WO2020234513A1

WO2020234513A1 - Verifying positioning data

Info

Publication number: WO2020234513A1
Application number: PCT/FI2020/050334
Authority: WO
Inventors: Lauri Lipasti; Miika IHONEN
Original assignee: Navigs Oy
Priority date: 2019-05-20
Filing date: 2020-05-19
Publication date: 2020-11-26
Also published as: FI20195412A1

Abstract

A method comprising determining, by a positioning unit, a first location and a second location, wherein the first location is determined by a first receiver that is of a first implementation based on a first satellite-based positioning system and the second location is determined by a second receiver that is of a second implementation based on the first satellite-based positioning system; comparing the first location and the second location and if the second location is within a threshold deviation from the first location determining that the first location is reliable.

Description

VERIFYING POSITIONING DATA

FIELD

The present application relates to determining a position based on signals received. BACKGROUND

A position of an object may be determined based on a positioning signal received. The positioning signal may be received from a satellite and the received signal may be used as an input based on which the position is determined. Yet, the determined position may not always be accurate or there may be incorrect positions determined based on interference in the received signal for example.

BRIEF DESCRIPTION

According to an aspect there is provided a method comprising determining, by a positioning unit, a first location and a second location, wherein the first location is determined by a first receiver that is of a first implementation based on a first satellite-based positioning system and the second location is determined by a second receiver that is of a second implementation based on the first satellite-based positioning system; comparing the first location and the second location and if the second location is within a threshold deviation from the first location determining that the first location is reliable.

According to another aspect there is provided an apparatus comprising means for determining a first location and a second location, wherein the first location is determined by a first receiver that is of a first implementation based on a first satellite-based positioning system and the second location is determined by a second receiver that is of a second implementation based on the first satellite- based positioning system; comparing the first location and the second location and if the second location is within a threshold deviation from the first location determining that the first location is reliable.

According to another aspect there is provided an apparatus comprising at least one processor, and at least one memory including a computer program code, wherein the at least one memory and the computer program code are configured, with the at least one processor, to cause the apparatus to determine a first location and a second location, wherein the first location is determined by a first receiver that is of a first implementation based on a first satellite-based positioning system and the second location is determined by a second receiver that is of a second implementation based on the first satellite-based positioning system; compare the first location and the second location and if the second location is within a threshold deviation from the first location determine that the first location is reliable.

According to another aspect there is provided a computer program product which when executed by a computing apparatus causes the apparatus to perform determining, by a positioning unit, a first location and a second location, wherein the first location is determined by a first receiver that is of a first implementation based on a first satellite-based positioning system and the second location is determined by a second receiver that is of a second implementation based on the first satellite-based positioning system; comparing the first location and the second location and if the second location is within a threshold deviation from the first location determining that the first location is reliable.

According to another aspect there is provided a computer program product comprising computer program code stored in a non-transitory memory medium, the computer program code being configured to cause an apparatus, when executing the program code by a processor circuitry, to perform at least the following: determining, by a positioning unit, a first location and a second location, wherein the first location is determined by a first receiver that is of a first implementation based on a first satellite-based positioning system and the second location is determined by a second receiver that is of a second implementation based on the first satellite-based positioning system; comparing the first location and the second location and if the second location is within a threshold deviation from the first location determining that the first location is reliable. BRIEF DESCRIPTION OF THE DRAWINGS

Figure 1 illustrates an exemplary embodiment of a satellite-based positioning system;

Figure 2 illustrates an exemplary embodiment of determining a position of a self-driving vehicle;

Figures 3 and 4 illustrate exemplary embodiments of a positioning unit;

Figure 5 illustrates a flow chart; and

Figure 6 illustrates an exemplary embodiment of an apparatus. DETAILED DESCRIPTION

The following embodiments are exemplifying. Although the specification may refer to "an", "one", or "some" embodiment(s) in several locations of the text, this does not necessarily mean that each reference is made to the same embodiment(s), or that a particular feature only applies to a single embodiment. Single features of different embodiments may also be combined to provide other embodiments.

Self-driving vehicles that do not necessarily need a person to control the movement of the vehicle may have various benefits and may increase the efficiency of the vehicle, security relating to operating the vehicle and also reduce costs related to operating the vehicle. Such self-driving vehicles may include cars, agricultural vehicles and vessels for example.

