• The Journal of Korea Robotics Society
• /
• v.19 no.1
• /
• pp.92-97
• /
• 2024

This paper provides a study of distributional perspective on reinforcement learning for application in mobile robot navigation. Mapless navigation algorithms based on deep reinforcement learning are proven to promising performance and high applicability. The trial-and-error simulations in virtual environments are encouraged to implement autonomous navigation due to expensive real-life interactions. Nevertheless, applying the deep reinforcement learning model in real tasks is challenging due to dissimilar data collection between virtual simulation and the physical world, leading to high-risk manners and high collision rate. In this paper, we present distributional reinforcement learning architecture for mapless navigation of mobile robot that adapt the uncertainty of environmental change. The experimental results indicate the superior performance of distributional soft actor critic compared to conventional methods.

• Journal of Positioning, Navigation, and Timing
• /
• v.13 no.3
• /
• pp.309-317
• /
• 2024

Satellite and receiver Inter-Frequency Biases (IFBs) should be estimated or calibrated by pre-defined values for generating precise navigation messages and augmentation data in satellite navigation systems or the augmentation system. In this paper, a Kalman filter is designed and implemented to estimate the ionospheric delay and satellite/receiver IFBs using a regional receiver network. First, an ionospheric model and its filter parameter is defined based on previous studies. Second, a measurement model for estimating the relative satellite/receiver IFBs without any constraints is proposed. Third, a procedure for ensuring the continuity of estimation is proposed in this paper. To verify the performance of the designed filter, six Continuously Operating Reference Stations (CORSs) are selected. Finally, the stability and accuracy of satellite/receiver IFB estimation are analyzed.

• Journal of Positioning, Navigation, and Timing
• /
• v.4 no.2
• /
• pp.43-55
• /
• 2015

In the case of satellite navigation positioning, the shielding of satellite signals is determined by the environment of the region at which a user is located, and the navigation performance is determined accordingly. The accuracy of user position determination varies depending on the dilution of precision (DOP) which is a measuring index for the geometric characteristics of visible satellites; and if the minimum visible satellites are not secured, position determination is impossible. Currently, the GLObal NAvigation Satellite system (GLONASS) of Russia is used to supplement the navigation performance of the Global Positioning System (GPS) in regions where GPS cannot be used. In addition, the European Satellite Navigation System (Galileo) of the European Union, the Chinese Satellite Navigation System (BeiDou) of China, the Quasi-Zenith Satellite System (QZSS) of Japan, and the Indian Regional Navigation Satellite System (IRNSS) of India are aimed to achieve the full operational capability (FOC) operation of the navigation system. Thus, the number of satellites available for navigation would rapidly increase, particularly in the Asian region; and when integrated navigation is performed, the improvement of navigation performance is expected to be much larger than that in other regions. To secure a stable and prompt position solution, GPS-GLONASS integrated navigation is generally performed at present. However, as available satellite navigation systems have been diversified, finding the minimum satellite constellation combination to obtain the best navigation performance has recently become an issue. For this purpose, it is necessary to examine and predict the navigation performance that could be obtained by the addition of the third satellite navigation system in addition to GPS-GLONASS. In this study, the current status of the integrated navigation performance for various satellite constellation combinations was analyzed based on 2014, and the navigation performance in 2020 was predicted based on the FOC plan of the satellite navigation system for each country. For this prediction, the orbital elements and nominal almanac data of satellite navigation systems that can be observed in the Korean Peninsula were organized, and the minimum elevation angle expecting signal shielding was established based on Matlab and the performance was predicted in terms of DOP. In the case of integrated navigation, a time offset determination algorithm needs to be considered in order to estimate the clock error between navigation systems, and it was analyzed using two kinds of methods: a satellite navigation message based estimation method and a receiver based method where a user directly performs estimation. This simulation is expected to be used as an index for the establishment of the minimum satellite constellation for obtaining the best navigation performance.

