Learning the inverse kinetics of an octopus-like manipulator in three-dimensional space

M. Giorelli, F. Renda, M. Calisti, A. Arienti, G. Ferri, C. Laschi

Research output: Contribution to journalArticlepeer-review

53 Scopus citations

Abstract

This work addresses the inverse kinematics problem of a bioinspired octopus-like manipulator moving in three-dimensional space. The bioinspired manipulator has a conical soft structure that confers the ability of twirling around objects as a real octopus arm does. Despite the simple design, the soft conical shape manipulator driven by cables is described by nonlinear differential equations, which are difficult to solve analytically. Since exact solutions of the equations are not available, the Jacobian matrix cannot be calculated analytically and the classical iterative methods cannot be used. To overcome the intrinsic problems of methods based on the Jacobian matrix, this paper proposes a neural network learning the inverse kinematics of a soft octopus-like manipulator driven by cables. After the learning phase, a feed-forward neural network is able to represent the relation between manipulator tip positions and forces applied to the cables. Experimental results show that a desired tip position can be achieved in a short time, since heavy computations are avoided, with a degree of accuracy of 8% relative average error with respect to the total arm length.

Original languageBritish English
Article number035006
JournalBioinspiration and Biomimetics
Volume10
Issue number3
DOIs
StatePublished - 1 Jun 2015

Keywords

  • inverse kinematics
  • neural networks
  • soft robotics

Fingerprint

Dive into the research topics of 'Learning the inverse kinetics of an octopus-like manipulator in three-dimensional space'. Together they form a unique fingerprint.

Cite this