research-article

Learning to guide task and motion planning using score-space representation

Authors:

Leslie Pack Kaelbling,

Tomás Lozano-PérezAuthors Info & Claims

The International Journal of Robotics Research, Volume 38, Issue 7

Pages 793 - 812

https://doi.org/10.1177/0278364919848837

Published: 01 June 2019 Publication History

Abstract

In this paper, we propose a learning algorithm that speeds up the search in task and motion planning problems. Our algorithm proposes solutions to three different challenges that arise in learning to improve planning efficiency: what to predict, how to represent a planning problem instance, and how to transfer knowledge from one problem instance to another. We propose a method that predicts constraints on the search space based on a generic representation of a planning problem instance, called score-space, where we represent a problem instance in terms of the performance of a set of solutions attempted so far. Using this representation, we transfer knowledge, in the form of constraints, from previous problems based on the similarity in score-space. We design a sequential algorithm that efficiently predicts these constraints, and evaluate it in three different challenging task and motion planning problems. Results indicate that our approach performs orders of magnitudes faster than an unguided planner.

References

[1]

Berenson D, Abbeel P, and Goldberg K (2012) A robot path planning framework that learns from experience. In: IEEE Conference on Robotics and Automation.

[2]

Dantam NT, Kingston Z, Chaudhuri S, and Kavraki L (2017) Incremental task and motion planning: A constraint-based approach. In: Robotics: Science and Systems.

[3]

Dey D, Liu TY, Sofman B, and Bagnell JA (2012 a) Efficient optimization of control libraries. In: AAAI Conference on Artificial Intelligence.

[4]

Dey D, Liu TY, Sofman B, Hebert M, and Bagnell JA (2012 b ) Contextual sequence prediction with application to control library optimization. In: Robotics: Science and Systems.

[5]

Diankov R (2010) Automated Construction of Robotic Manipulation Programs. PhD Thesis, CMU Robotics Institute.

Digital Library

[6]

Dragan A, Gordon GJ, and Srinivasa SS (2011) Learning from experience in manipulation planning: Setting the right goals. In: International Symposium on Robotics Research.

[7]

Finney S, Kaelbling LP, and Lozano-Pérez T (2007) Predicting partial paths from planning problem parameters. In: Robotics: Science and Systems.

[8]

Goodfellow I, Pouget-Abadie J, Mirza M, et al. (2014) Generative adversarial nets. In: Advances in Neural Information Processing Systems.

Digital Library

[9]

Gravot F, Cambon S, and Alami R (2005) asymov: A planner that deals with intricate symbolic and geometric problems. In: International Symposium on Robotics Research.

[10]

Hodál J and Dvořák J (2008) Using case-based reasoning for mobile robot path planning. Journal of Engineering Mechanics 15(3): 181–191.

[11]

Jetchev N and Toussaint M (2013) Fast motion planning from experience: Trajectory prediction for speeding up movement generation. Autonomous Robots 34(1–2): 111–127.

Digital Library

[12]

Kaelbling LP and Lozano-Pérez T (2013) Integrated task and motion planning in belief space. The International Journal of Robotics Research 32(9–10): 1194–1227.

Digital Library

[13]

Kim B, Kaelbling LP, and Lozano-Pérez T (2017) Learning to guide task and motion planning using score-space representation. In: IEEE Conference on Robotics and Automation.

[14]

Kroemer O and Sukhatme GS (2016) Meta-level priors for learning manipulation skills with sparse features. In: International Symposium on Experimental Robotics.

[15]

Kroemer O and Sukhatme GS (2017) Feature selection for learning versatile manipulation skills based on observed and desired trajectories. In: IEEE International Conference on Robotics and Automation.

[16]

Lien J and Lu Y (2009) Planning motion in environments with similar obstacles. In: Robotics: Science and Systems.

[17]

Lozano-Pérez T and Kaelbling L (2014) A constraint-based method for solving sequential manipulation planning problems. In: International Conference on Intelligent Robots and Systems.

