Method for determining trajectory of mobile device

Abstract

The invention relates to a method for determining a trajectory of a mobile device along which the mobile device is to be moved within a working area, comprising: providing object information about one or more selected objects selected from a plurality of objects within and / or outside the working area, the object information is used to determine an orientation of a selected object, at least one object of a plurality of selected objects or at least a plurality of objects of a plurality of selected objects on the basis of the object information, and to determine the trajectory, an orientation being specified for each of one or a plurality of trajectory sections of the trajectory, the orientation depends on the orientation of one selected object, at least one object of the plurality of selected objects or at least a plurality of objects of the plurality of selected objects according to at least one orientation criterion, and providing the trajectory for use by a control or regulation unit of the mobile device, in particular for manipulating the mobile device along a provided trajectory.

Description

Technical Field

[0001] The invention relates to a method for determining the trajectory of a mobile device, in particular an at least partially automatically moving vehicle and / or a robot, preferably a mowing robot, as well as a system for data processing, a mobile device and a computer program for carrying out the method. Background Art

[0002] Mobile devices, such as robots or at least partially automatically moving vehicles, typically move along a trajectory or movement path in an environment such as a home, in a garden or on the street, in the air or in water. For this purpose, the trajectory is planned or determined, for example, so that it is as short as possible when a specific destination is to be reached or a specific area is to be covered. Summary of the invention

[0003] According to the invention, a method for determining the trajectory of a mobile device is proposed, as well as a system for data processing, a mobile device and a computer program for carrying out the method, having the features of the independent claims. Preferred embodiments are the subject of the dependent claims and the subsequent description.

[0004] The invention generally relates to a mobile device that moves or is to move along a determined trajectory in a working area (which may be part of an environment) and in particular to determining (or planning) such a trajectory. Such a trajectory may also include a path or a movement path. In this context, we may also speak of trajectory planning or path planning or so-called "motion planning".

[0005] Examples of such mobile devices (or mobile working devices) are, for example, robots and / or drones and / or vehicles that move partially or (fully) automatically (on land, water or air). Robots include, for example, household robots, such as vacuuming and / or mopping robots, floor or street cleaning devices or lawn mowing robots, as well as other so-called service robots, vehicles that move at least partially automatically, such as passenger vehicles or freight vehicles (also so-called ground transport vehicles, for example in warehouses), and aircraft or watercraft such as so-called drones.

[0006] Such a mobile device has in particular a control and / or regulating unit and a drive unit for moving the mobile device so that it can be moved along a trajectory. The mobile device can also have one or more sensors, by means of which the environment or information in the environment and in this case in particular within and / or outside the working area can be detected.

[0007] The invention will be explained below in particular using a lawnmower robot as an example of a mobile device, but the principle can also be extended to other types of mobile devices. In this context, a trajectory or path can also be mentioned as a mowing pattern, because the lawnmower robot follows a certain path and at the same time mows the lawn. The result is a certain mowing pattern. Here, a typical goal when determining such a trajectory is to completely cover a certain working area, such as an area with a lawn, by the trajectory (as far as possible), so that when the lawnmower robot moves along the trajectory and at the same time mows the lawn, the lawn is completely mowed (as far as possible). Here, for example, the working width (or cutting or mowing width) of the lawnmower robot should be taken into account. Similar content also applies to other mobile devices, such as vacuuming and / or mopping robots, which should vacuum or mop a certain area of ​​the ground in the apartment as completely as possible.

[0008] In order to cover the defined working area as completely as possible with the trajectory, it is then practical for the trajectory to be as short as possible. The mobile device can thus travel through the working area as quickly as possible, i.e. in the shortest possible time, for example a lawn can be mowed as quickly as possible or a house can be vacuumed as quickly as possible. In addition, energy costs are saved.

