A method for handling multiple roadmaps and its use for complex manipulation planning

We propose a resolution scheme that is aimed to solve a wide range of multi-robot planning problems in a 3D geometrical environment. This complements our efforts in developing manipulation planning algorithms to deal with multiple robots and several movable objects problems. While the elementary planning step relies on Probabilistic Roadmap Methods (PRMs), the main contribution here is a reasoning level that adapts its control over the construction and extension of a number of roadmaps. The coherence between roadmaps and the hierarchical search process are done through a new type of graph built for a subset of objects or robots in the environment, called the Elementary Kinematic Graph. This paper describes the main ingredients of the proposed framework, and its first results.