Method, control unit, and a mining machine for managing a zone in mining environment

Abstract

A method for managing a zone in a mining environment is provided. A set of objects operate in the mining environment. The method comprises obtaining (201) from a set of sensors in the mining environment, sensor data indicative of one or more measured objects out of the set of objects. The method comprises, based on the sensor data, tracking (202) the set of objects. Tracking the set of objects at least comprises estimating locations of the set of objects in the mining environment. The method comprises, based on the tracked set of objects and their respective locations, estimating (206) a probability of that at least one object out of the set of objects is within the zone and / or is entering the zone. The method comprises, when the estimated probability is above a threshold, triggering (207) a preventive action for securing the zone.

Description

[0001] METHOD, CONTROL UNIT, AND A MINING MACHINE FOR MANAGING A ZONE IN

[0002] MINING ENVIRONMENT

[0003] TECHNICAL FIELD

[0004] Embodiments herein relate to a method, a control unit, and a mining machine for managing a zone in a mining environment. In particular where a set of objects operate in the mining environment. Furthermore, a computer program and a carrier are also provided herein.

[0005] BACKGROUND

[0006] In mining environments, it is essential to ensure a high level of safety for operators and other objects that are close to mining machines. This safety can be reached by physical barriers which can be obtrusive and not always perform as intended. However, barriers can be difficult to set up and may need to be rearranged often, thereby making barriers impractical or impossible to use for many situations.

[0007] Alternatively, or complementary, a variety of sensors can be used in order for the machine to measure its surroundings and take actions when an object is detected in an unwanted location. Each sensor technology have their own advantages or disadvantages, especially in a demanding environment where mining machines typically are located. For example optoelectronic sensors can have a high resolution and provide accurate distance measurements. They are however sensitive to particles in the air, such as dust or fog. As one example, ultrasound sensors are minimally affected by dust and fog and has accurate distance measurements, but are for example instead disturbed by compressed air. Radar based sensing is less sensitive to dust or fog. However, the radar technology has problems with reflections and can give rise to ghost objects in the vicinity of large metal objects and in tight spaces. Passive infrared PIR sensors can easily distinguish objects with different temperatures, but cannot detect objects that have a temperature close to the ambient temperature. PIR also cannot determine the distance to objects. In other words, despite what sensor is used, there may be drawbacks such that the respective sensor may not be limited in its ability to accurately detect objects in the mining environment, thereby operators and other objects that are close to mining machines may be at risk. When safety cannot be guaranteed, it is typically the case that entire fleets of machines and / or regions need to be shut down for manual inspection, thereby reducing productivity in the mining environments.

[0008] Hence there is a strive to improve safety in a mining environment while maintaining productivity.

[0009] SUMMARY

[0010] An object of embodiments herein is to improve safety in a mining environment while maintaining productivity.

[0011] According to a first aspect, a method for managing a zone in a mining environment is provided. A set of objects operate in the mining environment. The method comprises, obtaining from a set of sensors in the mining environment, sensor data indicative of one or more objects out of the set of objects. The method comprises, based on the sensor data, tracking the set of objects. Tracking the set of objects at least comprises estimating locations of the set of objects in the mining environment. The method comprises, based on the tracked set of objects and their respective locations, estimating a probability of that at least one object out of the set of objects is within the zone and / or is entering the zone. The method comprises, when the estimated probability is above a threshold, triggering a preventive action for securing the zone.

[0012] Since the preventive action is triggered based on when the estimated probability is above the threshold, an improved safety in an environment is achieved. This is since the preventive action is enabled to be triggered speculatively for all cases when it is possible that an object out of the set of objects is within the zone and / or is entering the zone.

[0013] In some example embodiments, the set of objects comprises at least one unauthorized object not allowed in the zone. In these example embodiments, estimating the probability of that the at least one object is within the zone and / or is entering the zone comprises estimating a probability of that the at least one unauthorized object out of the set of objects is within the zone and / or is entering the zone.

[0014] In this way, the safety of the mining environment is further improved. Furthermore, as there is no need to estimate the probability for authorized objects, the preventive action will not trigger for these objects and productivity will remain high when authorized objects enter the zone without having to trigger the preventive action.

[0015] In some example embodiments, tracking the set of objects comprises identifying the at least one unauthorized object out of the set of objects. In this way, the safety of the mining environment is further improved. This is since when identifying the at least one unauthorized object, it may be possible to determine from its respective location, if it is within the zone, or it may be possible to estimate in how long time the at least one object may appear in the zone, e.g., given a measured speed of the object, or a predefined default speed of the object.

[0016] In some example embodiments, triggering the preventive action comprises any one or more out of: triggering an alert, triggering a machine operating in the zone, to operate in a safe mode, triggering a halt of the machine operating in the zone, triggering a halt of an operation performed by the machine in the zone, and / or triggering the machine to one or more appropriate actions.

[0017] In this way, safety of the mining environment is further improved as unsafe operations may be prevented. Additionally, as some of the preventive actions can maintain operations and productivity of the machine, e.g., in a safe mode, productivity may also be improved while maintaining safety.

[0018] In some example embodiments, estimating the probability of that the at least one object is within the zone and / or is entering the zone is based on a location of the at least one object out of the set of objects measured during a first point in time, and an elapsed time since the first point in time.

[0019] In this way, the probability of that the at least one object is within the zone and / or is entering the zone is more accurately estimated, and thereby the safety of the mining environment is further improved. This is since if the at least one object has a measured position at the first point in time, based on a predetermined or measured speed of the object, it is possible to set an upper bound on where the object may be located with some probability, e.g., within a range from the position where it was measured during the first point in time.

[0020] In some example embodiments, estimating the probability of that the at least one object is within the zone and / or is entering the zone comprises estimating a probability of that one or more undetected objects is within the zone and / or is entering the zone. . In these example embodiments, the one or more undetected objects is part of the set of objects but not indicated by the sensor data.

[0021] In this way, the probability of that the at least one object is within the zone and / or is entering the zone is more accurately estimated, and thereby the safety of the mining environment is further improved. This is since it is possible to track objects and their probability of being within the zone even though they are not explicitly detected. For example, if one object is undetected and previous knowledge of its location has expired, e.g., its respective location data is older than a predetermined time period, it may be conservatively estimated, with high probability above a threshold, that the object is in the zone. If the object on the other hand was detected a long distance away very recently, it may be estimated that the object has low probability below a threshold, or a zero probability, to be in the zone. Furthermore, if the object was previously detected in a part of the mining environment without access to the zone, it can be estimated that the object has low or zero probability to be in the zone.

[0022] In some example embodiments, estimating the probability of that one or more undetected objects is within the zone and / or is entering the zone comprises determining whether the sensor data indicates all objects out of the set of objects.

[0023] In this way, the probability of that the at least one object is within the zone and / or is entering the zone is more accurately estimated, and thereby the safety of the environment is further improved. This is since if all objects are detected, then it can be known whether or not any of them are within the zone. If some objects are not detected, it is further derived that if the detected objects are outside the zone, then only the undetected objects need to be taken into account when estimating the probability of that one or more objects are in the zone and / or are entering the zone.

[0024] In some example embodiments, the method further comprises obtaining characteristics of the set of objects. In these example embodiments, estimating the probability of that the at least one object is within the zone and / or is entering the zone is further based on the characteristics set of objects.

