Adaptive Particle Filter Algorithm Research Articles

Adaptive MSSRCPF filtering based on constrained optimization and fading memory for SINS/GNSS integrated navigation

To address particle degeneracy and the challenge of selecting importance density functions in traditional particle filters for complex nonlinear systems, we propose an adaptive mixed-order spherical simplex-radial cubature particle filter algorithm based on constrained optimization and fading memory. This algorithm integrates constrained optimization, an adaptive fading memory strategy, adaptive adjustment of particle numbers and weights, and the advantages of mixed-order spherical simplex-radial cubature Kalman filtering. By designing the importance density function using a mixed-order integration method, the algorithm significantly improves filtering accuracy over traditional cubature Kalman filters while maintaining lower computational complexity than high-order cubature Kalman filter methods. The adaptive fading memory strategy dynamically adjusts the covariance matrix, enhancing sensitivity to current measurement information and reducing the influence of historical data. By dynamically adjusting the noise covariance matrix and constraining the ratio between the error covariance and measurement noise covariance, the algorithm improves the convergence speed and accuracy of state estimation. An adaptive particle number and weight adjustment strategy based on effective sample size and entropy regularization dynamically adjusts the number of particles to reduce computational complexity while ensuring filtering accuracy, and employs entropy regularization to suppress weight over-concentration, thereby reducing the impact of outliers on the filtering results. Simulation results demonstrate that in complex SINS/GNSS integrated navigation systems, especially under high-noise and nonlinear conditions, the proposed algorithm significantly improves positioning accuracy compared to the CPF method, with the maximum latitude error reduced by approximately 54.8%, the maximum longitude error reduced by approximately 40.5%, and the maximum altitude error reduced by approximately 68.3%. Compared to the FMCPF method, the proposed algorithm also shows clear advantages in positioning accuracy, convergence speed, and computational efficiency, validating its effectiveness and practicality in complex environments.

Vehicle dynamics prediction via adaptive robust unscented particle filter

Accurate knowledge of the vehicle dynamics response is a critical aspect to improve handling performance while ensuring safe driving at the same time. However, it poses a challenge since not all the quantities of interest can be directly measured due to cost and/or technological reasons. Therefore, combining the principle of robust filtering and unscented particle filtering algorithm, a filter estimation method of vehicle state is proposed to estimate driving state parameters of a vehicle. The adaptive robust unscented particle filter (ARUPF) is used to realize the longitudinal and lateral velocity as well as the side slip angle of the vehicle. The CarSim and Matlab/Simulink co-simulation platform is established to verify the estimation algorithm. The results show that based on the adaptive robust unscented particle filter algorithm, the vehicle driving states can be estimated, the measurement parameters can be effectively filtered, and the estimation accuracy is higher.

Estimation of the Charge State in Lithium-ion Batteries Based on an Adaptive Particle Filter

Lithium-ion batteries have the advantages of high energy density, long life, and environmental friendliness, and are widely used as sources of energy in new energy vehicles. The charge state (SOC) of lithium-ion battery greatly represents the remaining service time of the battery, and in electric vehicles, it greatly determines the range of the electric vehicle. Therefore, how to estimate SOC from physical quantities such as end voltage and end current is crucial. This paper introduces the common lithium-ion battery charge state estimation method and its state model, and estimates the charge state based on the adaptive particle filter algorithm.

Vehicle state and parameter estimation based on adaptive robust unscented particle filter

In order to solve the problem that the measured values of key state parameters such as the lateral velocity and yaw rate of the vehicle are easily interfered by random errors, a filter estimation method of vehicle state is proposed based on the principle of robust filtering and the unscented particle filter algorithm. Based on the establishment of a 3-DOF non-linear dynamic model and the Dugoff tire model of the vehicle, the adaptive robust unscented particle filter(ARUPF) is used to filter and estimate the parameters of the vehicle state, and to realize the longitudinal and lateral speed as well as the yaw rate of the vehicle during the driving process. The simulation and the real vehicle test results show that based on the adaptive robust unscented particle filter algorithm, the vehicle driving state estimation can be realized, the measurement parameters can be effectively filtered, and the estimation accuracy is high.

