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

Masaki Murooka (1, 2) , Iori Kumagai , Mitsuharu Morisawa , Fumio Kanehiro , Abderrahmane Kheddar

1 CNRS-AIST JRL - Joint Robotics Laboratory
2 AIST - National Institute of Advanced Industrial Science and Technology

In this letter, we propose an efficient and highly versatile loco-manipulation planning for humanoid robots. Locomanipulation 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 usecases, such as a bobbin rolling operation with regrasping, where the motion is automatically planned by our framework.

Mots clés: Humanoid and Bipedal Locomotion; Manipulation Planning; Multi-Contact Whole-Body Motion Planning and Control

Domaines: Robotique [cs.RO]

Masaki Murooka, Iori Kumagai, Mitsuharu Morisawa, Fumio Kanehiro, Abderrahmane Kheddar. Humanoid Loco-Manipulation Planning Based on Graph Search and Reachability Maps. IEEE Robotics and Automation Letters, 2021, 6 (2), pp.1840-1847. ⟨10.1109/LRA.2021.3060728⟩. ⟨hal-03425666⟩