`Feeling' the flow of time through sensorimotor co-ordination Export

@article{citeulike:145966, abstract = {In this paper, we aim to design decision-making mechanisms for a simulated Khepera robot equipped with simple sensors, which integrates over time its perceptual experience in order to initiate a simple signalling response. Contrary to other previous similar studies, in this work the decision-making is uniquely controlled by the time-dependent structures of the agent controller, which in turn are tightly linked to the mechanisms for sensorimotor 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. Further analysis of the evolved solutions reveals the nature of the selective pressures that facilitate the evolution of fully discriminating and signalling agents. Moreover, we show that, by simply working on the nature of the fitness function, it is possible to bring forth discrimination mechanisms that generalize to conditions never encountered during evolution.}, author = {Tuci, Elio and Trianni, Vito and Dorigo, Marco}, citeulike-article-id = {145966}, citeulike-linkout-0 = {http://dx.doi.org/10.1080/09540090412331314740}, citeulike-linkout-1 = {http://www.ingentaconnect.com/content/tandf/ccos/2004/00000016/00000004/art00006}, comment = {I'm not quite convinced by their argument for why this work is unlike most others. ---=note-separator=--- Tuci has some useful insights into evolutionary scaffolding for multi-part behaviours. Shame none of this has seemed to transfer into my work, but it's worth remembering.}, doi = {10.1080/09540090412331314740}, issn = {0954-0091}, journal = {Connection Science}, keywords = {ctrnns, decision\_making, dynamical\_systems, evolutionary\_robotics, learning}, month = {December}, number = {4}, pages = {301--324}, posted-at = {2005-05-25 04:32:34}, priority = {0}, publisher = {Taylor and Francis Ltd}, title = {`Feeling' the flow of time through sensorimotor co-ordination}, url = {http://dx.doi.org/10.1080/09540090412331314740}, volume = {16}, year = {2004} }

TY - JOUR ID - citeulike:145966 L3 - citeulike-article-id:145966 N2 - In this paper, we aim to design decision-making mechanisms for a simulated Khepera robot equipped with simple sensors, which integrates over time its perceptual experience in order to initiate a simple signalling response. Contrary to other previous similar studies, in this work the decision-making is uniquely controlled by the time-dependent structures of the agent controller, which in turn are tightly linked to the mechanisms for sensorimotor 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. Further analysis of the evolved solutions reveals the nature of the selective pressures that facilitate the evolution of fully discriminating and signalling agents. Moreover, we show that, by simply working on the nature of the fitness function, it is possible to bring forth discrimination mechanisms that generalize to conditions never encountered during evolution. IS - 4 JF - Connection Science SN - 0954-0091 EP - 324 TI - `Feeling' the flow of time through sensorimotor co-ordination PB - Taylor and Francis Ltd VL - 16 SP - 301 KW - ctrnns KW - decision_making KW - dynamical_systems KW - evolutionary_robotics KW - learning N1 - I'm not quite convinced by their argument for why this work is unlike most others. N1 - Tuci has some useful insights into evolutionary scaffolding for multi-part behaviours. Shame none of this has seemed to transfer into my work, but it's worth remembering. AU - Tuci, Elio AU - Trianni, Vito AU - Dorigo, Marco PY - 2004/12// UR - http://dx.doi.org/10.1080/09540090412331314740 ER -