Centralized Fusion Algorithm Research Articles

Asynchronous Federated Learning Over Wireless Communication Networks

The conventional federated learning (FL) framework usually assumes synchronous reception and fusion of all the local models at the central aggregator and synchronous updating and training of the global model at all the agents as well. However, in a wireless network, due to limited radio resource, inevitable transmission failures and heterogeneous computing capacity, it is very hard to realize strict synchronization among all the involved user equipments (UEs). In this paper, we propose a novel asynchronous FL framework, which well adapts to the heterogeneity of users, communication environments and learning tasks, by considering both the possible delays in training and uploading the local models and the resultant staleness among the received models that has heavy impact on the global model fusion. A novel centralized fusion algorithm is designed to determine the fusion weight during the global update, which aims to make full use of the fresh information contained in the uploaded local models while avoiding the biased convergence by enforcing the impact of each UE’s local dataset to be proportional to its sample share. Numerical experiments validate that the proposed asynchronous FL framework can achieve fast and smooth convergence and enhance the training efficiency significantly.

Centralized fusion robust filtering for networked uncertain systems with colored noises, one-step random delay, and packet dropouts

This paper studies the estimation problem for multisensor networked systems with mixed uncertainties, which include colored noises, same multiplicative noises in system parameter matrices, uncertain noise variances, as well as the one-step random delay (OSRD) and packet dropouts (PDs). This study utilizes the centralized fusion (CF) algorithm to combing all information received by each sensor, which improve the accuracy of the estimation. By using the augmentation method, de-randomization method and fictitious noise techniques, the original uncertain system is transformed into an augment model with only uncertain noise variances. Then, for all uncertainties within the allowable range, the robust CF steady-state Kalman estimators (predictor, filter, and smoother) are presented based on the worst-case CF system, in light of the minimax robust estimation principle. To demonstrate the robustness of the proposed CF estimators, the non-negative definite matrix decomposition method and Lyapunov equation approach are employed. It is proved that the robust accuracy of CF estimator is higher than that of each local estimator. Finally, the simulation example applied to the uninterruptible power system (UPS) with colored noises and multiple uncertainties illustrates the effectiveness of the proposed CF robust estimation algorithm.

Low-Cost Hybrid Multisensor Fusion Method and Implementation for Production Intelligent Vehicles

Faced with cost limitation and 360-degree fusion and tracking requirement of production intelligent vehicles, this paper proposes a low-cost hybrid multi-sensor fusion method, which provides flexibility and scalability for multi-level information input and different sensor configurations. By combining radar, lane detection and ego vehicle information, we design a centralized fusion algorithm for 360-degree object tracking, which provides a low-computation multi-sensor association algorithm by a scheme of local sensor to global track association, and proves an optimal centralized estimator in the condition of multi-coordinate system Doppler information. To make the sensor fusion system compatible with multi-level information input and enhance the redundancy to improve security, a distributed fusion algorithm based on covariance intersection method is also designed as a part of fusion framework for the secondary fusion of high-level information. We validate the feasibility of our fusion method in an industrial-level controller with only 10% computing power consumption and build a ground truth system to quantitatively evaluate the method, which shows that our fusion method performs well on 360-degree object tracking and guarantees stable object IDs, and greatly improves the accuracy especially for sensor boundary regions. Furthermore, we also test and evaluate the performance of our fusion method in a variety of complex open road scenarios including expressway, curved road and lane fading scenarios.

System Identification and Controller Design of a Novel Autonomous Underwater Vehicle

Autonomous underwater vehicle is an effective tool for humans to explore the ocean. It can be used for the monitoring of underwater structures and facilities, which puts forward more accurate and stable requirements for the system operation of the autonomous underwater vehicle. This paper studies the system and structural design, including the parameter identification design and control system design, of a novel autonomous underwater vehicle called “Arctic AUV”. The dynamic mathematical model of the “Arctic AUV” was established, and the system parameter identification method based on the multi-sensor least squares centralized fusion algorithm was proposed. The simplification of the mathematical model of the robot was theoretically derived, and the online parameter identification and motion control were combined, so that the robot could cope with the influence of the arctic water velocity and external turbulence. Based on the hybrid control scheme of adaptive PID and predictive control, the accurate motion control of the “Arctic AUV” was realized. A prototype of “Arctic AUV” was developed, and system parameter identification experiments were carried out in indoor pool water. Hybrid adaptive and predictive control experiments were also carried out. The validity of the parametric design method in this paper was verified, and by comparative experiment, the effect of the control method proposed in this paper was better than the traditional method.