[18]

Munos R (2011) Optimistic optimization of a deterministic function without the knowledge of its smoothness. In: Advances in Neural Information Processing Systems.

[19]

Munos R (2014) From bandits to Monte-Carlo Tree Search: The optimistic principle applied to optimization and planning. Foundations and Trends in Machine Learning 7(1): 1–129.

Digital Library

[20]

Pandya S and Hutchinson S (1992) A case-based approach to robot motion planning. In: IEEE International Conference on Systems, Man, and Cybernetics.

[21]

Phillips M, Cohen B, Chita S, and Likhachev M (2012) E-graphs: Bootstrapping planning with experience graphs. In: Robotics: Science and Systems.

[22]

Schulman J, Duan Y, Ho J, et al. (2014) Motion planning with sequential convex optimization and convex collision checking. The International Journal of Robotics Research 33(9): 1251–1270.

Digital Library

[23]

Snoek J, Larochelle H, and Adams RP (2012) Practical Bayesian optimization of machine learning algorithms. In: Advances in Neural Information Processing Systems.

[24]

Srinivas N, Krause A, Kakade S, and Seeger M (2010) Gaussian process optimization in the bandit setting: No regret and experimental design. In: International Conference on Machine Learning.

Digital Library

[25]

Srivastava S, Fang E, Riano L, Chitnis R, Russell S, and Abbeel P (2014) Combined task and motion planning through an extensible planner-independent interface layer. In: IEEE Conference on Robotics and Automation.

[26]

Toussaint M (2015) Logic-geometric programming: An optimization-based approach to combined task and motion planning. In: International Joint Conference on Artificial Intelligence.

[27]

Van Dyk DA and Meng XL (2001) The art of data augmentation. Journal of Computational and Graphical Statistics 10(1): 1–50.

[28]

Wang Z, Zhou B, and Jegelka S (2017) Optimization as estimation with Gaussian processes in bandit settings. In: International Conference on Artificial Intelligence and Statistics.

[29]

Zhu Y, Gordon D, Kolve E, et al. (2017) Visual semantic planning using deep successor representations. In: International Conference on Computer Vision.

Cited By

Huang YTaylor NConkey ALiu WHermans T(2024)Latent Space Planning for Multiobject Manipulation With Environment-Aware Relational ClassifiersIEEE Transactions on Robotics10.1109/TRO.2024.336095640(1724-1739)Online publication date: 1-Jan-2024
https://dl.acm.org/doi/10.1109/TRO.2024.3360956
Wang BWang ZWang XCao YSaurous RKim YOh ANaumann TGloberson ASaenko KHardt MLevine S(2023)Grammar prompting for domain-specific language generation with large language modelsProceedings of the 37th International Conference on Neural Information Processing Systems10.5555/3666122.3668959(65030-65055)Online publication date: 10-Dec-2023
https://dl.acm.org/doi/10.5555/3666122.3668959
Guo HWu FQin YLi RLi KLi K(2023)Recent Trends in Task and Motion Planning for Robotics: A SurveyACM Computing Surveys10.1145/358313655:13s(1-36)Online publication date: 13-Jul-2023
https://dl.acm.org/doi/10.1145/3583136
Show More Cited By

Index Terms

Learning to guide task and motion planning using score-space representation
1. Computing methodologies
  1. Artificial intelligence
  2. Machine learning
2. Theory of computation
  1. Design and analysis of algorithms

Index terms have been assigned to the content through auto-classification.

Recommendations

Learning to guide task and motion planning using score-space representation
2017 IEEE International Conference on Robotics and Automation (ICRA)
In this paper, we propose a learning algorithm that speeds up the search in task and motion planning problems. Our algorithm proposes solutions to three different challenges that arise in learning to improve planning efficiency: what to predict, how to ...
Multiple Mobile Robot Task and Motion Planning: A Survey
With recent advances in mobile robotics, autonomous systems, and artificial intelligence, there is a growing expectation that robots are able to solve complex problems. Many of these problems require multiple robots working cooperatively in a multi-robot ...
An incremental constraint-based framework for task and motion planning

We present a new constraint-based framework for task and motion planning TMP. Our approach is extensible, probabilistically complete, and offers improved performance and generality compared with a similar, state-of-the-art planner. The key idea is to ...

