Provision of a control signal relating to an elevator system

Abstract

According to an aspect, there is provided a solution in which a system is configured to obtain a fill level of an elevator car; obtain a first fill level threshold; obtain a second fill level threshold; compare the obtained fill level of the elevator car to at least one of the first threshold and the second threshold; and provide, based on the comparison, a control signal.

Description

[0001] PROVISION OF A CONTROL SIGNAL RELATING TO AN ELEVATOR SYSTEM TECHNICAL FIELD

[0002] Various example embodiments generally relate to the field of elevator systems . In particular, some example embodiments relate to a solution for providing a control signal relating to an elevator system.

[0003] BACKGROUND

[0004] An elevator car fill level indicating occupancy of the elevator car may be obtained, for example, by one or more sensors arranged inside the elevator car to sense obj ects in the elevator car . For example, a camera may be arranged in a ceiling of the elevator car to provide a wide angle view of the room inside the elevator car . The image provided by the camera may then be analyzed, for example, to provide information on the number of passengers in the elevator car, indicating the fill level .

[0005] The fill level is generally taken as an estimation, and one challenge of the image data provided by the sensor is that obj ects may be moving inside the elevator car during sensing, thus leading to fluctuations in the estimated fill level over time . These fluctuations may cause the elevator to unnecessarily skip allocated stops .

[0006] SUMMARY

[0007] The scope of protection sought for various example embodiments of the disclosure is set out by the independent claims . The example embodiments and features, if any, described in this specification that do not fall under the scope of the independent claims are to be interpreted as examples useful for understanding various example embodiments of the disclosure .According to a first aspect, there is provided a system comprising: at least one processor; and at least one memory storing instructions which, when executed by the at least one processor, cause the apparatus at least to : obtain a fill level of an elevator car; obtain a first fill level threshold; obtain a second fill level threshold; compare the obtained fill level of the elevator car to at least one of the first fill level threshold and the second fill level threshold; and provide, based on the comparison, a control signal .

[0008] In an implementation form of the first aspect, the first fill level threshold indicates a fill level where the elevator car is to skip an allocated stop, when the fill level of the elevator car is above the first fill level threshold; and the second fill level threshold indicates a fill level where the elevator car is to make the allocated stop, when if the fill level of the elevator car is below the second fill level threshold.

[0009] In an implementation form of the first aspect, the instructions, when executed by the at least one processor, may further cause the system at least to : determine a new value for the first fill level threshold and / or the second fill level threshold.

[0010] In an implementation form of the first aspect, the instructions, when executed by the at least one processor, further cause the system at least to : perform temporal filtering on the obtained fill level of the elevator car; and determine the control signal based at least in part on the temporally filtered fill level of the elevator car .

[0011] In an implementation form of the first aspect, the temporal filtering comprises moving average filtering.In an implementation form of the first aspect, the obtained fill level of the elevator car is based on sensor data received from one or more sensors arranged in the elevator car, and wherein the instructions when executed by the at least one processor, further cause the system at least to convert the sensor data to at least one specific data format .

[0012] In an implementation form of the first aspect, the instructions, when executed by the at least one processor, may further cause the system at least to : obtain reference sensor data from one or more sensors arranged in the elevator car, wherein the reference sensor data is associated with an empty elevator car; identify a floor plane of the empty elevator car based on the at least one reference sensor data; determining an area of the floor plane; receive sensor data from the one or more sensors arranged in the elevator car, wherein the sensor data is associated with a non-empty elevator car; perform item clustering of at least one object in the elevator car based on the sensor data and the identified floor plane; estimate a surface area of the at least one obj ect based on the performed item clustering; and obtain the fill level of the elevator car based on the estimated surface area of the at least one obj ect and the area of the floor plane .

[0013] In an implementation form of the first aspect, the instructions, when executed by the at least one processor, further cause the system at least to apply height filtering to remove the floor before performing the item clustering of the at least one obj ect .

[0014] In an implementation form of the first aspect, the control signal is indicative of whether to skip or make the allocated stop .According to a second aspect, there is provided an elevator system comprising: a system according to the first aspect; and at least one sensor arranged in an elevator car, the at least one sensor being configured to provide sensor data to the system.

[0015] According to a third aspect, there is provided a computer-implemented method comprising: obtaining a fill level of an elevator car; obtaining a first fill level threshold; obtaining a second fill level threshold; comparing the obtained fill level of the elevator car to at least one of the first fill level threshold and the second fill level threshold; and providing, based on the comparison, a control signal .

[0016] In an implementation form of the first third, the first threshold indicates a fill level where the elevator car is to skip an allocated stop, when the fill level of the elevator car is above the first threshold; and the second threshold indicates a fill level where the elevator car is to make the allocated stop, when if the fill level of the elevator car is below the second threshold .

