Section: New Results

Extended Automata for Temporal Planning of Interacting Agents

Participants : Christine Largouët, Omar Krichen, Yulong Zhao.

In this paper [5], we consider the planning problem for a system represented as a set of interacting agents evolving along time according to explicit timing constraints. Given a goal, the planning problem is to find the sequence of actions such that the system reaches the goal state in a limited time and in an optimal manner, assuming actions have a cost. In our approach, the planning problem is based on model-checking and controller synthesis techniques while the goal is defined using temporal logic. Each agent of the system is represented using the formalism of Priced Timed Game Automata (PTGA). PTGA is an extension of Timed Automata that allows the representation of cost on actions and the definition of uncontrollable actions. We define a planning algorithm that computes the best strategy to achieve a goal. To experiment our approach, we extend the classical Transport Domain with timing constraints, cost on actions and uncontrollable actions. The planning algorithm is finally presented on a marine ecosystem management problem.