Publication

Benchmarking cloth manipulation using action graphs: an example in placing flat

Conference Article

Conference

IROS Workshop on Benchmarking of robotic grasping and manipulation: protocols, metrics and data analysis (IROS BRGM)

Edition

2021

Pages

1-3

Doc link

https://www.robotics.qmul.ac.uk/content/events/iros-2021-workshop/files/Workshop_contribution_Garcia-Camacho_.pdf

File

Download the digital copy of the doc pdf document

Abstract

Benchmarking robotic manipulation is complex due to the difficulty in reproducing and comparing results across different embodiments and scenarios. Cloth manipula- tion presents additional challenges due to the complex object configuration space. Traditional cloth manipulation papers do not have well defined metrics to evaluate the success of a task or the quality of the result, and are tailored to each evaluation. In this paper we propose to evaluate cloth manipulation seg- menting a task into steps that can be evaluated independently, and to study how their success measures influence in the next segment and relate to task as a whole. In particular, we study a popular task such as placing a cloth flat on a table. We propose a benchmark with simple but continuous evaluation metrics that explore the influence of grasp location into the quality of the task. Our results show that grasp location doesn’t need to be precise on corners, that quality measures focused on evaluating different cloth parts can enlighten issues to solve and that success definition of a segment has to consider its influence on the ability to perform successfully the next segment of action.

Categories

manipulators, service robots.

Author keywords

Performance Evaluation & Benchmarking, Grasping & Manipulation

Scientific reference

I. Garcia-Camacho, J. Borràs and G. Alenyà. Benchmarking cloth manipulation using action graphs: an example in placing flat, 2021 IROS Workshop on Benchmarking of robotic grasping and manipulation: protocols, metrics and data analysis, 2021, Online, pp. 1-3, to appear.