Cooperative space object tracking via universal Kalman consensus filter

Cooperative space object tracking using a sensor network plays an important role in space situational awareness and improves the accuracy, robustness, and dependability of space object tracking over a single sensor. However, different sensors may have different sampling rates and may work asynchronously. It is difficult to fuse these asynchronous measurements together and track space objects in time using traditional consensus-based filters, which require synchronous measurements. To overcome this restriction, a universal Kalman consensus filter (UKCF) is proposed. Based on the state transition matrix, each sensor can fuse the received information within a measurement period and track the object over time. Sensors with arbitrary sampling rates and working times can be incorporated into the cooperative tracking system. Optical observations are an efficient way to track space objects, especially medium- or high-orbit objects. The ground-based and space-based optical (SBO) tracking models are established first. Then, a centralized fusion algorithm for an asynchronous sensor network is deduced. Based on this algorithm, the topology for an asynchronous sensor network is established and the UKCF is produced. To demonstrate its performance, cooperative tracking scenarios for a geosynchronous object that use SBO sensors with different working times and use both SBO and ground-based optical sensors with different sampling rates are simulated. As shown in the paper, the UKCF, which has a similar performance relative to the KCF but expands its application range, is more suitable for real cooperative space object tracking.

Asynchronous multi-rate multi-sensor fusion based on random finite set

Abstract This paper considers the asynchronous sensor fusion problem for an arbitrary number of sensors with different sampling rates in the framework of the random finite set (RFS) theory. By sequentially predicting and updating the posteriors with measurements according to the arrival time sequence of measurement sets, a centralized asynchronous fusion algorithm, centralized Sequential Processing (SP), is proposed first. It is optimal due to the usage of original measurement information. Considering the reliability, survivability and communication bandwidth as well as flexibility of output time, two distributed asynchronous fusion algorithms are also proposed by assuming that the process of tracking among sensors is independent. The first distributed asynchronous fusion algorithm, namely Batch Generalization Covariance Intersection (B-GCI), utilizes all the predicted local posteriors (LPs) from different sensors and fuses them simultaneously at the fusion center (FC) based on GCI rule, which avoids the complicated calculations of cross-covariance among the LPs of sensors. Considering the large computational burden of the B-GCI fusion algorithm, another one method, Sequential GCI (S-GCI) fusion algorithm, is proposed. The method sequentially fuses the predicted LPs in pairs based on GCI rule at the FC. Performance of proposed three algorithms, including a centralized fusion algorithm and two distributed fusion algorithms, is realized by using Gaussian Mixture Probability Hypothesis Density (GM-PHD) filter and some numerical simulations are given.

Centralized Fusion Based on Interacting Multiple Model and Adaptive Kalman Filter for Target Tracking in Underwater Acoustic Sensor Networks

Underwater acoustic sensor networks (UASNs) play an important role in the ocean's protection. They can realize real-time data collection, monitoring, exploration, and many other underwater applications by connecting and coordinating seafloor sensors and underwater vehicles. To achieve these application objectives, such as fishes tracking in biological monitoring field and submarines tracking in military field, target tracking is one of the key techniques. This paper presents a centralized fusion algorithm based on the interacting multiple models and the adaptive Kalman filter (IMMCFAKF) for target tracking in UASNs. Specifically, by introducing an adaptive forgetting factor into the optimal centralized fusion Kalman filter algorithm, the optimal centralized fusion adaptive Kalman filter (CFAKF) algorithm is obtained first. Then, combining the superiorities of both the optimal CFAKF algorithm and the conventional IMM algorithm, the optimal IMMCFAKF is achieved. The numerical simulations are provided to demonstrate the effectiveness of the proposed optimal IMMCFAKF algorithm.