Comments

Information & Contributors

Information

Published In

cover image International Journal of Robotics Research

International Journal of Robotics Research Volume 38, Issue 7

Jun 2019

108 pages

ISSN:0278-3649

Issue’s Table of Contents

© The Author(s) 2019.

Publisher

Sage Publications, Inc.

United States

Publication History

Published: 01 June 2019

Author Tags

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

13
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 14 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Huang YTaylor NConkey ALiu WHermans T(2024)Latent Space Planning for Multiobject Manipulation With Environment-Aware Relational ClassifiersIEEE Transactions on Robotics10.1109/TRO.2024.336095640(1724-1739)Online publication date: 1-Jan-2024
https://dl.acm.org/doi/10.1109/TRO.2024.3360956
Wang BWang ZWang XCao YSaurous RKim YOh ANaumann TGloberson ASaenko KHardt MLevine S(2023)Grammar prompting for domain-specific language generation with large language modelsProceedings of the 37th International Conference on Neural Information Processing Systems10.5555/3666122.3668959(65030-65055)Online publication date: 10-Dec-2023
https://dl.acm.org/doi/10.5555/3666122.3668959
Guo HWu FQin YLi RLi KLi K(2023)Recent Trends in Task and Motion Planning for Robotics: A SurveyACM Computing Surveys10.1145/358313655:13s(1-36)Online publication date: 13-Jul-2023
https://dl.acm.org/doi/10.1145/3583136
Kim BShimanuki LKaelbling LLozano-Pérez T(2022)Representation, learning, and planning algorithms for geometric task and motion planningInternational Journal of Robotics Research10.1177/0278364921103828041:2(210-231)Online publication date: 1-Feb-2022
https://dl.acm.org/doi/10.1177/02783649211038280
Zhang XZhu YDing YZhu YStone PZhang S(2022)Visually Grounded Task and Motion Planning for Mobile Manipulation2022 International Conference on Robotics and Automation (ICRA)10.1109/ICRA46639.2022.9812055(1925-1931)Online publication date: 23-May-2022
https://dl.acm.org/doi/10.1109/ICRA46639.2022.9812055
Osipov GPanov A(2021)Planning Rational Behavior of Cognitive Semiotic Agents in a Dynamic EnvironmentScientific and Technical Information Processing10.3103/S014768822106011348:6(502-516)Online publication date: 1-Dec-2021
https://dl.acm.org/doi/10.3103/S0147688221060113
Nanayakkara TBarfoot THoward TDriess DHa JToussaint M(2021)Learning to solve sequential physical reasoning problems from a scene imageInternational Journal of Robotics Research10.1177/0278364921105696740:12-14(1435-1466)Online publication date: 1-Dec-2021
https://dl.acm.org/doi/10.1177/02783649211056967
Jiao ZZhang ZWang WHan DZhu SZhu YLiu H(2021)Efficient Task Planning for Mobile Manipulation: a Virtual Kinematic Chain Perspective2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)10.1109/IROS51168.2021.9636554(8288-8294)Online publication date: 27-Sep-2021
https://dl.acm.org/doi/10.1109/IROS51168.2021.9636554
Kingston ZChamzas CKavraki L(2021)Using Experience to Improve Constrained Planning on Foliations for Multi-Modal Problems2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)10.1109/IROS51168.2021.9636236(6922-6927)Online publication date: 27-Sep-2021
https://dl.acm.org/doi/10.1109/IROS51168.2021.9636236
Mukherjee SPaxton CMousavian AFishman ALikhachev MFox D(2021)Reactive Long Horizon Task Execution via Visual Skill and Precondition Models2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)10.1109/IROS51168.2021.9636037(5717-5724)Online publication date: 27-Sep-2021
https://dl.acm.org/doi/10.1109/IROS51168.2021.9636037
Show More Cited By

View Options

View options

Media

Figures

Other

Tables

View Issue’s Table of Contents