[0017] In an implementation form of the third aspect, the method further comprises determining a new value for the first fill level threshold and / or the second fill level threshold .

[0018] In an implementation form of the third aspect, the method further comprises performing temporal filtering on the obtained fill level of the elevator car; and determining the control signal based at least in part on the temporally filtered fill level of the elevator car .In an implementation form of the third aspect, the temporal filtering comprises moving average filtering.

[0019] In an implementation form of the third aspect, the obtained fill level of the elevator car is based on sensor data received from one or more sensors arranged in the elevator car, and the method further comprises converting the sensor data to at least one specific data format .

[0020] In an implementation form of the third aspect, the method further comprises obtaining reference sensor data from one or more sensors arranged in the elevator car, wherein the reference sensor data is associated with an empty elevator car; identifying a floor plane of the empty elevator car based on the at least one reference sensor data; determining an area of the floor plane; receiving sensor data from the one or more sensors arranged in the elevator car, wherein the sensor data is associated with a non-empty elevator car; performing item clustering of at least one obj ect in the elevator car based on the sensor data and the identified floor plane; estimating a surface area of the at least one obj ect based on the performed item clustering; and obtaining the fill level of the elevator car based on the estimated surface area of the at least one obj ect and the area of the floor plane .

[0021] In an implementation form of the third aspect, the method further comprises applying height filtering to remove the floor before performing the item clustering of the at least one obj ect .

[0022] In an implementation form of the third aspect, the control signal is indicative of whether to skip or make the allocated stop .According to a fourth aspect, there is provided a computer program comprising instructions which, when the program is executed by at least one processor, cause a system to perform the method according to the third aspect .

[0023] According to a fifth aspect, there is provided a computer-readable medium comprising a computer program comprising instructions which, when the program is executed by at least one processor, cause a system to perform the method according to the third aspect .

[0024] According to a sixth aspect, there is provided a system comprising means for : obtaining a fill level of an elevator car; obtain a first threshold indicating a fill level where the elevator car is to skip an allocated stop, if the fill level of the elevator car is above the first threshold; obtaining a second threshold indicating a fill level where the elevator car is to make the allocated stop, if the fill level of the elevator car is below the second threshold; comparing the obtained fill level of the elevator car to at least one of the first threshold and the second threshold; and providing, based on the comparison, a control signal .

[0025] BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings, which are included to provide a further understanding of the invention and constitute a part of this specification, illustrate embodiments of the invention and together with the description help to explain the principles of the invention. In the drawings :

[0027] FIG. 1 illustrates an elevator system according to an example embodiment .FIG. 2 illustrates a diagram according to an example embodiment .

[0028] FIG. 3 illustrates a system according to an example embodiment .

[0029] FIG. 4 illustrates a diagram according to an example embodiment .

[0030] FIG. 5A illustrates an image provided by a sensor arranged in an elevator car according to an example embodiment .

[0031] FIG. 5B illustrates an image of an identified floor plane of an empty elevator car according to an example embodiment .

[0032] FIG. 50 illustrates an image of an obj ect cluster according to an example embodiment .

[0033] FIG. 6 illustrates a flow diagram according to an example embodiment .

[0034] FIG. 7 illustrates a flow diagram of a method according to an example embodiment .

[0035] DETAILED DESCRIPTION

[0036] Various examples and embodiments discussed below illustrate a solution in which a system, such as a computing apparatus, arranged in an elevator car, obtains a fill level of the elevator car . The system may further obtain high and low threshold fill level values indicating a fill level, which can be used to determine whether to make or skip an allocated stop . In some example embodiments, the system may obtain the fill level of the elevator car by receiving sensor data relating to both real obj ects sensed by at least onesensor associated with the elevator car . In some example embodiments, the precision of determining to make or skip the allocated stop is increased by temporally filtering the obtained fill level of the elevator, such as a moving average filter . Further, some example embodiments may provide a solution in which the system receives reference sensor data of the elevator car associated with a state, where the elevator car is empty. The reference sensor data can be used to obtain the fill level of the elevator car by removing an identified floor plane of the elevator car from an obj ect cluster when obtaining the fill level, for example .

[0037] Allocated stops of an elevator car may be understood as 'unnecessary' , when the elevator car cannot accommodate any more people and / or obj ects . Skipping such an unnecessary stop may reduce both journey and waiting times . Further, wear and tear on the hardware installed on an elevator shaft configured to accommodate movements (acceleration, deceleration) of the elevator car may be reduced, as skipping an unnecessary stop reduces strain on the hardware involved in controlling said movements .

