Skip to Main content Skip to Navigation
Conference papers

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

Samuel Felton 1, 2 Elisa Fromont 2 Eric Marchand 1
1 RAINBOW - Sensor-based and interactive robotics
Inria Rennes – Bretagne Atlantique , IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
2 LACODAM - Large Scale Collaborative Data Mining
Inria Rennes – Bretagne Atlantique , IRISA-D7 - GESTION DES DONNÉES ET DE LA CONNAISSANCE
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.
Document type :
Conference papers
Complete list of metadata

https://hal.inria.fr/hal-03173684
Contributor : Eric Marchand <>
Submitted on : Thursday, March 18, 2021 - 4:54:22 PM
Last modification on : Wednesday, March 24, 2021 - 8:49:18 AM

File

ICRA2021_Siame_se_3_.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03173684, version 2

Citation

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.1-7. ⟨hal-03173684v2⟩

Share

Metrics

Record views

56

Files downloads

285