his.sePublications
Change search
Link to record
Permanent link

Direct link
BETA
Bergfeldt, Niclas
Alternative names
Publications (4 of 4) Show all publications
Schäfer, B., Bergfeldt, N., Riveiro Carballa, M. J. & Ziemke, T. (2007). Evolution of Tool Use Behavior. In: Proceedings of the 2007 IEEE Symposium on Artificial Life (CI-ALife 2007). Paper presented at 1st IEEE Symposium on Artificial Life, IEEE-ALife'07;Honolulu, HI;1 April 2007through5 April 2007 (pp. 31-38). IEEE Press
Open this publication in new window or tab >>Evolution of Tool Use Behavior
2007 (English)In: Proceedings of the 2007 IEEE Symposium on Artificial Life (CI-ALife 2007), IEEE Press, 2007, p. 31-38Conference paper, Published paper (Refereed)
Abstract [en]

This paper focuses on the capability of artificial evolution to produce tool use behaviors of different complexity in simulated robotic agents and in the absence of learning or other lifetime methods. The results show by example that tool use behaviours of different complexity can evolve and do not necessarily rely on reasoning abilities.

Place, publisher, year, edition, pages
IEEE Press, 2007
Research subject
Technology
Identifiers
urn:nbn:se:his:diva-3860 (URN)000248557700005 ()2-s2.0-34548769197 (Scopus ID)1-4244-0701-X (ISBN)
Conference
1st IEEE Symposium on Artificial Life, IEEE-ALife'07;Honolulu, HI;1 April 2007through5 April 2007
Available from: 2010-04-12 Created: 2010-04-12 Last updated: 2017-11-27
Buason, G., Bergfeldt, N. & Ziemke, T. (2005). Brains, Bodies and Beyond: Competitive Co-Evolution of Robot Controllers, Morphologies and Environments. Genetic Programming and Evolvable Machines, 6(1), 25-51
Open this publication in new window or tab >>Brains, Bodies and Beyond: Competitive Co-Evolution of Robot Controllers, Morphologies and Environments
2005 (English)In: Genetic Programming and Evolvable Machines, ISSN 1389-2576, E-ISSN 1573-7632, Vol. 6, no 1, p. 25-51Article in journal (Refereed) Published
Abstract [en]

This paper presents a series of simulation experiments that incrementally extend previous work on neural robot controllers in a predator-prey scenario, in particular the work of Floreano and Nolfi, and integrates it with ideas from work on the ‘co-evolution’ of robot morphologies and control systems. The aim of these experiments has been to further systematically investigate the tradeoffs and interdependencies between morphological parameters and behavioral strategies through a series of predator-prey experiments in which increasingly many aspects are subject to self-organization through competitive co-evolution. Motivated by the fact that, despite the emphasis of the interdependence of brain, body and environment in much recent research, the environment has actually received relatively little attention, the last set of experiments lets robots/species actively adapt their environments to their own needs, rather than just adapting themselves to a given environment.

Place, publisher, year, edition, pages
Springer, 2005
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:his:diva-1603 (URN)10.1007/s10710-005-7618-x (DOI)2-s2.0-11144265793 (Scopus ID)
Available from: 2007-07-30 Created: 2007-07-30 Last updated: 2018-01-12Bibliographically approved
Bergfeldt, N. & Hansson, A. (2004). Evolutionary pressure on developing simple languages. Skövde: Institutionen för kommunikation och information
Open this publication in new window or tab >>Evolutionary pressure on developing simple languages
2004 (English)Report (Other academic)
Abstract [en]

The interest for studying the origin and development of language has increased greatly in the last decades. For a language to be developed the production and understanding of it must co evolve, otherwise the users will not be able to understand each other. Here, we show that the co-evolution of language production and understanding promotes the development of an efficient language, where the efficiency is measured in terms of number of symbols needed to transmit a message and distinguish it from other possible messages. We also show how agents evolve a very simple language in order to solve the task at hand, even though the simplicity is never enforced in any way.

Place, publisher, year, edition, pages
Skövde: Institutionen för kommunikation och information, 2004. p. 11
Series
IKI Technical Reports ; HS-IKI-TR-04-005
National Category
Information Systems
Identifiers
urn:nbn:se:his:diva-1255 (URN)
Available from: 2008-06-17 Created: 2008-06-17 Last updated: 2018-09-07Bibliographically approved
Ziemke, T., Bergfeldt, N., Buason, G., Susi, T. & Svensson, H. (2004). Evolving Cognitive Scaffolding and Environment Adaptation: A New Research Direction for Evolutionary Robotics. Connection Science, 16(4), 339-350
Open this publication in new window or tab >>Evolving Cognitive Scaffolding and Environment Adaptation: A New Research Direction for Evolutionary Robotics
Show others...
2004 (English)In: Connection Science, ISSN 0954-0091, Vol. 16, no 4, p. 339-350Article in journal (Refereed) Published
Abstract [en]

Many researchers in embodied cognitive science and artificial intelligence, and evolutionary robotics in particular, emphasize the interaction of brain, body and environment as crucial to the emergence of intelligent, adaptive behaviour. Accordingly, the interaction between agent and environment, as well as the co-adaptation of artificial brains and bodies, has been the focus of much research in evolutionary robotics. Hence, there are plenty of studies of robotic agents/species adapting to a given environment. Many animals, on the other hand, in particular humans, to some extent can choose to adapt the environment to their own needs instead of adapting (only) themselves. That alternative has been studied relatively little in robot experiments. This paper, therefore, presents some simple initial simulation experiments, in a delayed response task setting, that illustrate how the evolution of environment adaptation can serve to provide cognitive scaffolding that reduces the requirements for individual agents. Furthermore, theoretical implications, open questions and future research directions for evolutionary robotics are discussed.

Place, publisher, year, edition, pages
Taylor & Francis, 2004
Keywords
agent–environment interaction, cognitive congeniality, distributed cognition, environment adaptation, evolutionary robotics, niche construction
Identifiers
urn:nbn:se:his:diva-1602 (URN)10.1080/09540090412331314821 (DOI)000226050800008 ()2-s2.0-11144340948 (Scopus ID)
Available from: 2007-07-30 Created: 2007-07-30 Last updated: 2017-11-27Bibliographically approved
Organisations

Search in DiVA

Show all publications