Individuality is one of the most important qualities of humans. Socialrobots should be able to model the individuality of the human partners andto modify their behaviours accordingly.This paper proposes a profiling systemfor social robots to be able to learn the individuality of human partners in socialcontexts. Profiles are expressed in terms of of identities and preferences boundtogether. In particular, people’s identity is captured by the use of facial features,while preferences are extracted from the discussion between the partners. Bothare bound using an Hebb network. Experiments show the feasibility and the performancesof the approach presented.
|Titolo della pubblicazione ospite||Simulation, Modeling, and Programming for Autonomous Robots|
|Numero di pagine||12|
|Stato di pubblicazione||Published - 2012|
|Nome||LECTURE NOTES IN COMPUTER SCIENCE|
- Theoretical Computer Science