Work

Smoothing out the edges: continuous-time estimation with Gaussian process motion priors on factor graphs

Year: 2026

Type: article

Abstract: Continuous-time state estimation is gaining in popularity due to its abilities to provide smooth solutions, handle asynchronous sensors and interpolate between data points. While there are two main paradigms, parametric (e.g., temporal basis functions, splines) and nonparametric (Gaussian processes [GP]), the latter has seen less adoption despite its technical advantages and relative ease of implementation. This paper seeks to rectify this situation by providing a new simplified explanation of GP continuous-time estimation rooted in the language of factor graphs, which have become the de facto estimation paradigm in much of robotics. To simplify onboarding, this paper also provides three working examples implemented in the popular Georgia Tech Smoothing and Mapping estimation framework.

Source: Foundations and Trends in Robotics

DOI: 10.1108/ftrob-01-2026-0086

Authors: Connor Holmes, Sven Lilge, Zi Cong Guo, Frank Dellaert, Timothy D. Barfoot

Institutions: University of Toronto, Toronto Rehabilitation Institute, Metropolitan University, Georgia Institute of Technology

Language: English

Topic: Target Tracking and Data Fusion in Sensor Networks

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W7160920825

FWCI:

Cites:

Cited by:

Related to: