Automatic motion planning has applications ranging from traditional robotics to computer-aided design to computational biology and chemistry. Randomized planners, such as probabilistic roadmap methods (PRMs), have been highly successful in solving these high degree of freedom problems. However, the traditional PRM framework fails to address several practical issues. One of the most important issues is the difficulty of deciding what size roadmap is required to solve a given problem efficiently. PRMs do not provide an automated way to determine appropriate roadmap size. In this paper, we propose a new PRM-based framework called Incremental Map Generation (IMG) to address this problem. Our strategy is to break the map generation into independent processes. Each process generates an independent roadmap component. IMG proceeds by adding independent roadmap components to an existing roadmap until some user defined criteria are satisfied. In addition to addressing the roadmap size problem, this framework supports roadmap reproducibility in that any of the roadmap increments can be reproduced by using the same set of seeds. Finally, these independent processes are natural for parallelization.