The best way to test our prototype would be a study with persons with dementia. Still, testing the robot in a real environment would be very time-consuming, because it is not predictable if and when people with dementia start wandering. That is out of scoop for our project.
However, we want to get a first impression of how realistic and convincing the provided dialogues and suggested activities are. In a small study with students, who play the role of having dementia, we are observing the interaction with the robot and want to find out how effective it is in preventing people from wandering.

Problem statement and research questions

Goal: How effective is music and dialogue in preventing people with dementia from wandering?

Research Questions (RQ):
 

1. What percentage of people are prevented from going out unsupervised? (Quantitative) (CL01, CL05)
2. How does the interaction change the participant's mood? (CL02)
3. Can the robot respond appropriately to the participant's intention? (CL03) 
4. How do the participants react to the music? (CL04)
5. Does the activity that the robot suggests prevent people from wandering/ leaving? (CL06)
6. Can pepper identify and catch the attention of the PwD?

Future research questions

1. Does the interaction with Pepper make PwD come back to reality? (CL08)
2. Does the interaction with Pepper make PwD feel he/she is losing freedom? (CL09)
3. Does preventing the participant from going out alone make them feel dependent? (CL10)

Method

A between-subject study with students who play the role of having dementia. Data will be collected with a questionnaire (before and after participation), observing the participant's body language and the way that they're responding to Pepper.

Participants

18 students who play the role of having dementia. They will be divided into two groups. One group (11 participants) will be interacting with the intelligent (group 1) robot while the other group (7 students) will interact with the unintelligent robot (group 2).
It is assumed that all participants are living at the same care center.
Before they start, they can choose how stubborn they want to be and where they want to go.

Experimental design

All questions collect quantitative data, using a 5 point Likert scale wherever applicable. 

1. Observe the participant's mood and see how the conversation goes. Observe the level of aggression (tone, volume, pace)
2. Observe whether the mood is improved and the decision has been changed.
3. Observe how natural the conversation is. (conversation makes sense)
4. Participants fill out questionnaires. 

Tasks

Because our participants only play the role of having dementia, we will give them a level of stubbornness/ willpower with they are trying to leave. We try to detect this level with the robot.
Participants from group 1 (using intelligent robot) will also be given one of the reasons to leave, listed below: 

1. going to the supermarket
2. going to the office 
3. going for a walk

After this preparation, the participant is told to (try to) leave the building. The participant and robot have an interaction where the robot is trying to convince the participant to stay inside. 

Measures

We will be measuring this physically and emotionally.
Physically: whether the participant was stopped from leaving the building or not.
Emotionally: evaluate their responses to the robot and observe their mood before and after the interaction.

Procedure

Material

Pepper, laptop, door, and music. 

Results

Condition 1 - intelligent Prototype:

8 out of 11 Participants answered, that they don't know the music that has been played. If we told them afterward the title of the song, most participants do know the song. Why didn't they recognize it during the interaction?
This can have two reasons: The part of the song we pick was too short to be recognized or not the most significant part of the song. For example, the beginning of "escape - the pina colada song" is not as well known as its chorus. Another reason could be, that the participant was distracted or confused by the robot and therefore couldn't carefully listen to the music.

Only 4 out of 11 people agreed, that the music fits the situation. One of our claims, to use music that fits the situation or place, is therefore not reached and the music didn't have the intended effect. Even though we carefully choose the music and discussed a lot about our choice, it was hard to find music that different people connect with a certain place or activity. An approach to improve this could be using an individual playlist for each participant. 

Condition 2 - less intelligent prototype:

Participants assigned to condition 2 weren't convinced to leave. We saw, that most of them tried to continue talking to pepper when it raises its arm to block the door, even though it didn't listen. They were surprised by peppers reaction and asked for a reason why they are not allowed to leave. In order to have a natural conversation flow, the robot should provide an explanation for each scenario that tells why the person is not allowed to leave. This confirms that our approach, to give reason to stay inside, might be helpful to convince PwD to stay inside.

Comparison between intelligent (cond. 1) and less intelligent (cond. 2) prototype

Non of the participants who interacted with the less intelligent robot was prevented from leaving. Still, 3 people assigned to condition 1 weren't convinced to stay inside. A failure rate of 27,3 % is too high for this application since people could be in danger if the system fails. 

Mood evolution

Regarding the changes in mood, 4 out of 11 participants assigned to condition 1 had an increase in mood throughout the interaction. Only one participant felt less happy afterward, the rest stayed at the same level of happiness. The overall mood shifted to happier in general (as you can see in the graphic above), even though only small improvements in mood were detected (<= 2 steps on the scale)
The participants from condition 2 mostly stayed at the same mood level, 2 were less happy, one participant was happier afterward.

Interesting is also, non of the participants was in a really bad mood at the beginning or end.

Problems that occurred during the evaluation

1. lots of difficulties with speech recognition:
   1.1. even though the participant said one of the expected words, pepper understood it wrong and continued with a wrong path
   1.2. If the participant started to talk before pepper was listening (eyes turning blue), it misses a "yes" or "no" at the beginning of the sentence, which causes misunderstandings.
2. problems with face detection
   2.1. due to bad light face was not recognized
   2.2. if the participant passes pepper from the side, the face was not recognized. Therefore, we told people to walk from the front towards pepper. In most cases that helped detect the face.
   2.3. face detection doesn't work with face masks. This could lead to huge problems in the usage of pepper in care homes.

One of the most frequent and noticeable reactions from participants was confusion. This feeling was caused by two main factors:
misunderstandings from speech recognition which leads to unsuitable answers from pepper, as well as the unsuitable environment and setting of our evaluation.
The reasons for failure in speech recognition are listed above. An unsuitable answer can e.g. be an argument to stay inside, that doesn't fit the participant's reason to leave. Also, some people told in a long sentence that they don't like the provided activity and still want to leave. If the speech recognition fails in this case and pepper understood you would like to do the activity, it seems like it encourages you to leave, instead of doing the activity. This leads to the total opposite of our intention.
Furthermore, we found out, that our prototype doesn't fit in the environment of the lab. We encourage the participant to do some activities, that they can't do in the lab environment (go to the living room, have a coffee or do a puzzle). If the robot tells asks you if you want to do the activity, most people don't know how to react and are insecure about how to answer. Participants "freeze" in front of the robot or just left the room. 

Discussion

Conclusions

just some notes...

• Evaluation is not significant enough to answer our main question/ goal, due to many issues with speech reco and misunderstandings
• difference in effectiveness between cond 1 and cond 2, but not in all cases
• Confusion + waiting for the robot to listen -> bad for PwD, because they are already confused and might not remember to wait for the eyes to turn blue