Show simple item record

dc.contributor.authorLi, Qingbiaoen
dc.contributor.authorGama, Fernandoen
dc.contributor.authorRibeiro, Alejandroen
dc.contributor.authorProrok, Amandaen
dc.date.accessioned2020-07-16T23:30:41Z
dc.date.available2020-07-16T23:30:41Z
dc.identifier.isbn978-1-7281-6212-6en
dc.identifier.issn2153-0858
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/308037
dc.description.abstractEffective communication is key to successful, de- centralized, multi-robot path planning. Yet, it is far from obvious what information is crucial to the task at hand, and how and when it must be shared among robots. To side-step these issues and move beyond hand-crafted heuristics, we propose a combined model that automatically synthesizes local communication and decision-making policies for robots navigating in constrained workspaces. Our architecture is composed of a convolutional neural network (CNN) that extracts adequate features from local observations, and a graph neural network (GNN) that communicates these features among robots. We train the model to imitate an expert algorithm, and use the resulting model online in decentralized planning involving only local communication and local observations. We evaluate our method in simulations by navigating teams of robots to their destinations in 2D cluttered workspaces. We measure the success rates and sum of costs over the planned paths. The results show a performance close to that of our expert algorithm, demonstrating the validity of our approach. In particular, we show our model’s capability to generalize to previously unseen cases (involving larger environments and larger robot teams).
dc.description.sponsorshipWe gratefully acknowledge the support of ARL grant DCIST CRA W911NF-17-2-0181. A. Prorok was supported by the Engineering and Physical Sciences Research Council (grant EP/S015493/1). We gratefully acknowledge their support.
dc.publisherIEEE
dc.rightsAll rights reserved
dc.titleGraph Neural Networks for Decentralized Multi-Robot Path Planningen
dc.typeConference Object
prism.publicationName2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)en
dc.identifier.doi10.17863/CAM.55132
dcterms.dateAccepted2020-07-01en
rioxxterms.versionofrecord10.1109/IROS45743.2020.9341668en
rioxxterms.versionAM
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserveden
rioxxterms.licenseref.startdate2020-07-01en
dc.contributor.orcidProrok, Amanda [0000-0001-7313-5983]
dc.identifier.eissn2153-0866
rioxxterms.typeConference Paper/Proceeding/Abstracten
pubs.funder-project-idEPSRC (EP/S015493/1)
cam.issuedOnline2021-02-10en
pubs.conference-nameIEEE/RSJ International Conference on Intelligent Robots and Systemsen
pubs.conference-start-date2020-10-24en
cam.orpheus.successMon Feb 22 07:33:51 GMT 2021 - Embargo updated*
cam.orpheus.counter18*
rioxxterms.freetoread.startdate2021-01-01


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record