Stein Variational Belief Propagation for Multi-Robot Coordination

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Pavlasek, Jana, Mah, Joshua Jing Zhi, Xu, Ruihan, Jenkins, Odest Chadwicke, Ramos, Fabio
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910363777236992
author Pavlasek, Jana
Mah, Joshua Jing Zhi
Xu, Ruihan
Jenkins, Odest Chadwicke
Ramos, Fabio
author_facet Pavlasek, Jana
Mah, Joshua Jing Zhi
Xu, Ruihan
Jenkins, Odest Chadwicke
Ramos, Fabio
contents Decentralized coordination for multi-robot systems involves planning in challenging, high-dimensional spaces. The planning problem is particularly challenging in the presence of obstacles and different sources of uncertainty such as inaccurate dynamic models and sensor noise. In this paper, we introduce Stein Variational Belief Propagation (SVBP), a novel algorithm for performing inference over nonparametric marginal distributions of nodes in a graph. We apply SVBP to multi-robot coordination by modelling a robot swarm as a graphical model and performing inference for each robot. We demonstrate our algorithm on a simulated multi-robot perception task, and on a multi-robot planning task within a Model-Predictive Control (MPC) framework, on both simulated and real-world mobile robots. Our experiments show that SVBP represents multi-modal distributions better than sampling-based or Gaussian baselines, resulting in improved performance on perception and planning tasks. Furthermore, we show that SVBP's ability to represent diverse trajectories for decentralized multi-robot planning makes it less prone to deadlock scenarios than leading baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2311_16916
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Stein Variational Belief Propagation for Multi-Robot Coordination
Pavlasek, Jana
Mah, Joshua Jing Zhi
Xu, Ruihan
Jenkins, Odest Chadwicke
Ramos, Fabio
Robotics
Decentralized coordination for multi-robot systems involves planning in challenging, high-dimensional spaces. The planning problem is particularly challenging in the presence of obstacles and different sources of uncertainty such as inaccurate dynamic models and sensor noise. In this paper, we introduce Stein Variational Belief Propagation (SVBP), a novel algorithm for performing inference over nonparametric marginal distributions of nodes in a graph. We apply SVBP to multi-robot coordination by modelling a robot swarm as a graphical model and performing inference for each robot. We demonstrate our algorithm on a simulated multi-robot perception task, and on a multi-robot planning task within a Model-Predictive Control (MPC) framework, on both simulated and real-world mobile robots. Our experiments show that SVBP represents multi-modal distributions better than sampling-based or Gaussian baselines, resulting in improved performance on perception and planning tasks. Furthermore, we show that SVBP's ability to represent diverse trajectories for decentralized multi-robot planning makes it less prone to deadlock scenarios than leading baselines.
title Stein Variational Belief Propagation for Multi-Robot Coordination
topic Robotics
url https://arxiv.org/abs/2311.16916