Robust centralized and weighted measurement fusion white noise deconvolution estimators for multisensor systems with mixed uncertainties

SummaryEstimating the input signal of a system is called deconvolution or input estimation. The white noise deconvolution has important applications in oil seismic exploration, communications, and signal processing. This paper addresses the design of robust centralized fusion (CF) and weighted measurement fusion (WMF) white noise deconvolution estimators for a class of uncertain multisensor systems with mixed uncertainties, including uncertain‐variance multiplicative noises in measurement matrix, missing measurements, and uncertain‐variance linearly correlated measurement and process white noises. By introducing the fictitious noise, the considered system is converted into one with only uncertain noise variances. According to the minimax robust estimation principle, based on the worst‐case system with the conservative upper bounds of uncertain noise variances, the robust CF and WMF time‐varying white noise deconvolution estimators (predictor, filter, and smoother) are presented in a unified framework. Applying the Lyapunov equation approach, their robustness is proved in the sense that their actual estimation error variances are guaranteed to have the corresponding minimal upper bounds for all admissible uncertainties. Using the information filter, their equivalence is proved. Their accuracy relations are proved. The computational complexities are analyzed and compared. Compared with the CF algorithm, the WMF algorithms can significantly reduce the computational burden when the number of sensors is larger. The corresponding robust fused steady‐state white noise deconvolution estimators are also presented. A simulation example with respect to the multisensor IS‐136 communication systems shows the effectiveness and correctness of the proposed results.

Robust Centralized and Weighted Measurement Fusion Kalman Predictors with Multiplicative Noises, Uncertain Noise Variances, and Missing Measurements

For multisensor uncertain systems with mixed uncertainties, including multiplicative noises in state and process noise transition matrices, uncertain-variance multiplicative and additive white noises, and missing measurements, this paper addresses the problem of designing robust centralized fusion (CF) and weighted measurement fusion (WMF) Kalman predictors. By introducing fictitious noises, the system under study is converted into a system with only uncertain noise variances. According to the minimax robust estimation principle, which is based on the worst-case system with conservative upper bounds of uncertain noise variances, the robust CF and WMF time-varying Kalman predictors are presented in a unified framework. Using the Lyapunov equation, the robustness of these predictors is proven in the sense that the actual prediction error variances are guaranteed to have the corresponding minimal upper bounds for all admissible uncertainties. Using an information filter, they are proven to have the same robust and actual accuracies. The complexity analysis shows that when the number of sensors is larger, the WMF algorithm more significantly reduces the computational burden than the CF algorithm. The corresponding robust fused steady-state Kalman predictors are also presented. The three modes of convergence in a realization among the time-varying and steady-state robust fused Kalman predictors are proposed and proven using the dynamic error system analysis method. Two simulation examples, autoregressive moving average signal processing and an uninterruptible power system, demonstrate the effectiveness of the proposed methods.

Robust centralized and weighted measurement fusion Kalman estimators for multisensor systems with multiplicative and uncertain-covariance linearly correlated white noises

This paper addresses the design of robust centralized and weighted measurement fusion (WMF) Kalman estimators for a class of uncertain multisensor systems with linearly correlated measurement and process white noises. The uncertainties of the systems include the same multiplicative noises in state and measurement matrices, and the uncertain noise variances. By introducing the fictitious noises to compensate the multiplicative noises, the system under consideration is converted into one with only uncertain noise variances. According to the minimax robust estimation principle, based on the worst-case system with the conservative upper bounds of the noise variances, the robust centralized and two WMF time-varying Kalman estimators (predictor, filter, and smoother) are presented in a unified framework. Their robustness is proved by using Lyapunov equation approach, such that their actual estimation error variances are guaranteed to have the corresponding minimal upper bounds for all admissible uncertainties. Using the information filter, their equivalence is proved. Their accuracy relations are proved. The computational complexities are analyzed and compared. Compared with the centralized fusion algorithm, the two WMF algorithms can significantly reduce the computational burden when the number of sensors is larger. The corresponding robust local and fused steady-state Kalman estimators are also presented, and the convergence in a realization between the time-varying and steady-state robust fused Kalman estimators is proved by the dynamic error system analysis (DESA) method. A simulation example with application to signal processing to show the effectiveness and correctness of the proposed results.