A SOE estimation method for lithium batteries considering available energy and recovered energy

State of energy (SOE) is a critical index of lithium battery. The problem of the inaccurate available energy and recovered energy of lithium battery affects the accuracy of SOE estimation. In order to solve the problem, this paper proposes a method to estimate the available discharge energy of lithium batteries based on response surface model. In this method, the energy efficiency of lithium batteries in different states is obtained by establishing the relationship model of external charge voltage and external discharge voltage, so as to estimate the actual available energy of lithium batteries in different charge states. On this basis, a correction method based on radial basis function (RBF) neural network is proposed to estimate the actual energy released by the recovered energy when the current direction of the battery is changed. The proposed energy correction method is combined with the adaptive particle filter algorithm to estimate SOE. This method is not limited to the assumption of Gaussian function and can accurately predict the noise variance, so as to improve the estimation accuracy of SOE. Simulations under urban dynamometer driving schedule (UDDS) are conducted, and the result shows that the proposed method can effectively estimate the battery energy and improve the accuracy of SOE estimation.

A novel combined estimation method of online full‐parameter identification and adaptive unscented particle filter for Li ‐ion batteries SOC based on fractional‐order modeling

Accurate estimation of the state of charge (SOC) of Li-ion battery can ensure the reliability of the storage system. A combined estimator of online full-parameter identification and adaptive unscented particle filter for Li-ion battery SOC based on an improved fractional-order model is proposed, which overcomes the shortcomings of the traditional SOC cumulative error and the difficulty of OCV acquisition. The proposed adaptive fractional unscented particle filter algorithm introduces fractional parameters as hidden parameters and reduces the complexity of the algorithm iteration by reducing the number of particles. At the same time, the noise adaptive algorithm based on the residual sequence can solve the divergence problem of the filter and improve the adaptability of the algorithm. To verify the feasibility of the algorithm under complex operating conditions, the urban dynamometer driving schedule dynamic working conditions of Li-ion batteries are verified. The experimental results show that the evaluation index of the algorithm is the best, the RMSE is 0.67%, and the SOC estimation is more accurate. It shows that the algorithm has strong robustness and fast convergence.

An Adaptive Evolving Fuzzy Technique for Prognosis of Dynamic Systems

The evolving fuzzy technique is a recent development in the soft-computing field that has shown some promising results in applications such as control, classification, and short-term prediction. However, evolving fuzzy techniques still have challenges in terms of high-speed processing of cluster/rule generation, especially in long-term prediction applications due to the broader distribution of the input space. These factors can lead to problems such as overfitting in optimization and high computational costs, which could limit their applications in real-time monitoring. In this article, an adaptive evolving fuzzy (AEF) technique consisting of two novel aspects is developed to tackle these problems. First, an error-assessment method is suggested to monitor the trend of the cumulative training errors and to control the fuzzy cluster evolving process. Second, an adaptive particle filter algorithm is proposed to optimize the fuzzy clusters in order to enhance incremental learning and improve modeling efficiency. The effectiveness of the proposed AEF predictor is verified by simulation tests; it is also implemented for battery remaining useful life forecasting. Test results have shown that the proposed AEF technique can effectively capture the system's dynamic characteristics with fewer rules and can provide more flexibility in fuzzy modeling.

A Novel Cooperative Localization Method Based on IMU and UWB.

