Method and system for estimating a location of a mining and / or construction machine

Abstract

A method for estimating a location of a mining and / or construction machine operating in a mining environment is provided. A current set of range scanning data of the mining environment surrounding the machine is obtained from the one or more sensors. A local map of the mining environment is updated taking the current set of range scanning data into account. The local map comprises one or more previously obtained sets of range scanning data. A first location estimation of the machine is performed based on the updated local map. The updated local map is aligned with a global map of the mining environment by performing a scan registration between the updated local map and the global map. The alignment comprises taking the first location estimation into account. A second location estimation of the machine is performed based on the alignment of the updated local map with the global map.

Description

TECHNICAL FIELD The disclosure relates to a method and system for estimating a location of a mining and / or construction machine operating in a mining environment. The disclosure further relates to a computer program and computer-readable medium for performing the method, to a control unit, and to mining and / or construction machine comprising the system or the control unit. BACKGROUND In mining environments, knowing the position of an asset is an essential part of planning work and operations. With increasing usage of autonomous machines, a central system is increasingly needed for controlling the machines. These central systems need to know where autonomous machines are located in order to plan their route operations, etc. Identifying and communicating a position can however be problematic in a mining environment. Not only can network infrastructure be lacking, but machines may be obstructing radio signals in tunnels. Therefore, positions of the autonomous machines may sometimes be difficult to determine. In these situations, operations in the mining operations need to stop to ensure there are no accidents, thereby reducing productivity. Hence there is a strive to improve localization and productivity. SUMMARY Global localization in a mining environment may be based on map of said mining environment. Scan registration may be performed in order to determine a position of a machine operating in the mining environment. A problem with localization may occur e.g., due to changes in the mining environment, which may cause the localization of a machine to be lost. This may cause the machine to stop, and manual operation may be required. This leads to a decreased productivity, and may also decrease operational safety in the mining environment due to lack of positioning information. An object of embodiments herein is to provide a mechanism that improves safety and productivity in a mining environment. The object is achieved by the independent claims. According to a first aspect, a computer-implemented method for estimating a location of a mining and / or construction machine operating in a mining environment is provided. The machine comprises one or more sensors. A current set of range scanning data of the mining environment surrounding the machine is obtained from the one or more sensors. A local map of the mining environment is updated taking the current set of range scanning data into account. The local map comprises one or more previously obtained sets of range scanning data. A first location estimation of the machine is performed based on the updated local map. The updated local map is aligned with a global map of the mining environment by performing a scan registration between the updated local map and the global map. The alignment comprises taking the first location estimation into account. A second location estimation of the machine is performed based on the alignment of the updated local map with the global map. In this way, it is possible to improve the productivity in the mining environment by aligning local map of the mining environment, comprising obtained range scanning data, with a global map. This since it enables an improved positioning accuracy and reduces the risk of losing the positioning of the machine. In some exemplary embodiments, updating the local map comprises aligning the current set of range scanning data with the local map by performing an initial scan registration between the current set of range scanning data and the local map, and adding the aligned current set of range scanning data to the local map. Aligning the range scanning data enables an accurate positioning of the machine in view of the local map. In some exemplary embodiments, the current set of range scanning data comprises range scanning data from two or more sensors. Obtaining the current set of range scanning data may comprise aggregating the range scanning data from the two or more sensors. By using range scanning data from more than one sensor, a more accurate representation of the mining environment is achieved. Further, two or more sensor may provide range scanning data of larger area around the machine. Aggregating the range scanning data enable a more efficient updating of the local map, since is allows the updating procedure to be performed in a single iteration. In some exemplary embodiments, aggregating the range scanning data from the two or more sensors is based on one or more of: A steering articulation angle of the machine, and a respective position and / or orientation of the two or more sensors. In this way, a more efficient updating of the local map is achieved, since it the current range scanning data will more closely represent the scanned mining environment making it easier to e.g., align the range scanning data with the local map. In some exemplary embodiments, updating the local map further comprises obtaining an initial estimate of a spatial alignment between the current set of range scanning data and an immediately preceding obtained set of range scanning data comprised in the local map. The estimate may be based on odometry data obtained from an odometry unit comprised in the machine. In this way, a more efficient updating of the local map is achieved, since the initial estimate may be used, e.g., as a starting point when aligning the range scanning data with the local map. In some exemplary embodiments, a set of range scanning data comprises a set of measurement points. A measurement point may be represented by a range value and an angular value. In some exemplary embodiments, a localization quality index is calculated based on the updated local map and the global map. In this way, the quality, such as the accuracy or confidence, of the estimated position of the machine may be evaluated. In some exemplary embodiments, the localization quality index is evaluated based on a threshold. In this way, it possible to determine whether the quality of the localization quality index is high enough to be trusted. In some exemplary embodiments, the localization quality index represents a degree of similarity between the updated local map and the global map at the estimated location. In some exemplary embodiments, evaluating the localization quality index comprises triggering a warning event when the localization quality index is below the threshold. This enables actions to be performed when the quality of the estimated location is not high enough, improving the safety in the mining environment. In some exemplary embodiments, the local map represents an area of the mining environment around the machine. The size of the area may be limited by a