Where Can I Do This? Geometric Affordances from a Single Example with the Interaction Tensor

Eduardo Ruiz Libreros; Walterio Mayol-Cuevas

doi:10.1109/ICRA.2018.8462835

Where Can I Do This? Geometric Affordances from a Single Example with the Interaction Tensor

Eduardo Ruiz Libreros, Walterio Mayol-Cuevas

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

6 Citations (Scopus)

381 Downloads (Pure)

Abstract

This paper introduces and evaluates a new tensor field representation to express the geometric affordance of one object relative to another, a key competence for Cognitive and Autonomous robots. We expand the bisector surface representation to one that is weight-driven and that retains the provenance of surface points with directional vectors. We also incorporate the notion of affordance keypoints which allow for faster decisions at a point of query and with a compact and straightforward descriptor. Using a single interaction example, we are able to generalize to previously-unseen scenarios; both synthetic and also real scenes captured with RGB-D sensors. Evaluations also include crowdsourcing comparisons that confirm the validity of our affordance proposals, which agree on average 84 % of the time with human judgments, that is 20-40 % better than the baseline methods.

Original language	English
Title of host publication	2018 IEEE International Conference on Robotics and Automation (ICRA 2018)
Subtitle of host publication	Proceedings of a meeting held 21-25 May 2018, Brisbane, Australia.
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	2192-2199
Number of pages	8
ISBN (Electronic)	9781538630815
ISBN (Print)	9781538630822
DOIs	https://doi.org/10.1109/ICRA.2018.8462835
Publication status	Published - Nov 2018
Event	2018 IEEE International Conference on Robotics and Automation (ICRA) - Brisbane, Australia Duration: 21 May 2018 → 25 May 2018

Publication series

Name	International Conference on Robotics and Automation
Publisher	IEEE
ISSN (Print)	1050-4729

Conference

Conference	2018 IEEE International Conference on Robotics and Automation (ICRA)
Abbreviated title	ICRA
Country/Territory	Australia
City	Brisbane
Period	21/05/18 → 25/05/18

Access to Document

10.1109/ICRA.2018.8462835

Full-text PDF (accepted author manuscript)
This is the accepted author manuscript (AAM). The final published version (version of record) is available online via IEEE at https://doi.org/10.1109/ICRA.2018.8462835 . Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 1.92 MBLicence: Other

Handle.net

Persistent link

Cite this

Ruiz Libreros, E., & Mayol-Cuevas, W. (2018). Where Can I Do This? Geometric Affordances from a Single Example with the Interaction Tensor. In 2018 IEEE International Conference on Robotics and Automation (ICRA 2018): Proceedings of a meeting held 21-25 May 2018, Brisbane, Australia. (pp. 2192-2199). (International Conference on Robotics and Automation). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/ICRA.2018.8462835

Ruiz Libreros, Eduardo ; Mayol-Cuevas, Walterio. / Where Can I Do This? Geometric Affordances from a Single Example with the Interaction Tensor. 2018 IEEE International Conference on Robotics and Automation (ICRA 2018): Proceedings of a meeting held 21-25 May 2018, Brisbane, Australia.. Institute of Electrical and Electronics Engineers (IEEE), 2018. pp. 2192-2199 (International Conference on Robotics and Automation).

@inproceedings{6c08a31b833647b894fdadd964a35165,

title = "Where Can I Do This? Geometric Affordances from a Single Example with the Interaction Tensor",

abstract = "This paper introduces and evaluates a new tensor field representation to express the geometric affordance of one object relative to another, a key competence for Cognitive and Autonomous robots. We expand the bisector surface representation to one that is weight-driven and that retains the provenance of surface points with directional vectors. We also incorporate the notion of affordance keypoints which allow for faster decisions at a point of query and with a compact and straightforward descriptor. Using a single interaction example, we are able to generalize to previously-unseen scenarios; both synthetic and also real scenes captured with RGB-D sensors. Evaluations also include crowdsourcing comparisons that confirm the validity of our affordance proposals, which agree on average 84 % of the time with human judgments, that is 20-40 % better than the baseline methods.",

author = "{Ruiz Libreros}, Eduardo and Walterio Mayol-Cuevas",

year = "2018",

month = nov,

doi = "10.1109/ICRA.2018.8462835",

language = "English",

isbn = "9781538630822",

series = "International Conference on Robotics and Automation",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

pages = "2192--2199",

booktitle = "2018 IEEE International Conference on Robotics and Automation (ICRA 2018)",

address = "United States",

note = "2018 IEEE International Conference on Robotics and Automation (ICRA), ICRA ; Conference date: 21-05-2018 Through 25-05-2018",