In this paper, a range-based cooperative localization method is proposed for multiple platforms of various structures. The localization system of an independent platform might degrade or fail due to various reasons such as GPS signal-loss, inertial measurement unit (IMU) accumulative errors, or emergency reboot. It is a promising approach to solve this problem by using information from neighboring platforms, thus forming a cooperative localization network that can improve the navigational robustness of each platform. Typical ranging-based ultra-wideband (UWB) cooperative localization systems require at least three auxiliary nodes to estimate the pose of the target node, which is often hard to meet especially in outdoor environment. In this work, we propose a novel IMU/UWB-based cooperative localization solution, which requires a minimum number of auxiliary nodes that is down to 1. An Adaptive Ant Colony Optimization Particle Filter (AACOPF) algorithm is customized to integrate the dead reckoning (DR) system and auxiliary nodes information with no prior information required, resulting in accurate pose estimation, while to our knowledge the azimuth have not been estimated in cooperative localization for the insufficient observation of the system. We have given the condition when azimuth and localization are solvable by analysis and by experiment. The feasibility of the proposed approach is evaluated through two filed experiments: car-to-trolley and car-to-pedestrian cooperative localization. The comparison results also demonstrate that ACOPF-based integration is better than other filter-based methods such as Extended Kalman Filter (EKF) and traditional Particle Filter (PF).

Joint detection and tracking algorithm for cognitive radar based on parallel structure of EKF and particle filter

In order to reduce the uncertainty of radar manoeuvring target tracking (RMTT) in cluttered background, a joint detection and tracking algorithm based on cognitive radar is proposed. First, a prism structure resolution cell of time-delay, Doppler and azimuth is designed. Then, an approximate expression of measurement error covariance including waveform and detection threshold parameters is given. Then, based on the idea of human brain perception-action cycle, a joint waveform and detection threshold adaptive tracking algorithm based on minimum information entropy criterion is proposed. Finally, a cognitive structure adaptive particle filter (CSAPF) algorithm, based on parallel structure of extended Kalman filter (EKF) and particle filter, are used with Probabilistic Data Association (PDA) algorithm for RMTT. During the process, CSAPF-PDA can always obtain the best tracking performance with the minimum number of particle samples, thus effectively taking into account the tracking accuracy and efficiency. The effectiveness of the proposed algorithm is verified by simulation experiments.

Cognitive structure adaptive particle filter for radar manoeuvring target tracking

The accuracy and efficiency of the particle filter algorithm partly depend on the number of particles used in the estimation. The number of particles is specified beforehand and kept fixed in the process of radar manoeuvring target tracking (MTT). In practice this may be highly inappropriate since it ignores the uncertainty in the models and the varying dynamics of the processes. A cognitive structure adaptive particle filter (CSAPF) algorithm is proposed to increase the accuracy and efficiency by adapting the number of particles online. The name CSAPF is due to the fact that the authors change the number of particles dynamically with radar's real-time perceptual information entropy for MTT. The authors cognitive structure approach chooses a transmitted waveform to improve tracking accuracy and chooses the lower bound of required particles to improve tracking efficiency. Monte–Carlo simulation results show that the approach has significant improvements over the particle filter with a fixed number of particles and over the fixed waveform particle filter algorithm.

Multi-Camera Active-Vision for Markerless Shape Recovery of Unknown Deforming Objects

A novel multi-camera active-vision reconfiguration method is proposed for the markerless shape recovery of unknown deforming objects. The proposed method implements a model fusion technique to obtain a complete 3D mesh-model via triangulation and a visual hull. The model is tracked using an adaptive particle filtering algorithm, yielding a deformation estimate that can, then, be used to reconfigure the cameras for improved surface visibility. The objective of reconfiguration is maximization of the total surface area visible through stereo triangulation. The surface area based objective function directly relates to maximizing the accuracy of the shape recovered, as stereo triangulation is more accurate than visual hull building when the number of viewpoints is limited. The reconfiguration process comprises workspace discretization, visibility estimation, optimal stereo-pose selection, and path planning to ensure 2D tracked feature consistency. In contrast to other reconfiguration techniques that rely on a priori known, and at times static, object models, our method focuses on a priori unknown deforming objects. The proposed method operates on-line and has been shown to outperform static-camera based systems through extensive simulations and experiments with an increased surface visibility in the presence of occluding obstacles.