[0025] In this way, the probability of that the at least one object is within the zone and / or is entering the zone is more accurately estimated, and thereby the safety of the mining environment is further improved. This is since the characteristics of the set of objects may indicate the type of objects, number of objects in the set of objects identifier(s) of objects, which objects are authorized in the zone, the objects appearances, if it is a machine or a manual operator, etc., which information may assist in the estimation of the probability . The characteristics of the object may determine whether or not the respective object is authorized in the zone.

[0026] In some example embodiments, obtaining the characteristics of the set of objects comprises detecting at least one of the objects in the set of objects by a tag reader in the mining environment. In these example embodiments, the tag reader is arranged for registering objects in the mining environment.

[0027] In this way, the probability of that the at least one object is within the zone and / or is entering the zone is more accurately estimated, and thereby the safety of the mining environment is further improved. This is since reading with a tag reader ensures a high level of certainty where the object is located at a point in time.

[0028] In some example embodiments, the method further comprises establishing one or more lost objects out of the set of objects. In these example embodiments, each object out of the one or more lost objects have a respective certainty of their respective estimated location below a threshold. In these example embodiments, estimating the probability of that the at least one object is within the zone and / or is entering the zone comprises estimating a probability of that the one or more lost objects is within the zone and / or is entering the zone.

[0029] In this way, the probability of that the at least one object is within the zone and / or is entering the zone is more accurately estimated, and thereby the safety of the mining environment is further improved. This is since the certainty of the estimation of the lost object may correlate to a range or area of where the object may be located, and if said range or area intersects with the zone, it may be assumed that the object is within the zone.

[0030] In some example embodiments, estimating the probability of that the one or more lost objects is within the zone and / or is entering the zone comprises predicting one or more current locations of the one or more lost objects based on a respective last measured location of the one or more lost objects. In these example embodiments, estimating the probability of that the one or more lost objects is within the zone and / or is entering the zone based on the predicted one or more current locations.

[0031] In this way, the probability of that the at least one object is within the zone and / or is entering the zone is more accurately estimated, and thereby the safety of the mining environment is further improved. This is since whether the lost objects are in the zone is more accurately estimated.

[0032] In some example embodiments, estimating the probability of that the one or more lost objects is within the zone and / or is entering the zone comprises obtaining a time period since last measuring a location of at least one of the one or more lost objects, and estimating the probability of that the one or more lost objects is within the zone and / or is entering the zone based on the obtained time period. In this way, the probability of that the at least one object is within the zone and / or is entering the zone is more accurately estimated, and thereby the safety of the mining environment is further improved. This is since whether the lost objects are in the zone is more accurately estimated based on its last measured location, and how speculatively may have travelled during the obtained time period.

[0033] In some example embodiments, the set of sensors comprises any one or more out of: one or more Light, detection, and ranging sensors, one or more Radio, detection, and ranging sensors, one or more cameras, one or more tag readers, one or more machine sensors indicative of an operation of one or more machines in the mining environment, and / or indicative of one or more operators operating the one or more machines in the mining environment.

[0034] In this way, the probability of that the at least one object is within the zone and / or is entering the zone is more accurately estimated, and thereby the safety of the mining environment is further improved with improvements of sensor data, where an increased number of sensors and / or types of sensors used improves accuracy of tracking objects using said sensors.

[0035] In some example embodiments, the method further comprises obtaining an certainty of the obtained sensor data and / or obtaining an certainty of the estimated respective locations of the set of objects, and wherein estimating the probability of that the at least one object is within the zone and / or is entering the zone is further based on the certainty of the obtained sensor data and / or the certainty of the estimated respective locations of the set of objects.

[0036] In this way, the probability of that the at least one object is within the zone and / or is entering the zone is more accurately estimated, and thereby the safety of the mining environment is further improved. This is since the sensor data can be more accurately estimated in terms of certainty of identifying the respective locations of the set of objects.

[0037] In some example embodiments, the set of objects comprises operators in the mining environment.

[0038] In this way, the probability of that the at least one object is within the zone and / or is entering the zone is more accurately estimated, and thereby the safety of the mining environment is further improved. This is since it may be accurately estimated how an operator may move in the mining environment. Furthermore, in above example embodiments, when the probability of that the at least one object is within the zone and / or is entering the zone is more accurately estimated, productivity is further improved. This is since there is less need to speculatively trigger the preventive action if the probability is accurately estimated.

[0039] According to a second aspect, a control unit configured to manage a zone in a mining environment is provided. A set of objects are arranged to operate in the mining environment. The control unit is further configured to obtain from a set of sensors in the mining environment, sensor data indicative of one or more objects out of the set of objects. The control unit is further configured to, based on the sensor data, track the set of objects, by estimating locations of the set of objects in the mining environment. The control unit is further configured to, based on the tracked set of objects and their respective locations, estimate a probability of that at least one object out of the set of objects is within the zone and / or is entering the zone. The control unit is further configured to, when the estimated probability is above a threshold, trigger a preventive action for securing the zone.

[0040] According to a third aspect, a mining machine is provided. The mining machine is configured to perform actions according to the first aspect. Advantages and effects of the mining machine are analogous to the advantages and effects of the method of the first aspect and / or of the control unit of the second aspect. Further, all embodiments of the computer program are applicable to and combinable with all embodiments of the method of the first aspect and / or of the control unit of the second aspect, and vice versa.

[0041] According to a fourth aspect, a computer program comprising instructions, which when executed by a processor, causes the processor to perform actions according to the first aspect and / or of the control unit of the second aspect. Advantages and effects of the computer program are analogous to the advantages and effects of the method of the first aspect and / or of the control unit of the second aspect. Further, all embodiments of the computer program are applicable to and combinable with all embodiments of the method of the first aspect and / or of the control unit of the second aspect, and vice versa.

[0042] According to a fifth aspect, a carrier comprising the computer program according to the fourth aspect, wherein the carrier 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. Advantages and effects of the carrier are analogous to the advantages and effects of the method of the first aspect and / or the control unit of the second aspect. Further, all embodiments of the carrier are applicable to and combinable with all embodiments of the method of the first aspect and / or the control unit of the second aspect, and vice versa.

[0043] Further advantages and advantageous features of embodiments herein are disclosed in the following detailed description and in the dependent claims.

[0044] BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Examples of embodiments herein are described in more detail with reference to attached drawings in which:

[0046] Fig. 1 is a schematic block diagram illustrating a scenario according to example embodiments herein.

[0047] Fig. 2 is a flowchart depicting a method according to an example embodiments herein.

[0048] Fig. 3 is a schematic block diagram illustrating example embodiments herein.

[0049] Fig. 4 is a schematic block diagram illustrating example embodiments herein.

[0050] Fig. 5 is a schematic block diagram illustrating example embodiments herein.

[0051] Fig. 6 is a schematic block diagram illustrating example embodiments herein.

[0052] Fig. 7 is a schematic block diagram illustrating example embodiments herein.

[0053] Fig. 8 is a schematic block diagram illustrating example embodiments herein.

[0054] Fig. 9 is a schematic block diagram illustrating example embodiments of a control unit.

[0055] DETAILED DESCRIPTION

[0056] Fig. 1 is a schematic overview depicting a mining environment 100 of example embodiments herein. The mining environment 100 may be a pit, a quarry, or underground environment, etc. The mining environment 100 may be any suitable environment for performing mining operations, e.g., drilling, preparing to drill, rock reinforcement, prospecting, transporting materials, etc.

