Saved in:
Bibliographic Details
Main Authors: Rameshbabu, Bharath K, Balakrishna, Sumukh S, Flynn, Brian, Kapoor, Vinayak, Norton, Adam, Yanco, Holly, Calli, Berk
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2307.11622
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912627429474304
author Rameshbabu, Bharath K
Balakrishna, Sumukh S
Flynn, Brian
Kapoor, Vinayak
Norton, Adam
Yanco, Holly
Calli, Berk
author_facet Rameshbabu, Bharath K
Balakrishna, Sumukh S
Flynn, Brian
Kapoor, Vinayak
Norton, Adam
Yanco, Holly
Calli, Berk
contents We present a benchmarking study of vision-based robotic grasping algorithms and provide a comparative analysis. In particular, we compare two machine-learning-based and two analytical algorithms using an existing benchmarking protocol from the literature and determine the algorithms strengths and weaknesses under different experimental conditions. These conditions include variations in lighting, background textures, cameras with different noise levels, and grippers. We also run analogous experiments in simulations and with real robots and present the discrepancies. Some experiments are also run in two different laboratories using the same protocols to further analyze the repeatability of our results. We believe that this study, comprising 5040 experiments, provides important insights into the role and challenges of systematic experimentation in robotic manipulation and guides the development of new algorithms by considering the factors that could impact the performance. The experiment recordings and our benchmarking software are publicly available.
format Preprint
id arxiv_https___arxiv_org_abs_2307_11622
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle A Benchmarking Study of Vision-Based Robotic Grasping Algorithms: A Comparative Analysis
Rameshbabu, Bharath K
Balakrishna, Sumukh S
Flynn, Brian
Kapoor, Vinayak
Norton, Adam
Yanco, Holly
Calli, Berk
Robotics
We present a benchmarking study of vision-based robotic grasping algorithms and provide a comparative analysis. In particular, we compare two machine-learning-based and two analytical algorithms using an existing benchmarking protocol from the literature and determine the algorithms strengths and weaknesses under different experimental conditions. These conditions include variations in lighting, background textures, cameras with different noise levels, and grippers. We also run analogous experiments in simulations and with real robots and present the discrepancies. Some experiments are also run in two different laboratories using the same protocols to further analyze the repeatability of our results. We believe that this study, comprising 5040 experiments, provides important insights into the role and challenges of systematic experimentation in robotic manipulation and guides the development of new algorithms by considering the factors that could impact the performance. The experiment recordings and our benchmarking software are publicly available.
title A Benchmarking Study of Vision-Based Robotic Grasping Algorithms: A Comparative Analysis
topic Robotics
url https://arxiv.org/abs/2307.11622