The unscented Kalman filter for nonlinear estimation

4,471 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Continual Learning Of Predictive Models In Video Sequences Via Variational Autoencoders (2020, methodology): “For training N , the Gaussian distributions (approximated through [19]) related to every (μk, σ 2 k) data clustered in S; and their successive change μ̇k+1 are respectively used as inputs and outputs of the network, such that:”
A Separation Principle for Control in the Age of Deep Learning (2017, background): “Sigma-point filters [40] are deterministic sample-based representations that falls in between these two cases.”
Deep Learning Sensor Fusion for Autonomous Vehicle Perception and Localization: A Review (2020, positive): “The unscented Kalman ﬁlter (UKF) was next introduced to improve the performance of EKF.”
Residual Policy Learning (2018, methodology): “Learning an accurate dynamics model is another central focus for robotics (termed system identification), and has been approached using analytic gradients [23, 24], finite differences [25] or Bayesian Optimization [8].”
TrafficSim: Learning to Simulate Realistic Multi-Agent Behaviors (2021, methodology): “, Unscented Kalman filter [40] with kinematic bicycle model [28]).”
Variational Autoencoder for End-to-End Control of Autonomous Driving with Novelty Detection and Training De-biasing (2018, methodology): “The approach for pixelwise uncertainty estimates is similar to the unscented transform [31], and is captured in Algorithm 1.”