Self-driving may also be called autonomous driving. Various levels of autonomous operation of a self-driving vehicle may be utilized. For example, autonomous driving may take place when parking a vehicle for example or preventing the vehicle from colliding to an object that has been detected. In some exemplary embodiments a driver may still override the operations caused by autonomous driving of the vehicle. The overriding may take place in the vehicle or it may also take place by controlling the vehicle remotely using a remote device for example.

In some exemplary embodiments, the various level of autonomous driving may be divided into six different levels. At the first level, the autonomous driving provides help to the driver, but the driver is in control in each situation. For example, the self-driving may detect that the vehicle is too close to another vehicle and the signal a warning to the driver, but not take any action to alter the way the vehicle is being driven. Additionally, in some exemplary embodiments, the self diving may momentarily intervene by reducing the speed for example.

At the second level the self-driving may have some control of the vehicle being driven in addition to the driver controlling the vehicle. For example, if the speed is to be maintained at a certain level, the driver may determine the level and the self-driving then controls the vehicle such that the speed is kept at the determined level. Additionally, or alternatively, in some examples, the self-driving may park the vehicle independently.

At the third level the self-driving may control the operation of the vehicle independently, but the driver may still interfere if needed. For example, the self-driving may control the speed and steering of the vehicle but alert the driver in certain situations such that the driver may take over and control the vehicle. The driver therefore should at all times be prepared to take over the control from the self-driving.

At the fourth level the self-driving may control the operation of the vehicle also in situations that that may be critical but may alert the driver to take over as well. Therefore, the driver still needs to be prepared to take over controlling the vehicle from the self-driving.

At the fifth level the self-driving the vehicle may be operated by self driving in most situations but there may still be situations in which a driver is to take over. At the sixth level on the other hand the vehicle may be completely self- driven, and a driver is not expected to take over the control in any situation.

For a self-driving vehicle to be able to autonomously control the vehicle, it needs information from the surrounding environment. To gather such information, various sensors may be utilized to determine the needed information based on input provided by the sensors. The determination may be done by a control unit that may utilize computer program instructions to interpret the input received from the sensors and to determine howto operate the vehicle in response. The control unit may be an apparatus comprised in or connected to the self-driving vehicle. The sensors may comprise for example one or more radars, one or more cameras that may be for example 360 daylight cameras or thermal cameras, meteorological sensors, oceanographic sensors, inertial measurement sensors and location sensors.

The control unit may then interpret the input received from one or more sensors in order to detect for example the location of the vehicle, recognizing objects in the surrounding environment and relevant signage. In some exemplary embodiments image recognition may be applied to data received from one or more cameras. In order to recognize objects from the data received from the one or more cameras, artificial intelligence such as machine learning may be utilized. For example, in order to determine if an object in the data received from the one or more cameras is a person or not.

A self-driving vehicle may further have connectivity such as wireless connectivity that enables another apparatus to remotely connect to the self-driving vehicle. This connectivity may allow remote control of the self-driving vehicle as well as receiving data from the self-driving vehicle. The data may include for example the location of the vehicle, the speed of the vehicle and so on. The wireless connectivity may be for example cellular connectivity based such as 4G or 5G.

In order to determine the location of an object, Global Navigation Satellite System, GNSS, may be utilized as illustrated in Figure 1. GNSS comprises satellites 110 that orbit around the Earth and send signals that may be received by a receiver 120 and used as a basis for determining the location of the object that comprised the receiver 120. The receiver 120 may, in some exemplary embodiments, comprise two parts: an antenna and a processing unit. The antenna may receive a signal transmitted by a satellite 120 and the processing unit may determine, based on the signal received by the antenna, measurements such as latitude and longitude that may be used to determine a location. It is to be noted that the location determined corresponds to the location of the antenna that received the signal. In some exemplary embodiments, the antenna and the processing unit may be connected to each other but may be located separately. In some further exemplary embodiments, the antenna may be integrated to a circuit board as a so-called chip antenna. The antenna may be internal, such as a chip antenna, or it may be external antenna connected to a processing unit.

