Visual Servoing without Jacobian Using Modified Simplex Optimization

Kanako Miura; Jacques Gangloff; Michel De Mathelin; Hikaru Inooka

doi:10.11499/sicep.2004.0_56_4

SICE Annual Conference 2004

DOI https://doi.org/10.11499/sicep.2004.0_56_4

Conference information

Host: The Society of Instrument and Control Engineers

Co-host: The IEEE Industrial Electronics Society, The IEEE Robotics and Automation Society, The IEEE Control Systems Society, The IEEE Systems, Man and Cybernetics Society, The Instrumentation, Systems, and Automation Society

Visual Servoing without Jacobian Using Modified Simplex Optimization

*Kanako Miura, Jacques Gangloff, Michel De Mathelin, Hikaru Inooka

Author information

Keywords: Model-less visual servoing, Positioning task, Simplex optimization

CONFERENCE PROCEEDINGS FREE ACCESS

Pages 56

Details

Abstract

we present an uncalibrated visual servoing task with respect to a static target. The displacements of the robot are generated in real time in order to minimize an objective function. A simplex method is used for the minimization. On-line image Jacobian estimation runs at the same time and the process switches to a Newton-like optimization technique for quicker convergence.

Corresponding author

Register with J-STAGE for free!