Accounting for Directional Rigidity and Constraints in Control for Manipulation of Deformable Objects without Physical Simulation

Ruan, Mengyao; Conachie, Dale Mc; Berenson, Dmitry

doi:10.1109/iros.2018.8594520

Cited by 16 publications

(13 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where the control regulates the mismatch between current and goal state x g , possibly in a feature space (⋅). Because of real-time requirements, u is often derived using simple rules, such as a linear function between operating and feature points (95)(96)(97) or a numerical optimization process for an instantaneous step (98,99). Examples are proportional-integral-derivative controllers used for shape control of planar objects (78,96), meat cutting (100), and s` grasping (101).…”

Section: Control Strategies For Deformable Object Interactionmentioning

confidence: 99%

“…More physical plausibility is accounted by addressing an inverse simulation problem. This is demonstrated in simulated cloth manipulation (98). ( 99) adopts a linear FEM and quasi-static assumption for manipulating 3D deformable solids, using (22) to estimate the material parameters offline.…”

Section: Control Strategies For Deformable Object Interactionmentioning

confidence: 99%

“…In (118), spherical coordinates are used to characterize the hand motion with respect to a human head model, facilitating learning dualarm motion to put on a knit cap. (95,98,103). (Right) Estimating local linear relations based on perturbations and collected data.…”

Section: Imitation Learningmentioning

confidence: 99%

“…Massspring models are suitable for applications where objects are simple and real-time performance is critical. Integrated into simulators, these techniques have been used in synthesizing or learning manipulation skills (3,33,37,98).…”

Section: Modelingmentioning

confidence: 99%

“…Control actions are mainly derived from an approximated Jacobian relation (95,98) to visual features (42) and fast inverse simulation (99), yielding shape control and goal state regulation (97). Possible extensions include servoing upon other modalities, such as contact forces (102).…”

Section: Manipulationmentioning

confidence: 99%

See 4 more Smart Citations

Modeling, learning, perception, and control methods for deformable object manipulation

2021

View full text Add to dashboard Cite

Perceiving and handling deformable objects is an integral part of everyday life for humans. Automating tasks such as food handling, garment sorting, or assistive dressing requires open problems of modeling, perceiving, planning, and control to be solved. Recent advances in data-driven approaches, together with classical control and planning, can provide viable solutions to these open challenges. In addition, with the development of better simulation environments, we can generate and study scenarios that allow for benchmarking of various approaches and gain better understanding of what theoretical developments need to be made and how practical systems can be implemented and evaluated to provide flexible, scalable, and robust solutions. To this end, we survey more than 100 relevant studies in this area and use it as the basis to discuss open problems. We adopt a learning perspective to unify the discussion over analytical and data-driven approaches, addressing how to use and integrate model priors and task data in perceiving and manipulating a variety of deformable objects.

show abstract

Section: Control Strategies For Deformable Object Interactionmentioning

confidence: 99%

Section: Control Strategies For Deformable Object Interactionmentioning

confidence: 99%

Section: Imitation Learningmentioning

confidence: 99%

Section: Modelingmentioning

confidence: 99%

Section: Manipulationmentioning

confidence: 99%

See 3 more Smart Citations

Modeling, learning, perception, and control methods for deformable object manipulation

2021

View full text Add to dashboard Cite

show abstract

Collaborative Manipulation of Spherical-Shape Objects with a Deformable Sheet Held by a Mobile Robotic Team

Hunte

2021

IFAC-PapersOnLine

View full text Add to dashboard Cite

Tracking Partially-Occluded Deformable Objects while Enforcing Geometric Constraints

Wang

McConachie

Berenson

2021

2021 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

In order to manipulate a deformable object, such as rope or cloth, in unstructured environments, robots need a way to estimate its current shape. However, tracking the shape of a deformable object can be challenging because of the object's high flexibility, (self-)occlusion, and interaction with obstacles. Building a high-fidelity physics simulation to aid in tracking is difficult for novel environments. Instead we focus on tracking the object based on RGBD images and geometric motion estimates and obstacles. Our key contributions over previous work in this vein are: 1) A better way to handle severe occlusion by using a motion model to regularize the tracking estimate; and 2) The formulation of convex geometric constraints, which allow us to prevent self-intersection and penetration into known obstacles via a post-processing step. These contributions allow us to outperform previous methods by a large margin in terms of accuracy in scenarios with severe occlusion and obstacles.

show abstract

Accounting for Directional Rigidity and Constraints in Control for Manipulation of Deformable Objects without Physical Simulation

Cited by 16 publications

References 17 publications

Modeling, learning, perception, and control methods for deformable object manipulation

Modeling, learning, perception, and control methods for deformable object manipulation

Collaborative Manipulation of Spherical-Shape Objects with a Deformable Sheet Held by a Mobile Robotic Team

Tracking Partially-Occluded Deformable Objects while Enforcing Geometric Constraints

Contact Info

Product

Resources

About