Abstract-Robust, dependable and concise coordination between members of a robot team is a critical ingredient of any such collective activity. Depending on the availability and the characteristics of the particular communication infrastructure, coordination mechanisms can take varied forms, leading to distinct system behaviors. In this paper, we consider the case of robot teams operating within relatively sparse wireless sensor network deployments. We introduce Shared Memories, a trailbased coordination engine, that analyzes interaction patterns between participating team members and sensor network nodes capable to discover significant aggregate patterns, which are made available to the team. To this end, we propose a model for the representation of captured interactions and their sensory context developed as a probabilistic grammar, as well as associated metrics used to rank trails and quantify their significance. Such trails are used as the basis for coordinated operation in team tasks and are made available by the engine to all team members. Our implementation deploys ad-hoc wireless local networking capability available through surrogate devices to commodity robots and RFID proximity sensors. We report on the performance of this system in experiments conducted in a laboratory environment, which highlight the advantages and limitations of our approach.
I. INTRODUCTIONThe traditional robotics approach in capturing environmental information is one of self-sufficiency, that is each agent employs its own sensing capability to make sense of the environment around it and make task-related and navigation decisions. This mode of operation is challenged by two relatively recent developments: the wider availability of wireless adhoc networks which offer advanced networking opportunities; and the rapid proliferation of wireless sensor networks which establish a richer source of environmental information that can be employed to improve operational effectiveness. This recent shift in focus inevitably places greater importance in teams rather than individuals and the use of extended sensing capabilities as the enabler of new off-device functionalities. A critical challenge in capitalizing on these new developments is the management of the collective experience acquired in such a way, and the extraction of useful and usable knowledge.In this paper we propose a particular approach in organizing the collective information harvested by a robotic team and effective ways of providing cues for coordination employing a trail-based approach. We show within a simple feasibility study of this proposal how this approach can provide the foundation for effective coordinated operation. In addition to the use of trail records as the principle data primitive, our