Siame-se(3): regression in se(3) for end-to-end visual servoing - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

Siame-se(3): regression in se(3) for end-to-end visual servoing

Abstract

In this paper we propose a deep architecture and the associated learning strategy for end-to-end direct visual servoing. The considered approach allows to sequentially predict, in se(3), the velocity of a camera mounted on the robot's end-effector for positioning tasks. Positioning is achieved with high precision despite large initial errors in both cartesian and image spaces. Training is fully done in simulation, alleviating the burden of data collection. We demonstrate the efficiency of our method in experiments in both simulated and real-world environments. We also show that the proposed approach is able to handle multiple scenes.
Fichier principal
Vignette du fichier
ICRA2021_Siame_se_3_.pdf (1.11 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03173684 , version 1 (18-03-2021)
hal-03173684 , version 2 (18-03-2021)

Identifiers

  • HAL Id : hal-03173684 , version 2

Cite

Samuel Felton, Elisa Fromont, Eric Marchand. Siame-se(3): regression in se(3) for end-to-end visual servoing. ICRA 2021 - IEEE International Conference on Robotics and Automation, May 2021, Xi'an, China. pp.14454-14460. ⟨hal-03173684v2⟩
208 View
438 Download

Share

Gmail Facebook X LinkedIn More