[0009] However, as has now been demonstrated, there are also other criteria that can or should be considered when determining the trajectory. One aspect that the present invention addresses is to achieve a structured or as structured an orientation of the trajectory as possible. This means that even when redefining or planning, such a trajectory can be repeatedly obtained as similarly as possible.

[0010] For this purpose, object information of one or more selected objects is first obtained. Such object information can be, in particular, an image of the one or more selected objects, a predefined map with the one or more selected objects, or position and / or distance information about the one or more selected objects, and a plurality of information thereof is also conceivable, the object information can also be based on the aforementioned information and, for example, be derived from this information. The object information or at least part of this object information can be detected, for example, by means of one or more sensors, in particular image sensors (e.g. cameras) and / or lidar sensors of the mobile device, and then provided accordingly.

[0011] This one or these multiple selected objects are selected from multiple objects within and / or outside the working area (i.e., lawns to be mowed, for example). Here, objects outside the working area are particularly preferably under consideration. Such selected objects can be, for example, buildings, walls, windows, doors, hedges, roads and parking lots. The selected objects are such objects that should be considered for the determination of the orientation to be determined of track and especially this track. The mentioned objects are especially usually static and / or do not change or hardly change over time and are therefore particularly good for determining such objects that can be repeatedly obtained structured orientation under consideration. This also means that other objects within and / or outside the working area, for example movable objects, remain not considered in this case. How such object selection can be performed will be explained in more detail later, and this can be performed, for example, automatically or by the user.

[0012] At this point it should be mentioned that the selected objects should in particular not include boundary lines, such as those which are laid at the edge of a lawn (working area) in the case of a lawn mowing robot, so that the lawn mowing robot can identify the boundary of the working area, for example by electromagnetic detection of the boundary lines.

[0013] Based on the object information (about the one or more selected objects), the orientation of the one selected object or at least one or more of the multiple selected objects (in the case of only one selected object, respectively only for this one, in the case of multiple selected objects, for one or more or all of them) is then determined (or calculated). The orientation of the object is to be understood in this case in particular as the geometric orientation of the object within the environment and therefore, for example, also within or relative to the working area. The wall of a building can be oriented, for example, parallel to the lateral boundary of the working area. Determining or calculating such an orientation can be performed, for example, by means of classification of the object information and / or image analysis.

[0014] A trajectory is then determined (or calculated), wherein an orientation is respectively predetermined for one or more trajectory segments of the trajectory, which orientation depends on the orientation of a selected object, at least one of a plurality of selected objects, or at least a plurality of a plurality of selected objects (depending on how many selected objects are present) according to at least one orientation criterion. In other words, the trajectory is thus determined at least partially based on the previously determined orientation of one or more objects. A possible method in this case is, in particular, to determine or predetermine the mentioned trajectory segments with the orientation and then connect or associate these trajectory segments with other segments in order to obtain the final trajectory.

[0015] Such an orientation criterion can, for example, determine in which way the orientation of the track segment is to depend on the orientation of the object. This can be, for example, a specification that the track segment is to be parallel to the object (e.g. a wall), perpendicular to the object or at a certain angle. Such an orientation criterion can be stored on an execution system (e.g. a computer), if necessary after these orientation criteria have been initially created. However, it is also conceivable that the orientation criterion is specified by the user.

[0016] The trajectory is then provided for use by a control and / or regulating unit of the mobile device, in particular for controlling or moving the mobile device along the provided trajectory. Furthermore, preferably, control information for moving the mobile device is determined, more precisely based on the trajectory. This control information can then be provided, in particular the mobile device can then also be controlled (and therefore moved) based on this control information.

[0017] In this way, the trajectory of the mobile device can be created particularly easily and in particular with a structured orientation by taking into account the orientation of one or more objects relative to the working area. For example, the trajectory of the mowing robot can be such that it includes parallel trajectory segments (in particular in the form of straight lines) which in turn run parallel or perpendicular or at a certain angle to the orientation of a wall of a building next to the working area.

