arXiv subjects

Itzik Klein

Publications and source records attributed to Itzik Klein.

At least 73 records · Page 4Linked to original sources

arXiv2024

Outlier-Insensitive Kalman Filtering: Theory and Applications

State estimation of dynamical systems from noisy observations is a fundamental task in many applications. It is commonly addressed using the linear Kalman filter (KF), whose performance can significantly degrade in the presence of outliers in the observations, due to the sensitivity of its convex quadratic objective function. To mitigate such behavior, outlier detection algorithms can be applied. In this work, we propose a parameter-free algorithm which mitigates the harmful effect of outliers while requiring only a short iterative process of the standard update step of the KF. To that end, we model each potential outlier as a normal process with unknown variance and apply online estimation through either expectation maximization or alternating maximization algorithms. Simulations and field experiment evaluations demonstrate competitive performance of our method, showcasing its robustness to outliers in filtering scenarios compared to alternative algorithms.

eess.SP↗

arXiv2024

Pedestrian Inertial Navigation: An Overview of Model and Data-Driven Approaches

The task of indoor positioning is fundamental to several applications, including navigation, healthcare, location-based services, and security. An emerging field is inertial navigation for pedestrians, which relies only on inertial sensors for positioning. In this paper, we present inertial pedestrian navigation models and learning approaches. Among these, are methods and algorithms for shoe-mounted inertial sensors and pedestrian dead reckoning (PDR) with unconstrained inertial sensors. We also address three categories of data-driven PDR strategies: activity-assisted, hybrid approaches, and learning-based frameworks.

cs.RO↗

arXiv2024

Deep Learning Assisted Inertial Dead Reckoning and Fusion

The interest in mobile platforms across a variety of applications has increased significantly in recent years. One of the reasons is the ability to achieve accurate navigation by using low-cost sensors. To this end, inertial sensors are fused with global navigation satellite systems (GNSS) signals. GNSS outages during platform operation can result in pure inertial navigation, causing the navigation solution to drift. In such situations, periodic trajectories with dedicated algorithms were suggested to mitigate the drift. With periodic dynamics, inertial deep learning approaches can capture the motion more accurately and provide accurate dead-reckoning for drones and mobile robots. In this paper, we propose approaches to extend deep learning-assisted inertial sensing and fusion capabilities during periodic motion. We begin by demonstrating that fusion between GNSS and inertial sensors in periodic trajectories achieves better accuracy compared to straight-line trajectories. Next, we propose an empowered network architecture to accurately regress the change in distance of the platform. Utilizing this network, we drive a hybrid approach for a neural-inertial fusion filter. Finally, we utilize this approach for situations when GNSS is available and show its benefits. A dataset of 337 minutes of data collected from inertial sensors mounted on a mobile robot and a quadrotor is used to evaluate our approaches.

cs.RO↗

arXiv2024

VIO-DualProNet: Visual-Inertial Odometry with Learning Based Process Noise Covariance

Visual-inertial odometry (VIO) is a vital technique used in robotics, augmented reality, and autonomous vehicles. It combines visual and inertial measurements to accurately estimate position and orientation. Existing VIO methods assume a fixed noise covariance for the inertial uncertainty. However, accurately determining in real-time the noise variance of the inertial sensors presents a significant challenge as the uncertainty changes throughout the operation leading to suboptimal performance and reduced accuracy. To circumvent this, we propose VIO-DualProNet, a novel approach that utilizes deep learning methods to dynamically estimate the inertial noise uncertainty in real-time. By designing and training a deep neural network to predict inertial noise uncertainty using only inertial sensor measurements, and integrating it into the VINS-Mono algorithm, we demonstrate a substantial improvement in accuracy and robustness, enhancing VIO performance and potentially benefiting other VIO-based systems for precise localization and mapping across diverse conditions.

cs.RO↗

arXiv2024

Seamless Underwater Navigation with Limited Doppler Velocity Log Measurements

Autonomous Underwater Vehicles (AUVs) commonly utilize an inertial navigation system (INS) and a Doppler velocity log (DVL) for underwater navigation. To that end, their measurements are integrated through a nonlinear filter such as the extended Kalman filter (EKF). The DVL velocity vector estimate depends on retrieving reflections from the seabed, ensuring that at least three out of its four transmitted acoustic beams return successfully. When fewer than three beams are obtained, the DVL cannot provide a velocity update to bind the navigation solution drift. To cope with this challenge, in this paper, we propose a hybrid neural coupled (HNC) approach for seamless AUV navigation in situations of limited DVL measurements. First, we drive an approach to regress two or three missing DVL beams. Then, those beams, together with the measured beams, are incorporated into the EKF. We examined INS/DVL fusion both in loosely and tightly coupled approaches. Our method was trained and evaluated on recorded data from AUV experiments conducted in the Mediterranean Sea on two different occasions. The results illustrate that our proposed method outperforms the baseline loosely and tightly coupled model-based approaches by an average of 96.15%. It also demonstrates superior performance compared to a model-based beam estimator by an average of 12.41% in terms of velocity accuracy for scenarios involving two or three missing beams. Therefore, we demonstrate that our approach offers seamless AUV navigation in situations of limited beam measurements.