[0038] FIG. 1 illustrates an elevator system according to an example embodiment . At least one sensor 104A, 104B may be arranged inside an elevator car 100 to sense an interior of the elevator car 100. The at least one sensor 104A, 104B may comprise, for example, at least one of a camera, a time of flight (ToF) camera, a lidar, a radar, a thermal camera, an elevator scale, a drive torque sensor, a passive infrared sensor, a proximity sensor, an ultrasound sensor, a pressure sensor, a curtain of light sensor, a receiver or a transceiver to count people ( for example, implementing Bluetooth, Wi-Fi or Radio Frequency Identification (RFID) etc . Using various known techniques, it is possible to determine a filllevel of the elevator car 100 based on data provided by the at least one sensor 104A, 104B .

[0039] The sensor 104A, 104B may provide two-dimensional data or three-dimensional data about the interior of the elevator car 100. The at least one sensor 104A, 104B may be communicatively connected to a system 102. The connection between the system 102 and the at least one sensor 104A, 104B may be wired or wireless . The system 102 may be aware of the internal dimensions of the elevator car 100. The system 102 may comprise example embodiments described herein, or be used to, for example, perform a method according to an example embodiment described herein and discussed more in detail in reference to FIG. 6 and FIG. 7. In an example embodiment, the system 102 may be an internal entity of the elevator system. In another example embodiment, the system 102 may be a cloud-based entity, for example, a network server .

[0040] FIG. 2 illustrates a diagram according to an example embodiment . A fill level of the elevator car 100 is illustrated as percentage values in an x-axis of the diagram. It will be noted that the fill level may be embodied in a multitude of ways, such as an integer or a floating point, for example . The y-axis may represent a state of the elevator car, whether an allocated stop is to be made or skipped. The state may be a binary value ( 0 or 1 ) , a percentage value, a floating point value or an integer value, for example .

[0041] In the example of FIG. 2 relating to FIG. 1, it may be assumed that the elevator car 100 is moving from one floor to another, and one or more allocated stops are called from different floors of a building the elevator car 100 is configured in. The system 102 may obtain fill levels 202A, 202B, 202C and 202D of the elevator car 100at, for example, different times during operation of the elevator car 100. The fill level may be determined based on data from at least one sensor, for example, from at least one of a camera, a time of flight (ToF) camera, a lidar, a radar, a thermal camera, an elevator scale, a drive torque sensor, a passive infrared sensor, a proximity sensor, an ultrasound sensor, a pressure sensor, a curtain of light sensor, a receiver or a transceiver to count people ( for example, implementing Bluetooth, Wi-Fi or Radio Frequency Identification (RFID) ) etc . The fill levels 202A-202D may comprise a plurality of fill levels obtained over specific time intervals, for example . Further, in the example of FIG.

[0042] 2, a threshold 204 is set at 60% fill level of the elevator car 100, wherein the threshold 204 indicates a fill level where the elevator car 100 is to skip an allocated stop, such as a next allocated stop from the one or more allocated stops when moving from one floor to another (when the fill level is above the threshold 204 ) . The indicated threshold 204 set at 60% is just one example of possible threshold values and other threshold values can also be used.

[0043] In the example of FIG. 2, the fill level 202A may be obtained, for example, after a first group of people enter the elevator car 100 and make an elevator call from a first floor of the building to a fourth floor of the building. Between the first floor and the fourth floor, an allocated stop is to be made at the second floor . As the obtained fill level 202A is below the threshold 204, it indicates that there is enough room in the elevator car 100 and that a stop at the second floor should be made to accommodate more people .

[0044] The fill level 202B may be obtained after a second group of people enter the elevator car 100 and as an example, an allocated stop is made at a third floor of thebuilding. Now, as the fill level 202B is above the threshold 204, it would indicate that there is not enough room in the elevator car 100 to accommodate more people, and the allocated stop at the third floor is skipped, and the elevator car 100 travels directly to the fourth floor .

[0045] Fill levels may not be accurate, and inaccuracies to an estimation of a fill level can occur due to, for example, movement of people in the elevator car 100 or reflections from obj ects and surfaces inside the elevator car 100. As one example, the fill level 202C illustrates a situation, wherein after the fill level 202B has been observed, but due to inaccuracies such as movement of people inside the elevator car 100, the fill level 202B estimation of an occupancy of the elevator car 100 is in fact too high in relation to the threshold 204, and the fill level 202C represents more accurately the occupancy, and therefore the decision to skip the allocated stop at the third floor was not necessary and more people could have been accommodated.

[0046] Furthermore, it may be that the fill level 202B estimation is too low. For example, the field of view of the sensor 104A, 104B cannot capture all obj ects in the elevator car 100. Small obj ects and people ( for example, children) can be behind larger obj ects etc . Therefore, the fill level 202D might more accurately represent the occupancy of the elevator car 100, indicating there is no more accommodation space in the elevator car 100.