A signal 130 transmitted by a satellite 110 comprises data regarding positioning and timing. The signal 130 may be transmitted from the satellite 110 along a line of site using one or more carrier waves. The timing data may be used by the receiver 120 to determine current local data with high precision thereby allowing synchronization. In this exemplary embodiment, the satellites 110 orbit the Earth once in every 11 hours, 58 minutes and 2 seconds at a medium orbit altitude. The signal 130 that may be transmitted by a satellite 110 may be coded and it may comprise data regarding the satellite’s precise orbit details and a time stamp from an atomic clock. It is to be noted that satellites 110 comprised in the GNSS may vary in terms of their age and design. A satellite 110 may transmit two carrier waves in the L-band, LI and L2. These carries waves may be used to transmit the signal 130. In order to determine the position of the receiver 120, or the antenna 120, signal 130 may be received from more than one satellite 110. For example, a signal may be received from 3 or more satellites. The location of the receiver 120, or the antenna, may then be determined with regard to each satellite from which a signal 130 was received and used to determine the location by the processing unit. The location may be determined for example in terms of an Earth- based coordinate system comprising latitude, longitude and altitude. In some examples, signals 130 are to be received from at least three satellites 110 in order to determine a location and the more there are satellites 110 from which a signal is received the more reliable and accurate the determined location may be.

The accuracy of the determined position may vary. To enable determining a more precise position, the GNSS may be enhanced. Differential GNSS is an example of such enhancement. Differential GNSS comprises a network of reference stations 140 located on the Earth that broadcast differential information to the receivers 120. A reference station has a static position that is known. This static position may then be compared with a position determined based on GNSS as described above. As the static position and determined position are compared, a difference between the positions may be determined. As the static position is the correct position, an error in the determined position may be determined and data regarding the determined error may be provided to the receiver 120. The error may be provided using for example an indication 150 that may be transmitted using wireless communication. The error may then be taken into account by the receiver and the receiver 120 may determine a position with enhance accuracy.

Differential GNSS may further be enhanced by a phase of the satellite carrier wave is measured. Combining the carrier wave measurement with the determined error enables the receiver 120 to determine location at an accuracy that may be for example up to 1 centimetre or below. This may be called as real time kinematic, RTK, positioning.

It is to be noticed that in order to provide the error using the indication 150 that is transmitted using wireless connectivity such as 4G or 5G the receiver 120 is to be located such that the indication may be received. In case the receiver 120 is comprised in a vessel at sea for example, then the indication may be received close to a shore for example, but not necessarily further away from the shore as the coverage of the wireless connectivity network may not reach that far into the sea.

Various satellite-based positioning systems have been developed based on GNSS, which may also be considered as a satellite-based positioning system, or its enhanced versions to enable determining of a location of a device comprising a receiver such as the receiver 120 of Figure 1. More satellite-based positioning systems may also be developed in future. Examples of such satellite-based positioning systems comprise for example, Global Positioning System GPS, Russian Global Navigation Satellite System, GLOSNASS, and Chinese Satellite Navigation System BeiDou. The GPS transmits geolocation and time information to a GPS receiver, which may be comprised in a device or a vehicle. For a GPS based determination of location to function properly, a clear line of sight to four or more GPS satellites may be required. If there are mountains or high buildings for example in the surrounding environment of the GPS receiver, the position may not be determined or may not be determined in a reliable manner. GLOSNASS comprises satellites that are located in middle circular orbit and orbit the Earth at a period of 11 hours and 15 minutes which may be beneficial at high latitudes. BeiDou comprises satellites that are located in geostationary orbit which may reduce the number of satellites required for determining a position. On the other hand, satellites in a geostationary orbit may limit the areas covered to areas on the Earth that are visible to the satellites.

If a vehicle, such as a vessel at sea or an agricultural device on a field is to operate autonomously, it may be beneficial to ensure its location is accurately determined. This may help to verify that in addition to the position of the vehicle the movement and/or orientation of the vehicle are as expected. The vehicle is expensive, and it is therefore in the interest of the owner that the vehicle is only operated in locations it is suitable for and on the other hand, big enough to cause damaged should it collide with an object in its surroundings. Accurate determination of a location may therefore be of high importance. The vehicle may for example comprise a first receiver that is configured to receive signals from satellites comprised in a satellite-based positioning system, such as one of those mentioned above, and then determine its location, a first determined location, based on the received signals. It is to be noted that the accuracy of a determined position may be different when using different satellite-based positioning systems. It is also to be noted that the amount of satellites, from which a signal is to be received in order to determine a location, may vary in various satellite-based positioning systems. In some exemplary embodiments, three different satellites may be needed while is some alternative exemplary embodiments 4 or more satellites are needed. To verify that the first determined location is reliable, a second receiver is configured to receive signals from the satellites comprised in the satellite-based positioning system and determine its location based on the signals received from the satellites. If the determined first location and the determined second location are similar enough such that the difference between the determined first and second location is below a threshold value, it may be determined that the first determined location is reliable and correct. Yet, if the difference between the first and second determined locations is above the threshold, then it may be determined that the location is not reliable and, in some example embodiments, a notification may be sent to a remote device. Alternatively, or additionally, the operation of the vehicle may be adjusted such as stopping the device and waiting for further instructions from the remote device or by handing over the controlling of the vehicle to the remoter device that may be operated by a driver for example. The threshold for determining that the determined first and second locations are similar enough may be user-defined and it may depend on the context. In other words, a user may define a value for the threshold or, alternatively or additionally, one or more algorithms may be used to determine the value for the threshold.

