Humanoid Loco-Manipulation Planning Based on Graph Search and Reachability Maps

In this letter, we propose an efficient and highly versatile loco-manipulation planning for humanoid robots. Loco-manipulation is a key technological brick enabling robots to autonomously perform object transportation by manipulating them. We formulate of the alternation sequencing footsteps grasps as graph search problem with new transition model that allows flexible representation loco-manipulation. Our quickly evaluated relocating switching reachability maps depending on motion both robot object. evaluate our approach applying it use-cases, such bobbin rolling operation regrasping, where automatically planned framework.