Linear Dimensionality Reduction in Random Motion Planning

Sébastien Dalibard (1) , Jean-Paul Laumond (2)

1 LAAS - Laboratoire d'analyse et d'architecture des systèmes
2 LAAS-GEPETTO - Équipe Mouvement des Systèmes Anthropomorphes

The paper presents a method to control probabilistic diffusion in motion planning algorithms. The principle of the method is to use on line the results of a diffusion algorithm to describe the free space in which the planning takes place, by computing a Principal Component Analysis (PCA). This method identifies the locally free directions of the free space. Given that description, our algorithm accelerates the diffusion along these favoured directions. That way, if the free space appears as a small volume around a submanifold of a highly dimensioned configuration space, the method overcomes the usual limitations of diffusion algorithms and finds a solution quickly. The presented method is theoretically analyzed and experimentally compared to known motion planning algorithms.

Domaines: Robotique [cs.RO]; Automatique / Robotique

Sébastien Dalibard, Jean-Paul Laumond. Linear Dimensionality Reduction in Random Motion Planning. The International Journal of Robotics Research, 2011, 30 (12), pp. 1461-1476. ⟨hal-00486793v2⟩