In some exemplary embodiments, there may be a third receiver configured to receive signals from the satellites comprised in the satellite-based positioning system and providing a third determined location based on the signals received. In such exemplary embodiment the first, second and third determined locations are compared and if the difference is less than a threshold value, it may be determined that the first determined location is reliable. In case the difference of at least one of the determined locations is above the threshold value, an indication may be provided for example to an external device that, in some exemplary embodiments, may take over the controlling of the vehicle. Alternatively, or additionally, it may be determined that the correct location is that indicated by the majority of determined locations. It is to be noted that there may be even more receivers determining the location based on a different satellite- based positioning system.

In some exemplary embodiments, a first position may be determined by a first receiver that is configured to receive signals from satellites comprised in a first satellite-based positioning system. In such exemplary embodiments, a second position may be determined by a second receiver that is configured to receive signals from satellites comprised in a second satellite-based positioning system. Additionally, a third position may be determined by a third receiver that may be configured to receive signals from satellites comprised in a satellite-based positioning system that may be the same as the first or the second satellite-based positioning system or it may be different, a third satellite-based positioning system. The reliability of the first position may be determined in a similar manner as described above.

In some further exemplary embodiments, a receiver may detect that determining a position is difficult since adjacent signals received from the satellites of a satellite-based positioning system indicate locations that do not seem to be consistent. Such situation may occur for example if there is, intentional or unintentional, interfering towards the satellite-based positioning system. It may even be that the signals are blocked, and the receiver is not able to receive some or all of the signals transmitted by the satellites of the satellite-based positioning system. In such a situation, it may be determined, by the receiver or by a computing unit connected to it that the receiver will change from the satellite-based positioning system to another satellite-based positioning system. In other words, the antenna comprised in the receiver is configured to receive signals from satellites comprised in the other satellite-based positioning system. In some exemplary embodiments, there may be more than one receiver that detects inconsistencies in their respective determined locations and the antennas of those receivers are therefore configured to receive signals from satellites comprised in the other satellite-based positioning system.

Figure 2 illustrates an exemplary embodiment for determining the reliability of the determined location. In this exemplary embodiment, a self-driving vehicle 210 is a vehicle used for agricultural work, but in some other exemplary embodiments, the self-driving vehicle could be another type of vehicle such as a vessel or a truck. The self-driving vehicle 210 comprises a positioning unit 220. The positioning unit is utilized to determine the location of the self-driving vehicle 210. In this exemplary embodiment, the positioning unit 220 comprises three different receivers, receiver 222, receiver 224 and receiver 226. In some alternative exemplary embodiments, there may be two receivers comprised in the positioning unit or, alternatively, four or more receivers. The positioning unit may be integrated to the self-driving vehicle using the same interface or interfaces as another positioning unit or module, such as a GPS positioning module, would use. This may be beneficial as it allows for easy integration of the positioning unit without a need to modify the self-driving vehicle. This may also allow an existing positioning unit to be replaced by the positioning unit 220.

The receivers 222, 224, and 226 are configured to receive a signal 240 from a satellite 230. It is to be noted that although a satellite and a signal are mentioned here, a plurality of signals from a plurality of satellites may also be received. The satellite 230 may therefore be understood to refer to more than one satellite comprised in a satellite-based positioning system 235 and the signal 240 may be understood as the signals the more than one satellites comprised in the satellite-based positioning system 235 transmit. The receiver 222 may be considered as a first receiver that has been manufactured by a first manufacturer and configured to be compatible with the satellite-based positioning system 235. In this exemplary embodiment the satellite-based positioning system 235 is RTK GNSS, but in some alternative exemplary embodiments it could be another satellite-based positioning system. The receiver 222 therefore receives a signal transmitted by a satellite 230 comprised in RTK GNSS and based on that provides a first determined location 252.

