New extension of the Kalman filter to nonlinear systems

By Simon Justin Julier, Jeffrey K. Uhlmann. 1997

Subfields: Robotics & Control, Signal Processing

How researchers see this paper

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

In Robotics & Control

In Signal Processing

Citations in the corpus

Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data (2016, background): “[10] and are successfully applied in many areas, they suffer from two major drawbacks: Firstly, its assumptions are restrictive and are violated in practical applications, leading to suboptimal results.”
Kernel Bayes' Rule (2010, neutral): “Alternative stra tegies for state-space models with complex dynamics involve the extended Kalman filter (EKF) an d u scented Kalman filter (UKF, [11]).”
Recurrent Neural Filters: Learning Independent Bayesian Filtering Steps for Time Series Prediction (2019, methodology): “For many ﬁlter models – such as the Kalman ﬁlter (Kalman, 1960) and non-linear variants like the unscented Kalman ﬁlter (Julier & Uhlmann, 1997) – deterministic functions are used at each step to adjust the sufﬁcient statistics of the belief state, guided by generative models of the data.”
Fusing Physics-based and Deep Learning Models for Prognostics (2020, methodology): “Since calibration of the performance model itself is not within the scope of this research, we apply a state-of-the-art approach to calibration: an unscented Kalman filter [29] to infer the values of the model-correcting parameters ?̂?.”
Integrating generic sensor fusion algorithms with sound state representations through encapsulation of manifolds (2011, methodology): “2] and more recently the Unscented Kalman Filter (UKF) [18].”
Inflation Bets or Deflation Hedges? The Changing Risks of Nominal Bonds (2013, unknown): “To estimate the model, we use a nonlinear ltering technique, the unscented Kalman lter, proposed by Julier and Uhlmann (1997), reviewed by Wan and van der Merwe (2001), and recently applied in nance by Binsbergen and Koijen (2008).”
Indoor Tracking: Theory, Methods, and Technologies (2015, methodology): “Two popular methods are the extended KF (EKF) [42] and the unscented KF (UKF) [43], respectively.”
Filtering in Finance (2003, background): “1 Background and Notations Recently Julier and Uhlmann [18] proposed a new extension of the Kalman Filter to Nonlinear systems, different from the EKF.”
Sensor Failure Detection, Identification, and Accommodation Using Fully Connected Cascade Neural Network (2015, background): “Recent literature has seen efforts been made to address these issues, particularly with the linearity assumption of the Kalman filters [25].”
New developments in state estimation for nonlinear systems (2000, unknown): “Recently, there have been interesting developments in derivative-free state estimation techniques (Julier & Uhlmann, 1994; Julier, Uhlmann & Durrant-Whyte, 1995; Julier & Uhlmann, 1997; Schei, 1997).”
A deterministic formulation of the ensemble Kalman filter: an alternative to ensemble square root filters (2008, background): “This stability is not necessarily directly related to the scheme’s performance in terms of RMSE under normal conditions, but rather characterizes its ability to continue operation when the system turns out to be in an inconsistent state in the sense of Julier and Uhlmann (1997).”
On entropy approximation for Gaussian mixture random vectors (2008, background): “[10]) each Gaussian component of f (~) in (3) is replaced by a set of socalled sigma points.”
Simultaneous Localization and Mapping: A Survey of Current Trends in Autonomous Driving (2017, unknown): “All the lanes and features were acquired during a ﬁrst passage and fused in a UKF.”
Comparison of approximation methods to Kullback–Leibler divergence between Gaussian mixture models for satellite image retrieval (2016, methodology): “The unscented transformation The unscented transformation (Julier and Uhlmann 1997a; Goldberger, Gordon, and Greenspan 2003) is a method to estimate the expectation EfðxÞ½hðxÞ of a function h(x) with respect to a Gaussian probability density function fðxÞ ¼ N ðX; μ; Þ: It has been successfully…”