Shape Control of Elastic Objects Based on Implicit Sensorimotor Models and Data-Driven Geometric Features

Wanyu Ma, Jihong Zhu, David Navarro-Alarcon

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review


This paper proposes a general approach to design automatic
controls to manipulate elastic objects into desired shapes. The object’s
geometric model is defined as the shape feature based on the specific
task to globally describe the deformation. Raw visual feedback data is
processed using classic regression methods to identify parameters of data-driven geometric models in real-time. Our proposed method is able to
analytically compute a pose-shape Jacobian matrix based on implicit
functions. This model is then used to derive a shape servoing controller.
To validate the proposed method, we report a detailed experimental
study with robotic manipulators deforming an elastic rod.
Original languageEnglish
Title of host publication16th Int. Conf. on Intelligent Autonomous System (IAS-16)
Pageslink & page no. is not available yet
Publication statusPublished - Jun 2021
EventIAS-16 - , Singapore
Duration: 22 Jun 202125 Jun 2021



Cite this