Datasets

The extended Kalman filter (EKF) is a widely adopted method for sensor fusion in navigation applications. A crucial aspect of the EKF is the online determination of the process noise covariance matrix reflecting the model uncertainty. While common EKF implementation assumes a constant process noise, in real-world scenarios, the process noise varies, leading to inaccuracies in the estimated state and potentially causing the filter to diverge. To cope with such situations, model-based adaptive EKF methods were proposed and demonstrated performance improvements, highlighting the need for a robust adaptive approach. In this paper, we derive and introduce A-KIT, an adaptive Kalman-informed transformer to learn the varying process noise covariance online. The A-KIT framework is applicable to any type of sensor fusion. Here, we present our approach to nonlinear sensor fusion based on an inertial navigation system and Doppler velocity log. By employing real recorded data from an autonomous underwater vehicle, we show that A-KIT outperforms the conventional EKF by more than 49.5% and model-based adaptive EKF by an average of 35.4% in terms of position accuracy. 

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.

Mobile robots are used in industrial, leisure, and military applications. In some situations, a robot navigation solution relies only on inertial sensors and as a consequence, the navigation solution drifts in time. We propose the MoRPI framework, a mobile robot pure inertial approach. Instead of travelling in a straight line trajectory, the robot moves in a periodic motion trajectory to enable peak-to-peak estimation. In this manner, instead of performing three integrations to calculate the robot position in a classical inertial solution, an empirical formula is used to estimate the travelled distance. Two types of MoRPI approaches are suggested, where one is based on both accelerometer and gyroscope readings while the other is only on gyroscopes. Closed form analytical solutions are derived to show that MoRPI produces lower position error compared to the classical pure inertial solution. In addition, to evaluate the proposed approach, field experiments were made with a mobile robot equipped with two types of inertial sensors. In total, 143 trajectories with a time duration of 75 minutes were collected and evaluated. The results show the benefits of using our approach.

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 the learning-based models outperform traditional signal processing filtering in terms of pure inertial signal reconstruction. Moreover, they are shown to improve angular errors by one order of magnitude, given a navigation-related task.

Autonomous underwater vehicles (AUV) perform various applications such as seafloor mapping and underwater structure health monitoring. Commonly, an inertial navigation system aided by a Doppler velocity log (DVL) is used to provide the vehicle’s navigation solution. In such fusion, the DVL provides the velocity vector of the AUV, which determines the navigation solution’s accuracy and helps estimate the navigation states. In our paper we proposed BeamsNet, an end-to-end deep learning framework to regress the estimated DVL velocity vector that improves the accuracy of the velocity vector estimate, and could replace the model-based approach. Two versions of BeamsNet, differing in their input to the network, are suggested. The first uses the current DVL beam measurements and inertial sensors data, while the other utilizes only DVL data, taking the current and past DVL measurements for the regression process. Both simulation and sea experiments were made to validate the proposed learning approach relative to the model-based approach. Sea experiments were made with the Snapir AUV in the Mediterranean Sea, collecting approximately four hours of DVL and inertial sensor data. Our results show that the proposed approach achieved an improvement of more than 60% in estimating the DVL velocity vector.

One of the critical tasks required for fully autonomous functionality is the ability to achieve an accurate navigation solution; that is, to determine the platform position, velocity, and orientation. Various sensors, depending on the vehicle environment (air, sea, or land), are employed to achieve this goal. In parallel to the development of novel navigation and sensor fusion algorithms, machine-learning based algorithms are penetrating into the navigation and sensor fusion fields. An excellent example for this trend is pedestrian dead reckoning, used for indoor navigation, where both classical and machine learning approaches are used to improve the navigation accuracy. To facilitate machine learning algorithms’ derivation and validation for autonomous platforms, a huge quantity of recorded sensor data is needed. Unfortunately, in many situations, such datasets are not easy to collect or are not publicly available. To advance the development of accurate autonomous navigation, we presents the autonomous platforms inertial dataset. It contains inertial sensor raw data and corresponding ground truth trajectories. The dataset was collected using a variety of platforms including a quadrotor, two autonomous underwater vehicles, a land vehicle, a remote controlled electric car, and a boat. A total of 805.5 minutes of recordings were made using different types of inertial sensors, global navigation satellite system receivers, and Doppler velocity logs.