}

Ruiz Libreros, E & Mayol-Cuevas, W 2018, Where Can I Do This? Geometric Affordances from a Single Example with the Interaction Tensor. in 2018 IEEE International Conference on Robotics and Automation (ICRA 2018): Proceedings of a meeting held 21-25 May 2018, Brisbane, Australia.. International Conference on Robotics and Automation, Institute of Electrical and Electronics Engineers (IEEE), pp. 2192-2199, 2018 IEEE International Conference on Robotics and Automation (ICRA), Brisbane, Australia, 21/05/18. https://doi.org/10.1109/ICRA.2018.8462835

Where Can I Do This? Geometric Affordances from a Single Example with the Interaction Tensor. / Ruiz Libreros, Eduardo; Mayol-Cuevas, Walterio.
2018 IEEE International Conference on Robotics and Automation (ICRA 2018): Proceedings of a meeting held 21-25 May 2018, Brisbane, Australia.. Institute of Electrical and Electronics Engineers (IEEE), 2018. p. 2192-2199 (International Conference on Robotics and Automation).

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - Where Can I Do This? Geometric Affordances from a Single Example with the Interaction Tensor

AU - Ruiz Libreros, Eduardo

AU - Mayol-Cuevas, Walterio

PY - 2018/11

Y1 - 2018/11

N2 - This paper introduces and evaluates a new tensor field representation to express the geometric affordance of one object relative to another, a key competence for Cognitive and Autonomous robots. We expand the bisector surface representation to one that is weight-driven and that retains the provenance of surface points with directional vectors. We also incorporate the notion of affordance keypoints which allow for faster decisions at a point of query and with a compact and straightforward descriptor. Using a single interaction example, we are able to generalize to previously-unseen scenarios; both synthetic and also real scenes captured with RGB-D sensors. Evaluations also include crowdsourcing comparisons that confirm the validity of our affordance proposals, which agree on average 84 % of the time with human judgments, that is 20-40 % better than the baseline methods.

AB - This paper introduces and evaluates a new tensor field representation to express the geometric affordance of one object relative to another, a key competence for Cognitive and Autonomous robots. We expand the bisector surface representation to one that is weight-driven and that retains the provenance of surface points with directional vectors. We also incorporate the notion of affordance keypoints which allow for faster decisions at a point of query and with a compact and straightforward descriptor. Using a single interaction example, we are able to generalize to previously-unseen scenarios; both synthetic and also real scenes captured with RGB-D sensors. Evaluations also include crowdsourcing comparisons that confirm the validity of our affordance proposals, which agree on average 84 % of the time with human judgments, that is 20-40 % better than the baseline methods.

U2 - 10.1109/ICRA.2018.8462835

DO - 10.1109/ICRA.2018.8462835

M3 - Conference Contribution (Conference Proceeding)

SN - 9781538630822

T3 - International Conference on Robotics and Automation

SP - 2192

EP - 2199

BT - 2018 IEEE International Conference on Robotics and Automation (ICRA 2018)

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 2018 IEEE International Conference on Robotics and Automation (ICRA)

Y2 - 21 May 2018 through 25 May 2018

ER -

Ruiz Libreros E, Mayol-Cuevas W. Where Can I Do This? Geometric Affordances from a Single Example with the Interaction Tensor. In 2018 IEEE International Conference on Robotics and Automation (ICRA 2018): Proceedings of a meeting held 21-25 May 2018, Brisbane, Australia.. Institute of Electrical and Electronics Engineers (IEEE). 2018. p. 2192-2199. (International Conference on Robotics and Automation). Epub 2018 May 21. doi: 10.1109/ICRA.2018.8462835

Where Can I Do This? Geometric Affordances from a Single Example with the Interaction Tensor

Abstract

Publication series

Conference

Access to Document

Handle.net

Fingerprint

Cite this