pre-configured radius centered at the estimated location of the machine. This enables a more efficient location estimation, since the need for computing resources data storage is reduced by limiting the area covered by the local map, i.e., the local map comprises less data. In some exemplary embodiments, performing the first location estimation comprises estimating an orientation of the machine. In some exemplary embodiments, performing the second location estimation comprises estimating the orientation of the machine. In some exemplary embodiments, at least one of the one or more previously obtained sets of range scanning data have been obtained at a location different from the location the current set of range scanning data is obtained. In some exemplary embodiments, the method comprises iteratively repeating any one or more out obtaining the set of range scanning data, updating the local map, performing the first location estimation of the machine, aligning the updated local map with the global map and performing a second location estimation of the machine, and optionally calculating a localization quality index, and evaluating the localization quality index. In this way, it is possible to improve the productivity and safety in the mining environment is improved by always having up to date location data for the machine. According to a second aspect, a system configured to estimate a location of a mining and / or construction machine operating in a mining environment is provided. The system is configured to obtain a current set of range scanning data of the mining environment surrounding the machine from one or more sensors. The system is configured to update a local map of the mining environment taking the current set of range scanning data into account. The local map comprises one or more previously obtained sets of range scanning data. The system is configured to perform a first location estimation of the machine based on the updated local map. The system is configured to align the updated local map with a global map of the mining environment by performing a scan registration between the updated local map and the global map. The aligning comprises taking the first location estimation into account. The system is configured to perform a second location estimation of the machine based on the alignment of the updated local map with the global map. Advantages and effects of the system are analogous to the advantages and effects of the method of the first aspect. Further, all embodiments of the system are applicable to and combinable with all embodiments of the method of the first aspect, such as any one or more out of the above-mentioned exemplary embodiments, and vice versa. According to third aspect, a control unit configured to estimate a location of a mining and / or construction machine operating in a mining environment is provided. The control unit comprises a system according to the second aspect. Advantages and effects of the control unit are analogous to the advantages and effects of the method of the first aspect. Further, all embodiments of the control unit are applicable to and combinable with all embodiments of the method of the first aspect, such as any one or more out of the above-mentioned exemplary embodiments, and vice versa. According to a fourth aspect, a mining and / or construction machine is provided. The mining and / or construction machine comprises a system according to the second aspect or a control unit according to the third aspect. Advantages and effects of the machine are analogous to the advantages and effects of the method of the first aspect. Further, all embodiments of the machine are applicable to and combinable with all embodiments of the method of the first aspect, such as any one or more out of the above-mentioned exemplary embodiments, and vice versa. According to a fifth aspect, a computer program is proved. The computer program comprises instructions, which when executed by a processor, causes the processor to perform actions according to the method of the first aspect, the system of the second aspect, and / or the control unit of the third aspect. Advantages and effects of the system are analogous to the advantages and effects of the method of the first aspect. Further, all embodiments of the system are applicable to and combinable with all embodiments of the method of the first aspect, such as any one or more out of the above-mentioned exemplary embodiments, and vice versa. According to sixth aspect, a computer-readable medium is provided. The computer readable medium comprises instructions, which when executed by a processor, causes the processor to the method of the first aspect, the system of the second aspect, and / or the control unit of the third aspect. Advantages and effects of the computer-readable medium are analogous to the advantages and effects of the method of the first aspect. Further, all embodiments of the computer-readable medium are applicable to and combinable with all embodiments of the WO 2025 / 234901 PCT / SE2024 / 050432 6 method of the first aspect, such as any one or more out of the above-mentioned exemplary embodiments, and vice versa. Further advantages and advantageous features of embodiments herein are disclosed in the following detailed description and in the dependent claims. BRIEF DESCRIPTIONS OF DRAWINGS Examples of embodiments herein are described in more detail with reference to attached drawings in which: Fig. 1 shows an example of a mining environment according to embodiments herein. Fig. 2 shows a flowchart depicting a method according to embodiments herein. Fig. 3a is a schematic block diagram illustrating exemplary embodiments herein. Fig. 3b is a schematic block diagram illustrating exemplary embodiments herein. Fig. 3c is a schematic block diagram illustrating exemplary embodiments herein. Fig. 3d is a schematic block diagram illustrating exemplary embodiments herein. Fig. 3e is a schematic block diagram illustrating exemplary embodiments herein. Fig. 3f is a schematic block diagram illustrating exemplary embodiments herein. Fig. 3g is a schematic block diagram illustrating exemplary embodiments herein. Fig. 3h is a schematic block diagram illustrating exemplary embodiments herein. Fig. 3i is a schematic block diagram illustrating exemplary embodiments herein. Fig. 4 Fig. 5 shows an example of a mining and / or construction machine, shows schematic block diagrams illustrating embodiments of a control unit. DETAILED DESCRIPTION An object of embodiments herein is to provide a mechanism that improves safety and productivity in a mining environment. The object is achieved by the independent claims. Embodiments herein bring the advantage of increased operational safety in a mining environment. This may be achieved by making it possible to more accurately estimate a position of a mining and / or construction machine operating in the mining environment. Further, embodiments herein may bring the advantage of an improved productivity in the mining environment. This by reducing the number of stops of machines caused by insufficient and / or inaccurate positioning information. Fig. 1 shows a schematic illustration of a mining environment 1 according to embodiments herein. The mining environment 1 may be any one or more out of a pit, a quarry, or a underground environment. The mining environment 1 may be any suitable environment for performing mining operations, e.g., for drilling, preparing to drill, prospecting, transporting materials, etc. The mining environment 1 may comprise various passages and paths surrounded by rock foundation. Due to being underground and / or due to the rock foundation, special conditions for use of sensors and / or communications using wireless network connections are present. This is since radio waves may not easily travel through the rock foundation in the mining environment 1, as these are typically very dense and unsuitable for radio propagation. Radio signals in the mining environment 1 may instead bounce in the mining environment 1 in a manner much different from normal environments for wireless communications, and hence, normal approaches for network communication or positioning thereof may not apply as signals may be easily distorted or lost. Furthermore, the mining environment 1 may be dark and / or dusty, making some sensors used for positioning more prone to error. The effects of errors relating to positioning in the mining environment 1 may however at least partly be resolved by embodiments herein. The mining environment 1 comprises one or more machines, such as a mining and / or construction machine 10, also referred to as machine 10. Each machine, e.g., the machine 10, may respectively be any suitable machine for performing tasks in the mining environment 1, such as a vehicle or a mining machine, e.g., any suitable machine suitable to perform operations in the mining environment 1. For example, the machine 10 may be any type of fixed or mobile machine. Additionally or alternatively, the machine 10, may be any type of light vehicle, heavy vehicle, or unmanned aerial vehicle. As an example, the machine 10, may respectively be any one out of: - a transporting vehicle, e.g., a truck, - a Load-Haul-Dump (LHD) vehicle, - a mine truck, - a drill rig, -   a light vehicle, and -   an unmanned aerial vehicle. The machine 10 may e.g., comprise any type of kinematic configuration, such as a car-like steering, also known as Ackermann steering, center-articulated steering and / or skid steering. The machine 10, may be autonomous or at least partly autonomous. The machine 10, may be remote controlled. The machine 10, may or may not have an operator present within the machine. The machine 10, may comprise any suitable sensors, such as one or more sensors 12 and / or an odometry unit 13, and / or communication devices for positioning the machine 10. Estimating a location, or position, according to embodiments herein, may comprise establishing a position of the machine 10 using one or more maps of the mining environment 1, e.g., by comparing sensor inputs measured by or measured in relation to the machine, e.g., machine 10, with defined features or entities of a respective map. The machine 10, may report its position, e.g., by using a wireless communications network in the mining environment 1, to any suitable device or entity in need of the position of the respective machine, e.g., by unicast, broadcast, or multicast. Positions of each respective machine may be reported by the respective machine transmitting one or more positioning data, e.g., as part of transmitted machine data. The positioning data and / or the machine data, may be transmitted periodically and / or aperiodically, e.g., based on triggering events. The machine 10 operates in the mining environment 1. In order to keep track of the location of the machine 10, the machine 10, a system in the machine 10, a control unit 11 in the machine 10 and / or any other type of unit, device and / or computer in the machine 10, may obtain range scans, such as a set of range scanning data, from at least one sensor 12. Taking the range scanning data into account, a local map, e.g., representing an area around the machine 10 may be updated. A first location estimation of the machine 1 may be performed based on the updated local map. Taking the first location estimation into account, the update local map may be aligned with a global map of the mining environment 1, e.g., by performing a scan registration process. A second location estimation of the machine 10 may be performed based on the alignment of the updated local map with the global map. The second location estimation may be associated with same location as the first location estimation. Fig. 2 shows an example embodiment of a computer-implemented method for estimating a location of the mining and / or construction machine 10 operating in the mining environment 1. The machine 10 comprises one or more sensors 12. The method may e.g., be performed by a system, a control unit, such as the control unit 11, comprised in the machine 10, the machine 10 and / or any other type of unit, device and / or computer. The method comprises the following actions, which actions may be taken in any suitable order. Optional actions are represented by dashed boxes in Fig. 2. Action 201 A current set of range scanning data of the mining environment 1 surrounding the machine 10 is obtained from the one or more sensors 12. The one or more sensors 12 may e.g., comprise any type of sensors, such as lidar sensors, laser sensors, and / or cameras. The camera may, e.g., comprise a depth camera, such as a camera configured to provide range data, alternatively, two cameras may be used together to provide range data. In other words, the one or more sensors 12 performs range scans, thus collecting, such as obtaining, the range scanning data. In some embodiments, the current set of range scanning data comprises range scanning data from two or more sensors 12. The two or more sensors may collect range scanning data in different directions compared to each other. As an example with two sensors 12, a first sensor 12 may collect range scanning data in a forward direction and side directions of the machine 10, while a second sensor 12 may collect range scanning data in a backward direction and side directions of the machine 10. This way, the range scanning data from the two or more sensors may cover the mining environment surrounding the machine 10. The range scanning data from two sensors 12 may or may not overlap with each other. In some embodiments, a set of range scanning data, such as the current set range scanning data and / or a previous set of range scanning data, may comprise a set of measurement points. A measurement point may be represented by a range value and an angular value. That is, a measurement point may be represented by two different parameters, the range value and the angular value. The range value may e.g., be the range between the sensor 12 and the measurement point. The range value may e.g., be presented in such as millimeters, centimeters, decimeters, meters, inches or feet. These are just examples, and any other suitable length unit may be used, e.g., depending on the desired accuracy level. The angular value may e.g., be an angle between a reference measurement direction and the direction the measurement point was measured in, where the reference direction is considered to have an angular value of 0. The angular value may e.g., be presented in degrees, radians, or any other suitable unit for presenting an angular value. Alternatively, or additionally, the measurement point may be represented by the range value and two angular values, such that the measurement point is expressed in spherical coordinates. This way, the range scanning data may be used for a three-dimensional representation of the mining environment 1. In some embodiments, obtaining the current set of range scanning data comprises aggregating range scanning data from the two or more sensors 12. In other words, the range scanning data from the two or more sensors 12 is aggregated, or merged, into the current set of range scanning data. E.g., when range scanning data is obtained from two sensors 12, a first set of range