Autonomous 3d Object Modeling by a Humanoid Using an Optimization-Driven Next-Best View Formulation
|Title||Autonomous 3d Object Modeling by a Humanoid Using an Optimization-Driven Next-Best View Formulation|
|Publication Type||Journal Article|
|Year of Publication||2010|
|Authors||Foissotte, T, Stasse, O, Wieber, P-B, Escande, A, Kheddar, A|
|Journal||International Journal on Humanoid Robotics, Special issue on Cognitive Humanoid Vision|
|Keywords||Motion planning, Navigation, selected|
An original method to build a visual model for unknown objects by a humanoid robot is proposed. The algorithm ensures a 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 builds through successive two main repetitive processes: considering the current knowledge of the object, a preferred viewpoint is deduced in order to reduce the uncertainty on the object shape and appearance while taking into account the constraints related to the embodiment of the vision sensors in the humanoid head. Then a whole robot posture is generated using the desired head pose. 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, embedded vision sensor and redundant motion capabilities. This differs significantly from the traditional works addressing the problem of autonomously building a model of an object.