[0057] The mining environment 100 may comprise various passages and paths surrounded by rock foundation 8. Due to being underground and / or due to the rock foundation 8, 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 8 in the mining environment 100, as these are typically very dense and unsuitable for radio propagation. Radio signals in the mining environment 100 may instead bounce in the mining environment 100 in a manner much different from normal environments for wireless communications, and hence, normal approaches for network communication or positioning thereof may not apply. Furthermore, the mining environment 100 may be dark and / or dusty, making some sensors more prone to error, which errors cause problems of detecting objects, which problems are at least partially resolved by some embodiments herein.

[0058] The mining environment 100 comprises a zone 90. The zone 90 may be a well- defined area in the mining environment 100. The zone 90 may be a secure area where only authorized objects are allowed to enter. The zone 90 may be an area around any suitable machine, or may be an area where said machine is operating or is scheduled to operate. The zone 90 may comprise one or more machines performing one or more mining operations, e.g., drilling, which may be dangerous for objects if they are too close. In other words, the zone 90 may be any suitable area in the mining environment 100 which may need to be secured.

[0059] The mining environment 100 comprises a set of objects 10. Each object out of the set of objects 10 may respectively be an operator, i.e. , a human, or a machine, e.g., a work machine, a vehicle, a drill rig, a transport vehicle, an unmanned aerial vehicle, etc. When the respective object is a machine, the respective object may be unmanned or have an operator present. Each object out of the set of objects 10 may respectively be a human, e.g., an operator outside or inside of a machine. In some scenarios of embodiments herein, the set of objects 10 comprises one or more human operators.

[0060] The mining environment 100 comprises a set of sensors 20 used for identifying the set of objects 10. When identifying a respective object out of the set of objects 10, the respective object may be measured by one or more respective sensors out of the set of sensors 20. Identifying a respective object out of the set of objects may be associated with a certainty or probability of the respective object’s location, e.g., such that a location of a respective may be estimated with a probability. The probability may be represented by a range of area where the respective object may be present based on the accuracy of the estimated probability. Using multiple sensors to identify the respective object may increase the accuracy of the estimation of the object’s location. When the respective object is identified, its size may also be measured, depending on the sensor capability of the respective sensor. Each respective sensor out of the set of sensors 20 may be arranged in any suitable manner, e.g., as any one or more out of: mounted on the rock foundation, part of infrastructure, mounted on a barrier, mounted on a machine, mounted on an operator, in the zone 90, outside the zone 90, and mounted in the ceiling of the mining environment 100. As an example, the set of sensors 20 may comprise any one or more out of: one or more Light, detection, and ranging (Lidar) sensors, one or more Radio, detection, and ranging (Radar) sensors, one or more cameras, e.g., three-dimensional (3D) cameras, three-dimensional (3D) cameras, and / or infrared (IR) cameras, mono-cameras, stereo-cameras, RGB-D cameras, etc. one or more tag readers, e.g., Radio Frequency Identification (RFID) tag readers for high accuracy location measurement, one or more machine sensors indicative of an operation of one or more machines in the mining environment 100, e.g., as part of respective control and / or monitoring units, and / or indicative of one or more operators operating the one or more machines in the mining environment 100.

[0061] As used herein, when discussing sensor data, certainty may mean precision or accuracy, that the sensor data accurately identifies an object at a specific position.

[0062] The zone 90 may be comprised or encompassed by a second zone (not illustrated), which second zone is the field of view of the set of sensors 20.

[0063] Using the set of sensors 20, sensor data may be obtained, which sensor data may indicate one or more measured objects 11 out of the set of objects. In example embodiments herein, it may not always be possible to measure all of the set of objects 10, and therefore example embodiments herein may relate to estimate a probability of that at least one object out of the set of objects 10 are within the zone 90 and / or are entering the zone 90 based on what objects have recently been measured, i.e. , the positions of the one or more measured objects 11, derived information thereof, and / or based on previous measurements of the remaining set of objects 10.

[0064] The mining environment 100 may comprise a mining machine 80. The mining machine 80 may be any one out of, a work machine, a vehicle, a drill rig, a transport vehicle, and an unmanned aerial vehicle. The mining machine 80 may be arranged to perform mining operations in the mining environment 100 and / or may be arranged for handling the zone 90. The mining operations may comprise travelling in the zone 90. The mining machine 80 may be arranged to operate within and / or outside the zone 90. In some embodiments, all or part of the set of sensors 20 may be mounted on the mining machine 80.

[0065] Embodiments herein may be performed by any suitable control unit such as a control unit 70 and / or the mining machine 80. The control unit 70 may be located in any suitable location. For example, the control unit 70 may be located in the mining environment 100, e.g., in the mining machine 80 or as part of the infrastructure, or at a remote location, e.g. above ground. The control unit 70 may be part of a server but may also be part of the mining machine 80.

[0066] The control unit 70 and / or the mining machine 80 may be capable of managing the zone 90 according to example embodiments herein. The control unit 70 and / or the mining machine 80 may be capable of communicating with the set of sensors 20, e.g., for obtaining sensor data, and / or capable of communicating with any other suitable entity of the mining environment 100.

[0067] A number of embodiments will now be described, which embodiments may be used in any suitable combination.

[0068] Fig. 2 illustrates an example embodiment of a method for managing the zone 90 in the mining environment 100. The set of objects 10 operate in the mining environment 100. Operate in this example embodiment may mean that the objects 10 are merely present in the mining environment 100 and / or are moving / travelling in the mining environment 100. The set of objects 10 may be machines and / or humans which may or may not perform work or mining operations in the mining environment 100. In some example embodiments, the set of objects 10 comprises at least one unauthorized object not allowed in the zone 90.

[0069] In some example embodiments, the set of objects 10 comprises operators in the mining environment 100.

[0070] The method comprises one or more out of the following actions, which actions may be taken in any suitable order.

[0071] Action 201. The method comprises obtaining from the set of sensors 20 in the mining environment 100. The sensor data is indicative of one or more measured objects 11 out of the set of objects 10. In other words, the set of objects 10 may be objects in the mining environment 100 that are of interest to manage the zone 90. The one or more measured objects 11 may comprise a subset of the set of objects 10, or all of the set of objects 10.

[0072] In some example embodiments, the set of sensors 20 comprises any one or more out of: one or more Light sensors, one or more Radar sensors, one or more cameras, one or more tag readers, and / or one or more machine sensors indicative of an operation of one or more machines in the mining environment 100, and / or indicative of one or more operators operating the one or more machines in the mining environment 100.

[0073] In other words, sensor data of the set of sensors 20 may have different precision and / or accuracy under different circumstances. The use of multiple sensors for obtaining the one or more measured objects 11 may improve the accuracy and / or certainty of the one or more measured objects 11 respective measured location.

[0074] Obtaining the sensor data may comprise obtaining one or more location measurements of the one or more measured objects 11.

[0075] Obtaining the sensor data may comprise obtaining certainty of the sensor data. In some examples, uncertainty may also be obtained as long as it is possible to determine a reliability of the sensor data.

