scholarly journals Toward Accurate Position Estimation Using Learning to Prediction Algorithm in Indoor Navigation

Sensors ◽  
2020 ◽  
Vol 20 (16) ◽  
pp. 4410 ◽  
Author(s):  
Faisal Jamil ◽  
Naeem Iqbal ◽  
Shabir Ahmad ◽  
Do-Hyeun Kim
Keyword(s):  
Kalman Filter ◽  
Indoor Localization ◽  
Position Estimation ◽  
Indoor Navigation ◽  
Location Based Services ◽  
Prediction Algorithm ◽  
Measurement Unit ◽  
Sensor Reading ◽  
Learning Module ◽  
Estimation System

Internet of Things is advancing, and the augmented role of smart navigation in automating processes is at its vanguard. Smart navigation and location tracking systems are finding increasing use in the area of the mission-critical indoor scenario, logistics, medicine, and security. A demanding emerging area is an Indoor Localization due to the increased fascination towards location-based services. Numerous inertial assessments unit-based indoor localization mechanisms have been suggested in this regard. However, these methods have many shortcomings pertaining to accuracy and consistency. In this study, we propose a novel position estimation system based on learning to the prediction model to address the above challenges. The designed system consists of two modules; learning to prediction module and position estimation using sensor fusion in an indoor environment. The prediction algorithm is attached to the learning module. Moreover, the learning module continuously controls, observes, and enhances the efficiency of the prediction algorithm by evaluating the output and taking into account the exogenous factors that may have an impact on its outcome. On top of that, we reckon a situation where the prediction algorithm can be applied to anticipate the accurate gyroscope and accelerometer reading from the noisy sensor readings. In the designed system, we consider a scenario where the learning module, based on Artificial Neural Network, and Kalman filter are used as a prediction algorithm to predict the actual accelerometer and gyroscope reading from the noisy sensor reading. Moreover, to acquire data, we use the next-generation inertial measurement unit, which contains a 3-axis accelerometer and gyroscope data. Finally, for the performance and accuracy of the proposed system, we carried out numbers of experiments, and we observed that the proposed Kalman filter with learning module performed better than the traditional Kalman filter algorithm in terms of root mean square error metric.

scholarly journals Improving Accuracy of the Alpha–Beta Filter Algorithm Using an ANN-Based Learning Mechanism in Indoor Navigation System

Sensors ◽  
2019 ◽  
Vol 19 (18) ◽  
pp. 3946 ◽  
Author(s):  
Faisal Jamil ◽  
Do Hyeun Kim
Keyword(s):  
Inertial Measurement Unit ◽  
Indoor Environment ◽  
Indoor Localization ◽  
Indoor Navigation ◽  
Prediction Algorithm ◽  
Measurement Unit ◽  
Sensor Reading ◽  
Inertial Measurement ◽  
Learning Module ◽  
Alpha Beta

The navigation system has been around for the last several years. Recently, the emergence of miniaturized sensors has made it easy to navigate the object in an indoor environment. These sensors give away a great deal of information about the user (location, posture, communication patterns, etc.), which helps in capturing the user’s context. Such information can be utilized to create smarter apps from which the user can benefit. A challenging new area that is receiving a lot of attention is Indoor Localization, whereas interest in location-based services is also rising. While numerous inertial measurement unit-based indoor localization techniques have been proposed, these techniques have many shortcomings related to accuracy and consistency. In this article, we present a novel solution for improving the accuracy of indoor navigation using a learning to perdition model. The design system tracks the location of the object in an indoor environment where the global positioning system and other satellites will not work properly. Moreover, in order to improve the accuracy of indoor navigation, we proposed a learning to prediction model-based artificial neural network to improve the prediction accuracy of the prediction algorithm. For experimental analysis, we use the next generation inertial measurement unit (IMU) in order to acquired sensing data. The next generation IMU is a compact IMU and data acquisition platform that combines onboard triple-axis sensors like accelerometers, gyroscopes, and magnetometers. Furthermore, we consider a scenario where the prediction algorithm is used to predict the actual sensor reading from the noisy sensor reading. Additionally, we have developed an artificial neural network-based learning module to tune the parameter of alpha and beta in the alpha–beta filter algorithm to minimize the amount of error in the current sensor readings. In order to evaluate the accuracy of the system, we carried out a number of experiments through which we observed that the alpha–beta filter with a learning module performed better than the traditional alpha–beta filter algorithm in terms of RMSE.

