This contribution introduces two algorithms for adaptive on-line planning of oceanographic missions to be performed in cooperation by a team of AUVs. The mission goal is defined in terms of accuracy in the reconstruction of the environmental field to be sampled. Adaptive cooperative behaviour is achieved by each vehicle in terms of locally evaluating the smoothness of the sampled field, and selecting the next sampling point in order to achieve the desired accuracy; smoothness evaluation and accuracy estimation have been proposed either in terms of analytical formulation related to field estimation with RBFs, or in terms of empirically derived fuzzy-like rules. Simulative results show that the vehicles team does behave as expected, increasing the spatial sampling rate as an increase in the environmental variability is detected. The number of samples required by both algorithms is sensibly inferior to those needed by sampling the area at equally spaced locations, as in the case of off-line, nonadaptive planners.

Adaptive on-line planning of environmental sampling missions with a team of cooperating autonomous underwater vehicles

CAITI, ANDREA;A. MUNAFO';
2007-01-01

Abstract

This contribution introduces two algorithms for adaptive on-line planning of oceanographic missions to be performed in cooperation by a team of AUVs. The mission goal is defined in terms of accuracy in the reconstruction of the environmental field to be sampled. Adaptive cooperative behaviour is achieved by each vehicle in terms of locally evaluating the smoothness of the sampled field, and selecting the next sampling point in order to achieve the desired accuracy; smoothness evaluation and accuracy estimation have been proposed either in terms of analytical formulation related to field estimation with RBFs, or in terms of empirically derived fuzzy-like rules. Simulative results show that the vehicles team does behave as expected, increasing the spatial sampling rate as an increase in the environmental variability is detected. The number of samples required by both algorithms is sensibly inferior to those needed by sampling the area at equally spaced locations, as in the case of off-line, nonadaptive planners.
Caiti, Andrea; Munafo', A.; Viviani, R.
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/11568/111727
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 18
  • ???jsp.display-item.citation.isi??? 16
social impact