[0047] In an example embodiment, each of the fill levels 202A, 202B, 202C and 202D may have been calculated based on a plurality of fill levels / occupancy levels, depending on the configuration of the elevator system ( for example, sensor type, the system 102 processing configurationetc . ) . For example, the fill level 202A may have been calculated based on 10 obtained occupancy levels between a time interval of 0-5 seconds, the fill level 202B may have been calculated based on 10 obtained occupancy levels between a time interval of 20-25 seconds, the fill level 202C may have been calculated based on 10 obtained occupancy levels between a time interval of 35-40 seconds and the fill level 202D may have been calculated based on 10 obtained occupancy levels between a time intervals of 60-65 seconds .

[0048] According to an example embodiment, a first fill level threshold 206 and a second fill level threshold 208 may be applied for the fill levels . The first threshold 206 may comprise a 'high fill level threshold' and the second threshold 208 may comprise a 'low fill level threshold' . The first fill level threshold 206 and the second fill level threshold 208 may be obtained independently without the threshold 204. Alternatively or additionally, in some example embodiments, the first fill level threshold 206 and the second fill level threshold 208 may be referenced to the threshold 204. In other words, the first fill level threshold 206 can be, for example, 10-20% above the threshold 204 and the second fill level threshold 208 can be, for example, 10-20% below the threshold 204. The first fill level threshold 206 and the second fill level threshold 208 may be obtained, for example, by configuration or calibration as fixed, predetermined values .

[0049] FIG. 3 illustrates an example embodiment of the system 102, wherein the system 102 may comprise at least one processor 302 and at least one memory 304. The first fill level threshold 206 and the second fill level threshold 208 may comprise, for example, static or dynamic variables embodied as a part of a program code308 comprised in the at least one memory 304. In some embodiments, the first fill level threshold 206 and the second fill level threshold 208 may be stored in an external database (not shown in drawings) that comprises, for example, information on a plurality of elevators such as their control and / or calibration information .

[0050] In some embodiments, the first fill level threshold 206 and the second fill level threshold 208 can be updated. For example, when the system 102 obtains one or more fill levels, a statistical distribution of the obtained fill levels can be used to determine updated values for the first fill level threshold 206 and the fill level second threshold 208. In other words, the first fill level threshold 206 and the second fill level threshold 208 may comprise dynamic values, for example, based on sensor data, probability function statistics, waiting times etc . Temporal filtering, such as moving average, can also be used for determining the first fill level threshold 206 and the second fill level threshold 208 . In some other embodiments, instead of moving averaging to achieve temporal filtering, any of the following techniques may be used:

[0051] - Simple moving average : Averages the fill levels over a fixed number of past observations .

[0052] - Weighted moving average : Sums the fill levels with different weights assigned to each observation, giving more importance to recent data .

[0053] - A moving average with a context-specific window that adjusts the window size based on the specific context or conditions of the data being analyzed.

[0054] - Any other weighted integration method in general .In various embodiments, the first fill level threshold 206 and the second fill level threshold 208 may comprise values based on digital twin type simulations . In other words, a digital twin of the elevator car 100 can be used to simulate real-world scenarios with, for example, multiple different types of 3D models inside the digital twin, and how the first fill level threshold 206 and the second fill level threshold 208 should behave in these different situations . This data can be used for predetermining the initial values, for example .

[0055] In some embodiments, the first fill level threshold 206 and the second fill level threshold 208 may comprise values based on machine-learning models . For example, data on elevator rides in a building can be used to initialize and re-configure the first fill level threshold 206 and the second fill level threshold 208 for an elevator car that will be installed on the building. As another example, a machine-learning model, such as a neural network, using the obtained fill level as an input may be used to determine to yield, as an output, the first fill level threshold 206 and the second fill level threshold 208 during operation of the elevator car 100. The machine-learning model may use other available parameters as an input, such as the weight of the elevator car 100 and / or time of day, for example .

[0056] In some embodiments, values of the first fill level threshold 206 and the second fill level threshold 208 may be determined manually. Initial or new values of the first fill level threshold 206 and the second fill level threshold 208 can be overridden in, for example, emergency situations .In some embodiments, the first fill level threshold 206 and the second fill level threshold 208 can have two or more pre-defined values (i . e . , a pool of values) from which the (new) values of the first fill level threshold 206 and the second fill level threshold 208 can be chosen. As an example, the first fill level threshold 206 can have a pool of values as follows : 50%, 75%, 90% and the second fill level threshold 208 can have a pool of values as follows : 50% 35% 10% . Now depending on, for example, some parameter such as time-time-day and / or expected occupancy, the first fill level threshold 206 can change from 90% (very busy time / high expected occupancy) to 50% (low expected occupancy) .