cs.RO↗

arXiv2024

Inspection planning under execution uncertainty

Autonomous inspection tasks necessitate path-planning algorithms to efficiently gather observations from points of interest (POI). However, localization errors commonly encountered in urban environments can introduce execution uncertainty, posing challenges to successfully completing such tasks. Unfortunately, existing algorithms for inspection planning do not explicitly account for execution uncertainty, which can hinder their performance. To bridge this gap, we present IRIS-under uncertainty (IRIS-U^2), the first inspection-planning algorithm that offers statistical guarantees regarding coverage, path length, and collision probability. Our approach builds upon IRIS -- our framework for deterministic inspection planning, which is highly efficient and provably asymptotically-optimal. The extension to the much more involved uncertain setting is achieved by a refined search procedure that estimates POI coverage probabilities using Monte Carlo (MC) sampling. The efficacy of IRIS-U^2 is demonstrated through a case study focusing on structural inspections of bridges. Our approach exhibits improved expected coverage, reduced collision probability, and yields increasingly precise statistical guarantees as the number of MC samples grows. Furthermore, we demonstrate the potential advantages of computing bounded sub-optimal solutions to reduce computation time while maintaining statistical guarantees.

cs.RO↗

arXiv2024

Multiple and Gyro-Free Inertial Datasets

An inertial navigation system (INS) utilizes three orthogonal accelerometers and gyroscopes to determine platform position, velocity, and orientation. There are countless applications for INS, including robotics, autonomous platforms, and the internet of things. Recent research explores the integration of data-driven methods with INS, highlighting significant innovations, improving accuracy and efficiency. Despite the growing interest in this field and the availability of INS datasets, no datasets are available for gyro-free INS (GFINS) and multiple inertial measurement unit (MIMU) architectures. To fill this gap and to stimulate further research in this field, we designed and recorded GFINS and MIMU datasets using 54 inertial sensors grouped in nine inertial measurement units. These sensors can be used to define and evaluate different types of MIMU and GFINS architectures. The inertial sensors were arranged in three different sensor configurations and mounted on a mobile robot and a passenger car. In total, the dataset contains 35 hours of inertial data and corresponding ground truth trajectories. The data and code are freely accessible through our GitHub repository.

eess.SP↗

arXiv2024

Inertial Navigation Meets Deep Learning: A Survey of Current Trends and Future Directions

Inertial sensing is used in many applications and platforms, ranging from day-to-day devices such as smartphones to very complex ones such as autonomous vehicles. In recent years, the development of machine learning and deep learning techniques has increased significantly in the field of inertial sensing and sensor fusion. This is due to the development of efficient computing hardware and the accessibility of publicly available sensor data. These data-driven approaches mainly aim to empower model-based inertial sensing algorithms. To encourage further research in integrating deep learning with inertial navigation and fusion and to leverage their capabilities, this paper provides an in-depth review of deep learning methods for inertial sensing and sensor fusion. We discuss learning methods for calibration and denoising as well as approaches for improving pure inertial navigation and sensor fusion. The latter is done by learning some of the fusion filter parameters. The reviewed approaches are classified by the environment in which the vehicles operate: land, air, and sea. In addition, we analyze trends and future directions in deep learning-based navigation and provide statistical data on commonly used approaches.

cs.RO↗

arXiv2024

Underwater MEMS Gyrocompassing: A Virtual Testing Ground

In underwater navigation, accurate heading information is crucial for accurately and continuously tracking trajectories, especially during extended missions beneath the waves. In order to determine the initial heading, a gyrocompassing procedure must be employed. As unmanned underwater vehicles (UUV) are susceptible to ocean currents and other disturbances, the model-based gyrocompassing procedure may experience degraded performance. To cope with such situations, this paper introduces a dedicated learning framework aimed at mitigating environmental effects and offering precise underwater gyrocompassing. Through the analysis of the dynamic UUV signature obtained from inertial measurements, our proposed framework learns to refine disturbed signals, enabling a focused examination of the earth's rotation rate vector. Leveraging recent machine learning advancements, empirical simulations assess the framework's adaptability to challenging underwater conditions. Ultimately, its contribution lies in providing a resilient gyrocompassing solution for UUVs.