[0076] Action 202. The method comprises, based on the sensor data, tracking the set of objects 10. Tracking the set of objects 10 at least comprises estimating locations of the set of objects 10 in the mining environment 100. In other words, tracking the set of objects 10 may comprise estimating locations of the set of objects 10 based on the measured set of objects 11. In other words, tracking the set of objects 10 may comprise both using sensor data for the one or more measured objects 11 to estimate their receptive locations, and / or using information of lack of sensor data to estimate respective locations, e.g., by estimating that the respective object may have an area where it may be present based on a previous measurement and / or by estimating that the respective object is not present in locations associated with the sensor data.

[0077] In example embodiments herein, an authorized object may mean an object allowed in the zone 90. In example embodiments herein, an unauthorized object may mean an object not allowed in the zone 90.

[0078] In some example embodiments, tracking the set of objects 10 comprises identifying the at least one unauthorized object out of the set of objects 10. For example, an identifier of the unauthorized object may be read as part of the sensor data, or one of the object may be recognized by the sensor data, e.g., by image analysis, to be an unauthorized object. In some example embodiments, an object may as a default be unauthorized until identified as authorized, e.g., by an identifier indicating the object as authorized or by image detection of the sensor data detects that the object is authorized, i.e. , identification through sensor data.

[0079] Estimating locations of the set of objects 10 in the mining environment 100 may comprise estimating respective locations of the set of objects 10 with different levels of certainty. Certainty as used herein may mean precision, accuracy or a probability that the respective locations and / or sensor data is still valid. The certainty may correlate to an estimated maximum distance from a respective estimated location and / or to an expected area, e.g., an ellipsoid, enclosing the respective estimated location.

[0080] When the respective object is part of the one or more measured objects 11 , the certainty of the location may be high and may be based on certainty of the sensor data measuring the respective object.

[0081] When the respective object is not part of the one or more measured objects 11 , the certainty of the estimated location may be low, e.g., below a threshold, and may be based on a time since previously measuring the respective object at a set location, and certainty of sensor data when previously measuring the respective object. This means that tracking the set of objects 10 may comprise estimating the locations of the set of objects 10 based on a motion model, e.g., as discussed above with time as one factor. More advanced motion models may also be used, e.g., by tracking the set of objects 10 by estimating locations of the set of objects 10 by additionally or alternatively estimating a speed and / or direction of the set of objects 10.

[0082] Action 203. In some example embodiments, the method comprises obtaining characteristics of the set of objects 10. The characteristics of the set of objects 10 may indicate any one or more out of: a type of one or more objects in the set of objects 10, an identifier of one or more objects in the set of objects 10, a number of objects in the set of objects 10, a position of one or more objects in the set of objects 10, an authorization of one or more objects in the set of objects 10, e.g., if the respective object is authorized or unauthorized in the zone 90, appearances of one or more objects in the set of objects 10, e.g., size / dimensions, and whether one or more objects out of the set of objects 10 are respectively machines or manual operators.

[0083] The characteristics of the object may determine whether or not the respective object out of the set of objects 10 is authorized in the zone 90.

[0084] The characteristics may be used e.g., to obtain which objects are to be tracked and / or are present in the mining environment 100, i.e. , which objects may enter the zone 90. The characteristics may be used e.g., to obtain a quantity of the set of objects 10 in the mining environment 100.

[0085] In some example embodiments, obtaining the characteristics of the set of objects 10 comprises detecting at least one of the objects in the set of objects by a tag reader in the mining environment 100. In these example embodiments, the tag reader is arranged for registering objects in the mining environment 100. The tag reader may be an RFID reader. Obtaining the characteristics of the set of objects 10 may be part of a registration process of the set of objects 10, e.g., as part of entering the mining environment 100 and / or when initiating a work cycle and / or for authorizing access into the zone 90.

[0086] Action 204. In some example embodiments, the method further comprises obtaining an certainty of the obtained sensor data and / or obtaining an certainty of the estimated respective locations of the set of objects 10, e.g., as obtained in action 201 and / or as tracked in action 202..

[0087] The respective certainty may indicate how likely it is that the object is present at the respective estimated location. Additionally or alternatively, the certainty may indicate or correlate to a range or area of where the object may be present.

[0088] Action 205. In some example embodiments, the method comprises establishing one or more lost objects out of the set of objects 10. Each object out of the one or more lost objects may be defined as an object out of the set of objects 10 which has a respective certainty of their respective estimated location below a threshold.

[0089] In other words, the certainty of the one or more lost objects may be low, e.g., as the sensor data measuring said objects was low, e.g., below a threshold, and / or the one or more lost objects was not part of the one or more measured objects 11, i.e. , there may only be old location data available which may have low certainty, e.g., below a threshold, as the respective object may have moved since measuring its location.

[0090] Additionally or alternatively have establishing the one or more lost objects out of the set of objects 10 may comprises: detecting that an object is no longer tracked, e.g., a number of tracked objects is detected to have decreased, an identifier of at least one object is no longer valid, i.e., two objects may be mixed, e.g., authorized and unauthorized, such that it is no longer possible to estimate which object belong to which identity, an estimated position accuracy of an object out of the set of objects 10 is below a threshold Action 206. The method comprises, based on the tracked set of objects 10 and their respective locations, estimating a probability of that at least one object out of the set of objects 10 are within the zone 90 and / or are entering the zone 90.

[0091] The probability may be based on the certainty of the obtained sensor data and / or obtaining the certainty of the estimated respective locations of the set of objects 10, e.g., as obtained in action 205. In other words, the probability may be estimated based on a quality of direct measurements of the one or more measured objects 11 , or by estimating a probability, with respect to lack of recent measurements, of at least some objects not part of the one or more measured objects 11.

[0092] In some example embodiments, estimating the probability of that the at least one object are within the zone 90 and / or are entering the zone 90 is further based on the characteristics set of objects 10. For example, the characteristics may indicate the number of objects in the set of objects 10, if said number of objects matches the number of objects in the one or more measured objects 11 , then all of the objects are accounted for and the measured locations of the one or more measured objects 11 may be for estimating the probability of that the at least one object out of the set of objects 10 are within the zone 90 and / or are entering the zone 90.

[0093] In some example embodiments, estimating the probability of that the at least one object are within the zone 90 and / or are entering the zone 90 comprises estimating a probability of that the at least one unauthorized object out of the set of objects 10 are within the zone 90 and / or are entering the zone 90. In other words, authorized objects may not be accounted for when estimating the probability.

[0094] In some example embodiments, estimating the probability of that the at least one object are within the zone 90 and / or are entering the zone 90 is based on a location of the at least one object out of the set of objects 10 measured during a first point in time, and an elapsed time since the first point in time.

[0095] In other words, as measured sensor data of a respective location of an object grows older, the probability of the validity is lowered over time, and furthermore, probability of that the object can be at another location, e.g., within the zone 90 grows over time, or at least becomes more than zero after a set period of time, depending on a speed of the object. It may be assumed that the object moves at most with a predefined speed.

[0096] In some example embodiments, estimating the probability of that the at least one object are within the zone 90 and / or are entering the zone 90 comprises estimating a probability of that one or more undetected objects are within the zone 90 and / or are entering the zone 90. The one or more undetected objects may be part of the set of objects 10 but not indicated by the sensor data. In other words, objects not recently measured may be estimated as a probability of whether they are within the zone 90 or not. The probability may be based on a previous estimate of its respective location, that estimates certainty, and an elapsed time since said estimation.

[0097] In some example embodiments, estimating the probability of that one or more undetected objects are within the zone 90 and / or are entering the zone 90 comprises determining whether the sensor data indicates all objects out of the set of objects 10.

