Abstract
The UESMANN (Uniform Excitatory Switching Multifunction Artificial Neural Network) architecture has been shown to produce interesting transitions between multiple behaviours using an extremely simple neuromodulatory regime. Previous work has concentrated on discrete classification tasks. In this work, three different simple neuromodulatory architectures including UESMANN are used to control a robot in a homeostatic task.
The experiments show that UESMANN produces interesting and useful transitional behaviour in an embodied system, learning the two tasks in the same number of parameters (i.e. network weights) as networks which learned each individual task.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Finnis, J.C., Neal, M.: UESMANN: a feed-forward network capable of learning multiple functions. In: Tuci, E., Giagkos, A., Wilson, M., Hallam, J. (eds.) SAB 2016. LNCS, vol. 9825, pp. 101–112. Springer, Cham (2016). doi:10.1007/978-3-319-43488-9_10
Funahashi, K., Nakamura, Y.: Approximation of dynamical systems by continuous time recurrent neural networks. Neural Netw. 6(6), 801–806 (1993)
Husbands, P., Philippides, A., Smith, T., O’Shea, M.: Volume signalling in real and robot nervous systems. Theory Biosci. 120(3–4), 253–269 (2001)
Kaczmarek, L.K., Levitan, I.B.: Neuromodulation: The Biochemical Control of Neuronal Excitability. Oxford University Press, New York (1987)
Magg, S., Philippides, A.: GasNets and CTRNNs – a comparison in terms of evolvability. In: Nolfi, S., Baldassarre, G., Calabretta, R., Hallam, J.C.T., Marocco, D., Meyer, J.-A., Miglino, O., Parisi, D. (eds.) SAB 2006. LNCS, vol. 4095, pp. 461–472. Springer, Heidelberg (2006). doi:10.1007/11840541_38
Moioli, R.C., Vargas, P.A., Von Zuben, F.J., Husbands, P.: Towards the evolution of an artificial homeostatic system. In: IEEE Congress on Evolutionary Computation, pp. 4023–4030. IEEE (2008)
Neal, M.: Once more unto the breach: towards artificial homeostasis. In: De Castro, L.N., Von Zuben, F.J. (eds.) Recent Developments in Biologically Inspired Computing, pp. 340–365. Idea Group (2005)
Neal, M., Timmis, J.: Timidity: a useful emotional mechanism for robot control? Informatica (Slovenia) 27(2), 197–204 (2003)
Rodriguez, G., Weisbin, C.R.: A new method to evaluate human-robot system performance. Auton. Robots 14(2–3), 165–178 (2003)
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323(6088), 533–536 (1986)
Sauze, C., Neal, M.: Artificial endocrine controller for power management in robotic systems. IEEE Trans. Neural Netw. Learn. Syst. 24(12), 1973–1985 (2013)
Tunstel, E.: Operational performance metrics for Mars exploration rovers. J. Field Robot. 24(8–9), 651–670 (2007)
Vargas, P.A., Paolo, E.A., Husbands, P.: Preliminary investigations on the evolvability of a non spatial GasNet model. In: Almeida e Costa, F., Rocha, L.M., Costa, E., Harvey, I., Coutinho, A. (eds.) ECAL 2007. LNCS, vol. 4648, pp. 966–975. Springer, Heidelberg (2007). doi:10.1007/978-3-540-74913-4_97
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Finnis, J.C. (2017). Homeostatic Robot Control Using Simple Neuromodulatory Techniques. In: Gao, Y., Fallah, S., Jin, Y., Lekakou, C. (eds) Towards Autonomous Robotic Systems. TAROS 2017. Lecture Notes in Computer Science(), vol 10454. Springer, Cham. https://doi.org/10.1007/978-3-319-64107-2_26
Download citation
DOI: https://doi.org/10.1007/978-3-319-64107-2_26
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-64106-5
Online ISBN: 978-3-319-64107-2
eBook Packages: Computer ScienceComputer Science (R0)