Javascript must be enabled for the correct page display

Robotic object searching strategies based on partial knowledge

Luneburg, N. (2013) Robotic object searching strategies based on partial knowledge. Bachelor's Thesis, Artificial Intelligence.

[img]
Preview
Text
AI_BA_2013_NoelLuneburg.pdf - Published Version

Download (591kB) | Preview
[img] Text
akkoord_LuneborgN.pdf - Other
Restricted to Registered users only

Download (11kB)

Abstract

A robot assisting at home should be capable of searching for objects with incomplete knowledge of where these objects might be. The knowledge that it does have is the chance that an object will occur on any piece of furniture in the house. In this research, two searching strategies will be compared, through use of a performance measure consisting of multiple dependent variables. To test the searching implementations, the team BORG's Robocup@Home robot was used to attempt the task of finding certain objects when given a map with annotated furniture. The experiment gives us an insight into one example of how an autonomous robot can act with partial knowledge. The results show that both strategies perform similarly, even though errors that appear during searching seem to be caused by different factors depending on the searching strategy.

Item Type: Thesis (Bachelor's Thesis)
Degree programme: Artificial Intelligence
Thesis type: Bachelor's Thesis
Language: English
Date Deposited: 15 Feb 2018 07:55
Last Modified: 15 Feb 2018 07:55
URI: https://fse.studenttheses.ub.rug.nl/id/eprint/11454

Actions (login required)

View Item View Item