Multi-sensor surface analysis for robotic ironing

Li, Yinxiao; Hu, Xiuhan; Xu, Danfei; Yue, Yonghao; Grinspun, Eitan; Allen, Peter K.

doi:10.1109/icra.2016.7487788

Cited by 35 publications

(29 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Robotic manipulation of general deformable objects relies on a combination of different sensor measurements. The RGB images or RGB-Depth data are widely used for deformable object manipulation [1], [4], [9]. Fiducial markers can also be printed on the deformable object to improve the manipulation performance [16].…”

Section: B Deformable Object Manipulationmentioning

confidence: 99%

“…The problem of manipulating highly deformable materials such as clothes and fabrics frequently arises in different applications. These include laundry folding [1], robot-assisted dressing or household chores [2], [3], ironing [4], coat checking [5], sewing [6], and transporting large materials like cloth, leather, and composite materials [7]. Robot manipulation has been extensively studied for decades and there is extensive work on the manipulation of rigid and deformable objects.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Manipulating Highly Deformable Materials Using a Visual Feedback Dictionary

Jia

Pan

et al. 2018

2018 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

The complex physical properties of highly deformable materials such as clothes pose significant challenges fanipulation systems. We present a novel visual feedback dictionary-based method for manipulating defoor autonomous robotic mrmable objects towards a desired configuration. Our approach is based on visual servoing and we use an efficient technique to extract key features from the RGB sensor stream in the form of a histogram of deformable model features. These histogram features serve as high-level representations of the state of the deformable material. Next, we collect manipulation data and use a visual feedback dictionary that maps the velocity in the high-dimensional feature space to the velocity of the robotic end-effectors for manipulation. We have evaluated our approach on a set of complex manipulation tasks and humanrobot manipulation tasks on different cloth pieces with varying material characteristics.

show abstract

Section: B Deformable Object Manipulationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Manipulating Highly Deformable Materials Using a Visual Feedback Dictionary

Jia

Pan

et al. 2018

2018 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

show abstract

“…where Ω max is the upper threshold of the weight. In Equation 9, we do not update the color component via integration as in Equation 8. The main reason here is that our current work does not model and track the light environment and material albedo.…”

Section: Our Systemmentioning

confidence: 99%

“…Autonomous manipulation of deformable objects is an important and challenging topic in robotics, and recently it attracts much interest due to its potential applications in robot-assisted surgery [1]- [4] and service robots, including garments folding [5]- [7], ironing [8], and robot-assisted dressing [9]. Despite the difference in their technical details employed for specific tasks, most existing systems for deformable object manipulation can be described using the same shape control framework as shown in the top row of Figure 1.…”

Section: Introductionmentioning

confidence: 99%

Robust shape estimation for 3D deformable object manipulation

Han

Zhao

Sun

et al. 2018

Communications in Information and Systems

View full text Add to dashboard Cite

Existing shape estimation methods for deformable object manipulation suffer from the drawbacks of being off-line, model dependent, noise-sensitive or occlusion-sensitive, and thus are not appropriate for manipulation tasks requiring high precision.In this paper, we present a real-time shape estimation approach for autonomous robotic manipulation of 3D deformable objects. Our method fulfills all the requirements necessary for the high-quality deformable object manipulation in terms of being realtime, model-free and robust to noise and occlusion. These advantages are accomplished using a joint tracking and reconstruction framework, in which we track the object deformation by aligning a reference shape model with the stream input from the RGB-D camera, and simultaneously upgrade the reference shape model according to the newly captured RGB-D data. We have evaluated the quality and robustness of our real-time shape estimation pipeline on a set of deformable manipulation tasks implemented on physical robots. Videos are available at https://lifeisfantastic.github.io/DeformShapeEst/ arXiv:1809.09802v1 [cs.RO]

show abstract

“…Now, we briefly introduce a series of our work on developing smarter robots with the physics in consideration. We have focused on robotic folding of garments [29,30,31]. Figure 5.…”

Section: Physics For Smart Robotsmentioning

confidence: 99%

Bringing Computer and Physics Closer

Yue

2018

J. Phys.: Conf. Ser.

Self Cite

View full text Add to dashboard Cite

Abstract. Physically based simulations are important for predicting the future states of the objects in consideration, and have been one of the major research topics in computer graphics. Applications include optical simulations for realistic image synthesis given a 3D scene, and rigid/fluid dynamics for computer animations. The need for the ultimate realism may sometimes ask for more efficient and accurate methods than those available in other fields. In addition, physically based optimizations are useful for designing and fabricating man-made objects given some desirable functionalities governed by physical laws. The ability to incorporate predictive simulations also allows us to build smarter robots that can optimize for their next movement based on the predictions. We introduce some of our work performed from this perspective. IntroductionOur world is governed by physical laws: the way how light travels from the light source to our eye can be described by the radiative transport equation; the way how the water in a cup behaves as we interact with the cup is described by the Navier-Stokes equations. The ability of predicting such physical behaviors would allow us to estimate how objects would deform and how they would look like, and is hence useful for computer animations.Physical laws also come into play when we want to design and fabricate man-made objects. For example, understanding how the light refracts is essential for designing lenses, and understanding how the contact and frictional forces act against the gravity is important for designing a stable sculpture that is assembled from a number of small bricks. Optimizations with physically based constraints in consideration are thus fundamental for designing and fabricating functional man-made objects.With the ability to incorporate predictive simulations in planning, we can also build smarter robots that use vision techniques to acquire the external information, perform predictive simulations to estimate the future states of the objects, and determine the appropriate control based on the predicted states. In this paper, we will review and introduce a series of our past work done from the above perspective.

show abstract

Multi-sensor surface analysis for robotic ironing

Cited by 35 publications

References 22 publications

Manipulating Highly Deformable Materials Using a Visual Feedback Dictionary

Manipulating Highly Deformable Materials Using a Visual Feedback Dictionary

Robust shape estimation for 3D deformable object manipulation

Bringing Computer and Physics Closer

Contact Info

Product

Resources

About