Abstract
Members of effective teams must have knowledge about each other’s future actions. Typically, this is done through messages or precomputed divisions of labor. The former requires ongoing communication between the agents and the latter constrains the autonomy of the individual agents. We introduce coordination rules that facilitate collaboration between autonomous agents when communication is lost. By envisioning the results of all possible plan executions for each agent, we identify which actions result in the greatest increase of within-team uncertainty. If removing this action does not substantially reduce the expected utility of the plan, we create a coordination rule, a statement that the agent will or will not take a particular action in some possible future. Coordination rules facilitate collaboration by improving prediction by teammates. Towards supplying cognitive systems with coordination rules, this paper makes three contributions. First, we identify qualitative interactions by representing the space of decisions available to the agents in plan-with-options and their consequences in a factored envisionment that compactly represents multi-agent simulations. Second, we define two classes of within-team uncertainty metrics with respect to the envisionment. Third, we present an evaluation of the effects of coordination rules on action selection in three scenarios. In all three scenarios, coordination rules enabled extended planning horizons and reduced planning times with no substantial effect on plan quality.
