Model-Driven Feedforward Prediction for Manipulation of Deformable Objects

@article{Li2018ModelDrivenFP,
  title={Model-Driven Feedforward Prediction for Manipulation of Deformable Objects},
  author={Yinxiao Li and Yan Wang and Yonghao Yue and Danfei Xu and Michael Case and Shih-Fu Chang and Eitan Grinspun and Peter K. Allen},
  journal={IEEE Transactions on Automation Science and Engineering},
  year={2018},
  volume={15},
  pages={1621-1638}
}
  • Yinxiao Li, Y. Wang, +5 authors P. Allen
  • Published 2018
  • Computer Science
  • IEEE Transactions on Automation Science and Engineering
Robotic manipulation of deformable objects is a difficult problem especially because of the complexity of the many different ways an object can deform. Searching such a high-dimensional state space makes it difficult to recognize, track, and manipulate deformable objects. In this paper, we introduce a predictive, model-driven approach to address this challenge, using a precomputed, simulated database of deformable object models. Mesh models of common deformable garments are simulated with the… Expand
Sequential Topological Representations for Predictive Models of Deformable Objects
TLDR
This work constructs compact topological representations to capture the state of highly deformable objects that are topologically nontrivial and develops an approach that tracks the evolution of this topological state through time, proving that the topology of the scene and its evolution can be recovered from point clouds representing the scene. Expand
A Framework for Manipulating Deformable Linear Objects by Coherent Point Drift
TLDR
A uniform framework that includes state estimation, task planning, and trajectory planning is proposed in this letter based on the concept of coherent point drift (CPD), and a real-time observer is proposed to estimate the states of deformable objects from the perceived point clouds. Expand
Category Classification of Deformable Object using Hybrid Dynamic Model for Robotic Grasping
This work studies the problem of classification of a hung garment in the unfolding procedure by a home service robot. The sheer number of unpredictable configurations that the deformable object canExpand
Category Classification of Deformable Object using Hybrid Dynamic Model for Robotic Grasping
TLDR
This paper proposes a hybrid dynamic model to recognize the pose of hung garment using a single manipulator and shows that the proposed method performs well and is applicable to different garments in robotic manipulation. Expand
Modeling of Deformable Objects for Robotic Manipulation: A Tutorial and Review
TLDR
This survey article starts by providing a tutorial on foundational aspects of models of shape and shape dynamics and uses this as the basis for a review of existing work on learning and estimation of these models and on motion planning and control to achieve desired deformations. Expand
Localization and Tracking of User-Defined Points on Deformable Objects for Robotic Manipulation
TLDR
An efficient procedure to localize user-defined points on the surface of deformable objects and track their positions in 3D space over time, capable of solving the localization problem online in a data-parallel manner, making it ideally suitable for the perception of non-rigid objects in industrial manufacturing processes. Expand
Survey on multi-robot manipulation of deformable objects
TLDR
A survey of relevant state-of-the-art approaches concerning manipulation of deformable objects by multiple robots is contributed, which includes a specific classification with different criteria and a subsequent analysis of the leading methods, the main challenges and the future research directions. Expand
Interactive Robotic Manipulation of Elastic Objects
TLDR
This paper model elastic objects using the Finite Element Method through a quasi-static assumption, which enables an interactive, simulation-based control methodology, wherein user-specified deformations for the elastic objects are automatically mapped to joint angle commands. Expand
Dynamic Manipulation of Deformable Objects With Implicit Integration
TLDR
This letter develops, validate and analyze model-based optimal control techniques for dynamic manipulation of deformable objects, and studies the application of both the batch Newton method and the stagewise Differential Dynamic Programming approach to this challenging problem domain. Expand
Deformable Linear Object Prediction Using Locally Linear Latent Dynamics
TLDR
It is empirically demonstrated that the proposed framework for deformable linear object prediction can predict the rope state accurately up to ten steps into the future and that the algorithm can find the optimal action given an initial state and a goal state. Expand
...
1
2
...

References

SHOWING 1-10 OF 61 REFERENCES
Real-time pose estimation of deformable objects using a volumetric approach
TLDR
This work reconstructs a 3D model of the object from a low-cost depth sensor such as Kinect, and then searches a database of simulated models in different poses to predict the pose, producing a high-quality mesh model and camera pose which is necessary for other tasks such as regrasping and object manipulation. Expand
Recognition of deformable object category and pose
TLDR
The framework presented here represents the recognition part of the entire pipeline of dexterous manipulation of deformable objects, which contains grasping, recognition, regrasping, placing flat, and folding, and yields a robust system that first classifies deformable Objects on category level and then estimates the current pose from a group of predefined poses of a single deformable object. Expand
A geometric approach to robotic laundry folding
TLDR
An algorithm is presented which, given a 2D cloth polygon and a desired sequence of folds, outputs a motion plan for executing the corresponding manipulations, deemed g-folds, on a minimal number of robot grippers. Expand
Folding deformable objects using predictive simulation and trajectory optimization
TLDR
This work presents a novel solution to find an optimal trajectory to move the robotic arm to fold a garment, and demonstrates that the two-arm robot can follow the optimized trajectories, achieving accurate and efficient manipulations of deformable objects. Expand
Pose and category recognition of highly deformable objects using deep learning
TLDR
This study investigates recognition and pose estimation of garments hanging from a single point, using a hierarchy of deep convolutional neural networks, which has been evaluated using both synthetic and real datasets of depth images and an actual robotic platform. Expand
Regrasping and unfolding of garments using predictive thin shell modeling
  • Yinxiao Li, Danfei Xu, +4 authors P. Allen
  • Engineering, Computer Science
  • 2015 IEEE International Conference on Robotics and Automation (ICRA)
  • 2015
TLDR
A novel method to teach a two-arm robot to efficiently track the states of a garment from an unknown state to a known state by iterative regrasping is proposed. Expand
Tracking deformable objects with point clouds
TLDR
The proposed tracking algorithm is based on a probabilistic generative model that incorporates observations of the point cloud and the physical properties of the tracked object and its environment, and a modified expectation maximization algorithm to perform maximum a posteriori estimation to update the state estimate at each time step is proposed. Expand
The Columbia grasp database
TLDR
This work shows how to automate the construction of a database consisting of several hands, thousands of objects, and hundreds of thousands of grasps, and demonstrates a novel grasp planning algorithm that exploits geometric similarity between a 3D model and the objects in the database to synthesize form closuregrasps. Expand
Polygonal Models for Clothing
TLDR
The fitted model provides reliable estimation of garment landmark points which can be utilized for an automated folding using a pair of robotic arms. Expand
A model-driven method of estimating the state of clothes for manipulating it
  • Y. Kita, N. Kita
  • Computer Science
  • Sixth IEEE Workshop on Applications of Computer Vision, 2002. (WACV 2002). Proceedings.
  • 2002
TLDR
A model-driven method of estimating the state of hanging clothes using discriminative features of the predicted appearances and the state whose appearance successfully approaches closest to the observed appearance is selected as the final decision. Expand
...
1
2
3
4
5
...