Active perception and modeling of deformable surfaces using Gaussian processes and position-based dynamics
2016 (English)In: IEEE-RAS International Conference on Humanoid Robots, IEEE, 2016, 530-537 p.Conference paper (Refereed)
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 force-based 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.
Place, publisher, year, edition, pages
IEEE, 2016. 530-537 p.
Active perception, Deformability modeling, Gaussian process, Position-based dynamics, Tactile exploration, Anthropomorphic robots, Deformation, Dynamics, Gaussian noise (electronic), Probability distributions, Robots, Active perceptions, Environmental observation, Gaussian process regression, Gaussian Processes, Multiple interactions, Physical interactions, Probabilistic framework, Gaussian distribution
Computer Vision and Robotics (Autonomous Systems)
IdentifiersURN: urn:nbn:se:kth:diva-202842DOI: 10.1109/HUMANOIDS.2016.7803326ScopusID: 2-s2.0-85010190205ISBN: 9781509047185 OAI: oai:DiVA.org:kth-202842DiVA: diva2:1082624
16th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2016, 15 November 2016 through 17 November 2016
QC 201703172017-03-172017-03-172017-03-17Bibliographically approved