Item

Abstract

Imitation learning is frequently discussed as a method for generating complex behaviors
in robots by imitating human actors. The kinematic and the dynamic properties of
humans and robots are typically quite dierent, however. For this reason observed
human trajectories cannot be directly transferred to robots, even if their geometry is
humanoid. Instead the human trajectory must be approximated by trajectories that
can be realized by the robot. During this approximation deviations from the human
trajectory may arise that change the style of the executed movement. Alternatively, the
style of the movement might be well reproduced, but the imitated trajectory might be
suboptimal with respect to dierent constraint measures from robotics control, leading
to non-robust behavior. Goal of the presented work is to quantify this trade-o between
\imitation quality" and constraint compatibility for the imitation of complex writing
movements. In our experiment, we used trajectory data from human writing movements
(see the abstract of Ilg et al. in this volume). The human trajectories were mapped
onto robot trajectories by minimizing an error measure that integrates constraints that
are important for the imitation of movement style and a regularizing constraint that
ensures smooth joint trajectories with low velocities. In a rst experiment, both the
end-eector position and the shoulder angle of the robot were optimized in order to
achieve good imitation together with accurate control of the end-eector position. In
a second experiment only the end-eector trajectory was imitated whereas the motion
of the elbow joint was determined using the optimal inverse kinematic solution for the
robot. For both conditions dierent constraint measures (dexterity and relative jointlimit
distances) and a measure for imitation quality were assessed. By controling the
weight of the regularization term we can vary continuously between robot behavior
optimizing imitation quality, and behavior minimizing joint velocities.