scanning data is obtained from a first sensor 12 and a second set of range scanning data is obtained from a second sensor 12. The first set of range scanning data and second set of range scanning data is then aggregated. The aggregated range scanning data forms the current set of range scanning data. The same is applicable also when more than two sensors 12 are used. Aggregating the range scanning data from the two or more sensors may e.g., be based on one or more of a steering articulation angle of the machine 10, and a respective position and / or orientation of the two or more sensors 12. The respective position of the two or more sensors may refer to the position of the sensors 12 on the machine 10, i.e., where the sensors are positioned, such as located or mounted, on the machine 10. The respective orientation of the two or more sensors 12 may refer to the orientation of the sensors 12 with the respect to the machine 10, i.e., which way they are directed. The steering articulation angle of the machine 10 may refer to the steering angle of the machine 10 e.g., when the machine 10 is a center-articulated machine 10. The steering articulation angle may impact range scanning data obtained from the sensors 12, since it the area of the mining environment 1 that is scanned by a sensor 12 may change depending on said steering articulation angle. In some embodiments, the current set of range scanning data may be used to form a cartesian map, e.g., by using the measurement points represented by a respective range value and an angular value. The range value and angular value may be used to determine, for each measurement point, cartesian coordinates. The cartesian coordinates for the respective measurement points may together form the cartesian map. Action 202 A local map of the mining environment 1 is updated taking the current set of range scanning data into account. The local map comprises one or more previously obtained sets of range scanning data. This may e.g., comprise adding the current set of range scanning data, or a subset of the current set of range scanning data to the local map. Thus, the local map is updated by adding at least part of the current set range scanning data to the local map. After the update, the local map comprises the current set of range scanning data, or a subset thereof, in addition to the one or more previous sets of range scanning already comprised in, or added to, the local map. Thanks to this, an updated local map of the mining environment 1 is obtained, comprises the latest obtained range scanning data. Alternatively, or additionally, updating the local map may comprise removing data from the local map. The removed data may e.g., comprise range scanning data that is inconsistent with the current set of range scanning data and / or outdated range scanning data. Outdated range scanning data may e.g., comprise range scanning data that is considered to be too far away from the machine 10, such as outside a preconfigured radius, as explained further below. In some embodiments, updating the local map comprises aligning the current set of range scanning data with the local map by performing an initial scan registration between the current set of range scanning data and the local map. The aligned current set of range scanning data is added to the local map. By aligning the current set of range scanning data with the local map, the current set of range scanning data is added to the local map at the correct position, thus creating an accurate map of the mining environment. The initial scan registration comprises comparing the current set of range scanning data with the local map in order to obtain an alignment between the two, such as finding the correct location in the local map where the current set of range scanning data is to be added. The scan registration may e.g., comprise using a iterative closest point procedure, a gaussian mixture model procedure and / or a feature based procedure. The scan registration may comprise obtaining a geometrical transformation that aligns the current set of range scanning data to local map. In some embodiments, aligning the current set of range scanning data with the local map may comprise converting the range scanning data into a distribution representation, e.g., a normal-distributions representation, or any other distribution representation, of the mining environment 1. The converted current set of range scanning data is used for the alignment. When the alignment is complete, the converted current set of range scanning data is added to the local map according to the alignment. The current set of range scanning data is converted to the distribution used to represent the local map. Thus, if the local map is in a normal-distributions representation, the current set of range scanning data is converted to a normal-distributions representation. In some embodiments, updating the local map further comprises obtaining an initial estimate of a spatial alignment between the current set of range scanning data and an immediately preceding obtained set of range scanning data comprised in the local map. The estimate is based on odometry data obtained from an odometry unit 13 comprised in the machine 10. The odometry data may comprise data related to the movement of the machine 10, e.g., the movement of machine 10 since a previous update of the local map and / or a previous location estimation of the machine 10. This may mean that initial estimate of the spatial alignment is based on the movement of the machine 10. The initial estimate may e.g., be used as an initial guess when performing the initial scan registration, such as a starting point for aligning the current set of range scanning data to the local map. The initial estimate may enable a reduction in computational resources needed for updating the local map. In some embodiments, the local map represents an area of the mining environment 1 around the machine 10. The size of the area is limited by a pre-configured radius centered at the estimated location of the machine 10. This may mean that the local map represents a limited part of the mining environment 1. This reduces the processing capacity needed, since there is less data to handle. Further, it may mean that the local map does not comprise any outdated data in the sense that range scanning data that is too far away, i.e., outside the pre-configured radius, is removed. Thus, in some embodiments, range scanning data associated with a location in the mining environment 1 that is located outside of the pre-configured radius is removed from the local map. At least one of the one or more previously obtained sets of range scanning data may have been obtained at a location different from the location the current set of range scanning data is obtained. In other words, the local map comprises range scanning data obtained at a different location than the current location of the machine 10. Action 203 A first location estimation of the machine 10 is performed based on the updated local map. The first location estimation may e.g., further be based on a previous location estimation, e.g., an immediately preceding location estimation, such as the last performed location estimation. This may mean that that a previous location estimation and the updated local map are used together to perform the first location estimation of the machine 10. The previous location estimation, being the last estimated location, is present part of the updated local map. In some examples, the odometry data is also used to perform the first location estimation of the machine 10. In some embodiments, performing the first