Abstract

This work presents a strategy for coordinated multi-agent weeding under conditions of partial environmental information. The goal is to demonstrate the feasibility of coordination strategies for improving the weeding performance of autonomous agricultural robots. It is shown that, given a sufficient number of agents, a team of autonomous robots can successfully weed fields with various initial seed bank densities, even when multiple days are allowed to elapse before weeding commences. Furthermore, the use of information sharing between agents is demonstrated to strongly improve system performance as the number of agents increases. As a domain to test these algorithms, a simulation environment, Weed World, was developed, which allows real-time visualization of coordinated weeding policies, and includes realistic weed generation. In this work, experiments are conducted to determine the required number of agents for given initial seed bank densities and varying allowed days before the start of the weeding process.

Original languageEnglish (US)
Article number104827
JournalComputers and Electronics in Agriculture
Volume163
DOIs
StatePublished - Aug 2019

Fingerprint

robots
weed
weed control
seed bank
Robots
weeds
visualization
Visualization
simulation
experiment
Experiments
testing

ASJC Scopus subject areas

  • Forestry
  • Agronomy and Crop Science
  • Computer Science Applications
  • Horticulture

Cite this

Agbots : Weeding a field with a team of autonomous robots. / McAllister, Wyatt; Osipychev, Denis; Davis, Adam; Chowdhary, Girish.

In: Computers and Electronics in Agriculture, Vol. 163, 104827, 08.2019.

Research output: Contribution to journalArticle

@article{e943a70b68a54bcdaa7ef8eb4f17ab5d,
title = "Agbots: Weeding a field with a team of autonomous robots",
abstract = "This work presents a strategy for coordinated multi-agent weeding under conditions of partial environmental information. The goal is to demonstrate the feasibility of coordination strategies for improving the weeding performance of autonomous agricultural robots. It is shown that, given a sufficient number of agents, a team of autonomous robots can successfully weed fields with various initial seed bank densities, even when multiple days are allowed to elapse before weeding commences. Furthermore, the use of information sharing between agents is demonstrated to strongly improve system performance as the number of agents increases. As a domain to test these algorithms, a simulation environment, Weed World, was developed, which allows real-time visualization of coordinated weeding policies, and includes realistic weed generation. In this work, experiments are conducted to determine the required number of agents for given initial seed bank densities and varying allowed days before the start of the weeding process.",
author = "Wyatt McAllister and Denis Osipychev and Adam Davis and Girish Chowdhary",
year = "2019",
month = "8",
doi = "10.1016/j.compag.2019.05.036",
language = "English (US)",
volume = "163",
journal = "Computers and Electronics in Agriculture",
issn = "0168-1699",
publisher = "Elsevier",

}

TY - JOUR

T1 - Agbots

T2 - Weeding a field with a team of autonomous robots

AU - McAllister, Wyatt

AU - Osipychev, Denis

AU - Davis, Adam

AU - Chowdhary, Girish

PY - 2019/8

Y1 - 2019/8

N2 - This work presents a strategy for coordinated multi-agent weeding under conditions of partial environmental information. The goal is to demonstrate the feasibility of coordination strategies for improving the weeding performance of autonomous agricultural robots. It is shown that, given a sufficient number of agents, a team of autonomous robots can successfully weed fields with various initial seed bank densities, even when multiple days are allowed to elapse before weeding commences. Furthermore, the use of information sharing between agents is demonstrated to strongly improve system performance as the number of agents increases. As a domain to test these algorithms, a simulation environment, Weed World, was developed, which allows real-time visualization of coordinated weeding policies, and includes realistic weed generation. In this work, experiments are conducted to determine the required number of agents for given initial seed bank densities and varying allowed days before the start of the weeding process.

AB - This work presents a strategy for coordinated multi-agent weeding under conditions of partial environmental information. The goal is to demonstrate the feasibility of coordination strategies for improving the weeding performance of autonomous agricultural robots. It is shown that, given a sufficient number of agents, a team of autonomous robots can successfully weed fields with various initial seed bank densities, even when multiple days are allowed to elapse before weeding commences. Furthermore, the use of information sharing between agents is demonstrated to strongly improve system performance as the number of agents increases. As a domain to test these algorithms, a simulation environment, Weed World, was developed, which allows real-time visualization of coordinated weeding policies, and includes realistic weed generation. In this work, experiments are conducted to determine the required number of agents for given initial seed bank densities and varying allowed days before the start of the weeding process.

UR - http://www.scopus.com/inward/record.url?scp=85067352229&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85067352229&partnerID=8YFLogxK

U2 - 10.1016/j.compag.2019.05.036

DO - 10.1016/j.compag.2019.05.036

M3 - Article

AN - SCOPUS:85067352229

VL - 163

JO - Computers and Electronics in Agriculture

JF - Computers and Electronics in Agriculture

SN - 0168-1699

M1 - 104827

ER -