TY - GEN
T1 - Decentralized Learning With Limited Communications for Multi-robot Coverage of Unknown Spatial Fields
AU - Nakamura, Kensuke
AU - Santos, Maria
AU - Leonard, Naomi Ehrich
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - This paper presents an algorithm for a team of mobile robots to simultaneously learn a spatial field over a domain and spatially distribute themselves to optimally cover it. Drawing from previous approaches that estimate the spatial field through a centralized Gaussian process, this work leverages the spatial structure of the coverage problem and presents a decentralized strategy where samples are aggregated locally by establishing communications through the boundaries of a Voronoi partition. We present an algorithm whereby each robot runs a local Gaussian process calculated from its own measurements and those provided by its Voronoi neighbors, which are incorporated into the individual robot's Gaussian process only if they provide sufficiently novel information. The performance of the algorithm is evaluated in simulation and compared with centralized approaches.
AB - This paper presents an algorithm for a team of mobile robots to simultaneously learn a spatial field over a domain and spatially distribute themselves to optimally cover it. Drawing from previous approaches that estimate the spatial field through a centralized Gaussian process, this work leverages the spatial structure of the coverage problem and presents a decentralized strategy where samples are aggregated locally by establishing communications through the boundaries of a Voronoi partition. We present an algorithm whereby each robot runs a local Gaussian process calculated from its own measurements and those provided by its Voronoi neighbors, which are incorporated into the individual robot's Gaussian process only if they provide sufficiently novel information. The performance of the algorithm is evaluated in simulation and compared with centralized approaches.
UR - http://www.scopus.com/inward/record.url?scp=85146315035&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85146315035&partnerID=8YFLogxK
U2 - 10.1109/IROS47612.2022.9981665
DO - 10.1109/IROS47612.2022.9981665
M3 - Conference contribution
AN - SCOPUS:85146315035
T3 - IEEE International Conference on Intelligent Robots and Systems
SP - 9980
EP - 9986
BT - IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2022
Y2 - 23 October 2022 through 27 October 2022
ER -