Abstract
The knowledge representation of an embodied, intelligent, cognitive agent typically relies on symbols denoting objects of the world on the top level and perceptual, structured data on the bottom level. The process of determining and maintaining the correct connection between a symbolic object identifier and its perceptual image, both referring to the same physical object, is called symbol anchoring.
The dissertation presented here suggests a formal and general approach to the symbol anchoring problem, which enhances previous approaches in terms of generality and expressiveness.
Similar content being viewed by others
References
Bell J, Huang Z (1999) Seeing is believing: a common sense theory of the adoption of perception-based beliefs. J Artif Intell Eng Des, Anal Manuf 13:133–140
Coradeschi S, Saffiotti A (2001) Perceptual anchoring of symbols for action. In: Proc 17th Intern jt conf on artif intell (IJCAI-01), Seattle, WA, USA, pp 407–412
Fichtner M (2010) Anchoring symbols to percepts in the fluent calculus. PhD thesis, Inst Artif Intell, Dep Comput Sci, Technische Universität Dresden, Dresden, Germany. URL http://nbn-resolving.de/urn:nbn:de:bsz:14-qucosa-25900
Thielscher M (2005) Reasoning robots: the art and science of programming robotic agents. Applied logic series, vol 33. Springer, Dordrecht
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Fichtner, M. Anchoring Symbols to Percepts in the Fluent Calculus. Künstl Intell 25, 77–80 (2011). https://doi.org/10.1007/s13218-010-0051-1
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13218-010-0051-1