[0098] In other words, if all objects out of the set of objects are measured by the one or more measured objects 11 , then if these are not in the zone, then there are no objects in the zone 90.

[0099] In some example embodiments, estimating the probability of that the at least one object are within the zone 90 and / or are entering the zone 90 comprises estimating a probability of that the one or more lost objects, e.g., as established in action 205, are within the zone 90 and / or are entering the zone 90. In these example embodiments, a conservative estimate may be made, e.g., to assume that the objects have travelled towards the zone 90 since its last measured position. In some of these example embodiments, when an object is lost for a predefined period of time, it may be assumed, e.g., estimated with a high probability such as above a predefined threshold, that the object is present within the zone 90.

[0100] In some example embodiments, estimating the probability of that the one or more lost objects, e.g., as established in action 205, are within the zone 90 and / or are entering the zone 90 comprises predicting one or more current locations of the one or more lost objects based on a respective last measured location of the one or more lost objects, and estimating the probability of that the one or more lost objects are within the zone 90 and / or are entering the zone 90 based on the predicted one or more current locations.

[0101] In some example embodiments, estimating the probability of that the one or more lost objects e.g., as established in action 205, are within the zone 90 and / or are entering the zone 90 comprises obtaining a time period since last measuring a location of at least one of the one or more lost objects, and estimating the probability of that the one or more lost objects are within the zone 90 and / or are entering the zone 90 based on the obtained time period. In other words, the probability may be estimated with respect to, may the one or more lost objects have moved into the zone 90, during the obtained time period, from last measured respective location.

[0102] In some example embodiments, estimating the probability of that the at least one object is within the zone 90 and / or is entering the zone 90 is further based on the certainty, e.g., as obtained in action 205, of the obtained sensor data and / or the certainty of the estimated respective locations of the set of objects 10. When the certainties grow less certain, i.e., increased uncertainty, e.g., over time without measuring new respective locations, the estimation of the probability of that the at least one object is entering the zone grows higher, or at least becomes non-zero when deemed possible for the respective object to have moved to be within the zone 90.

[0103] In some example embodiments, estimating the probability of that the at least one object are within the zone 90 and / or are entering the zone 90 may correlate inversely with a certainty of an estimated location of a respective object. For example, when an object is estimated to be at a location outside the zone 90, with a certainty above a threshold, e.g., based on accuracy of the sensor data, then it may be estimated that there is small probability, above a threshold, that the object is within the zone 90 and / or are entering the zone 90.

[0104] Action 207. The method comprises when the estimated probability, as in action 206, is above a threshold, triggering a preventive action for securing the zone 90.

[0105] In some example embodiments, triggering the preventive action comprises any one or more out of: triggering an alert, e.g., a sound alert and / or light alert, triggering a machine operating in the zone 90, to operate in a safe mode, the safe mode may be to only perform operations predefined as safe and / or to reduce a speed of one or more operations, triggering a halt of the machine operating in the zone 90, triggering a halt of an operation performed by the machine 400 in the zone 90, and / or triggering the machine to one or more appropriate actions.

[0106] The threshold may be set very conservatively, e.g., at 1% probability, or lower, e.g., at 0%.

[0107] The threshold may be zero or may be, or may be zero added with an error margin, and / or may be based on an error margin. The threshold may be predefined.

[0108] The threshold may be set such that, whenever there is an uncertainty of respective locations for the tracked set of objects 10, the preventive action is triggered, i.e., the respective estimated probability of that at least one object is within the zone 90 and / or is entering the zone 90, is estimated to be a higher probability than the threshold for triggering the preventive action, thereby triggering the preventive action. The threshold may be set such that, whenever an object is lost, e.g., as established in action 205, e.g., for a predefined period of time, the respective estimated probability of that the one or more lost objects are within the zone 90 and / or are entering the zone 90, is estimated to be a higher probability than the threshold for triggering the preventive action, thereby triggering the preventive action.

[0109] The machine of the above options may be the mining machine 80 or any other suitable machine operating in the zone 90.

[0110] Fig. 3 illustrates an example scenario. In this scenario, the zone 90 may be restricted by that for objects to reach the zone 90, they need to pass a security area 301 , e.g., comprising a physical barrier or the like. The security area 301 may comprise a tag reader 300, e.g., an RFID reader. The tag reader 300 may be arranged for registering objects in the mining environment 100, e.g., by reading tags of the objects. The tags may be RFID or images, such as QR codes or other identifiers. In other words, the set of objects 10 may need to pass the tag reader 300, and wherein the tag reader 300 can read a tag of the respective object, e.g., an RFID tag. As an alternative to a tag reader, a camera can be used, and image detection can be used instead to detect and count objects in any suitable manner. Additionally or alternatively, other sensors, e.g., Lidar may also be used. The characteristics of the set of objects 10 may be obtained, e.g., as in action 203, by detecting at least one of the objects in the set of objects 10 by using a tag reader 300 in the mining environment 100. For example, the tag reader 300 may obtain the number of objects in the set of objects, and identifiers relating to them which can be used to derive or obtain, e.g., from a database, any suitable information of the respective object, e.g., capabilities, type, appearance, dimensions, etc. In the scenario of Fig. 3, the characteristics may be the number of objects in the set of objects 10. Since the number of objects is known, in this case four objects counted by the tag reader 300, e.g., as obtained in action 203, and since three different objects are measured in the one or more measured objects 11, e.g., as in action 201, estimating the probability of that at least one object out of the set of objects 10 are within the zone 90 and / or are entering the zone 90, e.g., as in action 206, may be estimated with respect to one object 302 out of the set of objects 10, not part of the one or more measured objects 11, e.g., as in action 201. The characteristics of the set of objects 10, may however have obtained that the object 302 is an authorized object in the zone 90, and thereby only the one or more measured objects 11 are unauthorized in the zone 90. Accordingly, there is no need to account for the authorized object 302 when estimating the probability of an object in the zone 90, and thereby the probability of an unauthorized object in the zone 90 may be estimated to be very low, e.g., below a threshold or zero, as all unauthorized objects are accounted for and measured at respective positions outside the zone 90 with high accuracy, e.g., by multiple different sensors out of the set of sensors 20.

[0111] Fig. 4 illustrates an example scenario wherein a machine 400 may be operating in the zone 90. The machine 400 may be the mining machine 80 or any other suitable machine performing one or more operations in the zone 90 which may be dangerous if performed with unauthorized objects present in the zone 90.

[0112] In these scenarios, when the estimated probability of that an unauthorized object is present in the zone 90, e.g., as in action 206, is above a threshold, triggering a preventive action for securing the zone 90 may comprise any one or more out of: triggering an alert, triggering the machine 400 operating in the zone 90, to operate in a safe mode, the safe mode may be to only perform operations predefined as safe and / or to reduce a speed of one or more operations, triggering a halt of the machine 400 operating in the zone 90, triggering a halt of an operation performed by the machine 400 in the zone 90, and / or triggering the machine 400 to one or more appropriate actions.

[0113] Fig. 5 illustrates an example scenario of losing track of an object. In this scenario one or more lost objects 500 out of the set of objects 10 are established, e.g., as in action 205. In Fig. 5, only one lost object 500 is illustrated, but many more may exist, e.g., all of objects not part of the one or more measured objects 11 may eventually be deemed lost if a respective certainty of its position is below a threshold.