Enhanced Kalman filter algorithm using fuzzy inference for improving position estimation in indoor navigation

2021 ◽  
Vol 40 (5) ◽  
pp. 8991-9005
Author(s):  
Faisal Jamil ◽  
DoHyeun Kim
Keyword(s):  
Kalman Filter ◽  
Indoor Environment ◽  
Fuzzy Inference ◽  
Position Estimation ◽  
Indoor Navigation ◽  
Measurement Unit ◽  
Fusion Algorithm ◽  
Positioning Systems ◽  
Sensory Data ◽  
Kalman Filter Algorithm

In recent few years, the widespread applications of indoor navigation have compelled the research community to propose novel solutions for detecting objects position in the Indoor environment. Various approaches have been proposed and implemented concerning the indoor positioning systems. This study propose an fuzzy inference based Kalman filter to improve the position estimation in indoor navigation. The presented system is based on FIS based Kalman filter aiming at predicting the actual sensor readings from the available noisy sensor measurements. The proposed approach has two main components, i.e., multi sensor fusion algorithm for positioning estimation and FIS based Kalman filter algorithm. The position estimation module is used to determine the object location in an indoor environment in an accurate way. Similarly, the FIS based Kalman filter is used to control and tune the Kalman filter by considering the previous output as a feedback. The Kalman filter predicts the actual sensor readings from the available noisy readings. To evaluate the proposed approach, the next-generation inertial measurement unit is used to acquire a three-axis gyroscope and accelerometer sensory data. Lastly, the proposed approach’s performance has been investigated considering the MAD, RMSE, and MSE metrics. The obtained results illustrate that the FIS based Kalman filter improve the prediction accuracy against the traditional Kalman filter approach.

scholarly journals DeepLocBox: Reliable Fingerprinting-Based Indoor Area Localization

Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 2000
Author(s):  
Marius Laska ◽  
Jörg Blankenbach
Keyword(s):  
Wireless Local Area Network ◽  
Indoor Localization ◽  
Local Area Network ◽  
Success Probability ◽  
Local Area ◽  
Position Estimation ◽  
Location Based Services ◽  
Global Navigation Satellite Systems ◽  
Area Network ◽  
Floor Plan

Location-based services (LBS) have gained increasing importance in our everyday lives and serve as the foundation for many smartphone applications. Whereas Global Navigation Satellite Systems (GNSS) enable reliable position estimation outdoors, there does not exist any comparable gold standard for indoor localization yet. Wireless local area network (WLAN) fingerprinting is still a promising and widely adopted approach to indoor localization, since it does not rely on preinstalled hardware but uses the existing WLAN infrastructure typically present in buildings. The accuracy of the method is, however, limited due to unstable fingerprints, etc. Deep learning has recently gained attention in the field of indoor localization and is also utilized to increase the performance of fingerprinting-based approaches. Current solutions can be grouped into models that either estimate the exact position of the user (regression) or classify the area (pre-segmented floor plan) or a reference location. We propose a model, DeepLocBox (DLB), that offers reliable area localization in multi-building/multi-floor environments without the prerequisite of a pre-segmented floor plan. Instead, the model predicts a bounding box that contains the user’s position while minimizing the required prediction space (size of the box). We compare the performance of DLB with the standard approach of neural network-based position estimation and demonstrate that DLB achieves a gain in success probability by 9.48% on a self-collected dataset at RWTH Aachen University, Germany; by 5.48% for a dataset provided by Tampere University of Technology (TUT), Finland; and by 3.71% for the UJIIndoorLoc dataset collected at Jaume I University (UJI) campus, Spain.

scholarly journals Improving Accuracy of the Kalman Filter Algorithm in Dynamic Conditions Using ANN-Based Learning Module

Symmetry ◽  
2019 ◽  
Vol 11 (1) ◽  
pp. 94 ◽  
Author(s):  
Israr Ullah ◽  
Muhammad Fayaz ◽  
DoHyeun Kim
Keyword(s):  
Kalman Filter ◽  
Prediction Model ◽  
Historical Data ◽  
Mean Squared Error ◽  
External Factors ◽  
Prediction Algorithm ◽  
Dynamic Conditions ◽  
Learning Module ◽  
Prediction Algorithms ◽  
Kalman Filter Algorithm