The receiver 224 may be considered as a second receiver that has been manufactured by a second manufacturer and configured to be compatible with the satellite-based positioning system 235. It is to be noted that in some alternative exemplary embodiments the receiver 224 could be configured to be compatible with another satellite-based positioning system. The receiver 224 in this exemplary embodiment receives a signal 240 transmitted by a satellite 230 comprised in the satellite-based positioning system 235 and based on that provides a second determined location 254.

The receiver 226 may be considered as a third receiver that has been manufactured by a third manufacturer and configured to be compatible with the satellite-based positioning system 235. It is to be noted that in some alternative exemplary embodiments the receiver 226 could be configured to be compatible with another satellite-based positioning system. The receiver 226 in this exemplary embodiment receives a signal 240 transmitted by a satellite 230 comprised in the satellite-based positioning system and based on that provides a third determined location 256.

The positioning unit may then be configured to compare the determined locations 252, 254 and 256. The determined locations 252, 254 and 256 indicate such location coordinates that they are all within a certain deviation 250 from each other, the location may be determined to be the first determined location. The certain deviation may correspond to a deviation value that has been predetermined for example based on the accuracy of each satellite-based positioning system or some other criteria that may be user-defined. In this exemplary embodiment, the first determined location 252 has the highest accuracy.

If, however one of the determined locations 254 or 256 indicates a location that is outside of the certain deviation 250, but the other determined location is within the certain deviation 250, then the first determined location 252 may be considered to be the location of the self-driving vehicle 210. Alternatively, or additionally, and indication 260 may be provided to a remote device 270 indicating that there is a certain level of uncertainty regarding the location. The indication 260 may be a message such as a text message or it may be a notification within an application or a phone call or any other suitable indication. The remote device 270 on the other hand may be a computer, a mobile device such as a phone or a tablet or any other device configured to receive the message 260.

Additionally, or alternatively, in some exemplary embodiments, the self-driving vehicle may comprise one or more cameras and a unit configured to determine objects based on data received from the one or more cameras. If one of the determined locations 252, 254 or 256 is outside the certain deviation 250, image recognition may be utilized to determine if there are buildings, people, big rocks or other obstacles that are to be avoided around in the adjacent environment. Image recognition may be achieved using one or more image recognition algorithms and/or artificial intelligence such as machine learning. Alternatively, or additionally, the objects recognized from the data received from the one or more cameras may be compared to pre-determined knowledge of the environment to further verify if the determined location 252 is correct. Further, an indication regarding the objects recognized using image recognition may be transmitted to the remote device 270. It is to be noted that although data received from one or more cameras is mentioned, also data received from other sensors may be utilized to verify if the first determined location 252 is reliable.

If neither of the determined locations 254 or 256 indicate coordinates within the certain deviation 250, then it may be determined that the first determined location 252 may not be reliable. Such determination may cause the self-driving vehicle 210 to take an action such as to stop the self-driving vehicle 210 or alert a user to take over the controlling of the self-driving vehicle 210, which may be achieved using a remote device in some exemplary embodiments. Alternatively, or additionally, data from other sensors may be obtained and used to determine if the first determined location 252 is reliable or not. For example, the data received from the one or more cameras may be used to recognize objects in the surrounding adjacent environment. The recognized objects may then be compared to objects known to be located in the area of the first determined location to determine if the first determined location could be reliable. Additionally, or alternatively, an indication 260 may be transmitted to the remote device 270 indicating that the first determined location 252 may not be reliable. The indication 260 may comprise data derived from other sensors as well such as objects determined based on image recognition applied to the data received from one or more cameras.

The indication 260 may be sent from a connectivity unit comprised in the self-driving vehicle. The connectivity unit may be configured to transmit and/or receive data wirelessly using for example cellular connectivity. In some exemplary embodiments, the connectivity unit may be comprised in or connected to the positioning unit 220.

In the exemplary embodiment illustrated in Figure 2, the receivers 222, 224 and 226 were obtained from different manufacturers. Therefore, it may be considered that the first receiver 222 is of first implementation, the second receiver 224 is of second implementation and the third receiver is of third implementation. It is to be noted that in some exemplary embodiments some or all of the receivers may be from one manufacturer. If the receivers are from the same manufacturer, they are considered to be of different implementation if the implementation of one receiver is independent of that of another receiver. This may be achieved for example if different algorithms are used to determine the position based on the received signal. A benefit that may be achieved if at least some of the receivers 222, 224 and 226 are of different implementation is that the locations determined may not be biased by a possible systematic error introduced in the implementation and thereby better independent of the determined location 252, 254 and 256 may be achieved. Thus, a potential error of one implementation does not reflect on all determined locations and the impact of such error may be mitigated.

