Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Robust Filtering and Smoothing with Gaussian Processes

About

We propose a principled algorithm for robust Bayesian filtering and smoothing in nonlinear stochastic dynamic systems when both the transition function and the measurement function are described by non-parametric Gaussian process (GP) models. GPs are gaining increasing importance in signal processing, machine learning, robotics, and control for representing unknown system functions by posterior probability distributions. This modern way of "system identification" is more robust than finding point estimates of a parametric function representation. In this article, we present a principled algorithm for robust analytic smoothing in GP dynamic systems, which are increasingly used in robotics and control. Our numerical evaluations demonstrate the robustness of the proposed approach in situations where other state-of-the-art Gaussian filters and smoothers can fail.

Marc Peter Deisenroth, Ryan Turner, Marco F. Huber, Uwe D. Hanebeck, Carl Edward Rasmussen• 2012

Related benchmarks

TaskDatasetResultRank
State estimationSynthetic nonlinear dynamical system dataset (test)
NLL (x)1.67
6
Inference in Gaussian Process Dynamical SystemsCMU Motion Capture subject 64 (Trial 10)
NLLz25.64
4
Pendulum TrackingPendulum-swing data (test)
NLL (x-axis)-0.8
4
Inference in Gaussian Process Dynamical SystemsCMU Motion Capture subject 64 (Trial 9)
NLLz15.19
4
Inference in Gaussian Process Dynamical SystemsCMU Motion Capture subject 64 (Trial 8)
NLLz14.28
4
Showing 5 of 5 rows

Other info

Follow for update