Abstract
The realistic representation of deformations is still an active area of research, especially for deformable objects whose behavior cannot be simply described in terms of elasticity parameters. This paper proposes a data-driven neural-network-based approach for capturing implicitly and predicting the deformations of an object subject to external forces. Visual data, in the form of 3D point clouds gathered by a Kinect sensor, is collected over an object while forces are exerted by means of the probing tip of a force-torque sensor. A novel approach based on neural gas fitting is proposed to describe the particularities of a deformation over the selectively simplified 3D surface of the object, without requiring knowledge of the object material. An alignment procedure, a distance-based clustering, and inspiration from stratified sampling support this process. The resulting representation is denser in the region of the deformation (an average of 96.6% perceptual similarity with the collected data in the deformed area), while still preserving the object’s overall shape (86% similarity over the entire surface) and only using on average of 40% of the number of vertices in the mesh. A series of feedforward neural networks is then trained to predict the mapping between the force parameters characterizing the interaction with the object and the change in the object shape, as captured by the fitted neural gas nodes. This series of networks allows for the prediction of the deformation of an object when subject to unknown interactions.
Highlights
The acquisition and realistic simulation of deformations, especially for soft objects whose behavior cannot be described in terms of elasticity parameters, is still an active area of research
The objective of this work is to propose an original solution to the modeling and prediction of the deformation of soft objects that does not make assumptions about the material of the object and that capitalizes on computational intelligence solutions, namely on combining neural gas fitting with feedforward neural network prediction
A solution to deal with this problem is to use the adapted data simplification algorithm that we presented in Section 3.2.3, but to constrain the number of triangles in the mesh to be equal to the average number of faces in the reference mesh model, Ms, representing the various deformation instances of an object
Summary
The acquisition and realistic simulation of deformations, especially for soft objects whose behavior cannot be described in terms of elasticity parameters, is still an active area of research. Realistic and plausible deformable object models require experimental measurements acquired through physical interaction with the object in order to capture its complex behavior when subject to various forces. The measurement of the behavior of an object can be carried out based on the results of instrumented indentation tests. Such tests usually involve the monitoring of the evolution of the force (e.g., its magnitude, direction, and location) using a force-feedback sensor. The active indentation probing is usually accompanied by a visual capture of the deformed object to collect geometry data characterizing the local surface deformation.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