location estimation comprises estimating an orientation of the machine 10. The orientation may e.g., be estimated based on the steering articulation angle of the machine 10, a steering angle of the machine’s 10 wheels, the odometry data obtained from the odometry unit 13, the current set of range scanning data and / or an initial scan registration. Action 204 The updated local map is aligned with a global map of the mining environment 1 by performing a scan registration between the updated local map and the global map. The aligning comprises taking the first location estimation into account. By aligning the local map with the global map, a global location of the machine 10 may be estimated, such as a location estimation of the machine 10 with reference to the global map of the mining environment 1. The scan registration may comprise obtaining a geometrical transformation that aligns the updated local map to the global map. Taking the first location estimation into account may mean that the first location estimation is used as input, such a first guess or estimation, to the alignment process. The global map may e.g., comprise range scanning data obtained to generate, or build, the global map. In some embodiments, the global map comprises a distribution representation of the mining environment 1, e.g., a normal-distributions representation, or any other distribution representation. The distribution representation of the global map may be the same type of distribution representation as used for the local map. By this, a conversion of the local map may be avoided. Action 205 A second location estimation of the machine 10 is performed based on the alignment of the updated local map with the global map. In other words, the location of the machine 10 is estimated a second time, where the second estimation is based on the alignment of the updated local map with the global map. Implicit from this, the second location estimation is also based on the first location estimation of the machine 10, since the location estimation is used during the alignment of the updated local map with the global map. This may mean that the second estimation may be a more accurate estimation, since the local map has been aligned with the global map. In some embodiments, performing the second location estimation comprises estimating the orientation of the machine 10. The orientation may e.g., be estimated based on the steering articulation angle of the machine 10, a steering angle of the machine’s 10 wheels, the odometry data obtained from the odometry unit 13, the current set of range scanning data and / or the scan registration between the updated local map and the global map. Action 206 In some embodiments, a localization quality index is calculated based on the updated local map and the global map. E.g., the scan registration performed when aligning the local map to the global map may be used to calculate the localization quality index. The index may e.g., be calculated by doing a closest neighbor search for each mean in the local map on the global map. The calculation may further comprise checking if there is a mean in the global map sufficiently close to each point in the local map. The index may be a percentage of the means in the local map that have a close enough neighbor in the global map. Sufficiently close as used above may be a configured value. In other words, the index may be a percentage of the means the local map that have neighbor in the global map within a threshold, where the threshold is the configured value. The localization quality index may represent a degree of similarity between the updated local map and the global map at the estimated location. This may e.g., mean that a higher degree of similarity gives a higher value of the localization quality index. Alternatively, a higher degree of similarity gives a lower value of the localization quality. This may depend on configuration, and either of the alternatives are possible. Action 207 In some embodiments, the localization quality index is evaluated based on a threshold. The threshold may be a fixed threshold, or it may be an adaptive threshold. An adaptive threshold may e.g., change depending on the location of the machine 10, the time of day and / or the type of machine 10. Evaluating the localization quality index may e.g., comprise comparing the index with the threshold, and determining whether the index is above, below or equal to the threshold. In some embodiments, evaluating the localization quality index comprises triggering a warning event when the localization quality index is below the threshold. Alternatively, the warning event may be triggered when the localization index is above the threshold. This may depend on whether a higher degree of similarity gives a higher value of the localization quality index or whether a higher degree of similarity gives a lower value of the localization quality. When a higher degree of similarity gives a higher value of the localization quality index, the warning event is triggered when the index is below the threshold. Correspondingly, when a higher degree of similarity gives a lower value of the localization quality index, the warning event is triggered when the index is above the threshold. The warning event may e.g., comprise an alarm indicating that the uncertainty of the estimated location is too high. The warning event, or alarm, may be handled by an operator that may initiate one or more actions to be performed. Alternatively, the warning event, or alarm, enables the machine 10 to initiate one or more actions to be performed, the one or more actions to be performed may e.g., comprise stopping the machine 10, applying operational restrictions, such as reducing the speed, stopping the machine from moving through a barrier into another zone of the mining environment 1 and / or limiting operations allowed to be performed by the machine 10. In some embodiments, any one or more out obtaining the set of range scanning data, updating the local map, performing the first location estimation of the machine 10, aligning the updated local map with the global map and performing a second location estimation of the machine 10, and optionally calculating the localization quality index, and evaluating the localization quality index may be iteratively repeated. The iterations may depend on the one or more sensors 12 scanning of the mining environment 1. E.g., the method may be iteratively repeated every time the one or more sensors 12 scans the mining environment 1. Alternatively, the method may be iteratively repeated every second time, every third time and so on, the one or more sensors 12 scans the mining environment 1. The repletion interval may be fixed or may e.g., depend on the location of the machine 10, the time of day and / or the type of machine 10. Fig. 3a illustrates an example scenario according to one or more example embodiments herein. Fig. 3a shows an example of a center-articulated machine 10. The machine 10 comprises two sensors 12 for performing range scans to collect, or measure, the range scanning data. The two sensors 12 are located a respective end of the machine 10. A first sensor 12 is located at the front of the machine 12 and a second sensor 12 is located at the back of the machine 10. The first sensor 12 is oriented in forward direction of the machine 10, and the second sensor 12 is oriented in a backward direction of the machine 10. The two sensors 12 in this example have a 180 degrees field of vision. Other degrees of field of vision are also possible, 180 degrees as shown in Fig.3 is only an example and should not be seen as