Leveraging contact forces for learning to grasp

Hamza Merzic, Miroslav Bogdanovic, Daniel Kappler, Ludovic Righetti, Jeannette Bohg

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

Abstract

Grasping objects under uncertainty remains an open problem in robotics research. This uncertainty is often due to noisy or partial observations of the object pose or shape. To enable a robot to react appropriately to unforeseen effects, it is crucial that it continuously takes sensor feedback into account. While visual feedback is important for inferring a grasp pose and reaching for an object, contact feedback offers valuable information during manipulation and grasp acquisition. In this paper, we use model-free deep reinforcement learning to synthesize control policies that exploit contact sensing to generate robust grasping under uncertainty. We demonstrate our approach on a multi-fingered hand that exhibits more complex finger coordination than the commonly used two-fingered grippers. We conduct extensive experiments in order to assess the performance of the learned policies, with and without contact sensing. While it is possible to learn grasping policies without contact sensing, our results suggest that contact feedback allows for a significant improvement of grasping robustness under object pose uncertainty and for objects with a complex shape.

Original languageEnglish (US)
Title of host publication2019 International Conference on Robotics and Automation, ICRA 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3615-3621
Number of pages7
ISBN (Electronic)9781538660263
DOIs
StatePublished - May 1 2019
Event2019 International Conference on Robotics and Automation, ICRA 2019 - Montreal, Canada
Duration: May 20 2019May 24 2019

Publication series

NameProceedings - IEEE International Conference on Robotics and Automation
Volume2019-May
ISSN (Print)1050-4729

Conference

Conference2019 International Conference on Robotics and Automation, ICRA 2019
CountryCanada
CityMontreal
Period5/20/195/24/19

Fingerprint

Feedback
Grippers
Reinforcement learning
Robotics
Robots
Uncertainty
Sensors
Experiments

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Artificial Intelligence
  • Electrical and Electronic Engineering

Cite this

Merzic, H., Bogdanovic, M., Kappler, D., Righetti, L., & Bohg, J. (2019). Leveraging contact forces for learning to grasp. In 2019 International Conference on Robotics and Automation, ICRA 2019 (pp. 3615-3621). [8793733] (Proceedings - IEEE International Conference on Robotics and Automation; Vol. 2019-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICRA.2019.8793733

Leveraging contact forces for learning to grasp. / Merzic, Hamza; Bogdanovic, Miroslav; Kappler, Daniel; Righetti, Ludovic; Bohg, Jeannette.

2019 International Conference on Robotics and Automation, ICRA 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 3615-3621 8793733 (Proceedings - IEEE International Conference on Robotics and Automation; Vol. 2019-May).

