Unifying scene registration and trajectory optimization for learning from demonstrations with application to manipulation of deformable objects
Open accessAbstract
Recent work [1], [2] has shown promising results in enabling robotic manipulation of deformable objects through learning from demonstrations. Their method computes a registration from training scene to test scene, and then applies an extrapolation of this registration to the training scene gripper motion to obtain the gripper motion for the test scene. The warping cost of scene-to-scene registrations is used to determine the nearest neighbor from a set of training demonstrations. Then once the gripper motion has been generalized to the test situation, they apply trajectory optimization [3] to plan for the robot motions that will track the predicted gripper motions. In many situations, however, the predicted gripper motions cannot be followed perfectly due to, for example, joint limits or obstacles. In this case the past work finds a path that minimizes deviation from the predicted gripper trajectory as measured by its Euclidean distance for position and angular distance for orientation. Measuring the error this way during the motion planning phase, however, ignores the underlying structure of the problem-namely the idea that rigid registrations are preferred to generalize from training scene to test scene. Deviating from the gripper trajectory predicted by the extrapolated registration effectively changes the warp induced by the registration in the part of the space where the gripper trajectories are. The main contribution of this paper is an algorithm that considers this effective final warp as the criterion to optimize for in a unified optimization that simultaneously considers the scene-to-scene warping and the robot trajectory (which were separated into two sequential steps by the past work). This results in an approach that adjusts to infeasibility in a way that adapts directly to the geometry of the scene and minimizes the introduction of additional warping cost. In addition, this paper proposes to learn the motion of the gripper pads, whereas past work considered the motion of a coordinate frame attached to the gripper as a whole. This enables learning more precise grasping motions. Our experiments, which consider the task of knot tying, show that both unified optimization and explicit consideration of gripper pad motion result in improved performance.
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?
Most knot tying systems act either on the table or in the air.
“Most KT systems act either on the table [243,244,275,282,286,287] or in the air [52,91,105,239,284,285] as shown in Figure 6.”
From Data-Driven Robotic Manipulation of Cloth-like Deformable Objects: The Present, Challenges and Future Prospects (2023) · cites this paper as [243]
The Introduction (p. 4402) identifies this paper as a robotic overhand-knot-tying study, so it supports citing it as an example of a knot-tying system. The passages in our copy do not establish whether this system acts on a table or in the air, or support the claim that most systems fall into those categories. (LLM, conf=0.76)
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
Spline Models for Observational Data.
Müller, H., & Wahba, G. (1991) · Journal of the American Statistical Association · doi:10.2307/2290434 · Cited by 4,992 · see citing works
Spline Models for Observational Data
Wahba, G. (1990) · doi:10.1137/1.9781611970128 · Cited by 4,184 · see citing works
A survey of robot learning from demonstration
Argall, B. D., Chernova, S., Veloso, M., & Browning, B. (2009) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2008.10.024 · Cited by 3,227 · see citing works
A new point matching algorithm for non-rigid registration
Chui, H., & Rangarajan, A. (2003) · Computer Vision and Image Understanding · doi:10.1016/s1077-3142(03)00009-2 · Cited by 1,560 · see citing works
Splines minimizing rotation-invariant semi-norms in Sobolev spaces
Duchon, J. (1977) · Lecture notes in mathematics · doi:10.1007/bfb0086566 · Cited by 1,397 · see citing works
Is imitation learning the route to humanoid robots?
Schaal, S. (1999) · Trends in Cognitive Sciences · doi:10.1016/s1364-6613(99)01327-3 · Cited by 1,325 · see citing works
On Learning, Representing, and Generalizing a Task in a Humanoid Robot
Calinon, S., Guenter, F., & Billard, A. (2007) · IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics) · doi:10.1109/tsmcb.2006.886952 · Cited by 1,090 · see citing works
Finding Locally Optimal, Collision-Free Trajectories with Sequential Convex Optimization
Schulman, J., Ho, J., Lee, A., Awwal, I., Bradlow, H., & Abbeel, P. (2013) · Robotics: Science and Systems · doi:10.15607/rss.2013.ix.031 · Cited by 442 · see citing works
Self-citationPath planning for deformable linear objects
Moll, M., & Kavraki, L. E. (2006) · IEEE Transactions on Robotics · doi:10.1109/tro.2006.878933 · Cited by 205 · see citing works
Planning Paths for Elastic Objects under Manipulation Constraints
Lamiraux, F., & Kavraki, L. E. (2001) · The International Journal of Robotics Research · doi:10.1177/02783640122067354 · Cited by 161 · see citing works
Learning from Demonstrations Through the Use of Non-rigid Registration
Schulman, J., Ho, J., Lee, C., & Abbeel, P. (2016) · Springer Tracts in Advanced Robotics · doi:10.1007/978-3-319-28872-7_20 · Cited by 133 · cited 8× · see citing works
“’s approach to learning from demonstrations [1] calculates the new trajectory by first using a modified thin plate spline robust point matching (TPS-RPM) algorithm [19] to calculate a non-rigid scene registration that maps points from the demonstration scene to the new scene.”
