Knowledge as a Window into Distributed Coordination

Yoram Moses, Department of Electrical Engineering Technion-Israel Institute of Engineering, Israel

Distributed and multi-agent systems come in many forms, serving various purposes and spanning a large variety of properties. They include networked processors communicating via message-passing, shared-memory systems in which processes interact by reading from and writing to shared variables, and even systems of robots that coordinate their actions by viewing each others’ actions and locations, and perform no explicit communication actions. While distinct systems may differ completely in their detailed structure and operation, fundamental to all distributed systems is the fact that decisions are performed based on a local, partial, view of the state of the system. Proper coordination among different sites of such a system requires information flow among them, to ensure that decisions are taken base on appropriate knowledge. Reasoning about when elements of the system do or do not know relevant facts is therefore a central aspect of the design and construction of distributed systems and distributed protocols.