Learning to segment and unfold polyhedral mesh from failures

Xi, Zhonghua; Kim, Yun-hyeong; Kim, Young Jin; Lien, Jyh-Ming

doi:10.1016/j.cag.2016.05.022

Cited by 20 publications

(11 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other methods, such as flat-tree unfolding ( fig. S3B) (16) and genetic algorithm (GA) methods (22,24), are also available to unfold nonconvex polyhedra ( fig. S3C).…”

Section: Resultsmentioning

confidence: 99%

“…S3C). As it is critically important that a conformal device is composed of one or as few pieces as possible, our recently developed GA method can evolve the unfoldings by mutating the edge weights until a net with zero overlaps is found (22). This evolution is controlled by a fitness function f : N → ℝ that evaluates an unfolding.…”

Section: Resultsmentioning

confidence: 99%

“…The computer science community has recently exerted great efforts to algorithmically determine surface cuts that segment a nondevelopable surface into developable surface patches called polyhedral nets (or simply nets) (16)(17)(18). Beyond designing valid nets, recent computational methods, including those developed by the authors (19)(20)(21)(22), have focused on optimizing net quality and foldability using machine learning techniques that drastically reduce the time and effort needed relative to traditional trial-and-error approaches.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Computational wrapping: A universal method to wrap 3D-curved surfaces with nonstretchable materials for conformal devices

Lee

et al. 2020

Sci. Adv.

Self Cite

View full text Add to dashboard Cite

This study starts from the counterintuitive question of how we can render conventional stiff, nonstretchable, and even brittle materials sufficiently conformable to fully wrap curved surfaces, such as spheres, without failure. Here, we extend the geometrical design method of computational origami to wrapping. Our computational wrapping approach provides a robust and reliable method for fabricating conformal devices for arbitrary curved surfaces with a computationally designed nonpolyhedral developable net. This computer-aided design transforms two-dimensional (2D)–based materials, such as Si wafers and steel sheets, into various targeted conformal structures that can fully wrap desired 3D structures without fracture or severe plastic deformation. We further demonstrate that our computational wrapping approach enables a design platform that can transform conventional nonstretchable 2D-based devices, such as electroluminescent lighting and flexible batteries, into conformal 3D curved devices.

show abstract

“…Other methods, such as flat-tree unfolding ( fig. S3B) (16) and genetic algorithm (GA) methods (22,24), are also available to unfold nonconvex polyhedra ( fig. S3C).…”

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Computational wrapping: A universal method to wrap 3D-curved surfaces with nonstretchable materials for conformal devices

Lee

et al. 2020

Sci. Adv.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Given a mesh M , we first inflate the mesh to reduce surface concavity (Section 5), then remove structural concavity by decomposing the mesh into several part-aware, nearly convex components (Section 6). For each component we find a net using a genetic-based algorithm (GA) [21], the initial population are generated using heuristic methods. Once we obtained the net, motion planning (Section 7) is introduced to find a feasible path that folds the net back to its 3D shape continuously to ensure we can build a physical copy even use rigid materials instead of flexible materials, such as paper which could be easily bent during folding.…”

Section: Methods Overviewmentioning

confidence: 99%

Polyhedra Fabrication Through Mesh Convexification: A Study of Foldability of Nearly Convex Shapes

Lien

2017

Volume 5B: 41st Mechanisms and Robotics Conference

Self Cite

View full text Add to dashboard Cite

A polyhedron can be unfolded to a net, i.e., an unfolding without overlapping, by carefully cutting along the surface. If the cuts are restricted only on the edges of the polyhedron, where should the cuts be? This is called an edge-unfolding problem, which has been extensively studied in the literature for centuries. Although several promising properties have been discovered, several recent preliminary works show that no valid net exists even for certain simple non-convex polyhedra. Therefore, we propose to convexify the input polyhedron before unfolding. More specifically, we remove local concave surface features via inflation simulation. We then eliminate global concave structure features by segmenting the polyhedron to a small number of part-aware and nearly convex components. Then the net for each nearly convex component can be obtained. We further show that convexified shapes can be continuously folded and can be easily realized by a physical self-folding machine Our experimental results show that the proposed convexification approaches can reduce the computation time by several folds.

show abstract

“…Heuristic methods [1,15] have been developed to unfold convex polyhedra. Finding nets of non-convex shapes is significantly more challenging and segmentation is often needed to avoid overlapping [15,16,17]. For (self-)foldable structures, collision-free folding motion that brings it back to the 3D shape is essential but non-trivial.…”

Section: Foldable Structure Optimizationmentioning

confidence: 99%

Planning Folding Motion with Simulation in the Loop Using Laser Forming Origami and Thermal Behaviors as an Example

Yue¹,

Guan²,

Hernandez³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Designing a robot or structure that can fold itself into a target shape is a process that involves challenges originated from multiple sources. For example, the designer of rigid self-folding robots must consider foldability from geometric and kinematic aspects to avoid self-intersection and undesired deformations. Recent works have shown success in estimating foldability of a design using robot motion planners. However, many foldable structures are actuated using physically coupled reactions (i.e., folding originated from thermal, chemical, or electromagnetic loads). Therefore, a reliable foldability analysis must consider additional constraints that resulted from these critical phenomena. This work investigates the idea of efficiently incorporating computationally expensive physics simulation within the folding motion planner to provide a better estimation of the foldability. In this paper, we will use laser forming origami as an example to demonstrate the benefits of considering the properties beyond geometry. We show that the design produced by the proposed method can be folded more efficiently.

show abstract

Learning to segment and unfold polyhedral mesh from failures

Cited by 20 publications

References 17 publications

Computational wrapping: A universal method to wrap 3D-curved surfaces with nonstretchable materials for conformal devices

Computational wrapping: A universal method to wrap 3D-curved surfaces with nonstretchable materials for conformal devices

Polyhedra Fabrication Through Mesh Convexification: A Study of Foldability of Nearly Convex Shapes

Planning Folding Motion with Simulation in the Loop Using Laser Forming Origami and Thermal Behaviors as an Example

Contact Info

Product

Resources

About