Distributed control architecture for collaborative physical robot agents

Abstract

This paper reports on an on-going research to make coordination and cooperation ubiquitous to the control and tasking, of multiple heterogeneous physical robot agents (PRA). The primary objective of the work presented here is to develop a distributed architectural framework that enables multiple PRAs to coordinate high-level tasks in a collaborative manner. The proposed architecture is based on distributing the elements of the system at two levels, namely abstract and physical. At the abstract level, we identify two layers, cognitive and action layers, based on the type of the PRA's responsibilities. At the physical level, our architecture recognizes the coexistence of agent-oriented framework, such as JADE, and non-agent frameworks, like CORBA, to accommodate the cognitive and the action layers respectively. This paper will also present the implementation challenges and our experience with the integration of heterogeneous agent and non-agent frameworks.