Decentralized Multi-Robot Cooperation with Auctioned POMDPs

J. Capitan, M. Spaan, L. Merino, and A. Ollero. Decentralized Multi-Robot Cooperation with Auctioned POMDPs. International Journal of Robotics Research, 32:650–671, 2013.

Download

[PDF] [html] 

Abstract

Planning under uncertainty faces a scalability problem when considering multi-robot teams, as the informationspace scales exponentially with the number of robots. To address this issue, this paper proposes to decentralizemulti-robot Partially Observable Markov Decision Processes (POMDPs) while maintaining cooperation betweenrobots by using POMDP policy auctions. Auctions provide a flexible way of coordinating individual policiesmodeled by POMDPs and have low communication requirements. Additionally, communication models in themulti-agent POMDP literature severely mismatch with real inter-robot communication. We address this issue byexploiting a decentralized data fusion method in order to efficiently maintain a joint belief state among the robots.The paper presents two different applications: environmental monitoring with UnmannedAerial Vehicles (UAVs);and cooperative tracking, in which several robots have to jointly track a moving target of interest. The first one isused as a proof of concept and illustrates the proposed ideas through different simulations. The second one addsreal multi-robot experiments, showcasing the flexibility and robust coordination that our techniques can provide.

BibTeX Entry

@ARTICLE{capitan13ijrr,
  author = {J. Capitan and M. Spaan and L. Merino and A. Ollero},
  title = {{D}ecentralized {M}ulti-{R}obot {C}ooperation with {A}uctioned {POMDP}s},
  journal = IJRR,
  year = {2013},
  volume = {32},
  issue = {6},
  pages = {650--671},
   abstract={Planning under uncertainty faces a scalability problem when considering multi-robot teams, as the information
space scales exponentially with the number of robots. To address this issue, this paper proposes to decentralize
multi-robot Partially Observable Markov Decision Processes (POMDPs) while maintaining cooperation between
robots by using POMDP policy auctions. Auctions provide a flexible way of coordinating individual policies
modeled by POMDPs and have low communication requirements. Additionally, communication models in the
multi-agent POMDP literature severely mismatch with real inter-robot communication. We address this issue by
exploiting a decentralized data fusion method in order to efficiently maintain a joint belief state among the robots.
The paper presents two different applications: environmental monitoring with UnmannedAerial Vehicles (UAVs);
and cooperative tracking, in which several robots have to jointly track a moving target of interest. The first one is
used as a proof of concept and illustrates the proposed ideas through different simulations. The second one adds
real multi-robot experiments, showcasing the flexibility and robust coordination that our techniques can provide.},
}

Generated by bib2html.pl (written by Patrick Riley ) on Thu Aug 16, 2018 19:28:37