[0057] In some embodiments, alternatively or additionally to the above example, one or more values of the first fill level threshold 206 and the second fill level threshold 208 can be associated with one or more parameters . For example, observed weight of the elevator plus the obtained fill level of the elevator can move the first fill level threshold value 206 from 60% to 75% etc .

[0058] The system 102 may further comprise at least one communication interface 306, as illustrated in FIG. 3. The at least one communication interface 306 may handle input / output of data between devices . For example, the at least one communication interface 306 may receive sensor data from the sensor 104A, 104B . The received sensor data, as described above, can be used to obtain the fill level of the elevator car 100. A more detailed example embodiment regarding obtaining the fill level is given however, in some embodiments, the fill level may be determined by a different device acting as an intermediate between the sensor 104A, 104B, and provide the fill level to the system 102 via, for example, the at least one communication interface 306. The at least one communication interface 306 may further provide acontrol signal to the elevator controller . The control signal may indicate, for example, whether the elevator car 100 is to make or skip the allocated stop . Consequently, if the system 102 is embodied as an elevator controller, the system 102 may directly control the elevator car 100, thus the control signal is directly provided to elevator car 100 as a command, via, for example, the communication interface 306. In other example embodiments, the control signal may relate to any other control signal that can be used to control an elevator car . For example, the control signal may control speed and / or acceleration of the elevator car, door opening times etc .

[0059] One or more of the at least one communication interface 306 may be for wired and / or wireless communication. Although the system 102 is depicted to include only one processor 302, the system 102 may include more than one processor . In an example embodiment, the memory 304 is capable of storing instructions, such as an operating system and / or various applications .

[0060] Further, the first fill level threshold 206 and the second fill level threshold 208 may also comprise a (dynamically adjustable) hysteresis, as in a sense, the first fill level threshold 206 and the second fill level threshold 208 can introduce a desired non-linearity (i . e . , lag with respect to the threshold 204 ) when determining if the elevator car 100 should skip or make an allocated stop . The area between the first fill level threshold 206 and the second fill level threshold 208 may be referred to as, for example, a 'window' , 'a threshold window' or 'a hysteresis window' .

[0061] FIG. 4 illustrates an example diagram 400. In the example of FIG. 4, the elevator car 100 may be configured, at first, to make an allocated stop (e . g. ,a next allocated stop) , for example, as an initial state . A fill level 402A is obtained, indicating that there is no reason to skip the allocated stop as it is between the first fill level threshold 206 and the second fill level threshold 208 (i . e . , inside the window) and the (initial) state of the elevator car 100 regarding to make or skip the allocated stop does not change . When a fill level 402B is obtained, the (initial) state of the elevator car 100 regarding to make or skip the allocated stop is not changed either, even if it is above the threshold 204. It will be noted that the threshold 204 is not a requirement for implementing embodiments described herein, but is only given as an example, where the first fill level threshold 206 and the second fill level threshold 208 can be referenced to .

[0062] When a fill level 402C is obtained, it indicates that the state of the elevator car 100 regarding to make or skip the allocated stop should change, and the allocated stop should be skipped, because the fill level 402C is observed to be above the first fill level threshold 206.

[0063] Consequently, when a fill level 402D is obtained, after obtaining the fill level 402C, the state of the elevator car 100 regarding to make or skip the allocated stop does not change either, when the latest state was that the elevator car 100 should skip the allocated stop . Only after a fill level 402E is obtained, the state of the elevator car 100 regarding to make or skip the allocated stop should change, and the allocated stop should be made, as it is observed to be below the second fill level threshold 208.

[0064] The state of the elevator car 100 to make or skip the allocated stop may comprise, for example, a dynamic variable such as a Boolean and it may be comprised in,for example, the at least one memory 304. Alternatively, the elevator controller (not shown in FIG. 1 ) may store information relating to the state . The elevator controller may provide the state to the system 102 via, for example, the communication interface 306. The state of the elevator car 100 to make or skip the allocated stop may be changed by, for example, when the system 102 provides an output signal ( for example, a control signal) that indicates which state the elevator car 100 should be . Alternatively, the system 102 may comprise the elevator controller as described above .

[0065] Referring to FIG. 4, the fill levels 402A-E are illustrated, as an example, as a set of fill levels . In an example embodiment, the system 102 may further process the obtained fill levels 402A-E, for example, by temporally filtering a plurality of obtained fill levels . One example of a temporal filter that can be used is a moving average . The temporal filtering may decrease any large deviations and inaccuracies in a fill level . For example, during a time interval of 0-5 seconds, 10 fill levels may be obtained, with 8 having a similar fill level percentage value and two deviating heavily due to, for example, movements in the elevator car 100 during sensing. Therefore, using the temporal filtering ( for example, the moving average) on the 10 obtained fill levels during the 0-5 second interval may increase the accuracy of the obtained fill level ( for example, fill levels 402A-E) which may be used to inspect if it exceeds the first fill level threshold 206 or is below the second fill level threshold 208, for example .