• The Journal of Korea Robotics Society
• /
• v.3 no.3
• /
• pp.194-202
• /
• 2008

This paper describes a new method for indoor environment mapping and localization with stereo camera. For environmental modeling, we directly use the depth and color information in image pixels as visual features. Furthermore, only the depth and color information at horizontal centerline in image is used, where optical axis passes through. The usefulness of this method is that we can easily build a measure between modeling and sensing data only on the horizontal centerline. That is because vertical working volume between model and sensing data can be changed according to robot motion. Therefore, we can build a map about indoor environment as compact and efficient representation. Also, based on such nodes and sensing data, we suggest a method for estimating mobile robot positioning with random sampling stochastic algorithm. With basic real experiments, we show that the proposed method can be an effective visual navigation algorithm.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.16 no.2
• /
• pp.191-198
• /
• 2013

Geo-pointing is a function that maintains LOS(Line of Sight) to a stationary ground target by controlling azimuth and elevation angles of a EOS(Electro-Optical System) which are calculated from aircraft navigation data and target coordinates. In design and implementation of the geo-pointing, a transmission time delay between GPS/INS and EOS is a major degradation factor of the geo-pointing performance when the aircraft is rapidly maneuvered especially. In this paper, a kalman filter is designed to compensate the transmission time delay of aircraft navigation data. Simulation and test results show that the geo-pointing performance is enhanced by the proposed compensation technique.

• Proceedings of the KSR Conference
• /
• 2010.06a
• /
• pp.1061-1067
• /
• 2010

In this paper, we propose a simulator for testing of the Navigation Control System(NCS) in Bimodal-tram. NCS uses values of all sorts of sensors installed in vehicle to decide current position, and to control speed and steering of vehicle to go to a next position. Major functions of simulator are input processing of the driver and generation of virtual sensor data and driving profile(navigation path, magnetic information), and the NCS function. Virtual sensor data is generated according to output data from the NCS, driving profile and input processing of the driver, and monitoring systems is operated separatedly to confirm of NCS operation. This paper discusses about the implementation of the simulator, and analyzes and evaluates the simulation results.

• Journal of information and communication convergence engineering
• /
• v.7 no.3
• /
• pp.297-303
• /
• 2009

Automatic Identification System (AIS) is a VHF radio broadcasting system where transmits packets of data via VHF data link. It enables vessels and coastal-based station that equipped with AIS equipment to send and receive useful information. This information can be help in situational awareness and provide a means to assist in collision avoidance. In addition, AIS can be use as Aid-To-Navigation, by providing the location and additional information on buoys and lights. Besides, it can also contain details information in meteorological status of a particular ship location. This paper presents the standalone AIS system that able to receive and report own ship location, meteorological data collection and broadcast safety related information if necessary. With the unique ship's MMSI number, all the information of that particular ship can be monitor by using AIS program written in C++ programming language.

• Bulletin of the Korean Space Science Society
• /
• 2004.10b
• /
• pp.376-379
• /
• 2004

Operational orbit determination (OOD) depends on the capability of generating accurate prediction of spacecraft ephemeris in a short period. The predicted ephemeris is used in the operations such as instrument pointing and orbit maneuvers. In this study the orbit prediction problem consists of the estimating diverse arc length orbit using GPS navigation data, the predicted orbit for the next 48 hours, and the fitted 30-hour arc length orbits of double differenced GPS measurements for the predicted 48-hour period. For 24-hour orbit arc length, the predicted orbit difference from truth orbit was 205 meters due to the along-track error. The main error sources for the orbit prediction of the Low Earth Orbiter (LEO) satellite are solar pressure and atmosphere density.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.19 no.2
• /
• pp.163-170
• /
• 2016

Tropospheric delay is one of the largest error source in pseudolite navigation system. Because a pseudolite is installed on the ground and transmits its signal to a user in the air or on the ground, the conventional tropospheric delay model developed for a satellite navigation doesn't work properly. In this paper, performance analysis of several pseudolite tropospheric delay models has been done using meteorological data. Based on the result, a new compensation method for Hopfield model has been proposed.

• Journal of Korean Society for Geospatial Information Science
• /
• v.24 no.2
• /
• pp.37-46
• /
• 2016

The difference between definition time of GPS (Global Positioning System) position data and actual display time of car positions on a map could reduce the accuracy of car positions displayed in PND (Portable Navigation Device)-type CNS (Car Navigation System). Due to the time difference, the position of the car displayed on the map is not its current position, so an improved method to fix these problems is required. It is expected that a method that uses predicted future positionsto compensate for the delay caused by processing and display of the received GPS signals could mitigate these problems. Therefore, in this study an analysis was conducted to correct late processing problems of map positions by mapmatching using a Kalman filter with only GPS position data and a RRF (Road Reduction Filter) technique in a light-weight CNS. The effects on routing services are examined by analyzing differences that are decomposed into along and across the road elements relative to the direction of advancing car. The results indicate that it is possible to improve the positional accuracy in the along-the-road direction of a light-weight CNS device that uses only GPS position data, by applying a Kalman filter and RRF.