ECAI 2004 Conference Paper

[full paper]

a Robot Task Planner that Merges Symbolic and Geometric Reasoning

Stephane Cambon, Fabien Gravot, Rachid Alami

We describe an original planner that has been specially designed to address intricate robot planning problems where geometric constraints cannot be simply ``abstracted'' in a way that has no influence on the obtained plan. This paper presents the ingredients that allowed us to establish an effective link between representations used by a symbolic task planner and a realistic motion and manipulation planning library using Probabilistic Roadmap Methods. The architecture and the main plan search strategies are presented. The symbolic representation not only let us represent constraints but also propose a relaxed problem used as a heuristic value. At each step of the planning process both symbolic and geometric data are considered. Besides, the planning process tries to arbitrate between finding a plan with the level of knowledge already acquired, or ``investing'' more in a deeper knowledge of the topology of the different configuration spaces it manipulates. The main topics are illustrated with an example inspired by the hanoi tower problem.

Keywords: Planning, Geometric reasoning, Robotic

Citation: Stephane Cambon, Fabien Gravot, Rachid Alami: a Robot Task Planner that Merges Symbolic and Geometric Reasoning. In R.López de Mántaras and L.Saitta (eds.): ECAI2004, Proceedings of the 16th European Conference on Artificial Intelligence, IOS Press, Amsterdam, 2004, pp.895-899.