[0114] Each object out of the one or more lost objects 500 may have a respective certainty of their respective estimated location below the threshold. To estimate the probability of that the at least one object are within the zone 90 and / or are entering the zone 90, e.g., as in action 206, may be performed by estimating a probability of that the one or more lost objects 500 are within the zone 90 and / or are entering the zone 90.

[0115] In this example scenario, the probability of that the one or more lost objects 500 are within the zone 90 and / or are entering the zone 90 may be estimated, e.g., as in action 206, based on predicted one or more current locations of the one or more lost objects 500. The one or more current locations may be predicted based on a respective last measured location of the one or more lost objects 500.

[0116] In this example scenario, the probability of that the one or more lost objects 500 are within the zone 90 and / or are entering the zone 90 may further be estimated, e.g., as in action 206, by obtaining a time period since last measuring a location of at least one of the one or more lost objects 500, and estimating the probability of that the one or more lost objects 500 are within the zone 90 and / or are entering the zone 90 based on the obtained time period.

[0117] In other words, based on previous measurements, and / or a time since the previous measurements of objects, it may be possible to estimate the probability that the respective object has moved into the zone 90.

[0118] Fig. 6 illustrates an example scenario wherein all objects out of the set of objects is indicated by the one or more measured objects 11. The sensor data indicating the one or more measured objects 11 may be of high certainty, i.e., the accuracy is high. Accordingly, estimating the probability of an object present in and / or entering the zone 90, may be estimated to be very low, e.g., below a threshold, or to be zero, e.g., as in action 206, as all objects have been measured outside of the zone 90, with high certainty.

[0119] Fig. 7 illustrates a scenario where one or more secondary machines 701 , 702, 703, 704 are present in the mining environment 100. In these scenarios, the set of sensors 20 may comprise one or more machine sensors, e.g., as part of the one or more secondary machines 701, 702, 703, 704. The set of sensors 20 may further be used to obtain sensor data indicative of an operation of one or more of the secondary machines 701 , 702, 703, 704 in the mining environment 100. Additionally or alternatively, the set of sensors 20 may further be used to obtain sensor data indicative one or more operators operating the one or more machines in the mining environment 100.

[0120] Since the respective secondary machine may need an operator, and the set of objects 10 comprises one or more operators, it may be derived that a respective operator out of the set of objects 10 is inside of a respective secondary machine 701, 702, 703, 704, when the secondary machine is operating. The identity or specific operator may be obtained, e.g., when the respective secondary machine 701 , 702, 703, 704, has a register function for the operator to use and / or if the respective secondary machine 701 , 702, 703, 704, is predefined to be operated by a specific operator.

[0121] In other words, status of machines operating in the mining environment 100 may be used as implicit sensors for tracking positions of at least some objects in the set of objects 10, e.g., as in action 202.

[0122] Fig. 8 illustrates an example scenario illustrating that all scenarios above, and / or all example embodiments discussed may be combined with each other. The machine 400 may operate in the zone 90 in any suitable scenario herein. The machine 400 may or may not be the mining machine 80. The tag reader 300 may be used to obtain characteristics of the set of objects 10, e.g., which objects are present that need to be tracked, e.g., as in action 202, and / or how many are these objects. The one or more secondary machines 701 , 702, 702, 704 may be part of the set of objects 10 and / or may implicitly be used as sensors as they may need an operator to be operated.

[0123] In some embodiments herein, a machine, e.g., mining machine 80 or the machine 400 may operate in the mining environment 100. The set of sensors 20 may be activated and may be used monitor a detection zone, i.e. , all they may measure in the mining environment or a sub-set thereof. The set of objects 10 may be measured by the set of sensors 20, e.g., as in action 201. The set of objects 10 may accordingly be tracked, e.g., as in action 202. The set of objects 10 may comprise people logging using RFID tags to be identified and / or authorized to be in the zone 90. When an unauthorized object out of the set of objects 10 is estimated to be within or entering the zone 90, e.g., as in action 206, the preventive action as in action 207 may be triggered . When a tracked object out of the set of objects 10 is lost, e.g., a certainty of its position is below a threshold, the preventive action of action 207 may also be triggered. The preventive action may be based on whether the last known position of the object. In any embodiment herein, the set of sensors 20 may further be configured monitor the second zone comprising or encompassing the zone 90, wherein, when estimating that at least one object out of the set of objects 10 is in or entering the second zone, an alert may be triggered. In other words, the second zone may be a warning zone. Estimating at least one object out of the set of objects to be within the second zone may be performed as anyone or more out of actions 201-206, but replacing the zone 90.

[0124] To perform embodiments herein, e.g. the method according to actions 201-207 above, may be performed by the control unit 70 and / or by any of the mining machine 80, 400. The control unit 70 may be arranged in a centralized location, e.g. as part of a server or a cloud service, or may be located in the mine, e.g. comprised in the mining machine 80. The control unit 70 is configured to manage the zone 90 in the mining environment 100. The set of objects 10 is arranged to operate in the mining environment 100. The control unit 70 and / or the mining machine 80 is further configured to obtain from the set of sensors 20 in the mining environment 100, sensor data indicative of one or more measured objects 11 out of the set of objects 10.

[0125] The control unit 70 is further configured to, based on the sensor data, track the set of objects 10, by estimating locations of the set of objects 10 in the mining environment 100. The control unit 70 is further configured to, based on the tracked set of objects 10 and their respective locations, estimate a probability of that at least one object out of the set of objects 10 are within the zone 90 and / or are entering the zone 90.

[0126] The control unit 70 is further configured to, when the estimated probability is above a threshold, trigger a preventive action for securing the zone 90.

[0127] Further, all embodiments of the control unit 70 and / or the mining machine 80 are applicable to and combinable with all embodiments of actions 201-207 above.

[0128] The control unit 70 may comprise an arrangement depicted in Fig. 9. The control unit 70 may comprise an input and output interface 900 e.g. for communicating with the set of sensors 20

[0129] The input and output interface 900 may comprise a wireless or wired receiver not shown, a transceiver, one or more antennas, and / or a wired or wireless transmitter not shown.

[0130] In some example embodiments, the set of objects 10 comprises at least one unauthorized object not allowed in the zone 90, and the control unit 70 is configured to estimate the probability of that the at least one object are within the zone 90 and / or are entering the zone 90 by estimating a probability of that the at least one unauthorized object out of the set of objects 10 are within the zone 90 and / or are entering the zone 90.

[0131] In some example embodiments, the control unit 70 is configured to track the set of objects 10 by identifying the at least one unauthorized object out of the set of objects 10.

[0132] In some example embodiments, the control unit 70 is configured to trigger the preventive action comprises any one or more out of: triggering an alert, triggering a machine 400 operating in the zone 90, to operate in a safe mode. triggering a halt of the machine 400 operating in the zone 90, triggering a halt of an operation performed by the machine 400 in the zone 90, and / or triggering the machine 400 to one or more appropriate actions.

[0133] In some example embodiments, the control unit is configured to estimate the probability of that the at least one object are within the zone 90 and / or are entering the zone 90 based on a location of the at least one object out of the set of objects 10 measured during a first point in time, and based on an elapsed time since the first point in time. In some example embodiments, the control unit 70 is configured to estimate the probability of that the at least one object are within the zone 90 and / or are entering the zone 90 by estimating a probability of that one or more undetected objects are within the zone 90 and / or are entering the zone 90, The one or more undetected objects may be adapted to be part of the set of objects 10 but not indicated by the sensor data.

