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 planning is a key technological brick enabling humanoid robots to autonomously perform object transportation by manipulating them. We formulate planning of the alternation and sequencing of footsteps and grasps as a graph search problem with a new transition model that allows for a flexible representation of loco-manipulation. Our transition model is quickly evaluated by relocating and switching the reachability maps depending on the motion of both the robot and object. We evaluate our approach by applying it to loco-manipulation use-cases, such as a bobbin rolling operation with regrasping, where the motion is automatically planned by our framework. OVING large objects is a typical task required for humanoid robots in large-scale manufacturing environments. As most of such objects are heavy, they need to be moved through manipulating them by taking advantage of the ground and any possible inertia properties.