Tasks prioritization for whole-body realtime imitation of human motion by humanoid robots

Sophie Sakka (1, 2) , Louise Penna Poubel (1) , Denis Cehajic (3)

1 IRCCyN - Institut de Recherche en Communications et en Cybernétique de Nantes
2 UP - Université de Poitiers = University of Poitiers
3 Lehrstuhl für Informationstechnische Regelung (ITR)

This paper deals with on-line motion imitation of a human being by a humanoid robot using inverse kinematics (IK). First, the human observed trajectories are scaled in order to match the robot geometric and kinematic description. Second, a task prioritization process is defined using both equality and minimized constraints in the robot IK model, with four tasks: balance management, end-effectors tracking, joint limits avoidance and staying close to the human joint trajectories. The method was validated using the humanoid robot NAO.

Mots clés: Human; humanoid; motion imitation; task prioritization; inverse kinematics

Domaines: Automatique / Robotique

Sophie Sakka, Louise Penna Poubel, Denis Cehajic. Tasks prioritization for whole-body realtime imitation of human motion by humanoid robots. Digital Intelligence (DI2014), Sep 2014, Nantes, France. 5 p. ⟨hal-01054887⟩