Deep Learning for Inertial Navigation
A short review of cutting edge deep learning-based solutions for inertial navigation.
Introduction
Many vision-aiding navigation approaches have been presented in the last decade, as there is a wide range of applications these days (Huang, 2019). In other words, the classical field of inertial navigation with low-cost inertial sensors as the only source of information has begun to receive attention from the novel deep-learning methods involved. The main problem of inertial navigation is drift, which is a crucial source of error. More problems involve wrong initialization, incorrect sensor modeling, and approximation errors.
In this post, we reviewed the integration of deep learning and inertial measurement unit (IMU) in the classic inertial navigation system (INS), which only solved some of the above problems. First, we present some cutting-edge architectures to improve speed estimation, noise reduction, zero-velocity detection, and attitude & position prediction. Secondly, the KITTI and OxIOD datasets are discussed. Lastly, schemes of pedestrian inertial navigation with deep learning are presented.
Cutting-edge deep learning-based Solutions
One of the main problems in the navigation field is speed estimation. As the estimation becomes accurate, it will also affect the position solution. In a work published in 2018 by Cortes et al., a deep learning-based speed estimation approach was suggested. The main idea was to add a speed constraint to the classical Inertial Navigation System (INS). They estimated the speed from the IMU only by using a CNN and then constrained the INS solution by this prediction. Formulating this estimation as a regression deep learning task, where the inputs are the six-channel of the IMU over a few seconds, and the output is the speed, which will improve trajectory tracking and motion mode classification.
The next work I want to present is regarding noise reduction. As many low-cost sensors suffer from the high magnitude of noise and are characterized by a noise profile, where the noise changes with time, there is a need to filter it. However, as these noise profiles are difficult to estimate, the use of a deep learning-based approach seems to solve this issue. Chen et al (2018) presented a novel deep-learning approach to deal with many error sources in sensor signals. By doing that, the sensors' signals can be corrected and only then to be used in the navigation scheme. They report that the accuracy of correctly identifying IMU signals is 80%. CNN was also used in this work, where it includes 5 convolutional layers and one fully-connected layer.
Another work by Wagstaff and Kelly (2018) involves indoor navigation tasks, in which a scheme to detect foot zero velocity was presented. By doing so, the accuracy of the velocity estimation is provided, and the accuracy is improved through the general INS. The detection was done by designing a Long Short-Term Memory (LSTM) neural network. By evaluating the design for indoor pedestrian motion data over 7.5 [km], they reported a reduction of more than 34% in positioning error. Their architecture includes 6-layers LSTM, each with 80 units, and a single fully-connected layer after LSTM.
The last work I want to discuss is related to one of the main problems in the navigation field: attitude and position prediction. Achieving precise state estimation of attitude is very important to multirotor systems, as small errors might lead to instability and eventually disaster. A work by Al-Sharman et al. (2019) presents a deep learning-based state estimation enhancement with a particular application to attitude estimation. They tackled the problem of precise attitude estimation by noise reduction technique, thereby determining the characteristics of measurement noise. They used a simple multilayer neural network with a dropout technique, which exhibited superiority over conventional approaches.
Common dataset
There are two common datasets available to evaluate the different suggestion approaches, and the first one is the KITTI dataset of the Karlsruhe Institute of Technology, which contains a significant amount of data: Velodyne, IMU, GPS, camera calibration, grayscale stereo sequences, 3D object trucklet labels, and many more. The paper by Geiger et al. (2013) reviews the entire dataset. Alto KITTI is the primary dataset in the field, and I would like to mention another entirely new dataset called “OxIOD” by Oxford. It is used for deep inertial odometry, and the complete information is available in the paper by Chen et al. (2018).
Pedestrian Inertial Navigation
Recently, there has been a growing interest in applying deep learning techniques to motion sensing and location estimation of pedestrians. In the work of Chen et al. (2020), a deep learning-based pedestrian INS method, dataset, and interface on the device were reviewed. In their work, they proposed L-IONet, a framework to learn inertial tracking from raw data. The architecture contains mainly 1D dilated convolutional layers, which are inspired by WaveNet and have fully connected layers.
Another work, by Klein et al (2020) presents the StepNet: a deep learning approach for step length estimation. The authors addressed the pedestrian indoor dead reckoning by a family of deep learning-based approaches to regress the step length. The suggested StepNet outperforms the traditional approaches as described in their paper.
Summary
With the popularity of deep learning keeps rising, it appears to solve many classical problems in the field of inertial navigation. As we described in this post, some researchers have addressed the integration of deep learning and inertial navigation with promising results.
References
Huang, Guoquan. “Visual-inertial navigation: A concise review.” 2019 International Conference on Robotics and Automation (ICRA). IEEE, 2019.
Cortés, Santiago, Arno Solin, and Juho Kannala. “Deep learning based speed estimation for constraining strapdown inertial navigation on smartphones.” 2018 IEEE 28th International Workshop on Machine Learning for Signal Processing (MLSP). IEEE, 2018.
Chen, Hua, et al. “Improving inertial sensor by reducing errors using deep learning methodology.” NAECON 2018-IEEE National Aerospace and Electronics Conference. IEEE, 2018.
Wagstaff, Brandon, and Jonathan Kelly. “LSTM-based zero-velocity detection for robust inertial navigation.” 2018 International Conference on Indoor Positioning and Indoor Navigation (IPIN). IEEE, 2018.
Al-Sharman, Mohammad K., et al. “Deep-learning-based neural network training for state estimation enhancement: application to attitude estimation.” IEEE Transactions on Instrumentation and Measurement 69.1 (2019): 24–34.
Geiger, Andreas, et al. “Vision meets robotics: The kitti dataset.” The International Journal of Robotics Research 32.11 (2013): 1231–1237.
Chen, Changhao, et al. “Oxiod: The dataset for deep inertial odometry.” arXiv preprint arXiv:1809.07491 (2018).
Chen, Changhao, et al. “Deep-Learning-Based Pedestrian Inertial Navigation: Methods, Data Set, and On-Device Inference.” IEEE Internet of Things Journal 7.5 (2020): 4431–4441.
Klein, Itzik, and Omri Asraf. “StepNet — Deep Learning Approaches for Step Length Estimation.” IEEE Access 8 (2020): 85706–85713.
About the Author
Dr. Barak Or is a well-versed professional in the field of artificial intelligence and data fusion. He is a researcher, lecturer, and entrepreneur who has published numerous patents and articles in professional journals. Dr. Or is also the founder of ALMA Tech. LTD, an AI and advanced navigation company. He has worked with Qualcomm as DSP and machine learning algorithms expert. He completed his Ph.D. in machine learning for sensor fusion at the University of Haifa, Israel. He holds M.Sc. (2018) and B.Sc. (2016) degrees in Aerospace Engineering and B.A. in Economics and Management (2016, Cum Laude) from the Technion, Israel Institute of Technology. He has received several prizes and research grants from the Israel Innovation Authority, the Israeli Ministry of Defence, and the Israeli Ministry of Economic and Industrial. In 2021, he was nominated by the Technion for “graduate achievements” in the field of High-tech.
Website www.barakor.com Linkedin www.linkedin.com/in/barakor/ YouTube www.youtube.com/channel/UCYDidZ8GUzUy_tYtxvVjRiQ
