Dynamic Association of Semantics and Parameter Estimates by Filtering

TL;DR

This paper introduces a probabilistic filtering framework that dynamically associates semantic classes with system parameters, improving the modeling of time-varying relationships in complex environments.

Contribution

It extends existing semantic filtering methods to multi-parameter settings with a scalable Bayesian approach, better capturing dynamic parameter-semantic associations.

Findings

The proposed filter scales linearly with parameter space dimension.

It outperforms existing methods in capturing time-varying associations.

Demonstrated effectiveness in a driving domain scenario.

Abstract

We propose a probabilistic semantic filtering framework in which parameters of a dynamical system are inferred and associated with a closed set of semantic classes in a map. We extend existing methods to a multi-parameter setting using a posterior that tightly couples semantics with the parameter likelihoods, and propose a filter to compute this posterior sequentially, subject to dynamics in the map's state. Using Bayesian moment matching, we show that the computational complexity of measurement updates scales linearly in the dimension of the parameter space. Finally, we demonstrate limitations of applying existing methods to a problem from the driving domain, and show that the proposed framework better captures time-varying parameter-to-semantic associations.