Decentralized Classification in Societies of Autonomous and Heterogenous RobotsReportar como inadecuado


Decentralized Classification in Societies of Autonomous and Heterogenous Robots


Decentralized Classification in Societies of Autonomous and Heterogenous Robots - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

This paper addresses the classification problemfor a set of autonomous robots that interact with each other.The objective is to classify agents that -behave- in -differentway-, due to their own physical dynamics or to the interactionprotocol they are obeying to, as belonging to different -species-.This paper describes a technique that allows a decentralizedclassification system to be built in a systematic way, once thehybrid models describing the behavior of the different speciesare given. This technique is based on a decentralized identificationmechanism, by which every agent classifies its neighborsusing only local information. By endowing every agent withsuch a local classifier, the overall system is enhanced with theability to run behaviors involving individuals of the same speciesas well as of different ones. The mechanism can also be usedto measure the level of cooperativeness of neighbors and todiscover possible intruders among them. General applicabilityof the proposed solution is shown through examples of multi-agent systems from Biology and from Robotics.



Georgia Robotics and InTelligent Systems Laboratory GRITS - Georgia Robotics and InTelligent Systems Laboratory GRITS Publications -



Autor: Martini, Simone - Fagiolini, Adriano - Zichittella, Giancarlo - Egerstedt, Magnus B. - Bicchi, Antonio - -

Fuente: https://smartech.gatech.edu/







Documentos relacionados