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

Merzic, H, Bogdanovic, M, Kappler, D, Righetti, L & Bohg, J 2019, Leveraging contact forces for learning to grasp. in 2019 International Conference on Robotics and Automation, ICRA 2019., 8793733, Proceedings - IEEE International Conference on Robotics and Automation, vol. 2019-May, Institute of Electrical and Electronics Engineers Inc., pp. 3615-3621, 2019 International Conference on Robotics and Automation, ICRA 2019, Montreal, Canada, 5/20/19. https://doi.org/10.1109/ICRA.2019.8793733
Merzic H, Bogdanovic M, Kappler D, Righetti L, Bohg J. Leveraging contact forces for learning to grasp. In 2019 International Conference on Robotics and Automation, ICRA 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 3615-3621. 8793733. (Proceedings - IEEE International Conference on Robotics and Automation). https://doi.org/10.1109/ICRA.2019.8793733
Merzic, Hamza ; Bogdanovic, Miroslav ; Kappler, Daniel ; Righetti, Ludovic ; Bohg, Jeannette. / Leveraging contact forces for learning to grasp. 2019 International Conference on Robotics and Automation, ICRA 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 3615-3621 (Proceedings - IEEE International Conference on Robotics and Automation).
@inproceedings{00ebe6fa354e4445b04424c01c22afe6,
title = "Leveraging contact forces for learning to grasp",
abstract = "Grasping objects under uncertainty remains an open problem in robotics research. This uncertainty is often due to noisy or partial observations of the object pose or shape. To enable a robot to react appropriately to unforeseen effects, it is crucial that it continuously takes sensor feedback into account. While visual feedback is important for inferring a grasp pose and reaching for an object, contact feedback offers valuable information during manipulation and grasp acquisition. In this paper, we use model-free deep reinforcement learning to synthesize control policies that exploit contact sensing to generate robust grasping under uncertainty. We demonstrate our approach on a multi-fingered hand that exhibits more complex finger coordination than the commonly used two-fingered grippers. We conduct extensive experiments in order to assess the performance of the learned policies, with and without contact sensing. While it is possible to learn grasping policies without contact sensing, our results suggest that contact feedback allows for a significant improvement of grasping robustness under object pose uncertainty and for objects with a complex shape.",
author = "Hamza Merzic and Miroslav Bogdanovic and Daniel Kappler and Ludovic Righetti and Jeannette Bohg",
year = "2019",
month = "5",
day = "1",
doi = "10.1109/ICRA.2019.8793733",
language = "English (US)",
series = "Proceedings - IEEE International Conference on Robotics and Automation",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "3615--3621",
booktitle = "2019 International Conference on Robotics and Automation, ICRA 2019",

}

TY - GEN

T1 - Leveraging contact forces for learning to grasp

AU - Merzic, Hamza

AU - Bogdanovic, Miroslav

AU - Kappler, Daniel

AU - Righetti, Ludovic

AU - Bohg, Jeannette

PY - 2019/5/1

Y1 - 2019/5/1

N2 - Grasping objects under uncertainty remains an open problem in robotics research. This uncertainty is often due to noisy or partial observations of the object pose or shape. To enable a robot to react appropriately to unforeseen effects, it is crucial that it continuously takes sensor feedback into account. While visual feedback is important for inferring a grasp pose and reaching for an object, contact feedback offers valuable information during manipulation and grasp acquisition. In this paper, we use model-free deep reinforcement learning to synthesize control policies that exploit contact sensing to generate robust grasping under uncertainty. We demonstrate our approach on a multi-fingered hand that exhibits more complex finger coordination than the commonly used two-fingered grippers. We conduct extensive experiments in order to assess the performance of the learned policies, with and without contact sensing. While it is possible to learn grasping policies without contact sensing, our results suggest that contact feedback allows for a significant improvement of grasping robustness under object pose uncertainty and for objects with a complex shape.

AB - Grasping objects under uncertainty remains an open problem in robotics research. This uncertainty is often due to noisy or partial observations of the object pose or shape. To enable a robot to react appropriately to unforeseen effects, it is crucial that it continuously takes sensor feedback into account. While visual feedback is important for inferring a grasp pose and reaching for an object, contact feedback offers valuable information during manipulation and grasp acquisition. In this paper, we use model-free deep reinforcement learning to synthesize control policies that exploit contact sensing to generate robust grasping under uncertainty. We demonstrate our approach on a multi-fingered hand that exhibits more complex finger coordination than the commonly used two-fingered grippers. We conduct extensive experiments in order to assess the performance of the learned policies, with and without contact sensing. While it is possible to learn grasping policies without contact sensing, our results suggest that contact feedback allows for a significant improvement of grasping robustness under object pose uncertainty and for objects with a complex shape.

UR - http://www.scopus.com/inward/record.url?scp=85071422957&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85071422957&partnerID=8YFLogxK

U2 - 10.1109/ICRA.2019.8793733

DO - 10.1109/ICRA.2019.8793733

M3 - Conference contribution

AN - SCOPUS:85071422957

T3 - Proceedings - IEEE International Conference on Robotics and Automation

SP - 3615

EP - 3621

BT - 2019 International Conference on Robotics and Automation, ICRA 2019

PB - Institute of Electrical and Electronics Engineers Inc.

ER -