[0066] In an example embodiment, the obtained fill level ( for example, 202A-D, 402A-E) of the elevator car 100 is based on sensor data received from the one or more sensors 104A, 104B arranged in the elevator car 100, andwherein the instructions when executed by the at least one processor 302 , may further cause the system 102 at least to convert the sensor data to a new format . For example, the data from sensor 104A, 104B can be converted into a 'ply' or 'ped' format, which are supported by multiple 3d processing libraries such as Open3d, using a conversion pipeline which is sensor specific .

[0067] As described above, the system 102 may obtain the fill levels based on the sensor data . In an example embodiment, the system 102 may perform a calibration before observing fill levels of the elevator car 100. The calibration may involve obtaining at least one reference frame from the one or more sensors 104A, 104B, wherein the reference frame is associated with an empty elevator car 100 (i . e . , no passengers and / or obj ects in the elevator car) . FIG. 5A illustrates an example embodiment of a reference frame 500.

[0068] A floor plane may be identified based on the reference frame . FIG. 5B illustrates an example, representation of an identified floor plane 510. The floor plane can be identified using plane estimation or a manual calibration step, for example, which involves measuring a length and a width of the elevator car 100. If a calibration fails due to excessive noise in the data, manual calibration can be used. Identifying the floor plane may comprise estimating an area of the floor plane, which can be computed by estimating it as a volume of an enclosing convex hull .

[0069] The calibration may be performed only once . Then, the system 102 may begin receiving sensor data from the one or more sensors 104A, 104B, wherein the sensor data is associated with a non-empty state of the elevator car .Then, the system 102 may perform item clustering of at least one obj ect based on the sensor data and based on the identified floor plane . The item clustering may involve setting the height of elevator car 100 to filter the identified floor plane . The system 102 may then further estimate a surface area of the at least one obj ect based on the performed item clustering and obtain at least one fill level based at least partially on the estimated surface area of the at least one obj ect . FIG.

[0070] 5C illustrates and example embodiment of an identified obj ect cluster 520, isolated from a point cloud received from, for example, the sensor 104A, 104B .

[0071] FIG. 6 illustrates a flow diagram according to an example embodiment, comprising steps that, for example, the system 102 may perform when obtaining the fill level of the elevator car 100. One or more of steps 600 to 616 may be performed by, for example, the system 102 or a computing device external to the system 102 which provides the fill level to the system 102.

[0072] At 600, input data for item clustering is received. The input data may comprise, for example, the sensor data received from the one or more sensors 104A, 104B . The input data may also comprise the reference frame for calibration. The one or more sensors 104A, 104B may comprise some pre-processing capabilities such as filtering and artefact removal, before providing the input data to the system 102.

[0073] At 602, the input data may be converted to a generally used format such as 'ply' .

[0074] At 604, point cloud processing may be performed on the (converted) input data .At 606, point cloud segmentation into distinct clusters may be performed. For example, a PCL (Point Cloud Library) may be used.

[0075] Step 608 illustrates a first example step of a calibration pipeline, where surface areas of clusters are isolated.

[0076] Step 610 illustrates a second example step of the calibration pipeline, where a surface area of the floor plane ( for example, FIG. 5B) is estimated. 'TFSA' abbreviates from 'Total Floor Surface Area' .

[0077] Step 612 illustrates a first example step of an item clustering pipeline, wherein obj ects from the clusters are isolated. This step may, for example, yield 'n' number of isolated obj ect clusters . Clustering can be performed by using a 'DBSCAN' algorithm, for example, to obtain an identifiable structure of each obj ect inside the elevator car 100, as illustrated in FIG. 5C .

[0078] Step 614 illustrates a second example step of the item clustering pipeline, where a surface area of the isolated obj ects is estimated. 'TOSA' abbreviates from 'Total Obj ect Surface Area' . The surface area can be computed by applying a convex hull for each obj ect in the obj ect cluster .

[0079] At 616, a fill level can be calculated, for example, by dividing TOSA with TFSA and converting the outcome to a percentage value . Further, a moving average or other suitable temporal filtering may be applied to the fill level to smooth out spikes and outliers caused by obj ects moving inside the elevator car 100 during sensing .After obtaining the fill level, the fill level can be compared to at least one of the first fill level threshold 206 or the second fill level threshold 208.

[0080] Additionally, whenever at least one of the first fill level threshold 206 and the second fill level threshold 208 is crossed (i . e . , above the first fill level threshold 206 or below the second fill level threshold 208 ) , an event can be logged in a, for example, text log with a timestamp, and at least one original frame may be stored for diagnostic and troubleshooting purposes .