[0134] In some example embodiments, the control unit 70 is configured to estimate the probability of that one or more undetected objects are within the zone 90 and / or are entering the zone 90 by determining whether the sensor data indicates all objects out of the set of objects 10.

[0135] In some example embodiments, the control unit 70 further is configured to obtain characteristics of the set of objects 10, and configured to estimate the probability of that the at least one object are within the zone 90 and / or are entering the zone 90 based on the characteristics set of objects 10.

[0136] In some example embodiments, the control unit 70 is configured to obtain the characteristics of the set of objects 10 by detecting at least one of the objects in the set of objects 10 by using a tag reader 300 in the mining environment 100, the tag reader 300 being arranged for registering objects in the mining environment 100.

[0137] In some example embodiments, the control unit 70 is configured to establish one or more lost objects 500 out of the set of objects 10. Each object out of the one or more lost objects 500 may be adapted to have a respective certainty of their respective estimated location below a threshold. The control unit 70 may be further configured to estimate the probability of that the at least one object are within the zone 90 and / or are entering the zone 90 by estimating a probability of that the one or more lost objects 500 are within the zone 90 and / or are entering the zone 90.

[0138] In some example embodiments, the control unit 70 is configured to estimate the probability of that the one or more lost objects 500 are within the zone 90 and / or are entering the zone 90 by predicting one or more current locations of the one or more lost objects 500 based on a respective last measured location of the one or more lost objects 500. The control unit 70 may further be configured to estimate the probability of that the one or more lost objects 500 are within the zone 90 and / or are entering the zone 90 based on the predicted one or more current locations.

[0139] In some example embodiments, the control unit 70 is configured to estimate the probability of that the one or more lost objects 500 are within the zone 90 and / or are entering the zone 90 by obtaining a time period since last measuring a location of at least one of the one or more lost objects 500, and estimating the probability of that the one or more lost objects 500 are within the zone 90 and / or are entering the zone 90 based on the obtained time period.

[0140] In some example embodiments, the set of sensors 20 is adapted to comprise any one or more out of: one or more Lidar sensors, one or more Radar sensors, one or more cameras, one or more tag readers, one or more machine sensors indicative of an operation of one or more machines in the mining environment 100, and / or indicative of one or more operators operating the one or more machines in the mining environment 100.

[0141] In some example embodiments, the control unit 70 is configured to obtain a certainty of the obtained sensor data and / or obtain a certainty of the estimated respective locations of the set of objects 10. The control unit 70 may further be configured to estimate the probability of that the at least one object are within the zone 90 and / or are entering the zone 90 further based on the certainty of the obtained sensor data and / or the certainty of the estimated respective locations of the set of objects 10.

[0142] In some example embodiments, the set of objects 10 comprises operators in the mining environment 100.

[0143] The embodiments herein may be implemented through one or more processors, such as a processor 910 of a processing circuitry in the control unit 70, depicted in Fig. 9, together with a computer program 930 comprising instructions, which when executed by a processor, causes the processor to perform the functions and actions of the embodiments herein.

[0144] In some embodiments, a respective carrier 940 comprises the respective computer program 930, wherein the carrier 940 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. For example, one such carrier may be in the form of a CD ROM disc or a memory stick. The computer program 930 may furthermore be provided as pure program code on a server and downloaded to the control unit 70.

[0145] The control unit 70 may further comprise a memory 920 comprising one or more memory units. The memory 920 comprises instructions executable by the processor in the control unit 70. The memory 920 is arranged to be used to store e.g. information, indications, data, configurations, position estimations, quality indicators, and applications to perform the embodiments herein when being executed in the control unit 70.

[0146] Those skilled in the art will appreciate that the units in the control unit 70 described above may refer to a combination of analog and digital circuits, and / or one or more processors configured with software and / or firmware, e.g. stored in the control unit 70, that when executed by the respective one or more processors such as the processors described above. One or more of these processors, as well as the other digital hardware, may be included in a single Application-Specific Integrated Circuitry ASIC, or several processors and various digital hardware may be distributed among several separate components, whether individually packaged or assembled into a system-on-a-chip SoC.

[0147] When using the word "comprise" or “comprising” it shall be interpreted as nonlimiting, i.e. meaning "consist at least of".

[0148] 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

CLAIMS1. A method for managing a zone (90) in a mining environment (100), wherein a set of objects (10) operate in the mining environment (100), the method comprising: obtaining (201) from a set of sensors (20) in the mining environment (100), sensor data indicative of one or more measured objects (11) out of the set of objects (10), based on the sensor data, tracking (202) the set of objects (10), wherein tracking the set of objects (10) at least comprises estimating locations of the set of objects (10) in the mining environment (100), based on the tracked set of objects (10) and their respective locations, estimating (206) a probability of that at least one object out of the set of objects (10) are within the zone (90) and / or are entering the zone (90), and- when the estimated probability is above a threshold, triggering (207) a preventive action for securing the zone (90).

2. The method according to claim 1 , wherein the set of objects (10) comprises at least one unauthorized object not allowed in the zone (90), and wherein estimating (206) the probability of that the at least one object are within the zone (90) and / or are entering the zone (90) comprises estimating a probability of that the at least one unauthorized object out of the set of objects (10) are within the zone (90) and / or are entering the zone (90).

3. The method according to claim 2, wherein tracking (202) the set of objects (10) comprises identifying the at least one unauthorized object out of the set of objects (10).

4. The method according to any of the preceding claims, wherein triggering (207) the preventive action comprises any one or more out of:- triggering an alert,- triggering a machine (400) operating in the zone (90), to operate in a safe mode.- triggering a halt of the machine (400) operating in the zone (90),- triggering a halt of an operation performed by the machine (400) in the zone (90), and / or- triggering the machine (400) to one or more appropriate actions.

5. The method according to any of the preceding claims, estimating (206) the probability of that the at least one object are within the zone (90) and / or are entering the zone (90) is based on a location of the at least one object out of the set of objects (10) measured during a first point in time, and an elapsed time since the first point in time.

6. The method according to any of the preceding claims, wherein estimating (206) the probability of that the at least one object are within the zone (90) and / or are entering the zone (90) comprises estimating a probability of that one or more undetected objects are within the zone (90) and / or are entering the zone (90), wherein the one or more undetected objects are part of the set of objects (10) but not indicated by the sensor data.

7. The method according to claim 5 or 6, wherein estimating the probability of that one or more undetected objects are within the zone (90) and / or are entering the zone (90) comprises determining whether the sensor data indicates all objects out of the set of objects (10).

8. The method according to any of the preceding claims, wherein the method further comprises obtaining (203) characteristics of the set of objects (10), and wherein estimating (206) the probability of that the at least one object are within the zone (90) and / or are entering the zone (90) is further based on the characteristics set of objects (10).

9. The method according to claim 8 wherein obtaining the characteristics of the set of objects (10) comprises detecting at least one of the objects in the set of objects (10) by a tag reader (300) in the mining environment (100), the tag reader (300) being arranged for registering objects in the mining environment (100).

