Study of Variational Inference for Flexible Distributed Probabilistic Robotics

Malte Rørmose Damgaard; Rasmus Pedersen; Thomas Bak

doi:10.3390/robotics11020038

Study of Variational Inference for Flexible Distributed Probabilistic Robotics

Malte Rørmose Damgaard^*, Rasmus Pedersen, Thomas Bak

^*Corresponding author for this work

Research output: Contribution to journal › Journal article › Research › peer-review

2 Citations (Scopus)

57 Downloads (Pure)

Abstract

By combining stochastic variational inference with message passing algorithms, we show how to solve the highly complex problem of navigation and avoidance in distributed multi-robot systems in a computationally tractable manner, allowing online implementation. Subsequently, the proposed variational method lends itself to more flexible solutions than prior methodologies. Furthermore, the derived method is verified both through simulations with multiple mobile robots and a real world experiment with two mobile robots. In both cases, the robots share the operating space and need to cross each other’s paths multiple times without colliding.

Original language	English
Article number	38
Journal	Robotics
Volume	11
Issue number	2
ISSN	2218-6581
DOIs	https://doi.org/10.3390/robotics11020038
Publication status	Published - Apr 2022

Bibliographical note

Publisher Copyright:
© 2022 by the authors. Licensee MDPI, Basel, Switzerland.

Keywords

distributed robotics
message-passing algorithm
probabilistic robotics
stochastic variational inference
variational inference

Access to Document

10.3390/robotics11020038

Open Access ArticleFinal published version, 1.91 MBLicence: CC BY 4.0

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

@article{2a666e57fedf4d77a74c53d1335d2a47,

title = "Study of Variational Inference for Flexible Distributed Probabilistic Robotics",

abstract = "By combining stochastic variational inference with message passing algorithms, we show how to solve the highly complex problem of navigation and avoidance in distributed multi-robot systems in a computationally tractable manner, allowing online implementation. Subsequently, the proposed variational method lends itself to more flexible solutions than prior methodologies. Furthermore, the derived method is verified both through simulations with multiple mobile robots and a real world experiment with two mobile robots. In both cases, the robots share the operating space and need to cross each other{\textquoteright}s paths multiple times without colliding.",

keywords = "distributed robotics, message-passing algorithm, probabilistic robotics, stochastic variational inference, variational inference",

author = "Damgaard, {Malte R{\o}rmose} and Rasmus Pedersen and Thomas Bak",

note = "Publisher Copyright: {\textcopyright} 2022 by the authors. Licensee MDPI, Basel, Switzerland.",

year = "2022",

month = apr,

doi = "10.3390/robotics11020038",

language = "English",

volume = "11",

journal = "Robotics",

issn = "2218-6581",

publisher = "MDPI",

number = "2",

}

TY - JOUR

T1 - Study of Variational Inference for Flexible Distributed Probabilistic Robotics

AU - Damgaard, Malte Rørmose

AU - Pedersen, Rasmus

AU - Bak, Thomas

PY - 2022/4

Y1 - 2022/4

N2 - By combining stochastic variational inference with message passing algorithms, we show how to solve the highly complex problem of navigation and avoidance in distributed multi-robot systems in a computationally tractable manner, allowing online implementation. Subsequently, the proposed variational method lends itself to more flexible solutions than prior methodologies. Furthermore, the derived method is verified both through simulations with multiple mobile robots and a real world experiment with two mobile robots. In both cases, the robots share the operating space and need to cross each other’s paths multiple times without colliding.

AB - By combining stochastic variational inference with message passing algorithms, we show how to solve the highly complex problem of navigation and avoidance in distributed multi-robot systems in a computationally tractable manner, allowing online implementation. Subsequently, the proposed variational method lends itself to more flexible solutions than prior methodologies. Furthermore, the derived method is verified both through simulations with multiple mobile robots and a real world experiment with two mobile robots. In both cases, the robots share the operating space and need to cross each other’s paths multiple times without colliding.

KW - distributed robotics

KW - message-passing algorithm

KW - probabilistic robotics

KW - stochastic variational inference

KW - variational inference

UR - http://www.scopus.com/inward/record.url?scp=85127437305&partnerID=8YFLogxK

U2 - 10.3390/robotics11020038

DO - 10.3390/robotics11020038

M3 - Journal article

AN - SCOPUS:85127437305

SN - 2218-6581

VL - 11

JO - Robotics

JF - Robotics

IS - 2

M1 - 38

ER -

Study of Variational Inference for Flexible Distributed Probabilistic Robotics

Abstract

Bibliographical note

Keywords

Access to Document

AUB Link

Other files and links

Fingerprint

Toward an idiomatic framework for cognitive robotics

Cite this