[0081] FIG. 7 illustrates a method 700 according to an example embodiment . The method 700 may be performed by a device comprising one or more processors and one or more memories, such as the system 102. An example embodiment of a computer-readable medium may store a computer program comprising instructions which, when the computer program is executed by at least one processor, may cause an apparatus to perform the method 700. The computer-readable medium may comprise, for example, a laser disk, a CD, a flash drive, a solid-state drive or the like .

[0082] At 702, the method 700 may comprise obtaining a fill level of an elevator car . The fill level of the elevator car, as described above, may comprise a plurality of fill levels . The fill levels may be obtained as described in reference to, for example, FIG. 6.

[0083] At 704, the method 700 may comprise obtaining a first fill level threshold ( for example, the first fill level threshold 206) . It may indicate a fill level, where the elevator car is to skip an allocated stop, if the obtained fill level of the elevator car is above the first fill level threshold.At 706, the method 700 may comprise obtaining a second fill level threshold ( for example, the second fill level threshold 208 ) . It may indicate a fill level, where the elevator car is to make the allocated stop, if the obtained fill level of the elevator car is below the second fill level threshold.

[0084] At 708, the method 700 may comprise comparing the obtained fill level of the elevator car to at least one of the first fill level threshold and the second fill level threshold.

[0085] At 710, the method may comprise providing a control signal based on the comparison. The control signal may indicate, for example, whether the elevator car is to make or skip the allocated stop .

[0086] The processor 302 may be capable of executing the stored instructions . In an example embodiment, the processor 302 may be embodied as a multi-core processor, a single core processor, or a combination of one or more multicore processors and one or more single core processors . For example, the processor 302 may be embodied as one or more of various processing devices, such as a coprocessor, a microprocessor, a controller, a digital signal processor (DSP) , a processing circuitry with or without an accompanying DSP, or various other processing devices including integrated circuits such as, for example, an application specific integrated circuit (ASIC) , a field programmable gate array (FPGA) , a microcontroller unit (MCU) , a hardware accelerator, a special-purpose computer chip, or the like . In an example embodiment, the processor 302 may be configured to execute hard-coded functionality. In an example embodiment, the processor 302 is embodied as an executor of software instructions, wherein the instructions may specifically configure the processor 302 to perform thealgorithms and / or operations described herein when the instructions are executed, for example, the steps discussed relating to FIG. 7.

[0087] The memory 304 may be embodied as one or more volatile memory devices, one or more non-volatile memory devices, and / or a combination of one or more volatile memory devices and non-volatile memory devices . For example, the memory 304 may be embodied as semiconductor memories (such as mask ROM, PROM (programmable ROM) , EPROM (erasable PROM) , flash ROM, RAM (random access memory) , etc . ) .

[0088] In an embodiment, the at least one memory 304 may store program instructions 308 that, when executed by the at least one processor 302, may cause the system 102 to perform the functionality of the various embodiments discussed herein. Further, in an embodiment, at least one of the processor 302 and the memory 304 may constitute means for implementing the discussed functionality .

[0089] At least one of the examples and embodiments disclosed above may enable a solution in which two threshold values (i . e . , the first fill level threshold 206 and the second fill level threshold 208) can be used to determine if an elevator car is to make or skip an allocated stop . The two threshold values may constitute a 'window' or more specifically a 'hysteresis window' that introduces non-linearity to an initial threshold value used for determining whether to make or skip the allocated stop . This may be beneficial for the accuracy of estimating whether the elevator car can accommodate more people and / or obj ects, as movements during the elevator travel can cause inaccuracies to observed fill levels . Consequently, skipping an unnecessary allocatedstop may reduce carbon footprint and strain on elevator hardware .

[0090] Example embodiments may be implemented in software, hardware, application logic or a combination of software, hardware and application logic . The example embodiments can store information relating to various methods described herein. This information can be stored in one or more memories, such as a hard disk, a solid state drive (SSD) , an optical disk, a magneto-optical disk, an RAM, and the like . One or more databases can store the information used to implement the example embodiments . The databases can be organized using data structures (e . g. , records, tables, arrays, fields, graphs, trees, lists, and the like) included in one or more memories or storage devices listed herein. The methods described with respect to the example embodiments can include appropriate data structures for storing data collected and / or generated by the methods of the devices and subsystems of the example embodiments in one or more databases .

[0091] The components of the example embodiments may include computer readable medium or memories for holding instructions programmed according to the teachings and for holding data structures, tables, records, and / or other data described herein. In an example embodiment, the application logic, software or an instruction set is maintained on any one of various conventional computer-readable media . In the context of this document, a "computer-readable medium" may be any media or means that can contain, store, communicate, propagate or transport the instructions for use by or in connection with an instruction execution system, apparatus, or device, such as a computer . A computer-readable medium may include a computer-readable storage medium that may be any media or means that can containor store the instructions for use by or in connection with an instruction execution system, apparatus, or device, such as a computer . A computer readable medium can include any suitable medium that participates in providing instructions to a processor for execution. Such a medium can take many forms, including but not limited to, non-volatile media, volatile media, transmission media, and the like .