10. The method according to any of the preceding claims, wherein the method further comprises: establishing (205) one or more lost objects (500) out of the set of objects (10), wherein each object out of the one or more lost objects (500) have a respective certainty of their respective estimated location below a threshold, and wherein estimating (206) the probability of that the at least one object are within the zone (90) and / or are entering the zone (90) comprises estimating a probability of thatthe one or more lost objects (500) are within the zone (90) and / or are entering the zone (90).

11. The method according to claim 10, wherein estimating (206) the probability of that the one or more lost objects (500) are within the zone (90) and / or are entering the zone (90) comprises predicting one or more current locations of the one or more lost objects (500) based on a respective last measured location of the one or more lost objects (500), and estimating the probability of that the one or more lost objects (500) are within the zone (90) and / or are entering the zone (90) based on the predicted one or more current locations.

12. The method according to claim 10 or 11 , wherein estimating (206) the probability of that the one or more lost objects (500) are within the zone (90) and / or are entering the zone (90) comprises obtaining a time period since last measuring a location of at least one of the one or more lost objects (500), and estimating the probability of that the one or more lost objects (500) are within the zone (90) and / or are entering the zone (90) based on the obtained time period.

13. The method according to any of the preceding claims, wherein the set of sensors (20) comprises any one or more out of: one or more Light, detection, and ranging (Lidar) sensors, one or more Radio, detection, and ranging (Radar) sensors, one or more cameras, one or more tag readers, one or more machine sensors indicative of an operation of one or more machines in the mining environment (100), and / or indicative of one or more operators operating the one or more machines in the mining environment (100).

14. The method according to any of the preceding claims, wherein the method further comprises obtaining (204) an certainty of the obtained sensor data and / or obtaining an certainty of the estimated respective locations of the set of objects (10), and wherein estimating (206) the probability of that the at least one object are within the zone (90) and / or are entering the zone (90) is further based on the certainty of the obtained sensor data and / or the certainty of the estimated respective locations of the set of objects (10).

15. The method according to any of the preceding claims, wherein the set of objects (10) comprises operators in the mining environment (100).

16. A control unit (70) configured to manage a zone (90) in a mining environment (100), wherein a set of objects (10) is arranged to operate in the mining environment (100), the control unit (70) is further configured to: obtain from a set of sensors (20) in the mining environment (100), sensor data indicative of one or more measured objects (11) out of the set of objects (10), based on the sensor data, track the set of objects (10), by estimating locations of the set of objects (10) in the mining environment (100), based on the tracked set of objects (10) and their respective locations, estimate a probability of that at least one object out of the set of objects (10) are within the zone (90) and / or are entering the zone (90), and- when the estimated probability is above a threshold, trigger a preventive action for securing the zone (90).

17. The control unit (70) according to claim 16, wherein the set of objects (10) comprises at least one unauthorized object not allowed in the zone (90), and wherein the control unit (70) is configured to estimate the probability of that the at least one object are within the zone (90) and / or are entering the zone (90) by estimating a probability of that the at least one unauthorized object out of the set of objects (10) are within the zone (90) and / or are entering the zone (90).

18. The control unit (70) according to claim 17 configured to track the set of objects (10) by identifying the at least one unauthorized object out of the set of objects (10).

19. The control unit (70) according to any of claims 16-18 configured to trigger the preventive action comprises any one or more out of:- triggering an alert,- triggering a machine (400) operating in the zone (90), to operate in a safe mode.- triggering a halt of the machine (400) operating in the zone (90),- triggering a halt of an operation performed by the machine (400) in the zone (90), and / or- triggering the machine (400) to one or more appropriate actions.

20. The control unit (70) according to any of the claims 16-19 further configured to estimate the probability of that the at least one object are within the zone (90) and / or are entering the zone (90) based on a location of the at least one object out of the set of objects (10) measured during a first point in time, and based on an elapsed time since the first point in time.

21. The control unit (70) according to any of the claims 16-20, further configured to estimate the probability of that the at least one object are within the zone (90) and / or are entering the zone (90) by estimating a probability of that one or more undetected objects are within the zone (90) and / or are entering the zone (90), wherein the one or more undetected objects are adapted to be part of the set of objects (10) but not indicated by the sensor data.

22. The control unit (70) according to any of the claims 20-21 , further configured to estimate the probability of that one or more undetected objects are within the zone (90) and / or are entering the zone (90) by determining whether the sensor data indicates all objects out of the set of objects (10).

23. The control unit (70) according to any of the claims 16-22, wherein the control unit (70) further is configured to obtain characteristics of the set of objects (10), and configured to estimate the probability of that the at least one object are within the zone (90) and / or are entering the zone (90) based on the characteristics set of objects (10).

24. The control unit (70) according to claim 23 further configured to obtain the characteristics of the set of objects (10) by detecting at least one of the objects in the set of objects (10) by using a tag reader (300) in the mining environment (100), the tag reader (300) being arranged for registering objects in the mining environment (100).

25. The control unit (70) according to any of the claims 16-24, wherein the control unit (70) further is configured to: establish one or more lost objects (500) out of the set of objects (10), wherein each object out of the one or more lost objects (500) are adapted to have a respective certainty of their respective estimated location below a threshold, andwherein the control unit (70) is further configured to estimate the probability of that the at least one object are within the zone (90) and / or are entering the zone (90) by estimating a probability of that the one or more lost objects (500) are within the zone (90) and / or are entering the zone (90).

26. The control unit (70) according to claim 25, further configured to estimate the probability of that the one or more lost objects (500) are within the zone (90) and / or are entering the zone (90) by predicting one or more current locations of the one or more lost objects (500) based on a respective last measured location of the one or more lost objects (500), and wherein the control unit (70) is further configured to estimate the probability of that the one or more lost objects (500) are within the zone (90) and / or are entering the zone (90) based on the predicted one or more current locations.

27. The control unit (70) according to claim 25 or 26, further configured to estimate the probability of that the one or more lost objects (500) are within the zone (90) and / or are entering the zone (90) by obtaining a time period since last measuring a location of at least one of the one or more lost objects (500), and estimating the probability of that the one or more lost objects (500) are within the zone (90) and / or are entering the zone (90) based on the obtained time period.

28. The control unit (70) according to any of the claims 16-27, wherein the set of sensors (20) is adapted to comprise any one or more out of: one or more Light, detection, and ranging (Lidar) sensors, one or more Radio, detection, and ranging (Radar) sensors, one or more cameras, one or more tag readers, one or more machine sensors indicative of an operation of one or more machines in the mining environment (100), and / or indicative of one or more operators operating the one or more machines in the mining environment (100).

29. The control unit (70) according to any of the claims 16-28, wherein the control unit (70) further is configured to obtain an certainty of the obtained sensor data and / or obtain an certainty of the estimated respective locations of the set of objects (10), and wherein the control unit (70) is configured to estimate the probability of that the atleast one object are within the zone (90) and / or are entering the zone (90) further based on the certainty of the obtained sensor data and / or the certainty of the estimated respective locations of the set of objects (10).

30. The control unit (70) according to any of the claims 16-29, wherein the set of objects (10) comprises operators in the mining environment (100).

31. A mining machine (80) configured to perform the method according to any one of claims 1-15.

32. The mining machine (80) according to claim 31 wherein the mining machine (80) comprises the control unit (70) according to any one of claims 16-30.

33. A computer program (930) comprising instructions, which when executed by a processor (910), causes the processor to perform actions according to any of the claims 1-15.

34. A carrier (940) comprising the computer program of claim 33, wherein the carrier 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.

Images