Clemente - XWiki

Miro-E

For our evaluation, we decided that that the functionality we want to test, is the ability of the Dogg0 (Miro-E) robot to entertain and interact with the PwD. Dogg0 will be introduced to the PwD in a safe and confined environment, like her room or living room.

5

6

7

In the final product, Miro-E needs to have the following capabilities to interact with the PwD:

8

9

* Locate the PwD with its camera sensors using a person/ face detector model.

10

* Interact with the PwD by making friendly noises and movements.

11

* Engage with the Pwd by reacting to touch with its tactile sensors.

12

* React to basic voice/ sound commands like “sit”, “sleep” or “go” or clapping your hands.

13

14

15

For our evaluation we decided to focus on one functionality, namely Interacting with the PwD by making friendly noises and movements. For simplification purposes there is assumed that the PwD is the only person in the view of the Miro-E and that there are no obstacles present.

16

17

18

The MiroCloud environment is used to program an interaction sequence for the Dogg0. This can be modeled as a finite state machine in which the states of the dogg0 are determined by the actions of the PwD. These actions include petting the dogg0, or a sound command (in this case a clap). For every state the dogg0’s behavior is hard-coded to come over as natural and smooth as possible.

Introduction

Section [[Prototype>>url:https://xwiki.ewi.tudelft.nl/xwiki/wiki/rejamexample/view/3.%20Evaluation/a.%20Prototype/]] presented the //socially intelligent// dog-robot Miro-E for the use case " UC02.0: Accompany and entertain the PwD". In this use case the hypothesis is tested that the PwD will feel companionship and lower level of stress due to interactions with the Dogg0. We will test these interactions by assess aspects like Trustworthiness, the effect it has on the mood of the PwD and the functionalities of the Dogg0. These aspects will be measured with a questionnaire that the participants fill in right after the experiment.

Method

The prototype was evaluated with an in-person experiment with multiple participants.

Participants

Unfortunately, we can’t do the experiment with real PwD, so the participants will be fellow students that also take the course. The data will be anonymized.

Experimental design

For the experiment, we used a within-subject design. All of the participants interacted with both versions of the robot, with half of the participants interacting with version 1 first and then version 2, and the other half in reverse order. This was done to counter-balance the carryover effects.

Tasks

The participants are instructed to interact with the Dogg0, without prior knowledge of all its functionalities.

Measures

The trustworthiness, the effect it has on the mood of the participant and the functionalities are being measured. This is done by filling in a questionnaire where these aspects are divided in sub questions. The level of agreement and feelings towards these aspects are captured using the Likert Scale.

Procedure

The procedure was conducted as follows:

68

69

1. Welcome participants and explain what they are going to be doing.

70

1. Have them sign the permission form.

71

1. Complete questionnaire 1 regarding their emotional state.

72

1. Engage with the robot.

73

1. Complete the questionnaire 2

74

1. Have a short interview during downtime (prepared questions).

Material

1. Consent form. To protect the privacy of participants and ensure the evaluation process goes smoothly, we will ask participants to sign a consent form, indicating they are willing to take part in the evaluation and the data gathered from the experiment will be analyzed by researchers.

79

1. Miro robot. Our robot is programmed using MiroCloud. The robot will have the same behaviour for every participant. However, the input data will be entered by the Activity Coordinator.

**Introduction**

The purpose of this study is to evaluate the effectiveness of a socially intelligent dog-robot, Dogg0, in providing companionship and reducing stress levels for people with dementia (PwD). The study aims to test the hypothesis that the interactions with the robot will improve the mood of the PwD and enhance their trust in the robot. To achieve this, we will measure trustworthiness, the effect on the mood of the PwD, and the functionalities of the robot. These aspects will be assessed using a questionnaire filled out by participants immediately after the experiment.

**Method:**

The prototype was evaluated through an in-person experiment involving multiple participants. Since we cannot conduct the experiment with real PwD, fellow students who are also taking the course were recruited as participants. All data collected will be anonymized to maintain confidentiality.

93

94

95

**Experimental Design:**

96

97

98

We used a within-subject design in which all participants interacted with both versions of the robot. Half of the participants interacted with version 1 first and then version 2, while the other half did the opposite. This was done to counter-balance the carryover effects.

**Tasks:**

Participants were instructed to interact with Dogg0 without prior knowledge of all its functionalities. They were free to engage with the robot as they wished.

**Measures:**

Trustworthiness, the effect on the mood of the participant, and the functionalities were measured using a questionnaire. The questionnaire consisted of sub-questions related to these aspects and used the Likert Scale to capture the level of agreement and feelings towards these aspects.

**Procedure:**

The procedure was conducted as follows:

117

118

1. Participants were welcomed and informed about the purpose of the study.

119

1. Participants signed a consent form to indicate their willingness to participate and allow researchers to analyze the data gathered from the experiment.

120

1. Participants completed the first questionnaire, which assessed their emotional state.

121

1. Participants interacted with the robot.

122

1. Participants completed the second questionnaire.

123

1. Researchers conducted a short interview during downtime, using prepared questions.

**Materials:**

Two main materials were used in this study. First, a consent form was used to ensure that participants were willing to participate, and their privacy was protected. Second, the Dogg0 robot was used to evaluate its effectiveness. The robot was programmed using MiroCloud and had the same behavior for every participant.

Discussion, how to redesign the experiment

144

145

146

If we had the possibility to do our experiment again there would be a few things we would do differently. Additional to the trust score, it would also be interesting to measure the intuitiveness of the Dogg0 and the effect former instructions had on the mood of the participants.

147

148

149

While conducting the experiment we switched from giving no instructions to giving more context and explanation about the functions of Dogg0. We saw a difference between the reactions of the participants to the Dogg0 of the two groups. This observation was merely anecdotal, and it would have been interesting to measure systematically whether giving former instructions or not would affect the mood of the participants. This could potentially give some meaningful results on how intuitive the Dogg0 is, which is one of the objectives.

**Reflection**

Week 1

* In the first week we had the introduction of socio-cognitive engineering (SCE). Whereas the focus of the robotics courses I had before was primarily focused on programming, the human-centered design approach of SCE was interesting and refreshing.

162

* On the second day we made our team for the project, and I liked that we immediately started out with designing the first draft of our story board and could present it to the class. We decided to use the Miro-E for our project because of its emotionally engaging appearance and flexible code platform. We also got introduced to Xwiki and used the rest of the week to write the Quick Start.

*

*

Week 2

* Use case

*