limiting. Fig. 3a further shows a steering articulation angle of the machine 10, as the angle between the front part of the machine 10 and the rear part of the machine 10. The steering articulation angle may e.g., be measured by a sensor or a steering articulation unit (not shown). Fig. 3b illustrates an example scenario according to one or more example embodiments herein. Fig. 3a shows an example of a center-articulated machine 10. The machine 10 comprises four sensors 12 for performing range scans to collect, or measure, the range scanning data. The two sensors 12 are located a respective end of the machine 10. A first sensor 12 is located at the front of the machine 12, a second sensor 12 is located at the back of the machine 10, a third sensor 12 is located at the right side of the machine 10 and a fourth sensor 12 is located the left side of the machine 10. The first sensor 12 is oriented in forward direction of the machine 10, the second sensor 12 is oriented in a backward direction of the machine 10, the third sensor 12 is oriented in a rightward direction of the machine 10 and the fourth sensor 12 is oriented in a leftward direction of the machine 10. The four sensors 12 in this example have a 180 degrees field of vision. Other degrees of field of vision are also possible, 180 degrees as shown in Fig.3 is only an example and should not be seen as limiting. Fig. 3b further shows a steering articulation angle of the machine 10, as the angle between the front part of the machine 10 and the rear part of the machine 10. The steering articulation angle may e.g., be measured by a sensor or a steering articulation unit (not shown). Fig. 3c illustrates an example scenario according to one or more example embodiments herein. Fig. 3a shows an example of a non center-articulated machine 10. The machine 10 comprises one sensor 12 for performing range scans to collect, or measure, the range scanning data. The sensor 12 in this example has a 360 degrees field of vision. Other degrees of field of vision are also possible, 360 degrees as shown in Fig.3c is only an example and should not be seen as limiting. The sensor 12 is located at a position machine 10 where its field of vision is limited by any element of the machine 10. The sensor thus performs range scans 360 degrees around the machine 10. Figs. 3d-i illustrates an example scenario according to one or more example embodiments herein. Figs. 3d-i illustrates the alignment of the current set of range scanning data to the local map, and then the alignment of the local map to the global map. Fig. 3d shows an example of range scanning data, such as the current set of range scanning data, e.g., obtained from the one or more sensors 12. In this example, the range scanning data shows the walls on the sides of the machine 10. Figs. 3e shows an example of a local map, such as the local map that will be updated with the current set of range scanning data. Fig. 3f-g shows an example of how the local map is updated. Fig. 3f shows how the local map is updated taking the range scanning data, such as the current set of range scanning data, into account, as described e.g., in Action 202 above. As mentioned above, updating the local map may comprise aligning the current set of range scanning data with the local map e.g., by performing the initial set of scan registration between the current set of range scanning data and the local map. Fig. 3g shows the resulting updated local map. Figs. 3h shows an example of global map, such as the global map that of the mining environment 1. Fig. 3i shows an example of global the updated local map is aligned with the global map by performing a scan registration between the updated local map and the global map, as described e.g., in Action 204 above. As mentioned above, alignment the local map with the global map may comprise taking the first location estimation, estimated based on the updated local map, into account. Fig. 4 depicts a schematic view of the machine 10, here illustrated as a center-articulated machine 10, according to example of embodiments of the present invention. The machine 10 may be configured to operate and estimate a location of the machine 10 in the mining environment 1 according to embodiments herein. Fig. 4 further shows the control unit 11 comprised in the machine 1. The control unit 10 may be configured to estimate the location of the machine 10 in the mining environment 10 according to embodiments herein. The machine further comprises at least one sensor 12. Fig. 4 further shows the optional odometry unit 13 comprised in the machine 10. The control unit 11 may comprise an arrangement depicted in Fig. 5. To perform embodiments herein, e.g. the method according to actions 201-207 above, the control unit 10 is configured to estimate a location of the machine 10 in the mining environment 1. The control unit 11 may comprise an input and output interface 500 e g. configured to communicate with each other. The input and output interface 500 may comprise a wireless or wired receiver not shown, a transceiver, one or more antennas, and / or a wired or wireless transmitter not shown. The embodiments herein may be implemented through a respective processor or one or more processors, such as at least one processor 560 of a processing circuitry in the control unit 11 depicted in Figure 5, together with computer program code for performing the functions and actions of the embodiments herein. The program code mentioned above may also be provided as a computer program product, for instance in the form of a data carrier carrying computer program code for performing the embodiments herein when being loaded into the control unit 11. One such carrier may be in the form of a CD ROM disc. It is however feasible with other data carriers such as a memory stick. The computer program code may furthermore be provided as pure program code on a server and downloaded to the control unit 11. The control unit 11 and / or processor 560 is configured to estimate a location of the mining and / or construction machine 10 operating in the mining environment 1. The machine 10 comprises one or more sensors 12. The control unit 11 and / or processor 560 is configured to obtain a current set of range scanning data of the mining environment 1 surrounding the machine 10 from the one or more sensors 12. The control unit 11 and / or processor 560 is configured to update a local map of the mining environment 1 taking the current set of range scanning data into account. The local map comprises one or more previously obtained sets of range scanning data. The control unit 11 and / or processor 560 is configured to perform a first location estimation of the machine 10 based on the updated local map. The control unit 11 and / or processor 560 is configured to align the updated local map with a global map of the mining environment 1 by performing a scan registration between the updated local map and the global map. The alignment comprises taking the first location estimation into account. The control unit 11 and / or processor 560 is configured to perform a second location estimation of the machine 10 based on the alignment of the updated local map with the global map. In some exemplary embodiments, the control unit 11 and / or processor 560 is configured to update the local map by aligning the current set of range scanning data with the local map by performing an initial scan registration between the current set of range scanning data and the local map, and adding the aligned current set of range scanning data to the local map. In some exemplary embodiments, the current set of range scanning data comprises