Figure 3 illustrates an exemplary embodiment of an apparatus that is a positioning unit 300 such as the positioning unit 220 illustrated in Figure 2. The positioning unit 300 comprises at least two receivers, a first receiver 310 and a second receiver 320. The first receiver 310 comprises an antenna that is configured to receive signals 340 from the satellites 330 comprised in a satellite-based positioning system. The first receiver 310 further comprises a processing unit that, based on the signals 340 received from the satellites 330, is configured to determine a first location 315 corresponding to the location of the antenna.

The second receiver 320 comprises an antenna that is configured to receive signals 340 from the satellites 330 comprised in the satellite-based positioning system. The second receiver 320 further comprises a processing unit that, based on the signals 340 received from the satellites 330, is configured to determine a second location 325 corresponding to the location of the antenna.

It is to be noted that in some other exemplary embodiment there may be more than two receivers. The first receiver 310 in this exemplary embodiment is of first implementation and the second receiver 320 is of second implementation.

In the exemplary embodiment of Figure 3, the positioning unit 300 compares the first determine location 315 and the second determined location 325. The comparison may be implemented for example by using an algorithm that may be executed by a processor comprised in the positioning unit. If the coordinates of the second determined location are within a threshold deviation 350, the first determined location 315 is considered to be reliable and if not, the first determined location may be determined not to be reliable. The positioning unit 300 may provide an output, which may be a signal provided as an output or a message transmitted for example, that comprises information regarding if the first determined location 315 is reliable or not.

Figure 4 illustrates an exemplary embodiment of a positioning unit 400 in which one antenna 410 is used to receive signal from satellites and that signal is then provided to a plurality of processing units 405. The antenna 410 may be external or it may be internal. In this exemplary embodiment, the antenna 410 is external antenna that is connected to the positioning unit 400. The positioning unit 400 may be integrated to a self-driving vehicle 440 using the same interface or interfaces as another positioning unit or module, such as a GPS positioning module, would use. The positioning unit 400 could be used in the exemplary embodiment of Figure 2 as the positioning unit 220.

The antenna 410 is connected to an amplifier 420 that may be used to minimize the amount of noise in the received signal and keep the signal as clear as possible. The amplifier 420 is then connected to a splitter 430 that splits the received signal for the processing units 405. As the splitting attenuates the received signal, having the amplifier may help to compensate the effects of the attenuation caused by the splitter 430.

There may be various amounts of the processing units 405. In this exemplary embodiment there are three processing units. The processing units, which may also be considered as receivers that are connected to an antenna, are of different implementation. Each processing unit determines a location and the determined locations are then compared to each other to determine if they are similar enough. This comparison may be done as was described above in the exemplary embodiments. Once a reliable location has been determined, the location may be provided by the positioning unit to the self-driving vehicle using for example a message according to a specification defined by National Maine Electronics Association, NMEA. In other words, the message may be an NMEA message.

Optionally, in the exemplary embodiment of Figure 4, differential GNSS may be utilized such that an indication of an error 400 obtained from reference stations may be provided to one or more of the processing units 405. The indication of the error 400 may be provided using communication that may be IP-based or it may be based on cellular connectivity such as 4G or 5G. In some exemplary embodiments, the error may be indicated using a real-time correction message, RTCM.

In some exemplary embodiments the differential GNSS may be RTK. This may be beneficial if accurate positioning information is needed. For example, an agricultural vehicle may comprise equipment for spraying and the sprays are only a few centimetres apart and therefore accurate positioning may be needed to verify that correct sprays are used at a given time for example.

Figure 5 illustrates a flow chart according to an exemplary embodiment. In step SI it is determined, by a positioning unit, a first location and a second location, wherein the first location is determined by a first receiver that is of a first implementation based on a first satellite-based positioning system and the second location is determined by a second receiver that is of a second implementation based on the first satellite-based positioning system. In step S2 the first location and the second location are compared. If the second location is within a threshold deviation from the first location, according to step S3 it is determined that the first location is reliable.