BackgroundMethodResultInfluentialSelf-citationKnotting/unknotting manipulation of deformable linear objects
Wakamatsu, H., Arai, E., & Hirai, S. (2006) · The International Journal of Robotics Research · doi:10.1177/0278364906064819 · Cited by 132 · see citing works
Motion Planning for Robotic Manipulation of Deformable Linear Objects
Saha, M., Isto, P., & Latombe, J. (2008) · Springer eBooks · doi:10.1007/978-3-540-77457-0_3 · Cited by 101 · see citing works
Schulman, J., Gupta, A., Venkatesan, S., Tayson-Frederick, M., & Abbeel, P. (2013) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2013.6696945 · Cited by 84 · see citing works
Self-citationMotion planning for robotic manipulation of deformable linear objects
Saha, M., & Isto, P. (2006) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2006.1642074 · Cited by 81 · see citing works
Representation for knot-tying tasks
Takamatsu, J., Morita, T., Ogawara, K., Kimura, H., & Ikeuchi, K. (2006) · IEEE Transactions on Robotics · doi:10.1109/tro.2005.855988 · Cited by 79 · see citing works
Calinon, S., D'halluin, F., Caldwell, D. G., & Billard, A. G. (2009) · 2009 9th IEEE-RAS International Conference on Humanoid Robots · doi:10.1109/ichr.2009.5379592 · Cited by 73 · see citing works
(2003) · doi:10.1109/robot.2003.1242193 · Cited by 73 · see citing works
Intelligent Learning for Deformable Object Manipulation
Howard, A., & Bekey, G. A. (2000) · Autonomous Robots · doi:10.1023/a:1008924218273 · Cited by 51 · see citing works
Bell, M. (2010) · doi:10.1349/ddlp.367 · Cited by 35 · see citing works
Robust Manipulation of Deformable Objects Using Model Based Technique
Wada, T., Hirai, S., Mori, H., et al. (2000) · Lecture notes in computer science · doi:10.1007/10722604_1 · Cited by 13 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Kadi, H. A., & Terzić, K. (2023) · Sensors · doi:10.3390/s23052389 · Cited by 19 · see citing works
“Most KT systems act either on the table [243,244,275,282,286,287] or in the air [52,91,105,239,284,285] as shown in Figure 6.”
BackgroundMethodInfluentialLee, A. X., Goldstein, M. A., Barratt, S. T., & Abbeel, P. (2015) · 2015 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2015.7139289 · Cited by 12 · see citing works
Self-citation
- Authors
- Lee, A. X., Huang, S. H., Hadfield-Menell, D., Tzeng, E., & Abbeel, P.
- Affiliations
- University of California, Berkeley (US)
- Venue
- 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems
- Publisher
- IEEE
- Published
- 2014-09
- Pages
- 4402-4407
- ISSN
- 2153-0858 (ISSN-L)
- OpenAlex
- W2091344462
- Cited by
- 32
- References
- 21
- Citations by year
- 2024: 1 · 2023: 5 · 2022: 1 · 2021: 7 · 2020: 3 · 2019: 1 · 2018: 7 · 2017: 1 · 2016: 3 · 2015: 3
- FWCI
- 3.23
- Type
- conference paper
- Language
- en
- Open access
- green
- zenodo.org
- Licence
- public-domain
- Locations
- IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (publishedVersion)
- Zenodo (CERN European Organization for Nuclear Research) (submittedVersion, public-domain)
- Topics
- Physical Sciences › Engineering › Control and Systems Engineering › Robot Manipulation and Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Engineering › Biomedical Engineering › Soft Robotics and Applications
- Keywords
- imitation learning, deformable object manipulation, trajectory optimization, motion planning, knot tying, robotic grasping
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
