Florian T. Pokorny
Assistant Professor, School of Computer Science and Communication, KTH Royal Institute of TechnologyMulti-Armed Bandit Models for 2D Grasp Planning with Uncertainty
In Proc. of the IEEE International Conference on Automation Science and Engineering (CASE), to appear, 2015
Abstract
For applications such as warehouse order fulfillment, robot grasps must be robust to uncertainty arising from sensing,
mechanics, and control. One way to achieve robustness is to evaluate the performance of candidate grasps by sampling
perturbations in shape, pose, and gripper approach and to compute the probability of force closure for each candidate to
identify a grasp with the highest expected quality. Since evaluating the
quality of each grasp is computationally demanding, prior work has turned to cloud computing. To improve computational efficiency and to extend this work, we consider how
Multi-Armed Bandit (MAB) models for optimizing decisions can be applied in this context. We formulate robust grasp
planning as a MAB problem and evaluate convergence times towards an optimal grasp candidate using 100 object shapes from
the Brown Vision 2D Lab Dataset with 1000 grasp candidates per object. We consider the case where shape uncertainty is represented as a Gaussian process implicit surface (GPIS) with Gaussian uncertainty in pose, gripper approach angle, and coefficient of friction.
We find that Thompson Sampling and the Gittins index MAB methods converged to within 3% of the optimal grasp up to 10x faster than uniform allocation and 5x faster than iterative pruning.
Bibtex
@inproceedings{laskey2015a,
title={Multi-Armed Bandit Models for 2D Grasp Planning with Uncertainty},
author={Laskey, Michael and Mahler, Jeff and McCarthy, Zoe and Pokorny, Florian T. and Patil, Sachin and van den
Berg, Jur and Kragic, Danica and Abbeel, Pieter and Goldberg, Ken},
booktitle = {Proc. of the IEEE International Conference on Automation Science and Engineering (CASE), to appear},
year = {2015}
}