Efficient optimization for autonomous robotic manipulation of natural objects

Abdeslam Boularias, J. Andrew Bagnell, Anthony Stentz

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

7 Citations (Scopus)

Abstract

Manipulating natural objects of irregular shapes, such as rocks, is an essential capability of robots operating in outdoor environments. Physics-based simulators are commonly used to plan stable grasps for man-made objects. However, planning is an expensive process that is based on simulating hand and object trajectories in different configurations, and evaluating the outcome of each trajectory. This problem is particularly concerning when the objects are irregular or cluttered, because the space of feasible grasps is significantly smaller, and more configurations need to be evaluated before finding a good one. In this paper, we first present a learning technique for fast detection of an initial set of potentially stable grasps in a cluttered scene. The best detected grasps are further optimized by fine-tuning the configuration of the hand in simulation. To reduce the computational burden of this last operation, we model the outcomes of the grasps as a Gaussian Process, and use an entropy-search method in order to focus the optimization on regions where the best grasp is most likely to be. This approach is tested on the task of clearing piles of real, unknown, rock debris with an autonomous robot. Empirical results show a clear advantage of the proposed approach when the time window for decision is short.

Original languageEnglish (US)
Title of host publicationProceedings of the National Conference on Artificial Intelligence
PublisherAI Access Foundation
Pages2520-2526
Number of pages7
ISBN (Electronic)9781577356806
StatePublished - Jan 1 2014
Event28th AAAI Conference on Artificial Intelligence, AAAI 2014, 26th Innovative Applications of Artificial Intelligence Conference, IAAI 2014 and the 5th Symposium on Educational Advances in Artificial Intelligence, EAAI 2014 - Quebec City, Canada
Duration: Jul 27 2014Jul 31 2014

Publication series

NameProceedings of the National Conference on Artificial Intelligence
Volume4

Other

Other28th AAAI Conference on Artificial Intelligence, AAAI 2014, 26th Innovative Applications of Artificial Intelligence Conference, IAAI 2014 and the 5th Symposium on Educational Advances in Artificial Intelligence, EAAI 2014
CountryCanada
CityQuebec City
Period7/27/147/31/14

Fingerprint

Robotics
Rocks
Trajectories
Robots
Debris
Piles
Entropy
Physics
Tuning
Simulators
Planning

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

Cite this

Boularias, A., Bagnell, J. A., & Stentz, A. (2014). Efficient optimization for autonomous robotic manipulation of natural objects. In Proceedings of the National Conference on Artificial Intelligence (pp. 2520-2526). (Proceedings of the National Conference on Artificial Intelligence; Vol. 4). AI Access Foundation.
Boularias, Abdeslam ; Bagnell, J. Andrew ; Stentz, Anthony. / Efficient optimization for autonomous robotic manipulation of natural objects. Proceedings of the National Conference on Artificial Intelligence. AI Access Foundation, 2014. pp. 2520-2526 (Proceedings of the National Conference on Artificial Intelligence).
@inproceedings{9c4037043d9545048e4a4f78d1bfaa43,
title = "Efficient optimization for autonomous robotic manipulation of natural objects",
abstract = "Manipulating natural objects of irregular shapes, such as rocks, is an essential capability of robots operating in outdoor environments. Physics-based simulators are commonly used to plan stable grasps for man-made objects. However, planning is an expensive process that is based on simulating hand and object trajectories in different configurations, and evaluating the outcome of each trajectory. This problem is particularly concerning when the objects are irregular or cluttered, because the space of feasible grasps is significantly smaller, and more configurations need to be evaluated before finding a good one. In this paper, we first present a learning technique for fast detection of an initial set of potentially stable grasps in a cluttered scene. The best detected grasps are further optimized by fine-tuning the configuration of the hand in simulation. To reduce the computational burden of this last operation, we model the outcomes of the grasps as a Gaussian Process, and use an entropy-search method in order to focus the optimization on regions where the best grasp is most likely to be. This approach is tested on the task of clearing piles of real, unknown, rock debris with an autonomous robot. Empirical results show a clear advantage of the proposed approach when the time window for decision is short.",
author = "Abdeslam Boularias and Bagnell, {J. Andrew} and Anthony Stentz",
year = "2014",
month = "1",
day = "1",
language = "English (US)",
series = "Proceedings of the National Conference on Artificial Intelligence",
publisher = "AI Access Foundation",
pages = "2520--2526",
booktitle = "Proceedings of the National Conference on Artificial Intelligence",
address = "United States",