eess.SY↗

arXiv2024

Data-Driven Strategies for Coping with Incomplete DVL Measurements

Autonomous underwater vehicles are specialized platforms engineered for deep underwater operations. Critical to their functionality is autonomous navigation, typically relying on an inertial navigation system and a Doppler velocity log. In real-world scenarios, incomplete Doppler velocity log measurements occur, resulting in positioning errors and mission aborts. To cope with such situations, a model and learning approaches were derived. This paper presents a comparative analysis of two cutting-edge deep learning methodologies, namely LiBeamsNet and MissBeamNet, alongside a model-based average estimator. These approaches are evaluated for their efficacy in regressing missing Doppler velocity log beams when two beams are unavailable. In our study, we used data recorded by a DVL mounted on an autonomous underwater vehicle operated in the Mediterranean Sea. We found that both deep learning architectures outperformed model-based approaches by over 16% in velocity prediction accuracy.

cs.RO↗

arXiv2024

DVL Calibration using Data-driven Methods

Autonomous underwater vehicles (AUVs) are used in a wide range of underwater applications, ranging from seafloor mapping to industrial operations. While underwater, the AUV navigation solution commonly relies on the fusion between inertial sensors and Doppler velocity logs (DVL). To achieve accurate DVL measurements a calibration procedure should be conducted before the mission begins. Model-based calibration approaches include filtering approaches utilizing global navigation satellite system signals. In this paper, we propose an end-to-end deep-learning framework for the calibration procedure. Using stimulative data, we show that our proposed approach outperforms model-based approaches by 35% in accuracy and 80% in the required calibration time.

cs.RO↗

arXiv2023

Towards Learning-Based Gyrocompassing

Inertial navigation systems (INS) are widely used in both manned and autonomous platforms. One of the most critical tasks prior to their operation is to accurately determine their initial alignment while stationary, as it forms the cornerstone for the entire INS operational trajectory. While low-performance accelerometers can easily determine roll and pitch angles (leveling), establishing the heading angle (gyrocompassing) with low-performance gyros proves to be a challenging task without additional sensors. This arises from the limited signal strength of Earth's rotation rate, often overridden by gyro noise itself. To circumvent this deficiency, in this study we present a practical deep learning framework to effectively compensate for the inherent errors in low-performance gyroscopes. The resulting capability enables gyrocompassing, thereby eliminating the need for subsequent prolonged filtering phase (fine alignment). Through the development of theory and experimental validation, we demonstrate that the improved initial conditions establish a new lower error bound, bringing affordable gyros one step closer to being utilized in high-end tactical tasks.

cs.RO↗

arXiv2023

Quadrotor Dead Reckoning with Multiple Inertial Sensors

Quadrotors are widely used for surveillance, mapping, and deliveries. In several scenarios the quadrotor operates in pure inertial navigation mode resulting in a navigation solution drift. To handle such situations and bind the navigation drift, the quadrotor dead reckoning (QDR) approach requires flying the quadrotor in a periodic trajectory. Then, using model or learning based approaches the quadrotor position vector can be estimated. We propose to use multiple inertial measurement units (MIMU) to improve the positioning accuracy of the QDR approach. Several methods to utilize MIMU data in a deep learning framework are derived and evaluated. Field experiments were conducted to validate the proposed approach and show its benefits.

cs.RO↗

arXiv2023

GHNet:Learning GNSS Heading from Velocity Measurements

By utilizing global navigation satellite system (GNSS) position and velocity measurements, the fusion between the GNSS and the inertial navigation system provides accurate and robust navigation information. When considering land vehicles,like autonomous ground vehicles,off-road vehicles or mobile robots,a GNSS-based heading angle measurement can be obtained and used in parallel to the position measurement to bound the heading angle drift. Yet, at low vehicle speeds (less than 2m/s) such a model-based heading measurement fails to provide satisfactory performance. This paper proposes GHNet, a deep-learning framework capable of accurately regressing the heading angle for vehicles operating at low speeds. We demonstrate that GHNet outperforms the current model-based approach for simulation and experimental datasets.

