A major goal in current mobile robotics research is to bring robots into natural human-populated environments. Such scenario requires safe navigation amongst people. Trying to completely avoid regions resulting from worst case predictions of the obstacle dynamics may leave no free space for a robot to move, especially within environments with high dynamic. To move deftly and goal-oriented within populated areas, the environmental dynamics has to be predicted and taken into account during path planning. This requires first to perceive dynamic objects, second to predict their future motions and third to plan a sophisticated path based on this knowledge.

Instead of navigation with full avoidance of potential obstacle areas, our research focus is on a ”soft” risk mapping of dynamic objects leaving the complete space free of static objects for path planning. Markov Chains are used to model the dynamics of moving persons and predict their potential future locations. These occlusion estimations are mapped into risk regions which serve to plan a path through potentially obstructed space searching for the trade-off between risk avoidance and efficient task completion.