulated environment. MBN is composed of two Continuous-Time Recurrent Neural Networks (CTRNNs), and is organized in a hierarchial way: Interpreter Module (IM) and Program Module (PM). IM is a fixed-weight CTRNN designed in such a way to behave as an interpreter of the signals coming from PM, thus being able to switch among different behaviors in response to the PM output programs. We suggest how such an MBN architecture can be incrementally trained in order to show and even acquire new behaviors by letting PM learn new programs, and without modifying IM structure.
KeywordsMultiple behaviors fixed-weights CTRNN programmability robotics
Unable to display preview. Download preview PDF.
- 1.Anderson, M.L.: Neural re-use as a fundamental organizational principle of the brain - target article. Behavioral and Brain Sciences 33(04) (2010)Google Scholar
- 3.Blynel, J., Floreano, D.: Exploring the T-Maze: Evolving Learning-Like Robot Behaviors using CTRNNs. In: 2nd European Workshop on Evolutionary Robotics (2003)Google Scholar
- 4.De Falco, I., Cioppa, A.D., Donnarumma, F., Maisto, D., Prevete, R., Tarantino, E.: CTRNN parameter learning using differential evolution. In: ECAI 2008, vol. 178, pp. 783–784 (July 2008)Google Scholar
- 5.Donnarumma, F.: A Model for Programmability and Virtuality in Dynamical Neural Networks. PhD thesis, Università di Napoli Federico II (2010)Google Scholar
- 6.Donnarumma, F., Prevete, R., Trautteur, G.: Virtuality in neural dynamical systems. In: International Conference on Morphological Computation, Venice, Italy (2007)Google Scholar
- 8.Floreano, D., Mondada, F.: Automatic creation of an autonomous agent: Genetic evolution of a neural-network driven robot. In: Proceedings of the Conference on Simulation of Adaptive Behavior, pp. 421–430. MIT Press, Cambridge (1994)Google Scholar