Advanced search
Start date
Betweenand

Learning by Demonstration in Cooperative Human-robot Interaction Scenarios

Grant number: 12/12640-1
Support type:Scholarships in Brazil - Post-Doctorate
Effective date (Start): November 01, 2012
Effective date (End): October 31, 2014
Field of knowledge:Engineering - Electrical Engineering
Principal researcher:Paulo Eduardo Santos
Grantee:Murilo Fernandes Martins
Home Institution: Campus de São Bernardo do Campo. Centro Universitário da FEI (UNIFEI). Fundação Educacional Inaciana Padre Sabóia de Medeiros (FEI). São Bernardo do Campo , SP, Brazil

Abstract

As robots become more accessible to humans, more intuitive and human-friendly methods of programming them are needed, chiefly with features such as interactive and group-aware behaviours.This project addresses a central problem which has not been sufficiently explored in the literature, the gap between Learning by Demonstration and Multi-robot systems. In particular, this proposal tackles the fundamental problem of learning multi-robot cooperative behaviour from concurrent multi-teacher demonstrations of task execution, where not only the performance at individual level must be taken in to account, but also the performance of the group as a whole.It is proposed the development, implementation and validation (through user experiments in a real environment) of a multi-layered framework for Learning by Demonstration in Multi-robot Systems. Such framework should be capable of a) extract and represent the structure of solutions to distinct tasks in hierarchical layers of abstraction; b) adapt such representations to new situations and user preferences; and c) jointly execute a given task with other robots and/or humans.

News published in Agência FAPESP Newsletter about the scholarship:
Articles published in other media outlets (0 total):
More itemsLess items
VEICULO: TITULO (DATA)
VEICULO: TITULO (DATA)

Scientific publications
(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)
BIANCHI, REINALDO A. C.; MARTINS, MURILO F.; RIBEIRO, CARLOS H. C.; COSTA, ANNA H. R.. Heuristically-Accelerated Multiagent Reinforcement Learning. IEEE TRANSACTIONS ON CYBERNETICS, v. 44, n. 2, p. 252-265, . (12/12640-1, 11/17610-0, 11/19280-8, 12/04089-3)
SANTOS, PAULO E.; MARTINS, MURILO F.; FENELON, VALQUIRIA; COZMAN, FABIO G.; DEE, HANNAHM.. Probabilistic self-localisation on a qualitative map based on occlusions. JOURNAL OF EXPERIMENTAL & THEORETICAL ARTIFICIAL INTELLIGENCE, v. 28, n. 5, SI, p. 781-799, . (12/12640-1, 12/04089-3)

Please report errors in scientific publications list by writing to: cdi@fapesp.br.