Data-driven grasping with partial sensor data

By Corey Goldfeder, Matei T. Ciocarlie, Jaime Peretzman, Hao Nguyen Dang, Peter K. Allen. 2009

100 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Control and Systems Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

Citations in the corpus

Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection (2016, methodology): “These methods typically need to understand the geometry of the scene, using depth or stereo sensors and matching of previously scanned models to observations (Goldfeder et al., 2009b).”
Robustness via Retrying: Closed-Loop Robotic Manipulation with Self-Supervised Learning (2018, background): “While object relocation with both non-prehensile [38, 39] and prehensile [40] manipulation strategies has been explored extensively in prior work, much of this research has focused on hand-designed models and feature representations, which require extensive engineering and make strong assumptions ab”
A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithms (2019, background): “To obtain valid grasp frames, the robot can learn a classifier to determine if sampled grasp frames will lead to successful grasps [324, 276, 154, 300], or sample from a learned probability density over successful grasps or cached grasps from similar objects [86, 41, 125].”
3DNet: Large-scale object class recognition from CAD models (2012, methodology): “Local descriptors with Bag-of-Words approaches as used in [5], [13] and [8] require an extra step of learning the visual-words which is not yet available in the framework.”
Completing 3D object shape from one depth image (2015, methodology): “[11] to retrieve models in order to transfer grasp points.”
Supervised learning of hidden and non-hidden 0-order affordances and detection in real scenes (2012, methodology): “We refer the reader to [4] for a detailed explanation on how we compute the stable planes of a 3D mesh.”
CAD-model recognition and 6DOF pose estimation using 3D cues (2011, methodology): “Most descriptors based on views of an object like VFH, CVFH, CAP-SIFT [3] are unable to deliver a complete 6- DOF pose.”