A dense and direct approach to visual servoing using depth maps

Céline Teulière 1, 2 Eric Marchand 2
2 Lagadic - Visual servoing in robotics, computer vision, and augmented reality
CRISAM - Inria Sophia Antipolis - Méditerranée , Inria Rennes – Bretagne Atlantique , IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
Abstract : This paper presents a novel 3D servoing approach using dense depth maps to perform robotic tasks. With respect to position- based approaches, our method does not require the estimation of the 3D pose (direct), nor the extraction and matching of 3D features (dense) and only requires dense depth maps provided by 3D sensors. Our approach has been validated in various servoing experiments using the depth information from a low cost RGB-D sensor. Positioning tasks are properly achieved despite noisy measurements, even when partial occlusions or scene modifications occur. We also show that, in cases where a reference depth map cannot be easily available, synthetic ones generated with a rendering engine still lead to satisfactory positioning performances. Application of the approach to the navigation of a mobile robot is also demonstrated.
Document type :
Journal articles
Complete list of metadatas

Cited literature [29 references]  Display  Hide  Download

https://hal.inria.fr/hal-00991641
Contributor : Eric Marchand <>
Submitted on : Tuesday, April 28, 2015 - 11:34:40 AM
Last modification on : Thursday, February 7, 2019 - 2:25:58 PM
Long-term archiving on : Wednesday, April 19, 2017 - 8:32:17 AM

File

ct-tro14_final.pdf
Files produced by the author(s)

Identifiers

Citation

Céline Teulière, Eric Marchand. A dense and direct approach to visual servoing using depth maps. IEEE Transactions on Robotics, IEEE, 2014, 30 (5), pp.1242-1249. ⟨10.1109/TRO.2014.2325991⟩. ⟨hal-00991641v2⟩

Share

Metrics

Record views

700

Files downloads

375