Figure 6 illustrates an exemplary embodiment of an apparatus such as positioning unit 220 or 300 or a device comprising a positioning unit. The apparatus is applicable for performing one or more example embodiments of the invention. The apparatus 600 comprises a processor 610, which may comprise one or more processing cores containing circuitry configured to executed instructions comprised in computer program code 630. The computer program code may be any such computer program code which can be stored, temporarily or permanently, in the memory 620 and executed by the processor 610. The memory 620 may be implemented using any suitable data storage technology, such as semiconductor-based memory devices, flash memory, magnetic memory devices and systems, optical memory devices and systems, fixed memory and removable memory. The apparatus 600 may further comprise a connectivity unit 640 configured to enable wired and/or wireless connectivity. The wireless connectivity may be cellular connectivity, Wi-Fi connectivity, Bluetooth connectivity and/or any other suitable method of connectivity. The input/output unit 650 may enable a user to interact with the apparatus 600. The input/output unit 650 may comprise for example a display, a loudspeaker, a keyboard, a mouse, a touch user interface and/or a microphone. Any other suitable means for user interaction could also be comprised in the user interface 650. Alternatively, or additionally, the input/output unit 650 may enable the apparatus 600 to connect to, or be comprised in, another device such that it may receive signals as input and also output signals to a device it is connected to or comprised in. Further, the apparatus 600 comprises an antenna 660 that is configured to receive a signal from a satellite comprised in a satellite-based positioning system. The processor 610 may, in some exemplary embodiments, together with computer program code 630 determine a location based on one or more signals received by the antenna 660.

As was mentioned above, artificial intelligence, such as machine learning, could be used to for example analyze data, create segments and harmonize formats of records comprised in a data set. Machine learning may be divided into several process steps. An example of such process steps is next described as an example only and are not to be taken as an exhaustive and complete set of process steps needed for machine learning. The data first need to be gathered and after that it should be prepared such that it is useful. The quality and quantity of the data affect how well the machine-learning may function. Data preparation may involve storing the data in a certain representation, modifying the data to, for example, remove unnecessary or extra aspects. Then a machine learning method is chosen. Various methods have been created by researches and data scientist that may be used for machine-learning purposes. The methods may have been developed with a certain purpose in mind, like image data, text or music, or the methods may be generic methods. Once the method has been chosen, the method is utilized in training a machine learning model. In training, the data gathered and prepared are used to incrementally improve the machine learning model in recognizing patterns and thereby providing correct outcomes. In the next step, validation may be used to test the trained machine learning model to see how well the machine learning model generalizes, that is, can classify data which it has not been introduced to before. This provides an indication regarding how well the machine learning model may function in usage of classifying new data. After evaluation it is possible to further improve the training of the machine learning model. This may be done by tuning the parameters that are used for training the machine learning model. Prediction is the final phase in which the machine learning model that has been trained is used to provide predictions regarding new data it is given as an input. It is to be noted that various other ways of using machine learning may also be used.

As mentioned, various machine learning methods, that may be used to train a machine learning model, exist. These methods include classification and regression trees, CART. The method is based on binary decisions, yes or no, made at each node of the tree. The leaf nodes of a tree comprise an output variable that is used to make a prediction. Bayesian network is also a machine learning method and it is a dependency graph in which each node represents a binary variable and each edge represents the dependency relationship. In this method the machine learning is based on finding at each node the joint probability distribution of all incoming edges. After that, a probability distribution table is updated. Once the probability distribution table is updated at every node, the probability of any hidden node can be calculated. Yet a further example of a machine learning method is support vector machine. It is a supervised learning method that is associated with learning algorithms which analyse data used for classification and regression analysis. The support vector machine learning method is provided with a set of training examples. The training examples may be marked as belonging to one of two possible categories. After this input the training algorithm builds a model that assigns new examples to one of the two categories. An advantage of a machine learning model trained using the support vector machine learning method is that it can handle large numbers of dimensions and non-linear relationships as well.

An example of a framework enabling machine learning is an artificial neural network, that may also be called neural network. An artificial neural network consists of connected neurons that loosely resemble neurons in a biological brain. The neurons are computing entities which, when connected, can form one or more layers. A connection between two neurons resembles a synapse in a biological brain.

