Autonomous 3D object modeling by a humanoid using an optimization-driven Next-Best-View formulation

Torea Foissotte 1, 2 Olivier Stasse 2 Pierre-Brice Wieber 3 Adrien Escande 4 Abderrahmane Kheddar 1, 2
1 IDH - Interactive Digital Humans
LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier
3 BIPOP - Modelling, Simulation, Control and Optimization of Non-Smooth Dynamical Systems
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : An original method to build a visual model for unknown objects by a humanoid robot is proposed. The algorithm ensures successful autonomous realization of this goal by addressing the problem as an active coupling between computer vision and whole-body posture generation. The visual model is built through the repeated execution of two processes. The first one considers the current knowledge about the visual aspects and the shape of the object to deduce a preferred viewpoint with the aim of reducing the uncertainty of the shape and appearance of the object. This is done while considering the constraints related to the embodiment of the vision sensors in the humanoid head. The second process generates a whole robot posture using the desired head pose while solving additional constraints such as collision avoidance and joint limitations. The main contribution of our approach relies on the use of different optimization algorithms to find an optimal viewpoint by including the humanoid specificities in terms of constraints, an embedded vision sensor, and redundant motion capabilities. This approach differs significantly from those of traditional works addressing the problem of autonomously building an object model.
Document type :
Journal articles
Complete list of metadatas

Cited literature [26 references]  Display  Hide  Download

https://hal.inria.fr/inria-00567850
Contributor : Pierre-Brice Wieber <>
Submitted on : Tuesday, February 22, 2011 - 9:18:42 AM
Last modification on : Tuesday, June 18, 2019 - 12:06:37 PM
Long-term archiving on : Thursday, June 30, 2011 - 1:52:09 PM

File

IJHRSpecialIssueSept2010_nbv.p...
Files produced by the author(s)

Identifiers

Collections

Citation

Torea Foissotte, Olivier Stasse, Pierre-Brice Wieber, Adrien Escande, Abderrahmane Kheddar. Autonomous 3D object modeling by a humanoid using an optimization-driven Next-Best-View formulation. International Journal of Humanoid Robotics, World Scientific Publishing, 2010, 7 (3), pp.407-428. ⟨10.1142/S0219843610002246⟩. ⟨inria-00567850⟩

Share

Metrics

Record views

1926

Files downloads

536