Changes for page b. Test

Summary

• Page properties (1 modified, 0 added, 0 removed)

Details

Page properties

Content

...	...	@@ -145,7 +145,7 @@
145	145
146	146	In terms of the research question, no significant differences were found between the two different motivational methods. This is however very likely influenced by the circumstances surrounding the design and the evaluation. The design is unfortunately rather limited and with limited capabilities, due to time constraints. Speech recognition didn't always work properly and was not as flexible as desired which made the interactions less realistic for the participant. Things such as elaborating, which would be something that would be a natural part of a leisurely conversation were made very difficult as the robot could not comprehend conversation to the fullest extent.  Since participants were also prompted to give shorter answers and try to keep to things like "yes" and "no" it greatly influenced how participants interacted with the robot.
147	147
148		-There were also other constraints to the interaction, which had to be given as instructions to the participant before testing. These things included at what distance to stay from the robot, when to join the robot's side when it's time for the walk, how long to wait to speak after a certain prompt, etc. This further made it unnatural but was necessary for the system to perform properly. Ideally, an individual would be able to join the robot's side at any given moment and the robot's movement would not be impacted by the fact that the participant stands too close. Further, one component that has a very significant effect on the results was that it was not possible to test the design with PwD. This was attempted to be resolved by providing a persona description for participants to keep in mind during the testing, but it is difficult to simulate conditions of dementia. Only one participant ended up embodying this character to the fullest extent which was very valuable for the sake of the evaluation but was not enough to explore the concept entirely.
	148	+There were also other constraints to the interaction, which had to be given as instructions to the participant before testing. These things included at what distance to stay from the robot, when to join the robot's side when it's time for the walk, how long to wait to speak after a certain prompt, and when to repeat themselves. This further made it unnatural but was necessary for the system to perform properly. Ideally, an individual would be able to join the robot's side at any given moment and the robot's movement would not be impacted by the fact that the participant stands too close. Further, one component that has a very significant effect on the results was that it was not possible to test the design with PwD. This was attempted to be resolved by providing a persona description for participants to keep in mind during the testing, but it is difficult to simulate conditions of dementia. Only one participant ended up embodying this character to the fullest extent which was very valuable for the sake of the evaluation but was not enough to explore the concept entirely.
149	149
150	150	This highlights the fact that the results may have been different if participants outside of the course were used since we are all very familiar with these robots and systems. On one hand, it could be positive, since we have all researched dementia and have gained a lot of knowledge within this which could make us better at simulating appropriate behavior with the robot or testing the systems in a reasonable way. But since participants also have an idea of how the robot works prior to the evaluation, based on their own experiences of working with the robot, perhaps some mistakes or issues went undetected. For example, a completely inexperienced user could potentially show other faults in the design that appear only if the system is entirely foreign to the user, which is likely what it would be like with a PwD. Of course, knowing about dementia is not the same thing as actually suffering from the diagnosis, so many aspects have most likely gone undetected there for that reason also.
151	151
...	...	@@ -155,7 +155,7 @@
155	155
156	156	A rather central aspect is also of course that the robot should really take a walk outside and not inside the lab room. Preferably, the test should have been performed in an actual garden in order to be able to assess its capabilities in the appropriate terrain. This would also make it possible to make the walk more elaborate and longer since observations during the evaluation show that participants would have rather had a longer and more extensive walk, which was not possible in the lab environment.
157	157
158		-In future studies, the number of participants should be considered, as well as testing the design on PwD and in an actual garden or at the very least a bigger space. The walk should preferably be more extensive and perhaps incorporate aspects of the garden or the environment into the conversation to make the experience more immersing, for example by referring to the flowers that are blooming in the garden and trying to draw PwD's attention to these aspects and create conversations from this. Hopefully, adjustments like these would improve the overall quality of the walk. Further improvements to speech recognition are needed, as well as the smoothness of the walking and the aspect of the participant's distance to the robot. Perhaps if the less realistic aspects discussed above are minimized, a robot that feels more realistic would result in participants listening to the actual prompts given to a larger extent, rather than going into the experiment with a predisposed idea of what they are going to do or answer and would also perhaps deter the participants from tending to reply positively. Further, the motivational prompts were certainly customized to the persona, but further customization could have been considered. For example, it would of course be far greater if the robot has some ability to adapt to the conversation more or less "in real time" by taking in the information given by the PwD and replying in an appropriate manner. Further, intonation could be interpreted and perhaps also shape the responses and prompts of the robot. These things are rather difficult and due to limitations in the current hardware and software may be hard to implement, but it is essential to consider these aspects for future work.
	158	+In future studies, the number of participants should be considered, as well as testing the design on PwD and in an actual garden or at the very least a bigger space. The walk should preferably be more extensive and perhaps incorporate aspects of the garden or the environment into the conversation to make the experience more immersing, for example by referring to the flowers that are blooming in the garden and trying to draw PwD's attention to these aspects and create conversations from this. Hopefully, adjustments like these would improve the overall quality of the walk. Further improvements to speech recognition are needed, as well as the smoothness of the walking and the aspect of the participant's distance to the robot. Perhaps if the less realistic aspects discussed above are minimized, a robot that feels more realistic would result in participants listening to the actual prompts given to a larger extent, rather than going into the experiment with a predisposed idea of what they are going to do or answer and would also perhaps deter the participants from tending to reply positively. Further, the motivational prompts were certainly customized to the persona, but further customization could have been considered. For example, it would of course be far greater if the robot has some ability to adapt to the conversation more or less "in real time" by taking in the information given by the PwD and replying in an appropriate manner. Further, intonation could be interpreted and perhaps also shape the responses and prompts of the robot. These things are rather difficult and due to limitations in the current hardware and software may be hard to implement, but it is essential to consider these aspects for future work. Finally, implementing route verification using GPS and adding safety monitoring features, could significantly broaden the applicability of the robot system.
159	159
160	160	= 5. Conclusions =
161	161