Towards co-robot navigation in manufacturing environments through machine learning of human movement patterns

A. Mohammed, T. Viola, C. S. Tucker, J. P. Duarte

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Co-robots refer to a class of robots that are collaborative in nature and learn from humans and their environments and in turn, enable humans to learn from them. In order for co-robots to learn and interact with humans and their environment, they must first be able to i) sense their environment and ii) navigate around their environment. The objective of this work is to explore the feasibility of co-robots learning how to navigate their environment, by observing the body movement patterns of their human counterparts. The co-robot introduced in this work is designed using Commercial, Off-The-Shelf (COTS) sensing systems such as the Microsoft Kinect. Knowledge gained from this work will inform decisions makers seeking to employ co-robots in manufacturing settings that involve human-robot interactions. A case study involving Pennie the co-robot is used to validate the proposed methodology.

Original languageEnglish (US)
Title of host publicationChallenges for Technology Innovation
Subtitle of host publicationAn Agenda for the Future - Proceedings of the International Conference on Sustainable Smart Manufacturing, S2M 2016
EditorsRita Almendra, Filipa Roseta, Paulo Bartolo, Fernando Moreira da Silva, Helena Bartolo, Henrique Amorim Almeida, Ana Cristina Lemos
PublisherCRC Press/Balkema
Pages189-194
Number of pages6
ISBN (Print)9781138713741
DOIs
StatePublished - Jan 1 2017
EventInternational Conference on Sustainable Smart Manufacturing, S2M 2016 - Lisbon, Portugal
Duration: Oct 20 2016Oct 22 2016

Publication series

NameChallenges for Technology Innovation: An Agenda for the Future - Proceedings of the International Conference on Sustainable Smart Manufacturing, S2M 2016

Other

OtherInternational Conference on Sustainable Smart Manufacturing, S2M 2016
CountryPortugal
CityLisbon
Period10/20/1610/22/16

Fingerprint

Learning systems
Navigation
Robots
Robot learning
Human robot interaction

All Science Journal Classification (ASJC) codes

  • Industrial and Manufacturing Engineering
  • Artificial Intelligence
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Mohammed, A., Viola, T., Tucker, C. S., & Duarte, J. P. (2017). Towards co-robot navigation in manufacturing environments through machine learning of human movement patterns. In R. Almendra, F. Roseta, P. Bartolo, F. M. da Silva, H. Bartolo, H. A. Almeida, & A. C. Lemos (Eds.), Challenges for Technology Innovation: An Agenda for the Future - Proceedings of the International Conference on Sustainable Smart Manufacturing, S2M 2016 (pp. 189-194). (Challenges for Technology Innovation: An Agenda for the Future - Proceedings of the International Conference on Sustainable Smart Manufacturing, S2M 2016). CRC Press/Balkema. https://doi.org/10.1201/9781315198101-39
Mohammed, A. ; Viola, T. ; Tucker, C. S. ; Duarte, J. P. / Towards co-robot navigation in manufacturing environments through machine learning of human movement patterns. Challenges for Technology Innovation: An Agenda for the Future - Proceedings of the International Conference on Sustainable Smart Manufacturing, S2M 2016. editor / Rita Almendra ; Filipa Roseta ; Paulo Bartolo ; Fernando Moreira da Silva ; Helena Bartolo ; Henrique Amorim Almeida ; Ana Cristina Lemos. CRC Press/Balkema, 2017. pp. 189-194 (Challenges for Technology Innovation: An Agenda for the Future - Proceedings of the International Conference on Sustainable Smart Manufacturing, S2M 2016).
@inproceedings{9170d1851997495f9ad8b7b088846a65,
title = "Towards co-robot navigation in manufacturing environments through machine learning of human movement patterns",
abstract = "Co-robots refer to a class of robots that are collaborative in nature and learn from humans and their environments and in turn, enable humans to learn from them. In order for co-robots to learn and interact with humans and their environment, they must first be able to i) sense their environment and ii) navigate around their environment. The objective of this work is to explore the feasibility of co-robots learning how to navigate their environment, by observing the body movement patterns of their human counterparts. The co-robot introduced in this work is designed using Commercial, Off-The-Shelf (COTS) sensing systems such as the Microsoft Kinect. Knowledge gained from this work will inform decisions makers seeking to employ co-robots in manufacturing settings that involve human-robot interactions. A case study involving Pennie the co-robot is used to validate the proposed methodology.",
author = "A. Mohammed and T. Viola and Tucker, {C. S.} and Duarte, {J. P.}",
year = "2017",
month = "1",
day = "1",
doi = "10.1201/9781315198101-39",
language = "English (US)",
isbn = "9781138713741",
series = "Challenges for Technology Innovation: An Agenda for the Future - Proceedings of the International Conference on Sustainable Smart Manufacturing, S2M 2016",
publisher = "CRC Press/Balkema",
pages = "189--194",
editor = "Rita Almendra and Filipa Roseta and Paulo Bartolo and {da Silva}, {Fernando Moreira} and Helena Bartolo and Almeida, {Henrique Amorim} and Lemos, {Ana Cristina}",
booktitle = "Challenges for Technology Innovation",

