Nonlinear Heterogeneous Bayesian Decentralized Data Fusion

TL;DR

This paper extends the factor graph decentralized data fusion framework to handle nonlinear models and unreliable networks, demonstrating scalable, robust multi-robot tracking with significant reductions in communication and computation costs.

Contribution

It introduces a generalized heterogeneous fusion rule that relaxes previous assumptions, enabling more practical and scalable multi-robot data fusion in complex environments.

Findings

FG-DDF remains consistent under non-linear models and communication dropouts.

Achieves over 99% reduction in communication and computation costs.

Proven effective through simulations and hardware experiments.

Abstract

The factor graph decentralized data fusion (FG-DDF) framework was developed for the analysis and exploitation of conditional independence in {heterogeneous Bayesian decentralized fusion problems, in which robots update and fuse pdfs over different, but overlapping subsets of random states. This allows robots to efficiently use smaller probabilistic models and sparse message passing to accurately and scalably fuse relevant local parts of a larger global joint state pdf while accounting for data dependencies between robots. Whereas prior work required limiting assumptions about network connectivity and model linearity, this paper relaxes these to explore the applicability and robustness of FG-DDF in more general settings. We develop a new heterogeneous fusion rule which generalizes the homogeneous covariance intersection algorithm for such cases and test it in multi-robot tracking and localization scenarios with non-linear motion/observation models under communication dropouts. Simulation and hardware experiments show that, in practice, the FG-DDF continues to provide consistent filtered estimates under these more practical operating conditions, while reducing computation and communication costs by more than 99\%, thus enabling the design of scalable real-world multi-robot systems.