Skip to Content

Changes for page Test

Last modified by Clara Stiller on 2022/04/05 13:44
From version Icon 55.1 Icon
edited by Sayak Mukherjee
on 2022/04/02 02:46
Change comment: There is no comment for this version
To version Icon 63.1 Icon
edited by Vishruty Mittal
on 2022/04/02 12:55
Change comment: There is no comment for this version

Summary

Details

Icon Page properties
Author
... ... @@ -1,1 +1,1 @@
1 -XWiki.SayakMukherjee
1 +XWiki.Vishruty
Content
... ... @@ -1,5 +1,4 @@
1 -The best way to test our prototype would be a study with persons with dementia. However, 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. Hence it is out of the scope of this project.
2 -Nevertheless, we wanted 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 with an aim to find out how effective it is in preventing people from wandering.
1 +Evaluation is an iterative process where the initial iterations focus on examining if the proposed idea is working as intended. Therefore, we want to first understand how realistic and convincing the provided dialogues and suggested activities are, and would they be able to prevent people from wandering. To examine this, we conduct a small pilot study with students, who role-play having dementia. We then observe their interaction with Pepper to examine the effectiveness of our dialog flow in preventing people from wandering.
3 3  
4 4  
5 5  = Problem statement and research questions =
... ... @@ -24,23 +24,37 @@
24 24  
25 25  = Method =
26 26  
27 -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.
26 +A between-subject study with students who play the role of having dementia. Data will be collected with a questionnaire that participants fill out before and after interacting with Pepper. The questionnaire captures different aspects of the conversation along with their mood before and after the interaction with Pepper.
28 28  
28 +For our between-subject study, our independent variable is Pepper trying to distract the users by mentioning different activities along with the corresponding music. Through this, we want to measure the effectiveness of music and activities in preventing people from leaving the care home, which is thereby our dependent variable. So we developed 2 different prototype designs-
29 +
30 +Design X - It is the full interaction flow where Pepper suggests activities and uses music to distract people from leaving.
31 +Design Y - It is the control condition where pepper simply tries to stop people from leaving by physically keeping its hand on the door.
32 +
29 29  == Participants ==
30 30  
31 -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).
35 +17 students who play the role of having dementia. They will be divided into two groups. One group (11 participants) will be interacting with design X (group 1) robot while the other group (6 students) will interact with the design Y (group 2).
32 32  It is assumed that all participants are living at the same care center.
33 -Before they start, they can choose how stubborn they want to be and where they want to go.
34 34  
35 35  == Experimental design ==
36 36  
37 -All questions collect quantitative data, using a 5 point Likert scale wherever applicable.
40 +Before Experiment:
38 38  
39 -1. Observe the participant's mood and see how the conversation goes. Observe the level of aggression (tone, volume, pace)
40 -1. Observe whether the mood is improved and the decision has been changed.
41 -1. Observe how natural the conversation is. (conversation makes sense)
42 -1. Participants fill out questionnaires.
42 +We will explain to the participants the goal of this experiment and what do they need to do to prevent ambiguity. Therefore, as our participants are students and only playing the role of having dementia, we will give them a level of stubbornness/ willpower with which they are trying to leave the care home.
43 +Participants will also be given a reason to leave, from the below list:
43 43  
45 +going to the supermarket
46 +going to the office
47 +going for a walk
48 +
49 +After this preparation, the participant fills a part of the questionnaire.
50 +
51 +Experiment:
52 +The participant begins interacting with Pepper who is standing near the exit door. The participant and robot have an interaction where the robot is trying to convince him/her to stay inside.
53 +
54 +After Experiment:
