A gradient-based path optimization method for motion planning - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Advanced Robotics Année : 2016

A gradient-based path optimization method for motion planning

Résumé

Most algorithms in probabilistic sampling-based path planning compute collision-free paths made of straight line segments lying in the configuration space. Due to the randomness of sampling, the paths make detours that need to be optimized. The contribution of this paper is to propose a basic gradient-based (GB) algorithm that transforms a polygonal collision-free path into a shorter one. While requiring only collision checking, and not any time-consuming obstacle distance computation nor geometry simplification, we constrain only part of the configuration variables that may cause a collision, and not entire configurations. Thus parasite motions that are not useful for the problem resolution are reduced without any assumption. Experimental results include navigation and manipulation tasks, e.g. a manipulator arm filling boxes and a PR2 robot working in a kitchen environment. Comparisons with a random shortcut optimizer and a partial shortcut have also been studied.
Fichier principal
Vignette du fichier
paper_HAL.pdf (2.65 Mo) Télécharger le fichier
path_optimization_video.mp4 (5.32 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01301233 , version 1 (11-04-2016)

Licence

Paternité - Pas d'utilisation commerciale

Identifiants

Citer

Mylène Campana, Florent Lamiraux, Jean-Paul Laumond. A gradient-based path optimization method for motion planning. Advanced Robotics, 2016, 30 (17-18), pp.1126-1144. ⟨10.1080/01691864.2016.1168317⟩. ⟨hal-01301233⟩
1934 Consultations
559 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More