IEEE Robotics & Automation Magazine - March 2023 - 20

giving users freedom to use robots outside and increasing
their self-efficacy in everyday tasks. In our experiments, we
consider different case scenarios where a user requests a
robot to take him or her outside the house (e.g., for shopping).
In this scenario, the user desires to go outside and asks
the computer (the global intelligence) for help. Then, the
computer processes the request based on the individual's
characteristics, preference, health status, and previous history
and suggests that the person use a wheelchair and prepares
to bring the supporting wheelchair to the entrance of
the Living Lab. Our system can also make other recommendations,
such as a walker robot based on user health conditions
that are continuously updated. For example, suppose
the computation based on captured sensory data shows that
the user has not walked a lot in a while. In that case, the
global intelligence will recommend that the participant use a
walker robot.
In Figure 11, at :,t 438=
the wheelchair is called to the
entrance from the outside. The wheelchair navigates the
entrance by using its onboard sensors. The wheelchair robot
has a ToF camera that uses the classifier for more information
about the environment. After the user sits in the wheelchair,
the robot takes the person safely to the front of the elevator.
Next, the elevator is called for the user via automated switches
that can be triggered as the person arrives near the elevator.
Finally, with existing shared control for the user, the user starts
to move the robot to the desired place in the elevator. In this
way, our system can design behaviors of the AI robot that can
assist the user in areas beyond the boundaries of home such
that the user can feel confident in her or her abilities if he or
she works with the AI robot.
EXPERT EVALUATION
To understand the potential of our framework and compare
the concept from different perspectives of experts in the field,
we developed a new nine-point evaluation. The method was
inspired by the NASA Task Load Index questionnaire, with
the aim to have a qualitative and quantitative performance
evaluation based on third-eye analysis by different experts in
the field. We considered respondents in engineering, health
professionals, and social scientists as well as the public (others),
with around 80 participants, in total, with an approximately
equal distribution. Over 58.8% of our participants
were aged over 35, and 26.3% were over the age of 45, which
has high potential to consider the following framework a
technology incubator, incremental research, or a consumer.
The questionnaire was designed with an inverse questioning
form to avoid biases by the participants, both favorable and
unfavorable. The questionnaire was taken for a period of one
week. Please refer to the supplementary information for
details of questions.
After preparing the data in a spiderweb nine-point scoring
format, we can see the results in Figure 12. It is important
to note that in our nine-point data evaluation, we have considered
our framework from three main factors: engineering
(intelligence, usefulness, and convenience), health (frustration
and physical and mental demands), and social (anxiety, sociability,
and trust) factors. Each expert was asked all the questions,
with values between one and 10, where value 5 presents
a neutral opinion with respect to the question, and the lower
the value, the more favorable the score is. We can see from
Figure 12(a) that the academics and professionals from the
engineering field showed great interest in the potential of the
t = 1:59
t = 2:20
(a)
(b)
t = 2:36
(c)
t = 2:53
t = 3:44
(d)
(e)
t = 3:59
(f)
FIGURE 10. The living room scene. (a) The walker robot approaches the user. (b) User leaves from the bed (automatic height adjustment)
to use the walker robot. (c) The robot walker assists the user with shared autonomy. (d) The robot walker returns to base after the task.
(e) The caretaker commands the global intelligence (computer) for delivering an item to the user. (f) The appropriate service robot
executes the requested task and delivers the object to the user using position tracking.
20 IEEE ROBOTICS & AUTOMATION MAGAZINE MARCH 2023

IEEE Robotics & Automation Magazine - March 2023

Table of Contents for the Digital Edition of IEEE Robotics & Automation Magazine - March 2023