Localized recursive spatial-temporal state quantification method for data assimilation of wildfire spread simulation

Data assimilation is a procedure to improve the state inference by assimilating the real-time observation data into dynamic systems, such as wildfire spread simulation. Various techniques are used for data assimilation, such as sequential Monte Carlo methods, also called particle filters. In the standard sequential Monte Carlo methods, the used number of particles is the same during the entire process and their convergence is not measured or characterized for runtime state estimation. Therefore, to guarantee the convergence, an abundance of particles is required so that they can be widely distributed in the state space to converge to the true posterior of the system state. In the application of wildfire spread simulation, the spatial states are large and the system behaves in a heterogeneous manner in different fire areas. The heterogeneous feature and the spatially and temporally dynamic behavior of the wildfire spread simulation cause the state inference uncertainty to be dynamically changed. In this paper, we propose the localized recursive spatial-temporal state quantification method to measure the convergence of particles at runtime and apply various approaches to improve the state inference. To show its effectiveness, we apply two different algorithms – the adaptively perturbing the localized state space algorithm and the adaptive particle filtering algorithm – to the localized recursive spatial-temporal state quantification method to improve the state estimation and enhance the performance respectively. The designed experiments are used to show the effectiveness of the adaptively perturbing the localized state space algorithm and the adaptive particle filtering algorithm in the improvement of the state estimation and the performance of data assimilation in wildfire spread simulation.

A model-based adaptive state of charge estimator for a lithium-ion battery using an improved adaptive particle filter

Obtaining accurate parameters, state of charge (SoC) and capacity of a lithium-ion battery is crucial for a battery management system, and establishing a battery model online is complex. In addition, the errors and perturbations of the battery model dramatically increase throughout the battery lifetime, making it more challenging to model the battery online. To overcome these difficulties, this paper provides three contributions: (1) To improve the robustness of the adaptive particle filter algorithm, an error analysis method is added to the traditional adaptive particle swarm algorithm. (2) An online adaptive SoC estimator based on the improved adaptive particle filter is presented; this estimator can eliminate the estimation error due to battery degradation and initial SoC errors. (3) The effectiveness of the proposed method is verified using various initial states of lithium nickel manganese cobalt oxide (NMC) cells and lithium-ion polymer (LiPB) batteries. The experimental analysis shows that the maximum errors are less than 1% for both the voltage and SoC estimations and that the convergence time of the SoC estimation decreased to 120s.

Target tracking algorithm based on adaptive strong tracking particle filter

The primary problem of tracking filtering algorithms is the tracking stability and effectiveness of target states. Based on the particle filter, an adaptive strong tracking particle filter algorithm is proposed in this study. According to the residual between actual measurement values and predicted measurement values of every moment, adjustment of the forgetting factor and the weakening factor is adaptively conducted. Then, by calculating the fading factor, transfer covariance matrix and filter gain of the system are obtained to estimate the particles state value. Updating the importance density function can alleviate the degradation phenomenon of particle filter, and it contributes to effective estimation for the optimal state value of a target. The simulation results demonstrate that the proposed algorithm provides a better tracking precision. In addition, when the target states make mutations, the proposed algorithm can track the mutation states of moving targets effectively and improve the stability of the system.

Adaptive Noise Parameter Determination Based on a Particle Filter Algorithm

Due to the growing number of vehicles using the national road networks that link major urban centers, traffic noise is becoming a major issue in relation to the transportation system. Thus, it is important to determine noise model parameters to predict road traffic noise levels as part of an environmental assessment, according to traffic volume and pavement surface type. To determine the parameters of a noise prediction model, statistical pass-by and close proximity tests are required. This paper provides a parameter determination procedure for noise prediction models through an adaptive particle filter (PF) algorithm, based on using a weigh-in-motion system, which obtains vehicle velocities and types, as well as step-up microphones, which measure the combined noises emitted by various vehicle types. Finally, an evaluation of the adaptive noise parameter determination algorithm was carried out to assess the agreement between predictions and measurements.