Prediction algorithms enable computers to learn from historical data in order to make accurate decisions about an uncertain future to maximize expected benefit or avoid potential loss. Conventional prediction algorithms are usually based on a trained model, which is learned from historical data. However, the problem with such prediction algorithms is their inability to adapt to dynamic scenarios and changing conditions. This paper presents a novel learning to prediction model to improve the performance of prediction algorithms under dynamic conditions. In the proposed model, a learning module is attached to the prediction algorithm, which acts as a supervisor to monitor and improve the performance of the prediction algorithm continuously by analyzing its output and considering external factors that may have an influence on its performance. To evaluate the effectiveness of the proposed learning to prediction model, we have developed the artificial neural network (ANN)-based learning module to improve the prediction accuracy of the Kalman filter algorithm as a case study. For experimental analysis, we consider a scenario where the Kalman filter algorithm is used to predict actual temperature from noisy sensor readings. the Kalman filter algorithm uses fixed process error covariance R, which is not suitable for dynamic situations where the error in sensor readings varies due to some external factors. In this study, we assume variable error in temperature sensor readings due to the changing humidity level. We have developed a learning module based on ANN to estimate the amount of error in current readings and to update R in the Kalman filter accordingly. Through experiments, we observed that the Kalman filter with the learning module performed better (4.41%–11.19%) than the conventional Kalman filter algorithm in terms of the root mean squared error metric.

scholarly journals Indoor Localization of Quadcopters in Industrial Environment

2020 ◽  
Author(s):  
Péter Troll ◽  
Károly Szipka ◽  
Andreas Archenti
Keyword(s):  
Computer Vision ◽  
Material Handling ◽  
Evaluation Method ◽  
Indoor Localization ◽  
Research Work ◽  
Fine Tuning ◽  
Measurement Unit ◽  
Positioning System ◽  
Estimation System ◽  
Slam Algorithm

The research work in this paper was carried out to reach advanced positioning capabilities of unmanned aerial vehicles (UAVs) for indoor applications. The paper includes the design of a quadcopter and the implementation of a control system with the capability to position the quadcopter indoor using onboard visual pose estimation system, without the help of GPS. The project also covered the design and implementation of quadcopter hardware and the control software. The developed hardware enables the quadcopter to raise at least 0.5kg additional payload. The system was developed on a Raspberry single-board computer in combination with a PixHawk flight controller. OpenCV library was used to implement the necessary computer vision. The Open-source software-based solution was developed in the Robotic Operating System (ROS) environment, which performs sensor reading and communication with the flight controller while recording data about its operation and transmits those to the user interface. For the vision-based position estimation, pre-positioned printed markers were used. The markers were generated by ArUco coding, which exactly defines the current position and orientation of the quadcopter, with the help of computer vision. The resulting data was processed in the ROS environment. LiDAR with Hector SLAM algorithm was used to map the objects around the quadcopter. The project also deals with the necessary camera calibration. The fusion of signals from the camera and from the IMU (Inertial Measurement Unit) was achieved by using Extended Kalman Filter (EKF). The evaluation of the completed positioning system was performed with an OptiTrack optical-based external multi-camera measurement system. The introduced evaluation method has enough precision to be used to investigate the enhancement of positioning performance of quadcopters, as well as fine-tuning the parameters of the used controller and filtering approach. The payload capacity allows autonomous material handling indoors. Based on the experiments, the system has an accurate positioning system to be suitable for industrial application.

scholarly journals An Indoor Localization Method Based on the Combination of Indoor Map Information and Inertial Navigation with Cascade Filter

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Yushuai Zhang ◽  
Jianxin Guo ◽  
Feng Wang ◽  
Rui Zhu ◽  
Liping Wang
Keyword(s):  
Indoor Localization ◽  
Inertial Navigation ◽  
Detection Algorithm ◽  
Position Estimation ◽  
Position Error ◽  
Indoor Navigation ◽  
Bayesian Filter ◽  
Pedestrian Navigation ◽  
Zero Velocity ◽  
Average Position

The specific objective of this study is to propose a low-cost indoor navigation framework with nonbasic equipment by combining inertial sensors and indoor map messages. The proposed pedestrian navigation framework consists of a lower filter and an upper filter. In the lower filter which is designed based on the Kalman filter, the adaptive zero velocity detection algorithm is used to detect the zero velocity interval at different motion speeds, and then, zero velocity update is applied to rectify the inertial navigation solutions’ errors. In the upper filter which is designed based on the nonrecursive Bayesian filter, the map matching method with nonrecursive Bayesian filter is adopted to fuse the map prior information and the lower filter estimation results to correct the errors of navigation. The position estimation presented in this study achieves an average position error of 0.53 m compared to the ZUPT-aided inertial navigation system (INS) method under different motion states. The proposed pedestrian navigation algorithm achieves an average position error of 0.54 m as compared to the ZUPT-aided INS method among the different tested distances. The proposed framework simplifies the indoor positioning system under multiple motion speed conditions by ensuring the accuracy and stability property. The effectiveness and accuracy of the proposed framework are experimentally verified in various real-world scenarios.

