Papers

Simulation-based Bayesian inference for robotic grasping

N Marlier, O Brüls, G Louppe - arXiv preprint arXiv:2303.05873, 2023 - arxiv.org
Computer Science paper cs.RO Suggest

… By framing robotic grasping as an inference task, we demonstrate the general applicability of simulation-based inference algorithms to complex robotic tasks and their usefulness to deal …

Cited by Link to paper

BibTeX

@article{2303.05873v1,
Author        = {Norman Marlier and Olivier Brüls and Gilles Louppe},
Title         = {Simulation-based Bayesian inference for robotic grasping},
Eprint        = {2303.05873v1},
ArchivePrefix = {arXiv},
PrimaryClass  = {cs.RO},
Abstract      = {General robotic grippers are challenging to control because of their rich
nonsmooth contact dynamics and the many sources of uncertainties due to the
environment or sensor noise. In this work, we demonstrate how to compute 6-DoF
grasp poses using simulation-based Bayesian inference through the full
stochastic forward simulation of the robot in its environment while robustly
accounting for many of the uncertainties in the system. A Riemannian manifold
optimization procedure preserving the nonlinearity of the rotation space is
used to compute the maximum a posteriori grasp pose. Simulation and physical
benchmarks show the promising high success rate of the approach.},
Year          = {2023},
Month         = {Mar},
Url           = {http://arxiv.org/abs/2303.05873v1},
File          = {2303.05873v1.pdf}
}

Share