User Routine Model Using a Cloud-Connected Social Robot

Luis Santos, Jorge Dias

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

In this manuscript we propose a distributed classifier to perform inference on a person daily behaviour routine, based on multi-modal input data. The model is implemented on a social robot and allows to efficiently fuse locally perceived information with data classified remotely on a cloud. Unlike the dominant multi-class approaches, where each class is classified separately, the multi-label scheme estimates all classes simultaneously from the available input instances. This method enables a robot to capture user typical behaviour and provides a simple scheme of regulation that allows the identification of abnormal situations. We propose to solve our problem in two steps based on the principles of Binary Relevance and Label Power-set: (1) a label classification is used to filter input instances into independent labels, (2) the algorithm will map the labels into an hyper-label space, where each hyper-label represents the behaviour which maximizes input instance correlations. Results show the proposed multi-label model to achieve a highly accurate comprehension of the user behaviour even within more demanding test scenarios. As for the regulatory experiments, initial results show that the proposed behaviour model allows to identify unexpected events, that can be used to trigger care giver interventions.

Original languageBritish English
Title of host publicationProceedings - 2016 5th IEEE International Conference on Cloud Networking, CloudNet 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages182-187
Number of pages6
ISBN (Electronic)9781509050932
DOIs
StatePublished - 6 Dec 2016
Event5th IEEE International Conference on Cloud Networking, CloudNet 2016 - Pisa, Italy
Duration: 3 Oct 20166 Oct 2016

Publication series

NameProceedings - 2016 5th IEEE International Conference on Cloud Networking, CloudNet 2016

Conference

Conference5th IEEE International Conference on Cloud Networking, CloudNet 2016
Country/TerritoryItaly
CityPisa
Period3/10/166/10/16

Keywords

  • Human robot interaction
  • Multi-label classification
  • Multi-modal interface
  • Robot perception
  • Service robots

Fingerprint

Dive into the research topics of 'User Routine Model Using a Cloud-Connected Social Robot'. Together they form a unique fingerprint.

Cite this