scholarly journals Sensors and Sensing Technologies for Indoor Positioning and Indoor Navigation

Sensors ◽  
2020 ◽  
Vol 20 (20) ◽  
pp. 5924
Author(s):  
Francesco Potortì ◽  
Filippo Palumbo ◽  
Antonino Crivello
Keyword(s):  
Indoor Localization ◽  
Indoor Positioning ◽  
Human Motion ◽  
Indoor Navigation ◽  
Location Based Services ◽  
Critical Systems ◽  
Special Issue ◽  
Privacy And Security ◽  
Novel Technologies ◽  
Public Areas

The last 10 years have seen enormous technical progress in the field of indoor positioning and indoor navigation; yet, in contrast with outdoor well-established GNSS solutions, no technology exists that is cheap and accurate enough for the general market. The potential applications of indoor localization are all-encompassing, from home to wide public areas, from IoT and personal devices to surveillance and crowd behavior applications, and from casual use to mission-critical systems. This special issue is focused on the recent developments within the sensors and sensing technologies for indoor positioning and indoor navigation networks domain. The papers included in this special issue provide useful insights to the implementation, modelling, and integration of novel technologies and applications, including location-based services, indoor maps and 3D building models, human motion monitoring, robotics and UAV, self-contained sensors, wearable and multi-sensor systems, privacy and security for indoor localization systems.

scholarly journals Indoor Navigation Using Particle Filter and Sensor Fusion

2012 ◽  
Vol 19 (2) ◽  
pp. 31-40
Author(s):  
Lukas Köping ◽  
Thomas Mühsam ◽  
Christian Ofenberg ◽  
Bernhard Czech ◽  
Michael Bernard ◽  
...  
Keyword(s):  
Angular Velocity ◽  
Particle Filter ◽  
Indoor Localization ◽  
High Accuracy ◽  
Position Estimation ◽  
Indoor Navigation ◽  
Sensor Data ◽  
Localization System ◽  
Multiple Sensor ◽  
Large Building

Abstract In this paper we present an indoor localization system based on particle filter and multiple sensor data like acceleration, angular velocity and compass data. With this approach we tackle the problem of documentation on large building yards during the construction phase. Due to the circumstances of such an environment we cannot rely on any data from GPS, Wi-Fi or RFID. Moreover this work should serve us as a first step towards an all-in-one navigation system for mobile devices. Our experimental results show that we can achieve high accuracy in position estimation.

scholarly journals Indoor Positioning System Based on Chest-Mounted IMU

Sensors ◽  
2019 ◽  
Vol 19 (2) ◽  
pp. 420 ◽  
Author(s):  
Chuanhua Lu ◽  
Hideaki Uchiyama ◽  
Diego Thomas ◽  
Atsushi Shimada ◽  
Rin-ichiro Taniguchi
Keyword(s):  
Particle Filtering ◽  
Dead Reckoning ◽  
Type Systems ◽  
Indoor Navigation ◽  
Location Based Services ◽  
Upper Body ◽  
Measurement Unit ◽  
Navigation Systems ◽  
3D Navigation ◽  
Zero Velocity

Demand for indoor navigation systems has been rapidly increasing with regard to location-based services. As a cost-effective choice, inertial measurement unit (IMU)-based pedestrian dead reckoning (PDR) systems have been developed for years because they do not require external devices to be installed in the environment. In this paper, we propose a PDR system based on a chest-mounted IMU as a novel installation position for body-suit-type systems. Since the IMU is mounted on a part of the upper body, the framework of the zero-velocity update cannot be applied because there are no periodical moments of zero velocity. Therefore, we propose a novel regression model for estimating step lengths only with accelerations to correctly compute step displacement by using the IMU data acquired at the chest. In addition, we integrated the idea of an efficient map-matching algorithm based on particle filtering into our system to improve positioning and heading accuracy. Since our system was designed for 3D navigation, which can estimate position in a multifloor building, we used a barometer to update pedestrian altitude, and the components of our map are designed to explicitly represent building-floor information. With our complete PDR system, we were awarded second place in 10 teams for the IPIN 2018 Competition Track 2, achieving a mean error of 5.2 m after the 800 m walking event.

Sign in / Sign up

Export Citation Format

Share Document