Evolving the “Feeling” of Time Through Sensory-Motor Coordination: A Robot Based Model
In this paper, we aim to design decision-making mechanisms for an autonomous robot equipped with simple sensors, which integrates over time its perceptual experience in order to initiate a simple signalling response. Contrary to other similar studies, in this work the decision-making is uniquely controlled by the time-dependent structures of the agent’s controller, which in turn are tightly linked to the mechanisms for sensory-motor coordination. The results of this work show that a single dynamic neural network, shaped by evolution, makes an autonomous agent capable of “feeling” time through the flow of sensations determined by its actions.
Unable to display preview. Download preview PDF.
- 1.Nonacs, P.: State dependent behavior and the marginal value theorem. Behavioral Ecology 12, 71–83 (2003)Google Scholar
- 3.Nolfi, S., Floreano, D.: Evolutionary Robotics: The Biology, Intelligence, and Technology of Self-Organizing Machines. MIT Press, Cambridge (2000)Google Scholar
- 4.Harvey, I., Husbands, P., Cliff, D.: Issues in evolutionary robotics. In: Meyer, J.A., Roitblat, H., Wilson, S. (eds.) Proc. of the 2nd Int. Conf. on Simulation of Adaptive Behavior, pp. 364–373. MIT Press, Cambridge (1992)Google Scholar
- 7.Tuci, E., Harvey, I., Todd, P.M.: Using a net to catch a mate: Evolving CTRNNs for the dowry problem. In: Hallam, B., Floreano, D., Hallam, J., Hayes, G., Meyer, J.A. (eds.) Proceedings of SAB 2002, MIT press, Cambridge (2002)Google Scholar
- 9.Nolfi, S.: EvoRob 1.1 User Manual. Institute of Psychology, National Research Council, CNR (2000), Available at http://gral.ip.rm.cnr.it/evorobot/simulator.html