Robust centralized and weighted measurement fusion Kalman estimators for uncertain multisensor systems with linearly correlated white noises

This paper addresses the design of robust centralized fusion (CF) and weighted measurement fusion (WMF) Kalman estimators for a class of uncertain multisensor systems with linearly correlated white noises. The uncertainties of the systems include multiplicative noises, missing measurements, and uncertain noise variances. By introducing the fictitious noises, the considered system is converted into one with only uncertain noise variances. According to the minimax robust estimation principle, based on the worst-case system with the conservative upper bounds of uncertain noise variances, the robust CF and WMF time-varying Kalman estimators (predictor, filter, and smoother) are presented in a unified framework. Applying the Lyapunov equation approach, their robustness is proved in the sense that their actual estimation error variances are guaranteed to have the corresponding minimal upper bounds for all admissible uncertainties. Using the information filter, their equivalence is proved. Their accuracy relations are proved. The computational complexities of their algorithms are analyzed and compared. Compared with CF algorithm, the WMF algorithm can significantly reduce the computational burden when the number of sensors is larger. A robust weighted least squares (WLS) measurement fusion filter is also presented only based on the measurement equation, and it is proved that the robust accuracy of the robust CF or WMF Kalman filter is higher than that of robust WLS filter. The corresponding robust fused steady-state estimators are also presented, and the convergence in a realization between the time-varying and steady-state robust fused estimators is proved by the dynamic error system analysis (DESA) method. A simulation example shows the effectiveness and correctness of the proposed results.

Cooperative space object tracking using space-based optical sensors via consensus-based filters

Cooperative tracking plays a key role in space situation awareness for scenarios with a limited number of observations or poor performance of a single sensor or both. To use the information from multiple networked sensors, both centralized and decentralized fusion algorithms can be used. Compared with centralized fusion algorithms, decentralized fusion algorithms are more robust in terms of communication failure and computational burden. One popular distributed estimation approach is based on the average consensus that asymptotically converges to the estimate by multiple exchanges of neighborhood information. Consensus-based algorithms have become popular in recent years due to the fact that they do not require global knowledge of the network or routing protocols. The main contributions of this paper are 1) an effective space-based object (SBO) measurement model that considers the geometric relation of the Sun, the space object, the SBO sensor, and the Earth; 2) two consensus-based filters, the information-weighted consensus filter (ICF) and the Kalman consensus filter (KCF), are used to track space objects by using multiple SBO sensors; and 3) the cubature rule-embedded ICF (Cub-ICF) and KCF (Cub-KCF) are proposed to improve the accuracy of the ICF and KCF. Three scenarios that contain one or two space objects and four SBOs are used to test proposed algorithms. We also compare the consensus-based space object tracking algorithms with the centralized extended information filter (centralized EIF) and the centralized cubature information filter (centralized Cub-IF). The simulation results indicate that 1) cooperative space object tracking algorithms provide better results than algorithms using a single sensor, 2) the consensus-based tracking algorithms can achieve performance close to that of the centralized algorithms, and 3) the Cub-ICF and Cub-KCF outperform the conventional ICF and KCF for a challenging space object tracking case shown in the paper. The proposed Cub-ICF and Cub-KCF algorithms should facilitate the application of using consensus-based filters for cooperative space object tracking.

Centralized Fusion Algorithms Based on EKF for Multisensor Non-linear Systems

Aiming at a kind of nonlinear multisensor systems, we study three classic nonlinear centralized fusion algorithms based on the extend Kalman filter (EKF) and extend some fusion theories for linear dynamic systems to nonlinear systems. On the basis of extend information filter (EIF), three kinds of fusion algorithms such as augmented measurements fusion, measurements weighted fusion and sequential filtering fusion are presented. Afterwards, we compare estimate accuracies of the three nonlinear fusion algorithms, and discuss the exchanging property of measurement's update order. The results are as follows. Firstly, when measurement properties are identical, the estimate of the augmented measurements fusion algorithm and the measurements weighted fusion algorithm are equivalcent. Secondly, the estimate accuracy of the sequential filtering fusion does not hold completely functional equivalence in linear systems as the other two fusion methods. Thirdly, the exchanging property of the measurement s update order of nonlinear sequential filtering fusion can no longer be guaranteed. Four examples based on bearings-only tracking are shown to demonstrat the validity of the conclusions.

