This paper presents an experimental evaluation of the performance of a novel add-on module for JADE intended to provide agents with estimates of their positions in known indoor environments with no need of dedicated infrastructures or specific onboard devices. First, the paper motivates the work and it details relevant assumptions regarding the applicability of the proposed module. The framework that the module provides to host localization algorithms is outlined, and the specific nomenclature is introduced. Then, the algorithm which ships with the module is briefly presented. Finally, the experimental campaign used to assess the performance of localization is detailed. Experimental results show that the accuracy of stationary localization is sufficient for envisaged application scenarios.
Experimental evaluation of agent-based localization of smart appliances / Monica, Stefania; Bergenti, Federico. - 10207:(2017), pp. 293-304. ( 14th European Conference on Multi-Agent Systems, EUMAS 2016 and 4th International Conference on Agreement Technologies, AT 2016 Valencia, Spagna 2016) [10.1007/978-3-319-59294-7_24].
Experimental evaluation of agent-based localization of smart appliances
MONICA, Stefania;BERGENTI, Federico
2017
Abstract
This paper presents an experimental evaluation of the performance of a novel add-on module for JADE intended to provide agents with estimates of their positions in known indoor environments with no need of dedicated infrastructures or specific onboard devices. First, the paper motivates the work and it details relevant assumptions regarding the applicability of the proposed module. The framework that the module provides to host localization algorithms is outlined, and the specific nomenclature is introduced. Then, the algorithm which ships with the module is briefly presented. Finally, the experimental campaign used to assess the performance of localization is detailed. Experimental results show that the accuracy of stationary localization is sufficient for envisaged application scenarios.
Pubblicazioni consigliate
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris
