Adaptive Robot Deployment Algorithms

Simple item page
dc.contributor.authorLE NY, Jerome
dc.contributor.authorPappas, George J
dc.date2023-05-17T03:37:57.000
dc.date.accessioned2023-05-22T19:14:21Z
dc.date.available2023-05-22T19:14:21Z
dc.date.issued2010-03-25
dc.date.submitted2010-03-25T18:42:24-07:00
dc.description.abstractIn robot deployment problems, the fundamental issue is to optimize a steady state performance measure that depends on the spatial configuration of a group of robots. For static deployment problems, a classical way of designing high- level feedback motion planners is to implement a gradient descent scheme on a suitably chosen objective function. This can lead to computationally expensive deployment algorithms that may not be adaptive to uncertain dynamic environments. We address this challenge by showing that algorithms for a variety of deployment scenarios in stochastic environments and with noisy sensor measurements can be designed as stochastic gradient descent algorithms, and their convergence properties analyzed via the theory of stochastic approximations. This approach yields often surprisingly simple algorithms that can accommodate complicated objective functions, and adapt to slow temporal variations in environmental parameters. To illustrate the richness of the framework, we discuss several applications, including searching for a field extrema, deployment with stochastic connectivity constraints, coverage, and vehicle routing scenarios.
dc.identifier.urihttps://repository.upenn.edu/handle/20.500.14332/34168
dc.legacy.articleid1003
dc.legacy.fulltexturlhttps://repository.upenn.edu/cgi/viewcontent.cgi?article=1003&context=ese_reports&unstamped=1
dc.source.issue4
dc.source.journalTechnical Reports (ESE)
dc.source.statuspublished
dc.subject.otherrobotics
dc.subject.otherpotential field methods
dc.subject.otherstochastic gradient descent algorithms
dc.subject.otherstochastic approximation
dc.subject.otherControls and Control Theory
dc.subject.otherRobotics
dc.titleAdaptive Robot Deployment Algorithms
dc.typeWorking Paper
digcom.contributor.authorisAuthorOfPublication|email:jerome.le-ny@polymtl.ca|institution:University of Pennsylvania|LE NY, Jerome
digcom.contributor.authorisAuthorOfPublication|email:pappasg@seas.upenn.edu|institution:University of Pennsylvania|Pappas, George J
digcom.identifierese_reports/4
digcom.identifier.contextkey1246551
digcom.identifier.submissionpathese_reports/4
digcom.typeworkingpaper
dspace.entity.typePublication
relation.isAuthorOfPublication5dd19597-53d3-49ad-a4a3-d0157ed710d9
relation.isAuthorOfPublication00473ef0-d415-4df9-b027-00f0cf171730
relation.isAuthorOfPublication.latestForDiscovery5dd19597-53d3-49ad-a4a3-d0157ed710d9
upenn.schoolDepartmentCenterTechnical Reports (ESE)
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
SA_multirobots.pdf
Size:
236.78 KB
Format:
Adobe Portable Document Format
Download
Collection
Working Papers