Grasping objects localized from uncertain point cloud data
8
TL;DR: This work presents a grasp planning method that explicitly considers the uncertainties on the visually-estimated object pose, and shows that, for grasping, some ambiguities are less unfavorable so the distribution can be used to select robust grasps.
read more
About: This article is published in Robotics and Autonomous Systems. The article was published on 01 Dec 2014. and is currently open access. The article focuses on the topics: 3D pose estimation & Pose.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Dexterous grasping under shape uncertainty
TL;DR: An approach for addressing the performance of dexterous grasping under shape uncertainty is presented, the uncertainty in object shape is parametrized and incorporated as a constraint into grasp planning and the grasp planning approach is hand interchangeable.
135
Robust grasping under object pose uncertainty
Kaijen Hsiao,Leslie Pack Kaelbling,Tomás Lozano-Pérez +2 more
- 01 Jul 2011
TL;DR: Hsiao et al. as discussed by the authors presented a decision-theoretic approach to problems that require accurate placement of a robot relative to an object of known shape, such as grasping for assembly or tool use.
61
•Proceedings Article
Merging Local and Global 3D Perception using Contact Sensing.
Rebecca Cox,Nikolaus Correll +1 more
- 01 Jan 2017
TL;DR: This paper's ongoing work towards fusing RGB-D images with data from contact and proximity sensors embedded in a robotic hand for improved object perception, recognition and manipulation is presented.
8
Merging Local and Global 3d Perception for Robotic Grasping and Manipulation
Rebecca E. Cox
- 01 Jan 2017
TL;DR: This paper uses contact information based on a novel contact sensor and additional pose information provided by the arm's pose to combine global pose information from RGB-D sensing with local proximity sensing during approach.
2
An Approach for Object Picking using Correlation analysis and Robotic Manipulation
S. Pradeep,Asha Rani,Vijander Singh,Shivangi Agarwal +3 more
- 17 Dec 2015
TL;DR: The proposed algorithm is simple, requires less memory space, does not require any filter, reduces the instruction set and has high accuracy.
1
References
A method for registration of 3-D shapes
Paul J. Besl,H.D. McKay +1 more
TL;DR: In this paper, the authors describe a general-purpose representation-independent method for the accurate and computationally efficient registration of 3D shapes including free-form curves and surfaces, based on the iterative closest point (ICP) algorithm, which requires only a procedure to find the closest point on a geometric entity to a given point.
20.6K
SURF: speeded up robust features
Herbert Bay,Tinne Tuytelaars,Luc Van Gool +2 more
- 07 May 2006
TL;DR: A novel scale- and rotation-invariant interest point detector and descriptor, coined SURF (Speeded Up Robust Features), which approximates or even outperforms previously proposed schemes with respect to repeatability, distinctiveness, and robustness, yet can be computed and compared much faster.
"GrabCut": interactive foreground extraction using iterated graph cuts
Carsten Rother,Vladimir Kolmogorov,Andrew Blake +2 more
- 01 Aug 2004
TL;DR: A more powerful, iterative version of the optimisation of the graph-cut approach is developed and the power of the iterative algorithm is used to simplify substantially the user interaction needed for a given quality of result.
3D is here: Point Cloud Library (PCL)
Radu Bogdan Rusu,Steve Cousins +1 more
- 09 May 2011
TL;DR: PCL (Point Cloud Library) is presented, an advanced and extensive approach to the subject of 3D perception that contains state-of-the art algorithms for: filtering, feature estimation, surface reconstruction, registration, model fitting and segmentation.
Robotic Grasping of Novel Objects using Vision
TL;DR: This work considers the problem of grasping novel objects, specifically objects that are being seen for the first time through vision, and presents a learning algorithm that neither requires nor tries to build a 3-d model of the object.