Asynchronous Multi-Sensor Fusion Algorithm Based on the Steady-State Kalman Filter

The paper studies an asynchronous multi-sensor fusion problem based a kind of asynchronous multi-sensor dynamic system. Firstly, this paper presents a centralized fusion algorithm based on the Kalman filter without ignoring the correlation between process noise and augmented measurement noise. It is optimal in minimum mean square error. Then using the steady-state Kalman filter to estimate and fuse. Secondly, in the condition that the local sensor estimation error is associated, a distributed fusion algorithm is given by utilizing S.L. Sun optimal information fusion criterion in minimum error covariance matrix trace at fusion center. In distributed algorithm, the value transmitting to the fusion center is determined by the local sensor estimation based on the steady-state Kalman filter and one step predictive value. Since both optimal fusion algorithm standards are different, so the fusion precision will vary. Finally the effectiveness of the algorithm is verified by computer simulation.

Globally optimal distributed Kalman filtering fusion

The goal of this paper is to give a survey of the previous works on the globally optimal distributed Kalman filtering fusion with classical and nonclassical dynamic systems. Then, we summarize some of our recent results on nonclassical and unideal dynamic systems, including dynamic systems with feedback and cross-correlated sensor measurement noises, dynamic systems with random parameter matrices, and dynamic systems with out-of-sequence or asynchronous measurements. The global optimality in this paper means that the distributed Kalman filtering fusion is exactly equal to the corresponding centralized optimal Kalman filtering fusion. Therefore, not only all of the proposed fusion algorithms here are distributed, but performance as good as that of the corresponding optimal centralized fusion algorithms is achieved. There also exist many papers for other fusion optimality (e.g., the optimal convex linear estimation/compression fusion) discussion, which are not involved in this paper.

Multi-Sensor Centralized Fusion without Measurement Noise Covariance by Variational Bayesian Approximation

The work presented here solves the multi-sensor centralized fusion problem in the linear Gaussian model without the measurement noise variance. We generalize the variational Bayesian approximation based adaptive Kalman filter (VB_AKF) from the single sensor filtering to a multi-sensor fusion system, and propose two new centralized fusion algorithms, i.e., VB_AKF-based augmented centralized fusion algorithm and VB_AKF-based sequential centralized fusion algorithm, to deal with the case that the measurement noise variance is unknown. The simulation results show the effectiveness of the proposed algorithms.

Estimation Fusion with General Asynchronous Multi-Rate Sensors

The asynchronous estimation fusion problem is investigated for an arbitrary number of sensors with arbitrary sampling rates. By constructing an augmented measurement equation at the fusion time instant, a centralized asynchronous fusion algorithm is developed based on the Kalman filter first without ignoring the correlation between the process noise and the augmented measurement noise. It is optimal in the minimum mean-squared error (MMSE) sense. A distributed asynchronous fusion algorithm is then proposed by reconstructing the optimal centralized fusion result with asynchronous local estimates and their error covariance matrices. It is equivalent to the centralized fusion algorithm under the full-rate communication assumption and outperforms the latter when at least one sensor communicates with the fusion center at a lower rate than its sampling rate. Compared with the existing distributed fusion algorithms for asynchronous sensors, the proposed distributed fusion algorithm avoids the complicated calculation of cross-covariance matrices between each pair of asynchronous local estimates. The communication burden can also be reduced since neither sensor measurement matrices nor local filtering gains need to be transmitted to the fusion center. Moreover all available local estimates are utilized as well as the fused one-step prediction. Some practical considerations of the proposed distributed fusion algorithm are also discussed. Performance of the proposed centralized and distributed fusion algorithms are illustrated through numerical simulations.