Sensing the partner: toward effective robot tutoring in motor skill learning

Effective tutoring during motor learning requires to provide
the appropriate physical assistance to the learners, but at the same time
to assess and adapt to their state, to avoid frustration. With the aim of
endowing robot tutors with these abilities, we designed an experiment
in which participants had to acquire a new motor ability - balancing
an unstable inverted pendulum - with the support of a robot providing
fixed physical assistance. We analyzed participants’ behavior and
explicit evaluations to (i) identify the motor strategy associated with
best performances in the task; (ii) assess whether natural facial expressions
automatically extracted from cameras during task execution can
inform about the participant’s state. The results indicate that the variation
and the mean of the wrist velocity are the most relevant in the
effective balancing strategy, suggesting that a robot tutor could reorient
the attention of the pupil on this parameter to facilitate the learning
process. Moreover, facial expressions vary significantly during the task,
especially in the dimension of Valence, which decreases with training.
Interestingly, only when the robot had an anthropomorphic presence,
Valence correlated with the degree of frustration experienced in the task.
These findings highlight that both physical behavior and affective signals
could be integrated by an autonomous robot to generate adaptive and
individualized assistance, mindful both of the learning process and the
partner’s affective state.