An Agent Based Multilevel architecture for Robotics Vision Systems

An approach to the design and implementation of a robotics vision system based on agent inserted in a generic multi-level architectures for mobile robotics is presented, that is based on the Unified Modelling Language. The main goal of the work is to provide a framework to perform a rigorous agent-based design process for cognitive architectures both in the case of a single robot, and in a multi-robot scenario. Details of the methodology, system implementation using FIPA-OS environment, along with real experiments are reported..