}

Boularias, A, Bagnell, JA & Stentz, A 2014, Efficient optimization for autonomous robotic manipulation of natural objects. in Proceedings of the National Conference on Artificial Intelligence. Proceedings of the National Conference on Artificial Intelligence, vol. 4, AI Access Foundation, pp. 2520-2526, 28th AAAI Conference on Artificial Intelligence, AAAI 2014, 26th Innovative Applications of Artificial Intelligence Conference, IAAI 2014 and the 5th Symposium on Educational Advances in Artificial Intelligence, EAAI 2014, Quebec City, Canada, 7/27/14.

Efficient optimization for autonomous robotic manipulation of natural objects. / Boularias, Abdeslam; Bagnell, J. Andrew; Stentz, Anthony.

Proceedings of the National Conference on Artificial Intelligence. AI Access Foundation, 2014. p. 2520-2526 (Proceedings of the National Conference on Artificial Intelligence; Vol. 4).

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

TY - GEN

T1 - Efficient optimization for autonomous robotic manipulation of natural objects

AU - Boularias, Abdeslam

AU - Bagnell, J. Andrew

AU - Stentz, Anthony

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Manipulating natural objects of irregular shapes, such as rocks, is an essential capability of robots operating in outdoor environments. Physics-based simulators are commonly used to plan stable grasps for man-made objects. However, planning is an expensive process that is based on simulating hand and object trajectories in different configurations, and evaluating the outcome of each trajectory. This problem is particularly concerning when the objects are irregular or cluttered, because the space of feasible grasps is significantly smaller, and more configurations need to be evaluated before finding a good one. In this paper, we first present a learning technique for fast detection of an initial set of potentially stable grasps in a cluttered scene. The best detected grasps are further optimized by fine-tuning the configuration of the hand in simulation. To reduce the computational burden of this last operation, we model the outcomes of the grasps as a Gaussian Process, and use an entropy-search method in order to focus the optimization on regions where the best grasp is most likely to be. This approach is tested on the task of clearing piles of real, unknown, rock debris with an autonomous robot. Empirical results show a clear advantage of the proposed approach when the time window for decision is short.

AB - Manipulating natural objects of irregular shapes, such as rocks, is an essential capability of robots operating in outdoor environments. Physics-based simulators are commonly used to plan stable grasps for man-made objects. However, planning is an expensive process that is based on simulating hand and object trajectories in different configurations, and evaluating the outcome of each trajectory. This problem is particularly concerning when the objects are irregular or cluttered, because the space of feasible grasps is significantly smaller, and more configurations need to be evaluated before finding a good one. In this paper, we first present a learning technique for fast detection of an initial set of potentially stable grasps in a cluttered scene. The best detected grasps are further optimized by fine-tuning the configuration of the hand in simulation. To reduce the computational burden of this last operation, we model the outcomes of the grasps as a Gaussian Process, and use an entropy-search method in order to focus the optimization on regions where the best grasp is most likely to be. This approach is tested on the task of clearing piles of real, unknown, rock debris with an autonomous robot. Empirical results show a clear advantage of the proposed approach when the time window for decision is short.

UR - http://www.scopus.com/inward/record.url?scp=84908204980&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84908204980&partnerID=8YFLogxK

M3 - Conference contribution

T3 - Proceedings of the National Conference on Artificial Intelligence

SP - 2520

EP - 2526

BT - Proceedings of the National Conference on Artificial Intelligence

PB - AI Access Foundation

ER -

Boularias A, Bagnell JA, Stentz A. Efficient optimization for autonomous robotic manipulation of natural objects. In Proceedings of the National Conference on Artificial Intelligence. AI Access Foundation. 2014. p. 2520-2526. (Proceedings of the National Conference on Artificial Intelligence).