IEEE Technology and Society Magazine - March 2018 - 27

can be predicted implicitly by human observers [26], [27].
Interestingly, it has been shown that a self-learning swivel-arm robot that is only programmed to reward joint task
completion efficiency with human partners, ultimately
results in performing more legible motion [25].
A highly predictable robot behavior, however, can be
established by various means. Aside from a robot's
motion design, other channels of human-robot communication can be exploited as well. Light signals have
been used in a flight path crossing task with a drone, for
example, to proactively express the drone's intent to
brake for a human pedestrian. With light signals given,
people walked significantly faster and displayed fewer
nonverbal cues of insecurity in comparison to the use
of an unpredictable control condition [31].
All in all, it is noted that certainty and transparency
in general are variables of high relevance for the perceived comfort of an HRI. This applies not only to the
next actions of a robot will take, but also to the broader
context of what can be expected from a robot, and what
a robot is able to sense, to decide, and to do autonomously. The more familiar people are with a robot, the
more they are willing to accept it as a partner, in either a
personal or work environment [2].
It is worth stressing, however, the relevance of mutual understanding in the sense that, even if we can think
that humans could easily learn to predict non-humane
robot behaviors (within the limits of our perceptual
abilities), the ability of the robot to anticipate human
behavior requires a very deep knowledge of the motor
and cognitive bases of human-human interaction. It
is easier to implement a robot moving in a human
way, than it is to implement a robot able to interpret
human movement. However, only the effective combination of understanding and being understood will
allow establishing a balanced interaction between the
two agents, human and robot, making their collaboration seamless and intuitive.

Dawn of a New Epoch
In the perception of many people, we are facing the dawn
of a new epoch. This is an epoch in which the images
with which we have long been familiar from science fiction films start to correspond to the realities of everyday
life. An epoch in which the robots - finally, really -
arrive at our workplaces and in our households, at hospitals and entertainment parks, on the roads and in the sky
above our heads. Regardless of how realistic or starryeyed many of these prospects of our impending hightech future might seem, it is clear that autonomous
machines will not be keeping to themselves for much longer. They will walk among us. And as they proceed to
carry out their respective missions, they will no longer be
segregated in machine-only realms; rather, they will be
march 2018

∕

The ability of the robot to anticipate
human behavior requires a very deep
knowledge of the motor and cognitive
bases of human-human interaction.
emerging in our quotidian environments. Accordingly
they will be getting closer and closer to us human beings
in a physical and psychological sense as well.
If robots would move amongst their own "species,"
their behavioral design could be purely functional.
There would not be any need for communicative signals
meant to be detectable by the human senses. However,
robots will be characterized by their co-existence and
collaboration with human partners much more than has
been trumpeted for a long time. With this article, we
therefore called for a humane vision of human-robot
interaction, fostered by a new design paradigm of bidirectional - mutual - understanding between humans
and machines.
Designing robots to be considerate of human interaction partners implies that they should be able to infer
what a human intends to do, what he or she needs, and
whether it is the right moment to intervene or whether it
would be better to wait a little. However, this won't be
enough: robots will need to be considerate also in their
actions, selecting behaviors that maximize human comfort. This implies not only aiming for safety and ergonomics, but also at an increase in intention expression
and action understandability. It is worth stressing here
that, in general, being considerate of humans requires
the robot to be able to understand and adapt to
human's skill at the individual/personal level in order to
interpret and use a shared vocabulary as people do, for
example, when exaggerating our movement in interacting with children or slowing down our movements when
interacting with the elderly. In this respect, roboticists
will have to take into consideration not only behaviors
that are common among all humans [46], such as the
way eye and hand motion are coordinated in a reaching
action - but also signals that vary widely between cultural or ethnic groups. Therefore, if the direction of a
gaze can be universally used by the robot to predict
which object a person is going to take [13], the interpretation of hand gestures or of the amount of eye contact
will need to be informed by the cultural context.
This underlines the importance of empirical research
into cultural differences influencing how people interact
with robots. Only in this way will the effort of adapting
to the partner in human-robot interaction fall also onto

IEEE Technology and Society Magazine

Table of Contents for the Digital Edition of IEEE Technology and Society Magazine - March 2018