Much navigation over the last several decades has been aided by the global navigation satellite system (GNSS). In addition, with the advent of the multi-GNSS era, more and more satellites are available for navigation purposes. However, the navigation is generally carried out by point positioning based on the pseudoranges. The real-time kinematic (RTK) and the advanced technology, namely, the network RTK (NRTK), were introduced for better positioning and navigation. Further improved navigation was also investigated by combining other sensors such as the inertial measurement unit (IMU). On the other hand, a deep learning technique has been recently evolving in many fields, including automatic navigation of the vehicles. This is because deep learning combines various sensors without complicated analytical modeling of each individual sensor. In this study, we structured the multilayer recurrent neural networks (RNN) to improve the accuracy and the stability of the GNSS absolute solutions for the autonomous vehicle navigation. Specifically, the long short-term memory (LSTM) is an especially useful algorithm for time series data such as navigation with moderate speed of platforms. From an experiment conducted in a testing area, the LSTM algorithm developed the positioning accuracy by about 40% compared to GNSS-only navigation without any external bias information. Once the bias is taken care of, the accuracy will significantly be improved up to 8 times better than the GNSS absolute positioning results. The bias terms of the solution need to be estimated within the model by optimizing the layers as well as the nodes each layer, which should be done in further research.
From the late 1990s, many studies on local geoid construction have been made in South Korea. However, the precision of the previous geoid has remained about 15 cm due to distribution and quality problems of gravity and GPS/levelling data. Since 2007, new land gravity data and GPS/levelling data have been obtained through many projects such as the Korean Land Spatilaization, Unified Control Point and Gravity survey on the Benchmark. The newly obtained data are regularly distributed to a certain degree and show much better improvement in their quality. In addition, an airborne gravity survey was conducted in 2008 to cover the Korean peninsula (South Korea only). Therefore, it is expected that the precision of the geoid could be improved. In this study, the new South Korean gravimetric geoid and hybrid geoid are presented based on land, airborne, ship‐borne, altimeter gravity data, geopotential model and topographic data. As for the methodology, the general remove‐restore approach was applied with the best chosen parameters in order to produce a precise local geoid. The global geopotential model EGM08 was used to remove the low‐frequency components using degree and order up to 360 and the short wavelength part of the gravity signal was dealt with by using the Shuttle Radar Topography Mission data. The parameters determined empirically in this study include for Stokes’ integral 0.5° and for Wong‐Gore kernel 110–120°, respectively and 10 km for both the Bjerhammar sphere depth and attenuation factor. The final gravimetric geoid in South Korea ranges from 20–31 m with a precision of 5.45 cm overall compared to 1096 GPS/levelling data. In addition, the South Korean hybrid geoid produces 3.46 cm and 3.92 cm for degrees of fitness and precision, respectively and a better statistic of 2.37 cm for plain and urban areas was achieved. The gravimetric and hybrid geoids are expected to improve further when the refined land gravity data are included in the near future.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.