In this paper we propose a new and integrated approach to solve planning problems with both symbolic and geometric aspects. Typical concerned domains are intricate manipulation and task planning problems involving multiple robots in three dimensional worlds. The approach involves a task planner that guides a probabilistic roadmap method used to capture the topology of the free space in various contexts. At each step of our hybrid planner aSyMov both symbolic and geometric data are taken into account. Specific predicates are used to link both aspects. Preliminary results obtained by a prototype implementation are shortly presented and discussed.