}

Mohammed, A, Viola, T, Tucker, CS & Duarte, JP 2017, Towards co-robot navigation in manufacturing environments through machine learning of human movement patterns. in R Almendra, F Roseta, P Bartolo, FM da Silva, H Bartolo, HA Almeida & AC Lemos (eds), Challenges for Technology Innovation: An Agenda for the Future - Proceedings of the International Conference on Sustainable Smart Manufacturing, S2M 2016. Challenges for Technology Innovation: An Agenda for the Future - Proceedings of the International Conference on Sustainable Smart Manufacturing, S2M 2016, CRC Press/Balkema, pp. 189-194, International Conference on Sustainable Smart Manufacturing, S2M 2016, Lisbon, Portugal, 10/20/16. https://doi.org/10.1201/9781315198101-39

Towards co-robot navigation in manufacturing environments through machine learning of human movement patterns. / Mohammed, A.; Viola, T.; Tucker, C. S.; Duarte, J. P.

Challenges for Technology Innovation: An Agenda for the Future - Proceedings of the International Conference on Sustainable Smart Manufacturing, S2M 2016. ed. / Rita Almendra; Filipa Roseta; Paulo Bartolo; Fernando Moreira da Silva; Helena Bartolo; Henrique Amorim Almeida; Ana Cristina Lemos. CRC Press/Balkema, 2017. p. 189-194 (Challenges for Technology Innovation: An Agenda for the Future - Proceedings of the International Conference on Sustainable Smart Manufacturing, S2M 2016).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Towards co-robot navigation in manufacturing environments through machine learning of human movement patterns

AU - Mohammed, A.

AU - Viola, T.

AU - Tucker, C. S.

AU - Duarte, J. P.

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Co-robots refer to a class of robots that are collaborative in nature and learn from humans and their environments and in turn, enable humans to learn from them. In order for co-robots to learn and interact with humans and their environment, they must first be able to i) sense their environment and ii) navigate around their environment. The objective of this work is to explore the feasibility of co-robots learning how to navigate their environment, by observing the body movement patterns of their human counterparts. The co-robot introduced in this work is designed using Commercial, Off-The-Shelf (COTS) sensing systems such as the Microsoft Kinect. Knowledge gained from this work will inform decisions makers seeking to employ co-robots in manufacturing settings that involve human-robot interactions. A case study involving Pennie the co-robot is used to validate the proposed methodology.

AB - Co-robots refer to a class of robots that are collaborative in nature and learn from humans and their environments and in turn, enable humans to learn from them. In order for co-robots to learn and interact with humans and their environment, they must first be able to i) sense their environment and ii) navigate around their environment. The objective of this work is to explore the feasibility of co-robots learning how to navigate their environment, by observing the body movement patterns of their human counterparts. The co-robot introduced in this work is designed using Commercial, Off-The-Shelf (COTS) sensing systems such as the Microsoft Kinect. Knowledge gained from this work will inform decisions makers seeking to employ co-robots in manufacturing settings that involve human-robot interactions. A case study involving Pennie the co-robot is used to validate the proposed methodology.

UR - http://www.scopus.com/inward/record.url?scp=85034653337&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85034653337&partnerID=8YFLogxK

U2 - 10.1201/9781315198101-39

DO - 10.1201/9781315198101-39

M3 - Conference contribution

AN - SCOPUS:85034653337

SN - 9781138713741

T3 - Challenges for Technology Innovation: An Agenda for the Future - Proceedings of the International Conference on Sustainable Smart Manufacturing, S2M 2016

SP - 189

EP - 194

BT - Challenges for Technology Innovation

A2 - Almendra, Rita

A2 - Roseta, Filipa

A2 - Bartolo, Paulo

A2 - da Silva, Fernando Moreira

A2 - Bartolo, Helena

A2 - Almeida, Henrique Amorim

A2 - Lemos, Ana Cristina

PB - CRC Press/Balkema

ER -

Mohammed A, Viola T, Tucker CS, Duarte JP. Towards co-robot navigation in manufacturing environments through machine learning of human movement patterns. In Almendra R, Roseta F, Bartolo P, da Silva FM, Bartolo H, Almeida HA, Lemos AC, editors, Challenges for Technology Innovation: An Agenda for the Future - Proceedings of the International Conference on Sustainable Smart Manufacturing, S2M 2016. CRC Press/Balkema. 2017. p. 189-194. (Challenges for Technology Innovation: An Agenda for the Future - Proceedings of the International Conference on Sustainable Smart Manufacturing, S2M 2016). https://doi.org/10.1201/9781315198101-39