Generating human-like reaching movements with a humanoid robot: A computational approach

This paper presents a computational approach for transferring principles of human motor control to humanoid robots. A neurobiological model, stating that the energy of motoneurons is minimized and that dynamic and static efforts are processed separately, is considered. This paradigm is used to produce humanoid robot's reaching movements obeying the rules of human kinematics. A nonlinear programming problem is solved to determine optimal trajectories. The optimal movements are then encoded by using a basis of motor primitives determined by principal component analysis. Finally, generalization to new movements is obtained by solving of a low-dimensional optimization problem in the operational space.

► A computational approach for transferring human motor control to humanoid robots.
► Minimization of the energy of motoneurons and separation of static and dynamic forces.
► This paradigm is used to produce human-like humanoid robots reaching movements.
► A basis of motor primitives is identified to encode the movement.
► A minimization in the operationa space allows the generalization to new movements.