The altruistic robot: do what I want, not just what I say
Paper
Paper/Presentation Title | The altruistic robot: do what I want, not just what I say |
---|---|
Presentation Type | Paper |
Authors | Billingsley, Richard (Author), Billingsley, John (Author), Gardenfors, Peter (Author), Peppas, Pavlos (Author), Prade, Henri (Author), Skillicorn, David (Author) and Williams, Mary-Anne (Author) |
Editors | Moral, S., Pivert, O., Sánchez, D. and Marín, N. |
Journal or Proceedings Title | Scalable Uncertainty Management: Proceedings of 11th International Conference (SUM 2017) |
Number of Pages | 14 |
Year | 2017 |
Place of Publication | Germany |
ISBN | 9783319675817 |
9783319675824 | |
Digital Object Identifier (DOI) | https://doi.org/10.1007/978-3-319-67582-4_11 |
Web Address (URL) of Paper | https://link.springer.com/chapter/10.1007/978-3-319-67582-4_11 |
Conference/Event | 11th International Conference on Scalable Uncertainty Management (SUM 2017) |
Event Details | 11th International Conference on Scalable Uncertainty Management (SUM 2017) Event Date 04 to end of 06 Oct 2017 Event Location Granada, Spain |
Abstract | As autonomous robots expand their application beyond research labs and production lines, they must work in more flexible and less well defined environments. To escape the requirement for exhaustive instruction and stipulated preference ordering, a robot’s operation must involve choices between alternative actions, guided by goals. We describe a robot that learns these goals from humans by considering the timeliness and context of instructions and rewards as evidence of the contours and gradients of an unknown human utility function. In turn, this underlies a choice-theory based rational preference relationship. We examine how the timing of requests, and contexts in which they arise, can lead to actions that pre-empt requests using methods we term contemporaneous entropy learning and context sensitive learning. We provide experiments on these two methods to demonstrate their usefulness in guiding a robot’s actions. |
Keywords | artificial intelligence; computer science; computers; robots; choice theory; context-sensitive learning; preference order; preference relationships; production line; research labs; utility functions |
ANZSRC Field of Research 2020 | 460299. Artificial intelligence not elsewhere classified |
Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
Byline Affiliations | University of Technology Sydney |
Institution of Origin | University of Southern Queensland |
Book Title | Scalable Uncertainty Management |
Edition | Springer International Publishing AG. Part of Springer Nature. |
https://research.usq.edu.au/item/q47y7/the-altruistic-robot-do-what-i-want-not-just-what-i-say
197
total views14
total downloads3
views this month0
downloads this month