[0092] While there have been shown and described and pointed out fundamental novel features as applied to preferred embodiments thereof, it will be understood that various omissions and substitutions and changes in the form and details of the devices and methods described may be made by those skilled in the art without departing from the spirit of the disclosure . For example, it is expressly intended that all combinations of those elements and / or method steps which perform substantially the same function in substantially the same way to achieve the same results are within the scope of the disclosure . Moreover, it should be recognized that structures and / or elements and / or method steps shown and / or described in connection with any disclosed form or embodiments may be incorporated in any other disclosed or described or suggested form or embodiment as a general matter of design choice . Furthermore, in the claims means-plus-function clauses are intended to cover the structures described herein as performing the recited function and not only structural equivalents, but also equivalent structures .

[0093] The applicant hereby discloses in isolation each individual feature described herein and any combination of two or more such features, to the extent that such features or combinations are capable of being carried out based on the present specification as a whole, in the light of the common general knowledge of a personskilled in the art, irrespective of whether such features or combinations of features solve any problems disclosed herein, and without limitation to the scope of the claims . The applicant indicates that the disclosed aspects / embodiments may consist of any such individual feature or combination of features . In view of the foregoing description it will be evident to a person skilled in the art that various modifications may be made within the scope of the disclosure .

Claims

CLAIMS1. A computer-implemented method (700) , comprising :obtaining a fill level (202A-D, 402A-E) of an elevator car ( 100) ;obtaining a first fill level threshold (206) ; obtaining a second fill level threshold (208 ) ; comparing the obtained fill level of the elevator car to at least one of the first fill level threshold and the second fill level threshold; and providing, based on the comparison, a control signal .

2. The computer-implemented method according to claim 1, wherein:the first fill level threshold (206) indicates a fill level where the elevator car is to skip an allocated stop, when the fill level of the elevator car is above the first fill level threshold; andthe second fill level threshold (208 ) indicates a fill level where the elevator car is to make the allocated stop, when if the fill level of the elevator car is below the second fill level threshold.

3. The computer-implemented method according to claim 1 or 2, further comprising:determining a new value for the first fill level threshold (206) and / or the second fill level threshold (208 ) .

4. The computer-implemented method according to any one of claims 1 - 3, further comprising:performing temporal filtering on the obtained fill level (202A-D, 402A-E) of the elevator car ( 100) ; anddetermining the control signal based at least in part on the temporally filtered fill level of the elevator car .

5. The computer-implemented method according to claim 4, wherein the temporal filtering comprises moving average filtering.

6. The computer-implemented method according to any one of claims 1 - 5, wherein the obtained fill level ( 202A-D, 402A-E ) of the elevator car ( 100) is based on sensor data received from one or more sensors ( 104A, 104B) arranged in the elevator car, and method further comprises converting the sensor data to at least one specific data format .

7. The computer-implemented method according to any one of claims 1 - 6, further comprising:obtaining reference sensor data from one or more sensors arranged in the elevator car ( 100) , wherein the reference sensor data is associated with an empty elevator car;identifying a floor plane of the empty elevator car based on the at least one reference sensor data;determining an area of the floor plane; receiving sensor data from the one or more sensors arranged in the elevator car, wherein the sensor data is associated with a non-empty elevator car;performing item clustering of at least one object in the elevator car based on the sensor data and the identified floor plane;estimating a surface area of the at least one obj ect based on the performed item clustering; and obtaining the fill level of the elevator car based on the estimated surface area of the at least one obj ect and the area of the floor plane .

8. The computer-implemented method according to claim 7, further comprising applying height filtering to remove the floor before performing the item clustering of the at least one obj ect .

9. The computer-implemented method according to any one of claims 1 - 8, wherein the control signal is indicative of whether to skip or make the allocated stop .

10. A system ( 102 ) , comprising:at least one processor (302 ) ; andat least one memory (304 ) storing instructions which, when executed by the at least one processor, cause the apparatus at least to perform the method of any one of claims 1 - 9.

11. An elevator system comprising:a system ( 102 ) according to claim 10; and at least one sensor ( 104A, 104B) arranged in an elevator car ( 102 ) , the at least one sensor being configured to provide sensor data to the system.

12. A computer program comprising instructions which, when the program is executed by at least one processor, cause a system to perform the method of any one of claims 1 - 9.

13. A computer-readable medium comprising a computer program comprising instructions which, when the program is executed by at least one processor, cause a system to perform the method of any one of claims 1 - 9.

Images