The Adaptive Federal Unscented Particle Filter Algorithm with Applications in All-Attitude Integrated BDS/INS Navigation System

In order to improve the attitude accuracy, the thesis establishes the all-attitude integrated BDS/INS navigation nonlinear system model based on the position, velocity, attitude by adding the BDS’s attitude measurement information into the measurement equation of the traditional BDS/INS integrated navigation nonlinear system model. Considering the problem that the dynamic navigation system model is difficult to accurately describe the complex navigation environment, the thesis improves the dynamic characteristics of the information distribution of the federal filter algorithm which could timely change based on the eigenvalues ratio of each subsystem’s error variance matrix. Then, the adaptive federal unscented particle filter (AFUPF) is proposed. The simulation shows that the proposed algorithm could effectively weaken the impact on the system accuracy of the inaccurate high-dynamic model, and improve the adaptability, the fault tolerance and the accuracy, especially the attitude accuracy. DOI: http://dx.doi.org/10.11591/telkomnika.v14i3.8069 Full Text: PDF

A sequential learning algorithm based on adaptive particle filtering for RBF networks

To address the problem of low filtering accuracy and divergence caused by unknown process noise statistics and local linearization in neural network state-space model, this paper proposes an adaptive process noise covariance particle filter algorithm for the radial basis function (RBF) networks. Using the algorithm, the evolution of the weights and centers of RBF networks is achieved sequentially in time by use of the extended Kalman particle filter algorithm, and the process noise covariance matrices are also obtained simultaneously by maximizing the evidence density function with respect to the process noise covariance matrices. Performance of the presented approach is evaluated by two function approximation problems. Experimental results show that the proposed approach obtains better prediction accuracy than other well-known training algorithms.

An Adaptive Unscented Particle Filter Algorithm through Relative Entropy for Mobile Robot Self-Localization

Self-localization is a basic skill for mobile robots in the dynamic environments. It is usually modeled as a state estimation problem for nonlinear system with non-Gaussian noise and needs the real-time processing. Unscented particle filter (UPF) can handle the state estimation problem for nonlinear system with non-Gaussian noise; however the computation of UPF is very high. In order to reduce the computation cost of UPF and meanwhile maintain the accuracy, we propose an adaptive unscented particle filter (AUPF) algorithm through relative entropy. AUPF can adaptively adjust the number of particles during filtering to reduce the necessary computation and hence improve the real-time capability of UPF. In AUPF, the relative entropy is used to measure the distance between the empirical distribution and the true posterior distribution. The least number of particles for the next step is then decided according to the relative entropy. In order to offset the difference between the proposal distribution, and the true distribution the least number is adjusted thereafter. The ideal performance of AUPF in real robot self-localization is demonstrated.

A New Adaptive UPF Algorithm through Improved Relative Entropy

Unscented particle filter (UPF) has high accuracy of state estimation for nonlinear system with non-Gaussian noise. While the computation of traditional unscented particle filter is huge and this depends on the particle number. In this paper we propose a new adaptive unscented particle filter algorithm AUPF through improved relative entropy which can adaptively adjust the particle number during filtering. Firstly the relative entropy is used to measure the distance between the posterior probability density and the importance proposal and the least number of particles for the next time step is decided according to the relative entropy. Then the least number is adjusted to offset the difference between the importance proposal and the true distribution. This algorithm can effectively reduce unnecessary particles meanwhile reduce the computation. The simulation results show the effectiveness of AUPF.

Confidence-Level-Based New Adaptive Particle Filter for Nonlinear Object Tracking

Nonlinear object tracking from noisy measurements is a basic skill and a challenging task of mobile robotics, especially under dynamic environments. The particle filter is a useful tool for nonlinear object tracking with non-Gaussian noise. Nonlinear object tracking needs the real-time processing capability of the particle filter. While the number in a traditional particle filter is fixed, that can lead to a lot of unnecessary computation. To address this issue, a confidence-level-based new adaptive particle filter (NAPF) algorithm is proposed in this paper. In this algorithm the idea of confidence interval is utilized. The least number of particles for the next time instant is estimated according to the confidence level and the variance of the estimated state. Accordingly, an improved systematic re-sampling algorithm is utilized for the new improved particle filter. NAPF can effectively reduce the computation while ensuring the accuracy of nonlinear object tracking. The simulation results and the ball tracking results of the robot verify the effectiveness of the algorithm.