GPS World

Tag: neural network

  • GNSS, INS and neural networks combine for Arctic navigation

    GNSS, INS and neural networks combine for Arctic navigation

    GNSS receivers combined with inertial navigation systems (INS) have been widely applied to various mobile platforms.

    However, in Arctic regions, GNSS positioning accuracy is severely degraded from low satellite elevation angles, frequent ionospheric disturbances, and insufficient visible satellites.

    Moreover, the limited validation of existing onboard navigation systems further exacerbates the challenges of Arctic navigation.

    To address these issues, a new research paper describes a hybrid neural network model based on temporal convolutional networks (TCN) and long short-term memory (LSTM) networks. The hybrid solution has been tested in the Artic with successful results.

    The paper, “Robust GNSS/INS Integrated Navigation in Arctic GNSS-Challenged Environments Based on TCN-LSTM and MDAREKF,” is authored by Wei Liu, Tengfei Qi, Yuan Hu, Kaiwei Zhu, Tsung-Hsuan Hsieh and Shengzheng Wang of Shanghai Maritime University (DOI 10.1088/1361-6501/ae5279).

    The proposal combines the pseudo-measurement information of GNSS predicted by the model with INS for integrated navigation to compensate for the interruption of GNSS and correct the error of INS.

    Considering the potential bias in predicted pseudomeasurements, an adaptive robust extended Kalman filter (AREKF) algorithm based on Mahalanobis distance is further developed to dynamically adjust the innovation covariance matrix, thereby enhancing filter robustness.

    Field experiments conducted on an Arctic survey vessel demonstrate that the proposed TCN-LSTM combined with AREKF significantly improves both the robustness and accuracy of integrated navigation under GNSS-constrained environments. In particular, during GNSS outages of 50 seconds, 140 seconds and 400 seconds, the proposed method reduces the horizontal root mean square error (RMSE) by 47%, 38% and 76% respectively.

  • AI helps create street maps from satellite imagery

    AI helps create street maps from satellite imagery

    Creating detailed street maps and keeping them updated is an expensive and time-consuming task performed mostly by large companies. They ignore the many parts of the world where this task is not profitable, even though the need is high due to rapid growth and change in the street network, such as in Thailand.

    To automate the process and make accurate digital maps available in any country, researchers at the Massachusetts Institute of Technology (MIT) and the Qatar Computing Research Institute have developed an artificial intelligence (AI) model called RoadTagger. It uses satellite imagery to tag road features in digital maps, such as lane counts, which are essential for reliable navigation.

    Satellite imagery companies are constantly expanding their coverage and increasing their refresh rate, so this source of mapping data is more readily available and up to date than the data collected on the ground, such as by Google’s fleet of mapping cars. However, satellite imagery often suffers from occlusion from trees, buildings, overpasses and other obstacles.

    RoadTagger gets around this problem by using a combination of neural network architectures to predict hidden features. Testing of the model with digital maps of 20 U.S. cities showed that it predicted the number of lanes with 77% accuracy and the road type with 93% accuracy.

    An AI model developed at MIT and Qatar Computing Research Institute that uses only satellite imagery to automatically tag road features in digital maps could improve GPS navigation, especially in countries with limited map data. (Image: Google Maps/MIT News)
    An AI model developed at MIT and Qatar Computing Research Institute that uses only satellite imagery to automatically tag road features in digital maps could improve GPS navigation, especially in countries with limited map data. (Map data: Google/MIT News)

    RoadTagger, which combines a convolutional neural network (CNN) and a graph neural network (GNN) is fed only raw data and automatically produces output, without human intervention. The CNN, commonly used for image-processing tasks, takes as input raw satellite images of target roads. The GNN — widely used to model relationships between connected nodes in a graph — breaks the road into roughly 20-meter “tiles,” each of which is a separate graph node.

    For each node, the CNN extracts road features and shares that information with its immediate neighbors, thereby propagating road information along the whole graph. For example, if only two lanes of a four-lane road are visible in an image, the model uses information from nearby tiles, such as road width, to conclude that the road has four lanes.

    The researchers trained and tested RoadTagger using the OpenStreetMap data set. First, they collected confirmed road attributes from 688 square kilometers of maps of 20 U.S. cities, then they gathered the corresponding satellite images from a Google Maps dataset. The training taught the model what weight to assign to various features and node connections, and it now automatically learns which image features are useful and how to propagate those features along the graph.

    The researchers hope that RoadTagger will help humans validate the constant stream of changes in OpenStreetMap and similar datasets as well as enrich them with details that they do not already contain, such as whether a road is paved.

    Citation. He, S., Bastani, F., Jagwani, S., Park, E., Abbar, S., Alizadeh, M., Balakrishnan, H., Chawla, S., Madden, S., & Sadeghi, M. A. (Dec. 28, 2019). “RoadTagger: Robust Road Attribute Inference with Graph Neural Networks.” arXiv:1912.12408v1.