55 +After the participant finishes interacting with Pepper, he/she will be asked to fill out the remaining questionnaire. Almost all the questions in the questionnaire collect quantitative data, using a 5 point Likert scale. The questionnaire also used images from Self Assessment Manikin (SAM) so that user can self attest to their mood before and after their interaction with Pepper.
56 +
44 44  == Tasks ==
45 45  
46 46  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.
... ... @@ -99,8 +99,8 @@
99 99  
100 100  Pepper, laptop, door, and music.
101 101  
102 -
103 103  = Results =
116 +
104 104  {{html}}
105 105  <!--=== Comparison between intelligent (cond. 1) and less intelligent (cond. 2) prototype ===
106 106  
... ... @@ -158,6 +158,7 @@
158 158  {{/html}}
159 159  
160 160  === RQ1: Are people convinced not to go out unsupervised? ===
174 +
161 161  {{html}}
162 162  <table style="width: 100%">
163 163  <tr>
... ... @@ -172,6 +172,7 @@
172 172  {{/html}}
173 173  
174 174  === RQ2: How does the interaction change the participant's mood? ===
189 +
175 175  {{html}}
176 176  <table style="width: 100%">
177 177  <tr>
... ... @@ -186,6 +186,7 @@
186 186  {{/html}}
187 187  
188 188  === RQ3: Can the robot respond appropriately to the participant's intention? ===
204 +
189 189  {{html}}
190 190  <table style="width: 100%">
191 191  <tr>
... ... @@ -200,6 +200,7 @@
200 200  {{/html}}
201 201  
202 202  === RQ4: How do the participants react to the music? ===
219 +
203 203  {{html}}
204 204  <table style="width: 100%">
205 205  <tr>
... ... @@ -214,6 +214,7 @@
214 214  {{/html}}
215 215  
216 216  === RQ5: Does the activity that the robot suggests prevent people from wandering/ leaving? ===
234 +
217 217  {{html}}
218 218  <table style="width: 100%">
219 219  <tr>
... ... @@ -228,6 +228,7 @@
228 228  {{/html}}
229 229  
230 230  === RQ6: Can pepper identify and catch the attention of the PwD? ===
249 +
231 231  {{html}}
232 232  <table style="width: 100%">
233 233  <tr>
... ... @@ -242,6 +242,7 @@
242 242  {{/html}}
243 243  
244 244  === Reliabity Scores ===
264 +
245 245  {{html}}
246 246  <table style="width: 100%">
247 247  <tr>
... ... @@ -255,7 +255,7 @@
255 255  </table>
256 256  {{/html}}
257 257  
258 -= Limitation=
278 += Limitation =
259 259  
260 260  * **Lab Environment**: The lab environment is different from a care home, the participants found it difficult to process the suggestions made by Pepper. For example, if Pepper asked someone to visit the living room, it created confusion among the participants regarding their next action.
261 261  
... ... @@ -266,6 +266,7 @@
266 266  * **Face Detection**: The face recognition module within Pepper is also rudimentary in nature. It can not detect half faces are when participants approach from the side. Adding to the problem, the lighting condition in the lab was not sufficient for the reliable functioning of the face recognition module. Hence Pepper failed to notice the participant in some cases and did not start the dialogue flow.
267 267  
268 268  = Conclusions =
289 +
269 269  * People who liked the activity tend to stay in
270 270  * People who knew the music found it more fitting
271 271  * People are more convinced to stay in with the intelligent prototype
... ... @@ -274,8 +274,8 @@
274 274  * Experiment with personalization
275 275  
276 276  = Future Work =
298 +
277 277  * **Personalisation**: Personalize music, and activity preferences according to the person interacting with Pepper.
278 278  * **Robot Collaboration**: Collaborate with other robots such as Miro to assist a person with dementia while going for a walk instead of the caretaker.
279 279  * **Recognise Person**: For a personalised experience, it is essential that Pepper is able to identify each person based on an internal database.
280 280  * **Fine Tune Speech Recognition**: Improvements are necessary for the speech recognition module before the actual deployment of the project in a care home. Additionally, support for multiple languages can be considered to engage with non-English speaking people.
281 -
Icon XWiki.XWikiComments[1]
Comment
... ... @@ -1,1 +1,1 @@
1 -Modified Research Questions so that they align with claims
1 +Add claim number with RQ6 once claims are fixed back
Date
... ... @@ -1,1 +1,1 @@
1 -2022-03-26 13:50:45.49
1 +2022-04-02 11:44:44.339
Icon XWiki.XWikiComments[2]
Author
... ... @@ -1,0 +1,1 @@
1 +XWiki.Vishruty
Comment
... ... @@ -1,0 +1,1 @@
1 +Check if RQ and claims align with each other(CL numbers) once claims are reverted.
Date
... ... @@ -1,0 +1,1 @@
1 +2022-04-02 11:45:38.960