The Autonomous Platforms Inertial Dataset

Shurin, Artur; Сараев, А. В.; Yona, Mor; Gutnik, Yivgeni; Faber, Sharon; Etzion, Aviad; Klein, Itzik

doi:10.1109/access.2022.3144076

Cited by 15 publications

(8 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The stationary conditions field experiment dataset is based on a dataset published in [53]. There, a unique device, as shown in Figure 9 was built to align between a Huawei P40 smartphone and an Inertial Lab MRU-P unit [54].…”

Section: B Field Experiments Datasetmentioning

confidence: 99%

“…Here, noisy samples are given by a consumergrade smartphone sensor, whose readings are submerged in lower levels of stochastic noise but higher bias levels, as smartphones can be prone to mechanical shocks that impair the orthogonality of the sensor axes. In contrast, the GT references are taken from a high-end sensor, whose accurate measurements are characterized by significantly lower noise levels [53]. In other words, the generalization task here is to find an approximation function that mimics best the GT sensor.…”

Section: B Experimental Assessmentmentioning

confidence: 99%

See 1 more Smart Citation

Data-Driven Denoising of Accelerometer Signals

Engelsman¹,

Klein²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

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. Both our code and dataset are publicly available @ GitHub.

show abstract

Section: B Field Experiments Datasetmentioning

confidence: 99%

Section: B Experimental Assessmentmentioning

confidence: 99%

Data-Driven Denoising of Accelerometer Signals

Engelsman¹,

Klein²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…To evaluate QuadNet's performance relative to the QDR approach, the same dataset as in [19] was used. This dataset was recently published in the autonomous platforms inertial dataset [43] and is available at https://github.com/ansfl/Navigation-Data-Project/, accessed on 22 December 2020.…”

Section: Data Collection and Preprocessingmentioning

confidence: 99%

QuadNet: A Hybrid Framework for Quadrotor Dead Reckoning

Shurin

Klein

2022

Sensors

Self Cite

View full text Add to dashboard Cite

Quadrotor usage is continuously increasing for both civilian and military applications such as surveillance, mapping, and deliveries. Commonly, quadrotors use an inertial navigation system combined with a global navigation satellite systems receiver for outdoor applications and a camera for indoor/outdoor applications. For various reasons, such as lighting conditions or satellite signal blocking, the quadrotor’s navigation solution depends only on the inertial navigation system solution. As a consequence, the navigation solution drifts in time due to errors and noises in the inertial sensor measurements. To handle such situations and bind the solution drift, the quadrotor dead reckoning (QDR) approach utilizes pedestrian dead reckoning principles. To that end, instead of flying the quadrotor in a straight line trajectory, it is flown in a periodic motion, in the vertical plane, to enable peak-to-peak (two local maximum points within the cycle) distance estimation. Although QDR manages to improve the pure inertial navigation solution, it has several shortcomings as it requires calibration before usage, provides only peak-to-peak distance, and does not provide the altitude of the quadrotor. To circumvent these issues, we propose QuadNet, a hybrid framework for quadrotor dead reckoning to estimate the quadrotor’s three-dimensional position vector at any user-defined time rate. As a hybrid approach, QuadNet uses both neural networks and model-based equations during its operation. QuadNet requires only the inertial sensor readings to provide the position vector. Experimental results with DJI’s Matrice 300 quadrotor are provided to show the benefits of using the proposed approach.

show abstract

“…The dataset was created by collecting DVL data from nine different missions performed by the AUV with a total time duration of 13,886 seconds, which translates to the same number of DVL measurements and 1,388,600 IMU measurements. This dataset is described in Shurin et al (2022) and can be found on https://github.com/ansfl/Navigatio n-Data-Project/. Each of the missions had different parameters regarding the length of the mission, the objective, the speed of the AUV, the depth of the AUV, and the maneuvers it performed.…”

Section: Auv Sea Experimentsmentioning

confidence: 99%

“…In parallel to the developments in underwater navigation, data-driven approaches show great results in different fields to improve navigation accuracy and robustness. In Shurin, Saraev, Yona, Gutnik, Faber, Etzion and Klein (2022) deep hybrid learning approach was implemented to improve quadrotor dead reckoning. In the field of indoor navigation with pedestrian dead reckoning, learning frameworks showed superior results over model-based approaches Gu, Khoshelham, Yu and Shang (2018); Chen, Zhao, Lu, Wang, Markham and Trigoni (2020); Asraf, Shama and Klein (2021).…”

Section: Introductionmentioning

confidence: 99%

BeamsNet: A data-driven Approach Enhancing Doppler Velocity Log Measurements for Autonomous Underwater Vehicle Navigation

Cohen,

Klein

2022

Preprint

Self Cite

View full text Add to dashboard Cite

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. This paper proposes 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.

show abstract

The Autonomous Platforms Inertial Dataset

Cited by 15 publications

References 36 publications

Data-Driven Denoising of Accelerometer Signals

Data-Driven Denoising of Accelerometer Signals

QuadNet: A Hybrid Framework for Quadrotor Dead Reckoning

BeamsNet: A data-driven Approach Enhancing Doppler Velocity Log Measurements for Autonomous Underwater Vehicle Navigation

Contact Info

Product

Resources

About