Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
A Decision-Theoretic Framework to Select Effective Observation Locations in Robotic Search and Rescue Scenarios
 

Summary: A Decision-Theoretic Framework to Select Effective Observation
Locations in Robotic Search and Rescue Scenarios
Francesco Amigoni, Nicola Basilico
Abstract-- In some applications, like mapping and search and
rescue, robots are autonomous when they are able to decide
where to move next, according to the data collected so far.
For this purpose, navigation strategies are used to drive the
robots around environments. Most of the navigation strategies
proposed in literature are based on the idea of evaluating a
number of candidate locations according to an utility function
and selecting the best one. Usually, ad hoc utility functions are
used to provide a global evaluation of candidates by combining
a number of criteria. In this paper, we propose to use a
more theoretically-grounded approach, based on Multi Criteria
Decision Making (MCDM), to define exploration strategies
for robots employed in search and rescue applications. We
implemented our MCDM-based exploration strategies within
an existing robot controller and we experimentally evaluated
their performance in environments used in the RoboCup Rescue
Virtual Robots Competition.

  

Source: Amigoni, Francesco - Dipartimento di Elettronica e Informazione, Politecnico di Milano

 

Collections: Computer Technologies and Information Sciences