Topological graphs can be used as a world representation for a mobile robot that navigates in an office-like environment. Nodes of the graph can represent the intrinsic structure of the environment like corridors, corners and so on. Arcs can capture the connectivity of the space. The task of building algorithms able to identify the characteristic features of nodes directly from sensory data requires several intermediate steps. They consist in the collection of the raw data, their reduction to a possibly one-dimensional representation, its "filtering" and, finally, the "feature recognition". In the paper several of the many possible methodological choices are shown, with a priority to the (according to the authors) most advanced ones. In particular, for the "feature recognition" step, two different policies are shown: one founded on the use of a static case library that takes into account the previous results through the Transferable Belief Model, and a second one exploiting an architecture based on Case-Based Reasoning, a method from the Artificial Intelligence domain. Using the latter the robot acquires knowledge on a progressive basis and is therefore able to navigate autonomously in an environment without any prior information. The chapter is based on a two years long research work in the field; during this period several methodologies have been considered and tested, with the aim of using a more abstract representation of knowledge both in planning and in navigation. -

Alessandro, M., Panzieri, S., Lorenzo, S., Ulivi, G. (2003). RAMSETE -Articulated and Mobile Robots for Services and Technology. In RAMSETE -Articulated and Mobile Robots for Services and Technology (pp. 227-250). Berlin, Heidelberg : Springer-Verlag.

RAMSETE -Articulated and Mobile Robots for Services and Technology

PANZIERI, Stefano;GIOVANNI ULIVI
2003-01-01

Abstract

Topological graphs can be used as a world representation for a mobile robot that navigates in an office-like environment. Nodes of the graph can represent the intrinsic structure of the environment like corridors, corners and so on. Arcs can capture the connectivity of the space. The task of building algorithms able to identify the characteristic features of nodes directly from sensory data requires several intermediate steps. They consist in the collection of the raw data, their reduction to a possibly one-dimensional representation, its "filtering" and, finally, the "feature recognition". In the paper several of the many possible methodological choices are shown, with a priority to the (according to the authors) most advanced ones. In particular, for the "feature recognition" step, two different policies are shown: one founded on the use of a static case library that takes into account the previous results through the Transferable Belief Model, and a second one exploiting an architecture based on Case-Based Reasoning, a method from the Artificial Intelligence domain. Using the latter the robot acquires knowledge on a progressive basis and is therefore able to navigate autonomously in an environment without any prior information. The chapter is based on a two years long research work in the field; during this period several methodologies have been considered and tested, with the aim of using a more abstract representation of knowledge both in planning and in navigation. -
2003
3-540-42090-8
Alessandro, M., Panzieri, S., Lorenzo, S., Ulivi, G. (2003). RAMSETE -Articulated and Mobile Robots for Services and Technology. In RAMSETE -Articulated and Mobile Robots for Services and Technology (pp. 227-250). Berlin, Heidelberg : Springer-Verlag.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11590/163168
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact