Filter Fusion Algorithm Research Articles

Design of an Autonomous Orchard Navigation System Based on Multi-Sensor Fusion

To address the limitations of traditional GNSS-based navigation systems in orchard environments, we propose a multi-sensor fusion-based autonomous navigation method for orchards. A crawler-type agricultural platform was used as a test vehicle, and an autonomous orchard navigation system was constructed using a 2D LiDAR, a dynamic electronic compass, and an encoder. The proposed system first filters LiDAR point cloud data and uses the DBSCAN–ratio–threshold method to process data and identify clusters of tree trunks. By matching the center coordinates of trunk clusters with a fruit tree distribution map, the platform’s positional measurements are determined. An extended Kalman filter fusion algorithm is then employed to obtain a posterior estimate of the platform’s position and pose. Experimental results demonstrate that in localization accuracy tests and navigation tests, the proposed system provides high navigation accuracy and robustness, making it suitable for autonomous walking operations in orchard environments.

Unstructured environment navigation and trajectory calibration technology based on multi-data fusion

In order to effectively improve the accuracy and efficiency of unstructured environment navigation and trajectory calibration, a multi data fusion based unstructured environment navigation and trajectory calibration method was studied. Described the basic principles of the Strapdown Inertial Navigation System and Doppler Log. After introducing DVL velocity information and relative position information of underwater robots into SINS, the Kalman filter fusion algorithm was used to obtain the system's state equation and measurement equation. The navigation parameter error and device error parameters of the system were selected as the state variables. The difference between SINS output speed and DVL measurement speed, as well as the difference between SINS output position and relative position, are used as the speed and position measurements of the measurement system. Error estimation is obtained through indirect filtering, and the accuracy of navigation and positioning is improved through output correction. The experimental results show that the proposed method has a good calibration effect and can effectively improve the accuracy and efficiency of trajectory calibration in unstructured environments.

A robust deep learning system for screening of obstructive sleep apnea using T-F spectrum of ECG signals

Obstructive sleep apnea (OSA) is a non-communicable sleep-related medical condition marked by repeated disruptions in breathing during sleep. It may induce various cardiovascular and neurocognitive complications. Electrocardiography (ECG) is a useful method for detecting numerous health-related disorders. ECG signals provide a less complex and non-invasive solution for the screening of OSA. Automated and accurate detection of OSA may enhance diagnostic performance and reduce the clinician’s workload. Traditional machine learning methods typically involve several labor-intensive manual procedures, including signal decomposition, feature evaluation, selection, and categorization. This article presents the time-frequency (T-F) spectrum classification of de-noised ECG data for the automatic screening of OSA patients using deep convolutional neural networks (DCNNs). At first, a filter-fusion algorithm is used to eliminate the artifacts from the raw ECG data. Stock-well transform (S-T) is employed to change filtered time-domain ECG into T-F spectrums. To discriminate between apnea and normal ECG signals, the obtained T-F spectrums are categorized using benchmark Alex-Net and Squeeze-Net, along with a less complex DCNN. The superiority of the presented system is measured by computing the sensitivity, specificity, accuracy, negative predicted value, precision, F1-score, and Fowlkes-Mallows index. The results of comparing all three utilized DCNNs reveal that the proposed DCNN requires fewer learning parameters and provides higher accuracy. An average accuracy of 95.31% is yielded using the proposed system. The presented deep learning system is lightweight and faster than Alex-Net and Squeeze-Net as it utilizes fewer learnable parameters, making it simple and reliable.

Anti-delay Kalman filter fusion algorithm for inter-vehicle sensor network with finite-step convergence

Intelligent vehicle applications in autonomous driving and obstacle avoidance commonly require the precise relative state of vehicles. Accordingly, this study focuses on the coordinate fusion of vehicle state problem experienced by an inter-vehicle sensor network with time-varying transmission delays. Using the ingeniously designed low-complexity integration with a consensus strategy and buffer technology, an anti-delay distributed Kalman filter (DKF) with finite-step convergence is proposed. By introducing an appropriate weight matrix to assess local estimates, the optimal fusion state result is available as a linear minimum variance. In addition, to accommodate practical engineering in intelligent vehicles, the communication weight coefficient and directed topology with unidirectional transmission are considered. From a theoretical perspective, the proof of error covariances’ upper bounds with different communication topologies with delays are presented. Furthermore, the maximum allowable delays of inter-vehicle sensor network are derived backwards. Simulations verify that while considering the various non-ideal factors presented above, the proposed DFK algorithm produces more accurate and robust fusion estimation state results than those of the existing algorithms, making it more valuable in practical applications. Moreover, a mobile car trajectory tracking experiment is conducted, which further verifies the feasibility of the proposed algorithm.

Online monitoring system of material moisture content based on the Kalman filter fusion algorithm in air-impingement dryer

A Kalman filter fusion algorithm was proposed, and an online monitoring system was developed for real-time monitoring of the moisture content of materials in an air-impingement dryer. The Kalman filter algorithm was used to estimate the optimal state of the original detection values of the weighting sensor and air velocity sensor. A backpropagation (BP) neural network fusion model was established, where the weight detection value, elastic substrate temperature, air velocity, and impingement distance were considered inputs and the real weight of the material was the output. The optimal topology of the BP neural network was selected, and the initial weights and thresholds of the BP neural network were optimized using a genetic algorithm. The coefficient of determination (R2) and root mean square error (RMSE) of the optimized BP neural network fusion model were 0.9995 and 4.9, respectively. The Kalman filter fusion algorithm, which can realize online monitoring of moisture content, was established using the Kalman filter algorithm and fusion model. Moreover, an online monitoring system for material moisture content was developed, validation experiments were carried out, and the R2 and RMSE of the nine sets of validation experiments were 0.9963 and 0.78, respectively. The monitoring system satisfied the requirements of material moisture content detection accuracy in the drying process. The developed monitoring system is greatly important for improving the automation level of the drying equipment for fruits and vegetables. The proposed Kalman filter fusion algorithm also provides a reference for other multifactor fusion detection.

ARWLS-AFEKE: SOC Estimation and Capacity Correction of Lithium Batteries Based on a Fusion Algorithm

Accuracy of battery charge status (SOC) estimation plays a significant role in the management of electric vehicle power batteries. However, recently, abrupt changes from SOC data often occurs in the actual operation of electric vehicles and some errors appear in the establishment of battery models and noise models, which give rise to the poorly adaptive and robust performance of traditional algorithms in the process of SOC estimation. The fusion algorithm proposed in this paper can effectively improve the accuracy of models and SOC estimation of lithium-ion batteries. Based on the second-order R-C network model, this method optimizes the accuracy of parameter identification by adopting the adaptive recursive weighted least square algorithm (ARWLS). In addition, the adaptive fading extended Kalman filter algorithm (AFEKF) is applied to estimate the SOC of lithium-ion batteries. Additionally, via introducing a fading factor, the optimal Kalman gain is updated in real-time, which can reduce the impact of data mutation on battery modeling. Compared with the offline AEKF algorithm and the EKF algorithm, the adaptive recursive weighted least square-adaptive fading extended Kalman filter (ARWLS-AFEKF) fusion algorithm had higher accuracy and adaptability, which can be adapted to the variable noise environment.

Vision and Inertial Navigation Combined-Based Pose Measurement Method of Cantilever Roadheader

Pose measurement of coal mine excavation equipment is an important part of roadway excavation. However, in the underground mining roadway of coal mine, there are some influencing factors such as low illumination, high dust and interference from multiple equipment, which lead to the difficulty in the position and pose measurement of roadheader with low measurement accuracy and poor stability. A combination positioning method based on machine vision and optical fiber inertial navigation is proposed to realize the position and pose measurement of roadheader and improve the accuracy and stability of the position and pose measurement. The visual measurement model of arm roadheader is established, and the optical fiber inertial navigation technology and the spatial coordinate transformation method are used. Finally, the Kalman filter fusion algorithm is used to fuse the two kinds of data to get the accurate roadheader pose data, and the inertia is compensated and corrected. Underground coal mine experiments are designed to verify the performance of the proposed method. The results show that the positioning error of the roadheader body using this method is within 40 mm, which meets the positioning accuracy requirements of roadway construction. This method compensates for the shortcomings of low accuracy and poor reliability of single vision measurement, single inertial navigation measurement and single odometer measurement.

A LiDAR SLAM-Assisted Fusion Positioning Method for USVs.

Confronted with unmanned surface vessel (USV) operations where GNSS signals are unavailable due to obscuration and other factors, a LiDAR SLAM-assisted fusion positioning method for USVs is proposed to combine GNSS/INS positioning with LiDAR-SLAM. When the USV works in wide-open water, the carrier phase differential GNSS/INS loosely coupled integration strategy is applied to fuse and calibrate the positioning data, and the positioning information of the USV is obtained through the coordinate conversion process. The system uses a dynamic switching strategy to enter to LiDAR-SLAM positioning when GNSS signals are not available, compensating the LiDAR data with precise angle information to ensure accurate and stable positioning. The experiments show that compared with the traditional Kalman filter and adaptive Kalman filter fusion algorithms, the positioning error is reduced by 55.4% and 43.5%. The velocity error is also limited by 78.2% and 57.9%. The standard deviation and the root mean square error are stable within 0.1 m, indicating that our method has better data stability, while the probability of positioning anomaly is effectively controlled.

Multi-Source Adaptive Selection and Fusion for Pedestrian Dead Reckoning

Accurate multi-source fusion is based on the reliability, quantity, and fusion mode of the sources. The problem of selecting the optimal set for participating in the fusion process is nondeterministic-polynomial-time-hard and is neither sub-modular nor super-modular. Furthermore, in the case of the Kalman filter (KF) fusion algorithm, accurate statistical characteristics of noise are difficult to obtain, and this leads to an unsatisfactory fusion result. To settle the referred cases, a distributed and adaptive weighted fusion algorithm based on KF has been proposed in this paper. In this method, on the basis of the pseudo prior probability of the estimated state of each source, the reliability of the sources is evaluated and the optimal set is selected on a certain threshold. Experiments were performed on multi-source pedestrian dead reckoning for verifying the proposed algorithm. The results obtained from these experiments indicate that the optimal set can be selected accurately with minimal computation, and the fusion error is reduced by 16.6% as compared to the corresponding value resulting from the algorithm without improvements. The proposed adaptive source reliability and fusion weight evaluation is effective against the varied-noise multi-source fusion system, and the fusion error caused by inaccurate statistical characteristics of the noise is reduced by the adaptive weight evaluation. The proposed algorithm exhibits good robustness, adaptability, and value on applications.

Pose Measurement Technology of Roadheader Body based on Fusion of Visual and SINS*

In order to solve the problem of pose measurement of roadheader body in low illumination and high dust environment in coal mine, a pose measurement technology of roadheader body based on visual and strapdown inertial navigation system (SINS) is proposed. By extracting the point and line features and using the monocular vision positioning principle based on the gate three lines, the spatial pose of the roadheader body measured by vision is obtained according to the spatial matrix transformation. At the same time, the spatial pose of the roadheader body measured by SINS is calculated by gyroscope and accelerometer. Then the least square method is used to align the two-sensor data, and the registration data is fused based on the extended Kalman filter fusion algorithm to obtain the final fusion roadheader pose data. The experimental results show that the measurement error of the roadheader body position in the x axis direction of the roadway coordinate system is less than ± 20 mm, the error of the y axis direction is less than ±35 mm, the error of the z axis direction is less than ± 10 mm, the yaw angle error is between-0.4° to 0.7°, the roll angle error is between -0.2° and 0.6°, and the pitch angle error is between -0.02° and 0.5°. This method can be used to measure the pose of the roadheader stably and accurately in the complex environment of high dust, miscellaneous light and low illumination.

Research on indoor positioning and navigation method of AGV based on multi-sensor fusion

In comparison with current AGV indoor positioning and navigation methods, the combination of IMU+2D LiDAR is prone to signal loss and cumulative error in indoor, so we propose an AGV indoor navigation and positioning method with multi-sensor fusion of odometer, IMU, LiDAR, and UWB. The model is based on the traceless Kalman filter fusion algorithm, and the UWB positioning provides accurate initial coordinates for the traceless Kalman filter. To verify the feasibility of the method, simulations and experiments are done on MatlabR2020a and experimental platform. The results show that the UWB localization can reduce the accumulated errors brought by IMU, the traceless Kalman filter has good trajectory fitting, the method has good performance in system stability and localization accuracy, and achieves the expected goal.

Fusion and detection for multi-sensor systems under false data injection attacks

This article investigates a security problem in cyber–physical systems under multisensory framework. Data packets from each sensor are transmitted to a remote estimator through wireless channels which could be attacked by a attacker and injected false data. Based on the data of reliable sensors and the relativity between reliable and unreliable sensors, a revised multi-sensor Kalman filter fusion algorithm is proposed. Under the proposed algorithm, an optimal linear false data injection attack strategy which is more general with an arbitrary mean of Gaussian distribution is designed. To further improve the detection performance, an Expected SARSA-based attack detection algorithm is proposed. Finally, simulation results based on an unmanned aerial vehicle are provided to illustrate the feasibility and efficiency of the obtained results.

Relatively Integrated Ship Navigation by H∞ Fusion Filters

For the system with unknown statistical property noises, the property that the energies of the system noise and the observation noise are limited is utilized in this paper. On this basis, two novel fusion algorithms are proposed for ship integrated navigation with the relative navigation information, broadcasted by the Automatic Identification Systems (AISs) in the adjacent ships. Firstly, an H∞ fusion filtering algorithm is given to deal with the navigation observation messages, under the centralized fusion framework. The integrated navigation method based on this algorithm cannot deal with the asynchronous navigation messages in real time. Therefore, a sequential H∞ fusion filtering algorithm is also given to sequentially deal with the asynchronous navigation messages, secondly. Finally, a computer simulation is employed to illustrate the validity and feasibility of the sequential method.

Millimeter-Wave Radar and Video Fusion Vehicle Detection based on Adaptive Kalman Filtering

Road traffic safety has always been the focus of social concern, and the actual road traffic scenes, where only a single sensor is applied cannot cope with the interference brought by complex external factors, which makes vehicle detection extremely challenging. This paper focuses on a vehicle detection algorithm for the fusion of millimeter-wave radar sensor and monocular camera sensor, including the calibration of millimeter-wave radar and camera, the establishment of a temporal fusion model of the two sensors. Finally, the target information obtained from the two sensors is fused with the data using the adaptive Kalman filter fusion algorithm, which can reduce data ambiguity and increase the reliability and validity of the data. Experiments show that the method can overcome the shortcomings of single sensor in target detection, and the obtained target information is more comprehensive compared with the monocular camera detection results.

Relatively-Integrated Ship Navigation by H¥ Fusion Filters

For the system with unknown statistical property noises, the property that the energies of the system noise and the observation noise are limited is utilized in this paper. On this basis, two novel fusion algorithms are proposed for ship integrated navigation with the relative navigation information, broadcasted by the Automatic Identification Systems (AISs) in the adjacent ships. Firstly, an H∞ fusion filtering algorithm is given to deal with the navigation observation messages, under the centralized fusion framework. The integrated navigation method based on this algorithm cannot deal with the asynchronous navigation messages in real time. Therefore, a sequential H∞ fusion filtering algorithm is also given to sequentially deal with the asynchronous navigation messages, secondly. Finally, a computer simulation is employed to illustrate the validity and feasibility of the sequential method.

Novel indoor positioning algorithm based on Lidar/inertial measurement unit integrated system

As an important research field of mobile robot, simultaneous localization and mapping technology is the core technology to realize intelligent autonomous mobile robot. Aiming at the problems of low positioning accuracy of Lidar (light detection and ranging) simultaneous localization and mapping with nonlinear and non-Gaussian noise characteristics, this article presents a mobile robot simultaneous localization and mapping method that combines Lidar and inertial measurement unit to set up a multi-sensor integrated system and uses a rank Kalman filtering to estimate the robot motion trajectory through inertial measurement unit and Lidar observations. Rank Kalman filtering is similar to the Gaussian deterministic point sampling filtering algorithm in structure, but it does not need to meet the assumptions of Gaussian distribution. It completely calculates the sampling points and the sampling points weights based on the correlation principle of rank statistics. It is suitable for nonlinear and non-Gaussian systems. With multiple experimental tests of small-scale arc trajectories, we can see that compared with the alone Lidar simultaneous localization and mapping algorithm, the new algorithm reduces the mean error of the indoor mobile robot in the X direction from 0.0928 m to 0.0451 m, with an improved accuracy rate of 46.39%, and the mean error in the Y direction from 0.0772 m to 0.0405 m, which improves the accuracy rate of 48.40%. Compared with the extended Kalman filter fusion algorithm, the new algorithm reduces the mean error of the indoor mobile robot in the X direction from 0.0597 m to 0.0451 m, with an improved accuracy rate of 24.46%, and the mean error in the Y direction from 0.0537 m to 0.0405 m, which improves the accuracy rate of 24.58%. Finally, we also tested on a large-scale rectangular trajectory, compared with the extended Kalman filter algorithm, rank Kalman filtering improves the accuracy of 23.84% and 25.26% in the X and Y directions, respectively, it is verified that the accuracy of the algorithm proposed in this article has been improved.

An INS and UWB Fusion Approach With Adaptive Ranging Error Mitigation for Pedestrian Tracking

Fusion techniques are employed in pedestrian tracking to achieve more accurate and robust tracking systems. A common approach is to fuse Inertial Navigation System (INS), worn by a pedestrian, with a radio-based system to complement each other and mitigate their shortcomings. Despite the increased accuracy achieved in the state-of-the-art approaches, the deployment complexity and cost of these tracking systems remain a major bottleneck. In this paper, a novel INS and Ultra-wideband (UWB) fusion approach, which complements INS only with ranging measurements obtained from UWB anchors placed at known location, is proposed. An adaptive UWB ranging uncertainty model is proposed and incorporated in a Particle Filter fusion algorithm, which reduces errors of the UWB measurements and enhances positioning accuracy. The proposed approach achieves significant reduction of the deployment complexity and cost compared to other approaches that have comparable tracking performance. The pedestrian tracking system is implemented using the built-in inertial measurement unit of a smartphone and DecaWave TREK1000 UWB development kit. Two practical long-distance pedestrian tracking experiments are conducted to demonstrate the accuracy and robustness of the proposed approach, which reduces mean position error up to 73.23 % when compared to INS only tracking results.

Research on guidance method of cooperative tracking ground multi-target using UAV group

Multi-UAV (unmanned aerial vehicle) cooperative tracking target is one of the standard exercises for unmanned aircraft systems, it is important to track multiple targets in actual missions due to the clustering of military missions. It is of great research interest and more difficult to use fewer multi-UAV to track more targets effectively, the aim of which is to be more efficient in tracking, and high precision positioning. This paper explores the key issues in the complex environment of UAV community cooperative multi-target monitoring. The architecture of the UAV group cooperative the multi-target tracking system is built in a complex environment firstly. Then a proposal was made for a dynamic grouping algorithm for multi-target UAV group tracking in an occlusion region, an adaptive multi-model unscented Kalman particle filter fusion algorithm, and a fast guidance method for cooperative target tracking in a restricted environment. The feasibility of the proposed method is validated by simulation and flight test evaluations. Finally, there is a prospect for the next course of research in this field.

Platform tilt stabilisation using inertial measurement unit sensor

This paper aims to develop a low cost two-axis pan-tilt platform stabilisation setup using a low-cost inertial measurement unit (IMU) sensor, utilise elegant and widely used sensor fusion and control algorithm, and demonstrate the performance of such a system. The IMU sensor and the other components for the two-axis platform setup are selected initially based on the design calculations and the platform stabiliser setup is then designed and manufactured in accordance with the selected components. To perform platform stabilisation, reliable pan-tilt angular estimates are required from the IMU sensor. For this purpose, techniques such as sensor bias removal, digital low pass filter (DLPF) and sensor fusion algorithms are deployed considering the robustness of their performance in the real-time embedded hardware. First-order impulse response (FIR) filter is chosen as the DLPF algorithm and the complementary filter (CF) is chosen as the sensor fusion algorithm as these are widely recognised for their need of very less computational power. Finally, the pan-tilt stabilisation is performed by two separate PID servo control tuned using Zeigler-Nichols manual tuning rules and finally the performance of the control system in tracking the angular estimates is finally studied.

Fusion identification and estimation of multisensor multichannel AR signals with missing measurements and sensor biases

This paper studies the problem of fusion identification and estimation for multisensor multichannel autoregressive (AR) signals with unknown missing measurement rates, model parameters (MPs), sensor biases and measurement noise variances. Optimal local filters, cross-covariance matrices (CCMs), and a distributed fusion filter for AR signal are presented when the system model is accurately known, respectively. A self-tuning (ST) fusion filter is presented when MPs of AR signal, sensor biases, missing measurement rates and measurement noise variances in the system model are unknown. First, MPs of AR signal and sensor biases are identified by using a multi-dimensional recursive extended least squares (MRELS) algorithm. Further, distributed fusion estimates of MPs of AR signal are obtained by using a matrix-weighted optimal fusion estimation algorithm in the sense of linear unbiased minimum variance (LUMV). Then, receiving measurement rates and measurement noise variances are identified by correlation functions. Finally, substituting the identified parameters into the proposed optimal filtering algorithms, a matrix-weighted self-tuning (ST) fusion filtering algorithm is obtained. An example verifies the effectiveness of algorithms.