range scanning data from two or more sensors 12. Obtaining the current set of range scanning data may comprise aggregating the range scanning data from the two or more sensors 12. In some exemplary embodiments, aggregating the range scanning data from the two or more sensors is based on one or more of: A steering articulation angle of the machine 10, and a respective position and / or orientation of the two or more sensors 12. In some exemplary embodiments, the control unit 11 and / or processor 560 is configured to update the local map by further obtaining an initial estimate of a spatial alignment between the current set of range scanning data and an immediately preceding obtained set of range scanning data comprised in the local map. The estimate is based on odometry data obtained from an odometry unit 13 comprised in the machine 1. In some exemplary embodiments, a set of range scanning data comprises a set of measurement points. A measurement point is represented by a range value and an angular value. In some exemplary embodiments, the control unit 11 and / or processor 560 is configured to calculate a localization quality index based on the updated local map and the global map. In some exemplary embodiments, the control unit 11 and / or processor 560 is configured to evaluate the localization quality index based on a threshold. In some exemplary embodiments, the localization quality index represents a degree of similarity between the updated local map and the global map at the estimated location. In some exemplary embodiments, the control unit 11 and / or processor 560 is configured to evaluate the localization quality index by triggering a warning event when the localization quality index is below the threshold. In some exemplary embodiments, the local map represents an area of the mining environment 1 around the machine 10. The size of the area is limited by a pre-configured radius centered at the estimated location of the machine 10. In some exemplary embodiments, the control unit 11 and / or processor 560 is configured to any one or more out of: perform the first location estimation by estimating an orientation of the machine 10, and perform the second location estimation by estimating the orientation of the machine 10. In some exemplary embodiments, at least one of the one or more previously obtained sets of range scanning data have been obtained at a location different from the location the current set of range scanning data is obtained. In some exemplary embodiments, the control unit 11 and / or processor 560 is configured to iteratively repeat any one or more out obtain the set of range scanning data, update the local map, perform the first location estimation of the machine 10, align the updated local map with the global map and perform a second location estimation of the machine 10, and optionally calculate a localization quality index, and evaluate the localization quality index. The control unit 11 may further comprise a memory 570 comprising one or more memory units. The memory 570 comprises instructions executable by the processor 560 in the control unit 11. The memory 570 is arranged to be used to store e.g. information, indications, range scanning data, location estimations, operating modes, positions, estimation, evaluations, spatial arrangements, maps, alignments, data, configurations, and applications to perform the methods herein when being executed in the control unit 11. In some embodiments, a computer program 580 comprises instructions, which when executed by the respective at least one processor 560, cause the at least one processor 560 of the control unit 11 to perform the actions above. In some embodiments, a computer readable medium 585 comprises instructions, which when executed by the respective at least one processor 560, cause the at least one processor 560 of the control unit 11 to perform the actions above. In some embodiments, a respective carrier 590 comprises the respective computer program 580 and / or computer readable medium 585, wherein the carrier 590 is one of an electronic signal, an optical signal, an electromagnetic signal, a magnetic signal, an electric signal, a radio signal, a microwave signal, or a computer-readable storage medium. Thus, embodiments herein may disclose the control unit 11 configured to estimate a location of the machine 10 in the mining environment 1. The control unit 11 comprises the processor 560 and the memory 570, said memory 570 comprising instructions executable by said processor 560 whereby said control unit 11 is operative to perform any of the methods herein. As will be readily understood by those familiar with communications design, that functions means or modules may be implemented using digital logic and / or one or more microcontrollers, microprocessors, or other digital hardware. In some embodiments, several or all of the various functions may be implemented together, such as in a single application-specific integrated circuit (ASIC), or in two or more separate devices with appropriate hardware and / or software interfaces between them. Several of the functions may be implemented on a processor shared with other functional components of a base station, for example. Alternatively, several of the functional elements of the processing means discussed may be provided through the use of dedicated hardware, while others are provided with hardware for executing software, in association with the appropriate software or firmware. Thus, the term “processor” or “controller” as used herein does not exclusively refer to hardware capable of executing software and may implicitly include, without limitation, digital signal processor (DSP) hardware, read-only memory (ROM) for storing software, random-access memory for storing software and / or program or application data, and non-volatile memory. Other hardware, conventional and / or custom, may also be included. Designers of communications receivers will appreciate the cost, performance, and maintenance trade-offs inherent in these design choices. Any appropriate steps, methods, features, functions, or benefits disclosed herein may be performed through one or more functional units or modules of one or more virtual apparatuses. Each virtual apparatus may comprise a number of these functional units. These functional units may be implemented via processing circuitry, which may include one or more microprocessor or microcontrollers, as well as other digital hardware, which may include digital signal processors (DSPs), special-purpose digital logic, and the like. The processing circuitry may be configured to execute program code stored in memory, which may include one or several types of memory such as read-only memory (ROM), random-access memory (RAM), cache memory, flash memory devices, optical storage devices, etc. Program code stored in memory includes program instructions for executing one or more telecommunications and / or data communications protocols as well as instructions for carrying out one or more of the techniques described herein. In some implementations, the processing circuitry may be used to cause the respective functional unit to perform corresponding functions according one or more embodiments of the present disclosure. It will be appreciated that the foregoing description and the accompanying drawings represent non-limiting examples of the methods and apparatus taught herein. As such, the apparatus and techniques taught herein are not limited by the foregoing description and accompanying drawings. Instead, the embodiments herein are limited only by the following claims and their legal equivalents.

