Improved IMM Algorithm based on RNNs

Deng, Lichuan; Li, Da; Li, Ruifang

doi:10.1088/1742-6596/1518/1/012055

Cited by 16 publications

(11 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of neural networks for non-linear filtering problems is very common in the literature, e.g., in online tracking prediction [Gao et al, 2019, Dan Iter, 2016, Coskun et al, 2017, fa Dai et al, 2020, Ullah et al, 2019, near-online prediction [Kim et al, 2018], and offline prediction [Liu et al, 2019b]. Neural networks were also considered for related problems such as data association [Liu et al, 2019a], model-switching [Deng et al, 2020], and sensors fusion [Sengupta et al, 2019].…”

Section: Related Workmentioning

confidence: 99%

“…They incorporate information from a monocular camera and a mmWave radar, and show how to handle failures in either of the sensors. Deng et al [2020] consider standard models as building blocks for IMM, and replace the mode-transition matrix with an LSTM that estimates the transition probabilities dynamically. Peng and Gu [2011] replace the standard building blocks of IMM with modes that are dedicatedly-designed to track highly-maneuvering targets.…”

Section: A Preliminaries: Extendedmentioning

confidence: 99%

See 1 more Smart Citation

The Fragility of Noise Estimation in Kalman Filter: Optimization Can Handle Model-Misspecification

Greenberg¹,

Mannor²,

Yannay³

2021

Preprint

View full text Add to dashboard Cite

Determining the noise parameters of a Kalman Filter (KF) has been researched for decades. The research focuses on the task of estimation of the noise under various conditions, since precise noise estimation is considered equivalent to errors minimization. However, we show that even a small violation of KF assumptions can significantly modify the effective noise, breaking the equivalence between the tasks and making noise estimation an inferior strategy. We show that such violations are very common, and are often not trivial to handle or even notice. Consequentially, we argue that a robust solution is needed -rather than choosing a dedicated model per problem. To that end, we use a simple parameterization to apply gradient-based optimization efficiently to the symmetric and positive-definite parameters of KF. In radar tracking and video tracking, we show that the optimization improves both the accuracy of KF and its robustness to design decisions. In addition, we demonstrate how a neural network model can seem to reduce the errors significantly compared to a KF -and how this reduction vanishes once the KF is optimized. This indicates how complicated models can be wrongly identified as superior to KF, while in fact they were merely over-optimized.Preprint. Under review.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: A Preliminaries: Extendedmentioning

confidence: 99%

The Fragility of Noise Estimation in Kalman Filter: Optimization Can Handle Model-Misspecification

Greenberg¹,

Mannor²,

Yannay³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Most of the approaches based on MM algorithms provide acceptable tracking performances only when the dynamic target motion can be described by a small set of models, otherwise, a degradation appears with the computational burden increment [13]. Furthermore, being a model-based approach, the most shortcoming of the IMM algorithm arises when models used are not representative of the target dynamics [13], [14]. Indeed, since the system model is only an approximation of the real plant, practical problems are inevitably affect by errors modeling, which can significantly compromise the the estimation quality [4].…”

Section: Introductionmentioning

confidence: 99%

Long Short-Term Memory-Based Neural Networks for Missile Maneuvers Trajectories Prediction^⋆

Lui

Tartaglione

Conti³

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Due to its extensive applications in different contexts, moving target tracking has become a hot topic in the last years, above all in the military field. Specifically, missile tracking research received a great effort, mainly for its importance in terms of security and safety. Herein, traditional solutions, e.g. Interacting Multiple Model (IMM) based on the Kalman estimation theory, achieve good performance under the main restrictive assumption of the a priori knowledge of the target model, so neglecting the unavoidable presence of model uncertainties and limiting the achievable tracking accuracy only by the presence of the measurement noise. With the specific aim of overcoming this narrowness, this work investigates the capability of deep neural networks in predicting the missile maneuvering trajectories in a model-free fashion. The idea is to leverage the Long-Short Term Memory (LSTM) net due to its excellent capability in learning long-term dependencies of temporal information. Two different LSTM-based architectures have been hence designed to predict both position and velocity of a missile using raw and noisy measurements provided by a realistic radar system, exploiting a large database abundant of realistic off-line data. Training results and theoretical derivations are verified through non-trivial scenarios in order to assess the capability of predicting unknown and realistic 3D missile maneuvers. Finally, the proposed approach has been also compared with a performing model-based IMM algorithm, suitably tuned to deal with realistic missile maneuvers, confirming the excellent generalization abilities of the developed data-driven architectures for different datasets.

show abstract

“…Ref. [18] uses the Recurrent Neural Networks (RNN) to identify the motion model of the target, then the recognition accuracy and speed of IMM is improved. Ref.…”

Section: Introductionmentioning

confidence: 99%

A hybrid‐driven continuous‐time filter for manoeuvering target tracking

Xiong¹,

Zhu²,

Cui³

2022

IET Radar Sonar & Navi

View full text Add to dashboard Cite

This paper considers the problem of target tracking in complex manoeuvering scenarios with a lack of relevant prior knowledge. This is a challenge for classical model‐based manoeuvering target tracking algorithms because they rely heavily on accurate domain and prior knowledge of target motion. To address this problem, we propose a hybrid‐driven continuous‐time filter algorithm in this paper, which combines the advantages of the model‐driven and data‐driven. We use the stochastic differential equation (SDE) with the acceleration model as the basic framework of the proposed algorithm. In order to deal with unpredictable manoeuvres and unknown perturbations, we adopt neural networks as data‐driven to estimate target accelerations and compensations of composite perturbations in real time using historical and current measurements. And the direction of gradient descent of the neural network is constrained by the motion model, thus the learning efficiency of the network and the interpretability of the proposed algorithm is improved. The proposed algorithm can simultaneously utilise historical trajectory information and domain knowledge as hybrid‐driven to achieve complex manoeuvering target tracking with little prior information. Experimental results demonstrate the superiority of our algorithm in tracking accuracy, robustness and environmental adaptability.

show abstract

Improved IMM Algorithm based on RNNs

Cited by 16 publications

References 2 publications

The Fragility of Noise Estimation in Kalman Filter: Optimization Can Handle Model-Misspecification

The Fragility of Noise Estimation in Kalman Filter: Optimization Can Handle Model-Misspecification

Long Short-Term Memory-Based Neural Networks for Missile Maneuvers Trajectories Prediction^⋆

A hybrid‐driven continuous‐time filter for manoeuvering target tracking

Contact Info

Product

Resources

About

Improved IMM Algorithm based on RNNs

Cited by 16 publications

References 2 publications

The Fragility of Noise Estimation in Kalman Filter: Optimization Can Handle Model-Misspecification

The Fragility of Noise Estimation in Kalman Filter: Optimization Can Handle Model-Misspecification

Long Short-Term Memory-Based Neural Networks for Missile Maneuvers Trajectories Prediction⋆

A hybrid‐driven continuous‐time filter for manoeuvering target tracking

Contact Info

Product

Resources

About

Long Short-Term Memory-Based Neural Networks for Missile Maneuvers Trajectories Prediction^⋆