paper-with-me

홈 › Papers

Practical Implementation of KalmanNet for Accurate Data Fusion in Integrated Navigation

2024-07-09 · IEEE Signal Processing Letters 2024 7 · Jian Song, Wei Mei; Yunfeng Xu, Qiang Fu, Lina Bu

The extended Kalman filter has been widely used in sensor fusion to achieve integrated navigation and localization. Efficiently integrating multiple sensors requires prior knowledge about their errors for setting the filter. The recently emerged KalmanNet managed to use recurrent neural networks to learn prior knowledge from data and carry out state estimation for problems under non-linear dynamics with partial information. In this letter, the KalmanNet is implemented for integrated navigation using data from GPS/Wheels and the Inertial Measurement Unit. Therein, a practical strategy for the training algorithm of truncated backpropagation through time is presented by taking advantage of the first-order Markov property of the system state of the Kalman filter, which improves the training robustness and performance of the existing KalmanNet. Experimental results on the Michigan NCLT dataset show that our fusion KalmanNet significantly outperforms the conventional EKF-based fusion algorithm with an improvement of 20%∼40% in average RMSE.

📄 PDF Abstract BibTeX

Code (1)

SongJgit/KalmanNet4SensorFusion pytorch

Tasks

Sensor FusionState Estimation

Similar Papers 제목 키워드 기반

Federated Data-Driven Kalman Filtering for State Estimation

2024-11-06 · Nikos Piperigkos, Alexandros Gkillas, Christos Anagnostopoulos, Aris S. Lalos

This paper proposes a novel localization framework based on collaborative training or federated learning paradigm, for highly accurate localization of autonomous vehicles. More specifically, we build on the standard appr…

Autonomous DrivingAutonomous VehiclesDecision MakingFederated Learning+2

Uncertainty in Data-Driven Kalman Filtering for Partially Known State-Space Models

2021-10-10 · Itzik Klein, Guy Revach, Nir Shlezinger, Jonas E. Mehr 외

Providing a metric of uncertainty alongside a state estimate is often crucial when tracking a dynamical system. Classic state estimators, such as the Kalman filter (KF), provide a time-dependent uncertainty measure from …

State Space Models

Bayesian KalmanNet: Quantifying Uncertainty in Deep Learning Augmented Kalman Filter

2023-09-06 · Yehonatan Dahan, Guy Revach, Jindrich Dunik, Nir Shlezinger

Recent years have witnessed a growing interest in tracking algorithms that augment Kalman Filters (KFs) with Deep Neural Networks (DNNs). By transforming KFs into trainable deep learning models, one can learn from data t…

Deep LearningState EstimationUncertainty Quantification

KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamics

2021-07-21 · Guy Revach, Nir Shlezinger, Xiaoyong Ni, Adria Lopez Escoriza 외

State estimation of dynamical systems in real-time is a fundamental task in signal processing. For systems that are well-represented by a fully known linear Gaussian state space (SS) model, the celebrated Kalman filter (…

State Estimation

Unsupervised Learned Kalman Filtering

2021-10-18 · Guy Revach, Nir Shlezinger, Timur Locher, Xiaoyong Ni 외

In this paper we adapt KalmanNet, which is a recently pro-posed deep neural network (DNN)-aided system whose architecture follows the operation of the model-based Kalman filter (KF), to learn its mapping in an unsupervis…