Claims

1. A computer-implemented method for estimating a location of a mining and / or construction machine (10) operating in a mining environment (1), wherein the machine (10) comprises one or more sensors (12), the method comprising:obtaining (201) a current set of range scanning data of the mining environment (1) surrounding the machine (10) from the one or more sensors (12),updating (202) a local map of the mining environment (1) taking the current set of range scanning data into account, wherein the local map comprises one or more previously obtained sets of range scanning data,performing (203) a first location estimation of the machine (10) based on the updated local map,aligning (204) the updated local map with a global map of the mining environment (1) by performing a scan registration between the updated local map and the global map, wherein the aligning comprises taking the first location estimation into account, and performing (205) a second location estimation of the machine (10) based on the alignment of the updated local map with the global map.

2. The method according to claim 1, wherein updating (202) the local map comprises aligning the current set of range scanning data with the local map by performing an initial scan registration between the current set of range scanning data and the local map, and adding the aligned current set of range scanning data to the local map.

3. The method according to claim 2, wherein the current set of range scanning data comprises range scanning data from two or more sensors (12), and wherein obtaining the current set of range scanning data comprises aggregating the range scanning data from the two or more sensors (12).

4. The method according to claim 3, wherein aggregating the range scanning data from the two or more sensors is based on one or more of:- a steering articulation angle of the machine (10), and- a respective position and / or orientation of the two or more sensors (12).

5. The method according to any of claims 1-4, wherein updating (202) the local map further comprises obtaining an initial estimate of a spatial alignment between the currentset of range scanning data and an immediately preceding obtained set of range scanning data comprised in the local map, which estimate is based on odometry data obtained from an odometry unit (13) comprised in the machine (1).

6. The method according to any of claims 1-5, wherein a set of range scanning data comprises a set of measurement points, wherein a measurement point is represented by a range value and an angular value.

7. The method according to claim 1-6, wherein the method further comprises: calculating (206) a localization quality index based on the updated local map and the global map, andevaluating (207) the localization quality index based on a threshold.

8. The method according to claim 7, wherein the localization quality index represents a degree of similarity between the updated local map and the global map at the estimated location.

9. The method according to any of claims 7-8, wherein evaluating (207) the localization quality index comprises triggering a warning event when the localization quality index is below the threshold.

10. The method according to any of claims 1-9, wherein the local map represents an area of the mining environment (1) around the machine (10), wherein the size of the area is limited by a pre-configured radius centered at the estimated location of the machine (10).

11. The method according to any of claims 1-11, wherein any one or more out of: performing (203) the first location estimation comprises estimating an orientation of the machine (10), andperforming (205) the second location estimation comprises estimating the orientation of the machine (10).

12. The method according to any of claims 1-12, wherein at least one of the one or more previously obtained sets of range scanning data have been obtained at a location different from the location the current set of range scanning data is obtained.

13. The method according to any of claims 1-12 wherein the method comprises iteratively repeating any one or more out obtaining (201) the set of range scanning data, updating (202) the local map, performing (203) the first location estimation of the machine (10), aligning (204) the updated local map with the global map and performing (205) a second location estimation of the machine (10), and optionally calculating (206) a localization quality index, and evaluating (207) the localization quality index.

14. A system configured to estimate a location of a mining and / or construction machine (10) operating in a mining environment (1), wherein the system is further configured to:obtain a current set of range scanning data of the mining environment (1) surrounding the machine (10) from one or more sensors (12),update a local map of the mining environment (1) taking the current set of range scanning data into account, wherein the local map comprises one or more previously obtained sets of range scanning data,perform a first location estimation of the machine (10) based on the updated local map.align the updated local map with a global map of the mining environment (1) by performing a scan registration between the updated local map and the global map, wherein the aligning comprises taking the first location estimation into account, and perform a second location estimation of the machine (10) based on the alignment of the updated local map with the global map.

15. The system according to claim 14, wherein the system is further configured to perform the method according to any of claims 2-13.

16. A control unit (11) configured to estimate a location of a mining and / or construction machine (10) operating in a mining environment (1), control unit (11) comprising the system according to claim 14.

17. A mining and / or construction machine (10), the mining and / or construction machine (10) comprising a system according to claim 14 or a control unit (11) according to claim 16.

18. A computer program (580) comprising instructions, which when executed by a processor (560), causes the processor (560) to perform actions according to any of the claims 1-13.5   19. A computer-readable medium (585) comprising instructions, which when executedby a processor (560), causes the processor (560) to perform actions according to any of the claims 1-13.10

Images