Cloth grasp point detection based on multiple-view geometric cues with application to robotic towel folding

By Jeremy B. Maitin-Shepard, Marco F. Cusumano-Towner, Jinna Lei, Pieter Abbeel. 2010

500 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Control and Systems Engineering, Human-Computer Interaction

How researchers see this paper

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

In Biomedical Engineering

In Control and Systems Engineering

In Human-Computer Interaction

Citations in the corpus

SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulation (2020, background): “However, programming a robot to perform these tasks has long been a challenge in robotics due to the high dimensional state representation and complex dynamics [1, 2, 3].”
Combining self-supervised learning and imitation for vision-based rope manipulation (2017, background): “Prior works have considered problems such as surgical suturing [8], [9], towel folding [7], knot tying and rope manipulation among many others.”
Learning to Control a Low-Cost Manipulator using Data-Efficient Reinforcement Learning (2011, background): “While existing techniques have the potential to solve various household manipulation tasks, they typically rely on extremely expensive robot hardware [12].”
Sim-to-Real Reinforcement Learning for Deformable Object Manipulation (2018, background): “The robot identiﬁes ideal grasping points based on heuristics (e.g. large curvature corresponds to a corner) and then executes a folding routine [11, 12, 13].”
Data-Driven Grasp Synthesis—A Survey (2013, methodology): “Bottom) Re-grasping a towel for unfolding [114].”
kPAM: KeyPoint Affordances for Category-Level Robotic Manipulation (2019, background): “making and towel folding. In contrast, we propose a novel categorylevel manipulation target speciﬁcation using costs and constraints deﬁned on 3D keypoints. Additionally the state-machine approach in [13,24] and manipulation primitives of [18,28] are speciﬁc to cloth and hence our manipulation task ”
Model for unfolding laundry using interactive perception (2011, background): “Folding, in particular, has received significant attention as of late [14] [15] [16].”
Modeling, learning, perception, and control methods for deformable object manipulation (2021, background): “Early works on folding detects corners for grasping (74).”
Deep Imitation Learning of Sequential Fabric Smoothing Policies (2019, background): “In particular, Maitin-Shepard et al. [25], Cusumano-Towner et al. [7], and Doumanoglou et al. [9] identiﬁed and tensioned corners to fold laundry or to bring clothing to desired positions.”
Parametrized shape models for clothing (2011, unknown): “Our earlier work [12] focused on perception algorithms for detection of the vertices of towels.”
Using depth and appearance features for informed robot grasping of highly wrinkled clothes (2012, methodology): “In [3] the authors designed a cloth grasping-point selection system to autonomously take elements from a pile of washed towels and fold and stack them using a Willow Garage PR2 robot.”
Robotic grasp detection using deep convolutional neural networks (2016, background): “[28] has very high precision of 92%, but it only works with cloth towels and cannot be used as a general purpose grasp detection technique.”
Dual arm manipulation - A survey (2012, methodology): “Finally, the active head of the PR2 robot and its vision system have been used for vision-based towel folding in [95].”
Learning spatial relationships between objects (2011, background): “An example of the usefulness of the relationships of parts of a domain in solving a problem can be seen in the robotic towel folding of Maitin-Shepard et al. (2010).”
Learning Rope Manipulation Policies Using Dense Object Descriptors Trained on Synthetic Depth Data (2020, background): “manipulation [18, 25, 27, 40], but these techniques can fail to generalize to novel configurations.”
Learning to Rearrange Deformable Cables, Fabrics, and Bags with Goal-Conditioned Transporter Networks (2020, background): “Subsequent work [43], [15], [16], generalized to a wider variety of initial configurations of new fabrics.”
Learning to place new objects in a scene (2012, background): “In the area of robotic manipulation, a wide range of problems have been studied so far, such as folding towels and clothes (Maitin-Shepard et al., 2010), opening doors (Jain and Kemp, 2010; Klingbeil et al.”
KETO: Learning Keypoint Representations for Tool Manipulation (2019, background): “In robotic manipulation tasks with visual inputs, keypoints can provide compact information of the environment and the objects [11], [17], [54], [49], [33], [37], [34].”