cs.RO↗

arXiv2023

Parametric and State Estimation of Stationary MEMS-IMUs: A Tutorial

Inertial navigation systems (INS) are widely used in almost any operational environment, including aviation, marine, and land vehicles. Inertial measurements from accelerometers and gyroscopes allow the INS to estimate position, velocity, and orientation of its host vehicle. However, as inherent sensor measurement errors propagate into the state estimates, accuracy degrades over time. To mitigate the resulting drift in state estimates, different approaches of parametric and state estimation are proposed to compensate for undesirable errors, using frequency-domain filtering or external information fusion. Another approach uses multiple inertial sensors, a field with rapid growth potential and applications. The increased sampling of the observed phenomenon results in the improvement of several key factors such as signal accuracy, frequency resolution, noise rejection, and higher redundancy. This study offers an analysis tutorial of basic multiple inertial operation, with a new perspective on the error relationship to time, and number of sensors. To that end, a stationary and levelled sensors array is taken, and its robustness against the instrumental errors is analyzed. Subsequently, the hypothesized analytical model is compared with the experimental results, and the level of agreement between them is thoroughly discussed. Ultimately, our results showcase the vast potential of employing multiple sensors, as we observe improvements spanning from the signal level to the navigation states. This tutorial is suitable for both newcomers and people experienced with multiple inertial sensors.

eess.SY↗

arXiv2023

Data-Driven Denoising of Stationary Accelerometer Signals

Modern navigation solutions are largely dependent on the performances of the standalone inertial sensors, especially at times when no external sources are available. During these outages, the inertial navigation solution is likely to degrade over time due to instrumental noises sources, particularly when using consumer low-cost inertial sensors. Conventionally, model-based estimation algorithms are employed to reduce noise levels and enhance meaningful information, thus improving the navigation solution directly. However, guaranteeing their optimality often proves to be challenging as sensors performance differ in manufacturing quality, process noise modeling, and calibration precision. In the literature, most inertial denoising models are model-based when recently several data-driven approaches were suggested primarily for gyroscope measurements denoising. Data-driven approaches for accelerometer denoising task are more challenging due to the unknown gravity projection on the accelerometer axes. To fill this gap, we propose several learning-based approaches and compare their performances with prominent denoising algorithms, in terms of pure noise removal, followed by stationary coarse alignment procedure. Based on the benchmarking results, obtained in field experiments, we show that: (i) learning-based models perform better than traditional signal processing filtering; (ii) non-parametric kNN algorithm outperforms all state of the art deep learning models examined in this study; (iii) denoising can be fruitful for pure inertial signal reconstruction, but moreover for navigation-related tasks, as both errors are shown to be reduced up to one order of magnitude.

eess.SP↗

arXiv2023

Learning Vehicle Trajectory Uncertainty

A novel approach for vehicle tracking using a hybrid adaptive Kalman filter is proposed. The filter utilizes recurrent neural networks to learn the vehicle's geometrical and kinematic features, which are then used in a supervised learning model to determine the actual process noise covariance in the Kalman framework. This approach addresses the limitations of traditional linear Kalman filters, which can suffer from degraded performance due to uncertainty in the vehicle kinematic trajectory modeling. Our method is evaluated and compared to other adaptive filters using the Oxford RobotCar dataset, and has shown to be effective in accurately determining the process noise covariance in real-time scenarios. Overall, this approach can be implemented in other estimation problems to improve performance.

cs.RO↗

arXiv2023

MissBeamNet: Learning Missing Doppler Velocity Log Beam Measurements

One of the primary means of sea exploration is autonomous underwater vehicles (AUVs). To perform these tasks, AUVs must navigate the rough challenging sea environment. AUVs usually employ an inertial navigation system (INS), aided by a Doppler velocity log (DVL), to provide the required navigation accuracy. The DVL transmits four acoustic beams to the seafloor, and by measuring changes in the frequency of the returning beams, the DVL can estimate the AUV velocity vector. However, in practical scenarios, not all the beams are successfully reflected. When only three beams are available, the accuracy of the velocity vector is degraded. When fewer than three beams are reflected, the DVL cannot estimate the AUV velocity vector. This paper presents a data-driven approach, MissBeamNet, to regress the missing beams in partial DVL beam measurement cases. To that end, a deep neural network (DNN) model is designed to process the available beams along with past DVL measurements to regress the missing beams. The AUV velocity vector is estimated using the available measured and regressed beams. To validate the proposed approach, sea experiments were made with the "Snapir" AUV, resulting in an 11 hours dataset of DVL measurements. Our results show that the proposed system can accurately estimate velocity vectors in situations of missing beam measurements. Our dataset and codebase implementing the described framework is available at our GitHub repository https://github.com/ansfl/MissBeamNet .

cs.RO↗