Optimization of stochastic strategies for spatially inhomogeneous robot swarms: A case study in commercial pollination

Spring Berman, Radhika Nagpal, Ádám Halász

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

8 Citations (Scopus)

Abstract

We present a scalable approach to optimizing robot control policies for a target collective behavior in a spatially inhomogeneous robotic swarm. The approach can incorporate robot feedback to maintain system performance in an unknown environmental flow field. We consider systems in which the robots follow both deterministic and random motion and transition stochastically between tasks. Our methodology is based on an abstraction of the swarm to a macroscopic continuous model, whose dimensionality is independent of the population size, that describes the expected time evolution of swarm subpopulations over a discretization of the environment. We incorporate this model into a stochastic optimization method and map the optimized model parameters onto the robot motion and task transition control policies to achieve a desired global objective. We illustrate our methodology with a scenario in which the behaviors of a swarm of robotic bees are optimized for both uniform and nonuniform pollination of a blueberry field, including in the presence of an unknown wind.

Original languageEnglish (US)
Title of host publicationIEEE International Conference on Intelligent Robots and Systems
Pages3923-3930
Number of pages8
DOIs
StatePublished - 2011
Externally publishedYes
Event2011 IEEE/RSJ International Conference on Intelligent Robots and Systems: Celebrating 50 Years of Robotics, IROS'11 - San Francisco, CA, United States
Duration: Sep 25 2011Sep 30 2011

Other

Other2011 IEEE/RSJ International Conference on Intelligent Robots and Systems: Celebrating 50 Years of Robotics, IROS'11
CountryUnited States
CitySan Francisco, CA
Period9/25/119/30/11

Fingerprint

Robots
Robotics
Flow fields
Feedback

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Software
  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Cite this

Berman, S., Nagpal, R., & Halász, Á. (2011). Optimization of stochastic strategies for spatially inhomogeneous robot swarms: A case study in commercial pollination. In IEEE International Conference on Intelligent Robots and Systems (pp. 3923-3930). [6048378] https://doi.org/10.1109/IROS.2011.6048378

Optimization of stochastic strategies for spatially inhomogeneous robot swarms : A case study in commercial pollination. / Berman, Spring; Nagpal, Radhika; Halász, Ádám.

IEEE International Conference on Intelligent Robots and Systems. 2011. p. 3923-3930 6048378.

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

Berman, S, Nagpal, R & Halász, Á 2011, Optimization of stochastic strategies for spatially inhomogeneous robot swarms: A case study in commercial pollination. in IEEE International Conference on Intelligent Robots and Systems., 6048378, pp. 3923-3930, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems: Celebrating 50 Years of Robotics, IROS'11, San Francisco, CA, United States, 9/25/11. https://doi.org/10.1109/IROS.2011.6048378
Berman S, Nagpal R, Halász Á. Optimization of stochastic strategies for spatially inhomogeneous robot swarms: A case study in commercial pollination. In IEEE International Conference on Intelligent Robots and Systems. 2011. p. 3923-3930. 6048378 https://doi.org/10.1109/IROS.2011.6048378
Berman, Spring ; Nagpal, Radhika ; Halász, Ádám. / Optimization of stochastic strategies for spatially inhomogeneous robot swarms : A case study in commercial pollination. IEEE International Conference on Intelligent Robots and Systems. 2011. pp. 3923-3930
@inproceedings{6b73843af19148d0bec2d6492e273ff8,
title = "Optimization of stochastic strategies for spatially inhomogeneous robot swarms: A case study in commercial pollination",
abstract = "We present a scalable approach to optimizing robot control policies for a target collective behavior in a spatially inhomogeneous robotic swarm. The approach can incorporate robot feedback to maintain system performance in an unknown environmental flow field. We consider systems in which the robots follow both deterministic and random motion and transition stochastically between tasks. Our methodology is based on an abstraction of the swarm to a macroscopic continuous model, whose dimensionality is independent of the population size, that describes the expected time evolution of swarm subpopulations over a discretization of the environment. We incorporate this model into a stochastic optimization method and map the optimized model parameters onto the robot motion and task transition control policies to achieve a desired global objective. We illustrate our methodology with a scenario in which the behaviors of a swarm of robotic bees are optimized for both uniform and nonuniform pollination of a blueberry field, including in the presence of an unknown wind.",
author = "Spring Berman and Radhika Nagpal and {\'A}d{\'a}m Hal{\'a}sz",
year = "2011",
doi = "10.1109/IROS.2011.6048378",
language = "English (US)",
isbn = "9781612844541",
pages = "3923--3930",
booktitle = "IEEE International Conference on Intelligent Robots and Systems",

}

TY - GEN

T1 - Optimization of stochastic strategies for spatially inhomogeneous robot swarms

T2 - A case study in commercial pollination

AU - Berman, Spring

AU - Nagpal, Radhika

AU - Halász, Ádám

PY - 2011

Y1 - 2011

N2 - We present a scalable approach to optimizing robot control policies for a target collective behavior in a spatially inhomogeneous robotic swarm. The approach can incorporate robot feedback to maintain system performance in an unknown environmental flow field. We consider systems in which the robots follow both deterministic and random motion and transition stochastically between tasks. Our methodology is based on an abstraction of the swarm to a macroscopic continuous model, whose dimensionality is independent of the population size, that describes the expected time evolution of swarm subpopulations over a discretization of the environment. We incorporate this model into a stochastic optimization method and map the optimized model parameters onto the robot motion and task transition control policies to achieve a desired global objective. We illustrate our methodology with a scenario in which the behaviors of a swarm of robotic bees are optimized for both uniform and nonuniform pollination of a blueberry field, including in the presence of an unknown wind.

AB - We present a scalable approach to optimizing robot control policies for a target collective behavior in a spatially inhomogeneous robotic swarm. The approach can incorporate robot feedback to maintain system performance in an unknown environmental flow field. We consider systems in which the robots follow both deterministic and random motion and transition stochastically between tasks. Our methodology is based on an abstraction of the swarm to a macroscopic continuous model, whose dimensionality is independent of the population size, that describes the expected time evolution of swarm subpopulations over a discretization of the environment. We incorporate this model into a stochastic optimization method and map the optimized model parameters onto the robot motion and task transition control policies to achieve a desired global objective. We illustrate our methodology with a scenario in which the behaviors of a swarm of robotic bees are optimized for both uniform and nonuniform pollination of a blueberry field, including in the presence of an unknown wind.

UR - http://www.scopus.com/inward/record.url?scp=84455175358&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84455175358&partnerID=8YFLogxK

U2 - 10.1109/IROS.2011.6048378

DO - 10.1109/IROS.2011.6048378

M3 - Conference contribution

AN - SCOPUS:84455175358

SN - 9781612844541

SP - 3923

EP - 3930

BT - IEEE International Conference on Intelligent Robots and Systems

ER -