Abstract

Individual robots in multi-robot teams usually behave according to relatively simple and often deterministic rules. This behavioral regularity may allow for variations in one robot's behavior to provide useful information about the state of other robots in the team. Thus, coordinated motion between distantly separated robots could be achieved without direct communication. Unfortunately, the dynamics describing a collective multi-robot system will often be too complex to analytically derive the relationship between observed nearest-neighbor variations and environmentally driven changes in the behavior of remote robots. Artificial neural networks (ANNs) may be used to find this relationship within training data, but scalability of the approach requires that the resulting ANNs be functional even in teams with sizes not represented in the training data. To this end, we train a communication-free, localization ANN on one robot in a 3-robot team and show how it can be extended without re-training to larger teams. We test our approach in a distributed caging scenario where a chain of simulated robots searches for an object to encircle and executes a coordinated behavior, ideally with no communication, shortly after only one detects the object.

Original languageEnglish (US)
Title of host publication2017 13th IEEE Conference on Automation Science and Engineering, CASE 2017
PublisherIEEE Computer Society
Pages1522-1527
Number of pages6
Volume2017-August
ISBN (Electronic)9781509067800
DOIs
StatePublished - Jan 12 2018
Event13th IEEE Conference on Automation Science and Engineering, CASE 2017 - Xi'an, China
Duration: Aug 20 2017Aug 23 2017

Other

Other13th IEEE Conference on Automation Science and Engineering, CASE 2017
CountryChina
CityXi'an
Period8/20/178/23/17

Fingerprint

Robots
Neural networks
Communication
Scalability

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Choi, T., Pavlic, T., & Richa, A. (2018). Automated synthesis of scalable algorithms for inferring non-local properties to assist in multi-robot teaming. In 2017 13th IEEE Conference on Automation Science and Engineering, CASE 2017 (Vol. 2017-August, pp. 1522-1527). IEEE Computer Society. https://doi.org/10.1109/COASE.2017.8256320

Automated synthesis of scalable algorithms for inferring non-local properties to assist in multi-robot teaming. / Choi, Taeyeong; Pavlic, Theodore; Richa, Andrea.

2017 13th IEEE Conference on Automation Science and Engineering, CASE 2017. Vol. 2017-August IEEE Computer Society, 2018. p. 1522-1527.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Choi, T, Pavlic, T & Richa, A 2018, Automated synthesis of scalable algorithms for inferring non-local properties to assist in multi-robot teaming. in 2017 13th IEEE Conference on Automation Science and Engineering, CASE 2017. vol. 2017-August, IEEE Computer Society, pp. 1522-1527, 13th IEEE Conference on Automation Science and Engineering, CASE 2017, Xi'an, China, 8/20/17. https://doi.org/10.1109/COASE.2017.8256320
Choi T, Pavlic T, Richa A. Automated synthesis of scalable algorithms for inferring non-local properties to assist in multi-robot teaming. In 2017 13th IEEE Conference on Automation Science and Engineering, CASE 2017. Vol. 2017-August. IEEE Computer Society. 2018. p. 1522-1527 https://doi.org/10.1109/COASE.2017.8256320
Choi, Taeyeong ; Pavlic, Theodore ; Richa, Andrea. / Automated synthesis of scalable algorithms for inferring non-local properties to assist in multi-robot teaming. 2017 13th IEEE Conference on Automation Science and Engineering, CASE 2017. Vol. 2017-August IEEE Computer Society, 2018. pp. 1522-1527
@inproceedings{657f35dd928b443489008fd7eef2301a,
title = "Automated synthesis of scalable algorithms for inferring non-local properties to assist in multi-robot teaming",
abstract = "Individual robots in multi-robot teams usually behave according to relatively simple and often deterministic rules. This behavioral regularity may allow for variations in one robot's behavior to provide useful information about the state of other robots in the team. Thus, coordinated motion between distantly separated robots could be achieved without direct communication. Unfortunately, the dynamics describing a collective multi-robot system will often be too complex to analytically derive the relationship between observed nearest-neighbor variations and environmentally driven changes in the behavior of remote robots. Artificial neural networks (ANNs) may be used to find this relationship within training data, but scalability of the approach requires that the resulting ANNs be functional even in teams with sizes not represented in the training data. To this end, we train a communication-free, localization ANN on one robot in a 3-robot team and show how it can be extended without re-training to larger teams. We test our approach in a distributed caging scenario where a chain of simulated robots searches for an object to encircle and executes a coordinated behavior, ideally with no communication, shortly after only one detects the object.",
author = "Taeyeong Choi and Theodore Pavlic and Andrea Richa",
year = "2018",
month = "1",
day = "12",
doi = "10.1109/COASE.2017.8256320",
language = "English (US)",
volume = "2017-August",
pages = "1522--1527",
booktitle = "2017 13th IEEE Conference on Automation Science and Engineering, CASE 2017",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Automated synthesis of scalable algorithms for inferring non-local properties to assist in multi-robot teaming

AU - Choi, Taeyeong

AU - Pavlic, Theodore

AU - Richa, Andrea

PY - 2018/1/12

Y1 - 2018/1/12

N2 - Individual robots in multi-robot teams usually behave according to relatively simple and often deterministic rules. This behavioral regularity may allow for variations in one robot's behavior to provide useful information about the state of other robots in the team. Thus, coordinated motion between distantly separated robots could be achieved without direct communication. Unfortunately, the dynamics describing a collective multi-robot system will often be too complex to analytically derive the relationship between observed nearest-neighbor variations and environmentally driven changes in the behavior of remote robots. Artificial neural networks (ANNs) may be used to find this relationship within training data, but scalability of the approach requires that the resulting ANNs be functional even in teams with sizes not represented in the training data. To this end, we train a communication-free, localization ANN on one robot in a 3-robot team and show how it can be extended without re-training to larger teams. We test our approach in a distributed caging scenario where a chain of simulated robots searches for an object to encircle and executes a coordinated behavior, ideally with no communication, shortly after only one detects the object.

AB - Individual robots in multi-robot teams usually behave according to relatively simple and often deterministic rules. This behavioral regularity may allow for variations in one robot's behavior to provide useful information about the state of other robots in the team. Thus, coordinated motion between distantly separated robots could be achieved without direct communication. Unfortunately, the dynamics describing a collective multi-robot system will often be too complex to analytically derive the relationship between observed nearest-neighbor variations and environmentally driven changes in the behavior of remote robots. Artificial neural networks (ANNs) may be used to find this relationship within training data, but scalability of the approach requires that the resulting ANNs be functional even in teams with sizes not represented in the training data. To this end, we train a communication-free, localization ANN on one robot in a 3-robot team and show how it can be extended without re-training to larger teams. We test our approach in a distributed caging scenario where a chain of simulated robots searches for an object to encircle and executes a coordinated behavior, ideally with no communication, shortly after only one detects the object.

UR - http://www.scopus.com/inward/record.url?scp=85044949324&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044949324&partnerID=8YFLogxK

U2 - 10.1109/COASE.2017.8256320

DO - 10.1109/COASE.2017.8256320

M3 - Conference contribution

AN - SCOPUS:85044949324

VL - 2017-August

SP - 1522

EP - 1527

BT - 2017 13th IEEE Conference on Automation Science and Engineering, CASE 2017

PB - IEEE Computer Society

ER -