Learning to Manipulate Articulated Objects in Unstructured Environments Using a Grounded Relational Representation
Open accessAbstract
We introduce a learning-based approach to manipulation in unstructured environments.This approach permits autonomous acquisition of manipulation expertise from interactions with the environment.The resulting expertise enables a robot to perform effective manipulation based on partial state information.The manipulation expertise is represented in a relational state representation and learned using relational reinforcement learning.The relational representation renders learning tractable by collapsing a large number of states onto a single, relational state.The relational state representation is carefully grounded in the perceptual and interaction skills of the robot.This ensures that symbolically learned knowledge remains meaningful in the physical world.We experimentally validate the proposed learning approach on the task of manipulating an articulated object to obtain a model of its kinematic structure.Our experiments demonstrate that the manipulation expertise acquired by the robot leads to substantial performance improvements.These improvements are maintained when experience is applied to previously unseen objects.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Relational Reinforcement approaches for learning robot strategies are based on the use of ground instances and do not involve predicate invention to extend the relational vocabulary provided by the user.
“However, unlike the approach for learning recursive robot strategies described in Sect. 5.1 the Relational Reinforcement approaches are based on the use of ground instances and do not involve predicate invention to extend the relational vocabulary provided by the user.”
From Meta-interpretive learning of higher-order dyadic datalog: predicate invention revisited (2015) · cites this paper as Katz et al. 2008
The section “Representation of Q-Value Function” (page unavailable) explicitly says that states and actions are relational and stored uninstantiated, contrary to the claim that the approach uses ground instances. The paper describes a defined set of predicates, but does not establish the broader claim about user-provided vocabularies or predicate invention across relational reinforcement approaches. (LLM, conf=0.88)
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Relational Reinforcement Learning
Džeroski, S., De Raedt, L., & Driessens, K. (2001) · Machine Learning · doi:10.1023/a:1007694015589 · Cited by 371 · see citing works
Flagged first, then by citations
Research works printed but not linked: 27
- J. D. Bernheisel and K. M. Lynch. Stable transport of assemblies by pushing. IEEE Transactions on Robotics, 22(4):740-750, 2006.
- A. Bicchi and V. Kumar. Robotics grasping and contact: A review. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), San Francisco, CA, 2000.
- R. R. Burridge, A. A. Rizzi, and D. E. Koditschek. Sequential composition of dynamically dexterous robot behaviors. International Journal of Robotics Research, 18(6):534-555, 1999.
- A. D. Christiansen, M. T. Mason, and T. M. Mitchell. Learning reliable manipulation strategies without initial physical models. Robotics and Autonomous Systems, 8(1-2):7-18, 1991.
- L. P. Cordella, P. Foggia, C. Sandone, and M. Vento. Performance evaluation of the VF graph matching algorithm. In Proceedings of the 10th ICIAP IEEE Computer Society Press, volume 2, pages 1038-1041, 1999. http://amalfi.dis.unina.it/graph/db/vflib-2.0/doc/vflib.html.
- K. Driessens and J. Ramon. Relational instance based regression for relational reinforcement learning. In Proceedings of the International Conference on Machine Learning (ICML), 2003.
- A. Edsinger and C. C. Kemp. Manipulation in human environments. In Proceedings of the IEEE International Conference on Humanoid Robots, 2006.
- R. Grupen and M. Huber. A framework for the development of robot behavior. In Proceedings of the 2005 AAAI Spring Symposium Series: Developmental Robotics, Stanford, USA, 2005.
- L. P. Kaelbling. Learning in Embedded Systems. MIT Press, 1993.
- D. Katz and O. Brock. Manipulating articulated objects with interactive perception. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Pasadena, USA, 2008.
- M. Kearns and S. Singh. Near-optimal reinforcement learning in polynomial time. In Proceedings of the International Conference on Machine Learning (ICML), pages 260-268.
- Morgan Kaufmann, San Francisco, CA, 1998.
- K. M. Lynch and M. T. Mason. Dynamic nonprehensile manipulation: Controllability, planning, and experiments. International Journal of Robotics Research, 18(1):64-92, 1999.
- M. T. Mason. Mechanics of Robotic Manipulation. MIT Press, 2001.
