Active exploration using Gaussian Random Fields and Gaussian Process Implicit Surfaces

Caccamo, Sergio; Bekiroglu, Yasemin; Ek, Carl Henrik; Kragić, Danica

doi:10.1109/iros.2016.7759112

Cited by 25 publications

(14 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Spatial location x i is usually associated with a target value y i which is indicative of whether the point is in the interior (y i < 0), on (y i = 0) or in the exterior (y i > 0) of the surface in question. A commonly used model in these approaches [31][32][33][34]45] is a gaussian process implicit surface (GPIS). It would seem an appropriate choice of a surface model since it readily incorporates the uncertainty involved in measurements.…”

Section: Theoretical Comparison and Challenges Across Touch Based Scanning Methodsmentioning

confidence: 99%

“…The model used is a 3D polygonal mesh, which is refined/morphed explicitly (as opposed to an implicit parameter that encodes the surface information) using differential equations. This is in contrast to the retraining step that is the state of the art currently [45]. By designing the differential equations with a visco-elastic form, we ensure the refinement is intuitive and the mesh deforms in a clay-like manner to actual forces exerted by the human operator on the real object using the haptic stylus.…”

Section: Theoretical Comparison and Challenges Across Touch Based Scanning Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Haptic Manipulation of 3D Scans for Geometric Feature Enhancement

Turlapati

Accoto

Campolo

2021

Sensors

View full text Add to dashboard Cite

Localisation of geometric features like holes, edges, slots, etc. is vital to robotic planning in industrial automation settings. Low-cost 3D scanners are crucial in terms of improving accessibility, but pose a practical challenge to feature localisation because of poorer resolution and consequently affect robotic planning. In this work, we address the possibility of enhancing the quality of a 3D scan by a manual ’touch-up’ of task-relevant features, to ensure their automatic detection prior to automation. We propose a framework whereby the operator (i) has access to both the actual work-piece and its 3D scan; (ii) evaluates the missing salient features from the scan; (iii) uses a haptic stylus to physically interact with the actual work-piece, around such specific features; (iv) interactively updates the scan using the position and force information from the haptic stylus. The contribution of this work is the use of haptic mismatch for geometric update. Specifically, the geometry from the 3D scan is used to predict haptic feedback at a point on the work-piece surface. The haptic mismatch is derived as a measure of error between this prediction and the real interaction forces from physical contact at that point on the work-piece. The geometric update is driven until the haptic mismatch is minimised. Convergence of the proposed algorithm is first numerically verified on an analytical surface with simulated physical interaction. Error analysis of the surface position and orientations were also plotted. Experiments were conducted using a motion capture system providing sub-mm accuracy in position and a 6 axis F/T sensor. Missing features are successfully detected after the update of the scan using the proposed method in an experiment.

show abstract

Section: Theoretical Comparison and Challenges Across Touch Based Scanning Methodsmentioning

confidence: 99%

Section: Theoretical Comparison and Challenges Across Touch Based Scanning Methodsmentioning

confidence: 99%

Haptic Manipulation of 3D Scans for Geometric Feature Enhancement

Turlapati

Accoto

Campolo

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Also, they are able to calculate more visually plausible deformations than MS models. Hence, they have been used in a wide range of interactive graphical applications (Tian et al, 2013;Macklin et al, 2014), particularly for modeling the deformation of human body parts (Zhu et al, 2008;Sidorov and Marshall, 2014;Romeo et al, 2020), and robotic manipulation tasks (Caccamo et al, 2016;Guler et al, 2017). A disadvantage of PBD methods is that they simulate physical deformation less accurately than constitutive models, since they are geometrically motivated.…”

Section: Position-based Dynamicsmentioning

confidence: 99%

Modeling of Deformable Objects for Robotic Manipulation: A Tutorial and Review

et al. 2020

Self Cite

View full text Add to dashboard Cite

Manipulation of deformable objects has given rise to an important set of open problems in the field of robotics. Application areas include robotic surgery, household robotics, manufacturing, logistics, and agriculture, to name a few. Related research problems span modeling and estimation of an object's shape, estimation of an object's material properties, such as elasticity and plasticity, object tracking and state estimation during manipulation, and manipulation planning and control. In this survey article, we start by providing a tutorial on foundational aspects of models of shape and shape dynamics. We then use 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. We also discuss potential future lines of work.

show abstract

“…Environmental observation can condition a GPR so that its posterior mean define the terrain property [9] of interest. Authors in [10], [8] show how to exploit the mean and variance of the joint distribution of a Gaussian Process for enhancing active perception algorithms in modeling geometric properties of objects.…”

Section: Related Workmentioning

confidence: 99%

Active perception and modeling of deformable surfaces using Gaussian processes and position-based dynamics

Caccamo

Güler

Kragić

2016

2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids)

Self Cite

View full text Add to dashboard Cite

Exploring and modeling heterogeneous elastic surfaces requires multiple interactions with the environment and a complex selection of physical material parameters. The most common approaches model deformable properties from sets of offline observations using computationally expensive forcebased simulators. In this work we present an online probabilistic framework for autonomous estimation of a deformability distribution map of heterogeneous elastic surfaces from few physical interactions. The method takes advantage of Gaussian Processes for constructing a model of the environment geometry surrounding a robot. A fast Position-based Dynamics simulator uses focused environmental observations in order to model the elastic behavior of portions of the environment. Gaussian Process Regression maps the local deformability on the whole environment in order to generate a deformability distribution map. We show experimental results using a PrimeSense camera, a Kinova Jaco2 robotic arm and an Optoforce sensor on different deformable surfaces.

show abstract

Active exploration using Gaussian Random Fields and Gaussian Process Implicit Surfaces

Cited by 25 publications

References 28 publications

Haptic Manipulation of 3D Scans for Geometric Feature Enhancement

Haptic Manipulation of 3D Scans for Geometric Feature Enhancement

Modeling of Deformable Objects for Robotic Manipulation: A Tutorial and Review

Active perception and modeling of deformable surfaces using Gaussian processes and position-based dynamics

Contact Info

Product

Resources

About