In our previous work, we proposed a hierarchical planner for bipedal and humanoid robots navigating complex environments based on a motion primitives framework. In this paper, we extend and improve that planner by proposing a different approach for the global and subgoal components of our planner. We continue to use a workspace decomposition that consists of a passage map, obstacle map, gradient map, and local map. We verify our approach using both simulation results and experimentally on a mechanical humanoid system.