An artificial neural network may be used as a framework for various different machine learning algorithms. A machine learning algorithm may correspond to a machine learning model that has been trained using a machine learning method. These algorithms may work together to process complex data. Neural network therefore enables learning from input data. Unlike in traditional software development, the decision logic to be used for a given input is not decided by an engineer. Instead, a developer, such as an engineer, defines a set of sample data that has been categorized and indicates the desired outcome. The algorithm that is executed in the framework provided by the artificial neural network learns to define the decision logic itself. The role of the developer therefore is focused on providing training data, selecting features and tuning the algorithms. The developer can also define the structure of the artificial neural network and select the algorithms to be used. The selection of training data has a significant impact on how well the algorithm executed on the framework offered by the neural network learns to provide correct and reliable results as the algorithm learns to recognize patterns of the training data and thereby is able to recognize new data. As the learning is based on patterns, the better the patterns are extracted from the training data, the better the algorithm can learn.lt will be obvious to a person skilled in the art that, as the technology advances, the inventive concept can be implemented in various ways. The invention and its embodiments are not limited to the examples described above but may vary within the scope of the claims.

Claims

1. A method comprising

determining, by a positioning unit, a first location and a second location, wherein the first location is determined by a first receiver, that is of a first implementation, based on a first satellite-based positioning system and the second location is determined by a second receiver, that is of a second implementation, based on the first satellite-based positioning system;

comparing the first location and the second location and if the second location is within a threshold deviation from the first location

determining that the first location is reliable.

2. A method according to claim 1, wherein at least one of the first receiver or the second receiver further receives a real-time correction message.

3. A method according to claim 1 or 2, further comprising verifying at least one of movement, position and orientation of a self-driving vehicle based on determining that the first location is reliable.

4. A method according to any previous claim further comprising determining that the first location is not reliable if the second location is not within the threshold deviation from the first location.

5. A method according to claim 4 further comprising transmitting an indication regarding the determination that the first location is not reliable.

6. A method according to claim 4 or 5 further comprising obtaining data from one or more sensors and determining, based on the obtained data, if the first position is reliable.

7. A method according to claim 6 when dependent on claim 3, wherein the one or more sensors are comprised in the self-driving vehicle.

8. A method according to any previous claim wherein the first satellite- based positioning system is global positioning system.

9. A method according to any previous claim, wherein the first receiver and the second receiver are connected to a shared antenna.

10. A method according to any previous claim, further comprising determining, by the positioning unit, a third location by a third receiver that is of a third implementation based on the first satellite-based positioning system, and comparing the first location and the third location and if the second location and the thirds location are within the threshold deviation from the first location

determining that the first location is reliable.

11. A method according to claim 11, wherein if at least one of the second or the third location is not within the threshold deviation from the first location, determining that the first location is not reliable.

12. A method according to any of claim 3 to 11, wherein the self-driving vehicle is an agricultural vehicle or a vessel.

13. An apparatus comprising means for

determining that the first location is reliable.

14. An apparatus according to claim 13, wherein at least one of the first receiver or the second receiver further receives a real-time correction message.

15. An apparatus according to claim 13 or 14, further comprising means for verifying at least one of movement, position and orientation of a self-driving vehicle based on determining that the first location is reliable.

16. An apparatus according to any of claims 13 to 15 further comprising means for determining that the first location is not reliable if the second location is not within the threshold deviation from the first location.

17. An apparatus according to any of claims 13 to 16 further comprising means for transmitting an indication regarding the determination that the first location is not reliable.

18. An apparatus according to any of claims 13 to 17 further comprising means for obtaining data from one or more sensors and determining, based on the obtained data, if the first position is reliable.

19. An apparatus according to any of claim 18 when dependent on claim 15, wherein the one or more sensors are comprised in the self-driving vehicle.

20. An apparatus according to any of claims 13 to 19 wherein the first satellite-based positioning system is global positioning system.

21. An apparatus according to any of claims 13 to 20, wherein the first receiver and the second receiver are connected to a shared antenna.

22. An apparatus according to any of claims 13 to 21, further comprising means for: determining, by the positioning unit, a third location by a third receiver, that is of a third implementation, based on the first satellite-based positioning system, and

comparing the first location and the third location and if the second location and the third location are within the threshold deviation from the first location determining that the first location is reliable.

23. An apparatus according to claim 22, wherein if at least one of the second or the third location is not within the threshold deviation from the first location, determining that the first location is not reliable.

24. An apparatus according to any of claim 15 to 23, wherein the self driving vehicle is an agricultural vehicle or a vessel.

25. A computer program product which when executed by a computing apparatus causes the apparatus to perform:

determining, by a positioning unit, a first location and a second location, wherein the first location is determined by a first receiver that is of a first implementation based on a first satellite-based positioning system and the second location is determined by a second receiver that is of a second implementation based on the first satellite-based positioning system;

comparing the first location and the second location, and if the second location is within a threshold deviation from the first location,

determining that the first location is reliable.