- A. W. Moore. Efficient memory-based learning for robot control. Technical Report UCAM-CL-TR-209, Computer Laboratory, University of Cambridge, 1990.
- A. M. Okamura, N. Smaby, and M. R. Cutkosky. An overview of dexterous manipulation. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), volume 1, pages 255- 262, San Franscisco, USA, 2000.
- R. Platt, R. Burridge, M. Diftler, J. Graf, M. Goza, E. Huber, and O. Brock. Humanoid mobile manipulation using controller refinement. In Proceedings of the IEEE International Conference on Humanoid Robots, Genova, Italy, December 2006.
- R. Platt, A. H. Fagg, and R. A. Grupen. Manipulation gaits: Sequences of grasp control tasks. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), New Orleans, USA, 2004.
- L. Sentis and O. Khatib. Synthesis of whole-body behaviors through hierarchical control of behavioral primitives. International Journal of Humanoid Robots, 2(4):505-518, 2005.
- T. Siméon, J.-P. Laumonde, J. Cortés, and A. Sahbani. Manipulation planning with probabilistic roadmaps. International Journal of Robotics Research, 23(7-8):729-746, 2004.
- S. S. Srinivasan, M. A. Erdmann, and M. T. Mason. Control synthesis for dynamic contact manipulation. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), pages 2523-2528, 2005.
- A. Stoytchev. Behavior-grounded representation of tool affordances. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), pages 3071-3076, Barcelona, Spain, 2005.
- A. Sudsang and J. Ponce. In-hand manipulation: Geometry and algo- rithms. Algorithmica, 26(4):466-493, 2000.
- P. Tadepalli, R. Givan, and K. Driessens. Relational reinforcement learning: An overview. In Proceedings of the Workshop on Relational Reinfocement Learning at ICML '04, Banff, Canada, 2004.
- J. C. Trinkle and R. P. Paul. Planning for dexterous manipulation with sliding contacts. International Journal of Robotics Research, 9(3):24- 48, 1990.
- S. Vijayakumar, A. D'Souza, T. Shibata, J. Conradt, and S. Schaal. Statistical learning for humaonid robots. Autonomous Robots, 12(1):59- 72, 2002.
- C. J. C. H. Watkins and P. Dayan. Q-learning. Machine Learning, 8(3):279-292, 1992.
Cited by
Sorted by citations
Reinforcement learning in robotics: A survey
Kober, J., Bagnell, J. A., & Peters, J. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913495721 · Cited by 3,160 · see citing works
Meta-interpretive learning of higher-order dyadic datalog: predicate invention revisited
Muggleton, S. H., Lin, D., & Tamaddoni-Nezhad, A. (2015) · Machine Learning · doi:10.1007/s10994-014-5471-y · Cited by 184 · see citing works
Interactive segmentation, tracking, and kinematic modeling of unknown 3D articulated objects
Katz, D., Kazemi, M., Andrew Bagnell, J., & Stentz, A. (2013) · 2013 IEEE International Conference on Robotics and Automation · doi:10.1109/icra.2013.6631292 · Cited by 74 · see citing works
Self-citation
- Authors
- Katz, D., Pyuro, Y., & Brock, O.
- Affiliations
- University of Massachusetts Amherst (US)
- ORCID
- Brock, Oliver
- Venue
- Robotics: Science and Systems IV
- Published
- 2008-06-25
- OpenAlex
- W2294729144
- Cited by
- 70
- References
- 1
- Citations by year
- 2023: 2 · 2022: 3 · 2021: 3 · 2020: 3 · 2019: 4 · 2018: 5 · 2017: 5 · 2016: 4 · 2015: 6 · 2014: 9 · 2013: 9 · 2012: 7
- FWCI
- 2.48
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Robotics: Science and Systems (publishedVersion)
- Funders
- National Science Foundation (0545934, 0454074)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Engineering › Control and Systems Engineering › Robot Manipulation and Learning
- Physical Sciences › Computer Science › Artificial Intelligence › AI-based Problem Solving and Planning
- Keywords
- articulated object manipulation, unstructured environments, relational reinforcement learning, robot learning, partial state information, unseen object generalization
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