[0018] In this sense, it is preferred that the trajectory is determined so that it includes a plurality of trajectory segments extending side by side at a predetermined spacing. As already mentioned, these trajectory segments can be, for example, a plurality of straight lines oriented parallel to each other. This is particularly suitable, for example, for a long straight wall as an object. However, other orientations are also contemplated. Thus, for example, arc-shaped or other irregularly shaped trajectory segments can also extend side by side at a predetermined spacing. Thus, for example, circular or spiral trajectory segments extending side by side at a predetermined spacing can be provided.

[0019] Preferably, a plurality of trajectory segments are determined based on the orientation of a selected object, at least one of a plurality of selected objects, or at least a plurality of a plurality of selected objects, wherein the plurality of trajectory segments have mutually different orientations. Here, a plurality of trajectory segments can also extend side by side at predetermined intervals. Thus, for example, a plurality of parallel lines parallel to a certain wall (object) can be determined as trajectory segments, and in addition, however, a plurality of parallel lines perpendicular to exactly this wall can also be determined.

[0020] In this context, it is particularly expedient to provide the user with information about a plurality of different trajectory segments, for example by output on a user interface (e.g. a so-called GUI, “Graphical User Interface”). The user can then, for example, receive information about at least one selected trajectory segment of the plurality of trajectory segments via the user interface, wherein the at least one selected trajectory segment is used for the trajectory. In the above example, the user can be offered a choice via the user interface between lines parallel to one another and also parallel to the wall and lines parallel to one another and also perpendicular to the wall. The user can then decide to select one of these two variants.

[0021] However, independently of the involvement of the user, for example, a plurality of track sections with mutually different orientations can also all be used for the track, for example for different areas of the working area. Thus, for example, lines parallel to one another and also to the wall can be used near a door in a wall, while lines parallel to one another and also perpendicular to the wall can be used further away from the door (for example at a certain distance of several meters).

[0022] The determination of one or more selected objects is preferably carried out with the aid of an algorithm, in particular with the aid of a classification of a plurality of objects. The objects thus determined can then be provided and in particular used to determine the orientation. This therefore allows the automation of the determination of the one / multiple selected objects and their provision. With the aid of such an algorithm, for example, dominant objects can be determined from the objects present in total, which are usually or according to a determined object criterion (for example a determined length or size or a determined relevance for the user, such as a window or a door) as the selected objects under consideration. For this purpose, for example, a hierarchical list with dominant objects can be present, which, for example, sorts the above-mentioned objects, which are preferably taken into consideration from the selected objects, by relevance. Then, for example, the object that is at the top in the hierarchical list, i.e. the most relevant, can be used. For example, it is conceivable that a wall is classified as more relevant than a hedge.

[0023] It is also preferred that a plurality of dominant objects are first determined from a plurality of objects based on at least one object criterion (e.g. as described above), in particular by means of classification. Information about these plurality of dominant objects can then be provided to the user, for example by output on a user interface (as already mentioned). Information about one or more objects selected from the plurality of dominant objects can then be obtained by the user, for example via the user interface, wherein the one or more selected objects are determined based on the obtained information. In this way, a plurality of objects, such as walls and hedges, can thus be displayed to the user, which objects have been automatically identified as follows: based on their orientation, the trajectory segment is oriented. The user can then select which object should be used, i.e. the trajectory should be oriented, for example, according to the wall or the hedge (or their respective orientation).

[0024] However, in addition to the information about the plurality of dominant objects, information about at least one trajectory segment can also be provided to the user, for example, by outputting it on a user interface (as already mentioned). The user can then, for example, receive information about changes to at least one trajectory segment and / or about at least one orientation criterion via the user interface, wherein the trajectory is determined based on the information received. In this way, it can therefore be shown to the user which objects should be used for orientation and how the trajectory should then be oriented. The user can then, for example, change the trajectory segment or change the orientation criterion. For example, instead of the usual orientation parallel to the wall, the user can determine that an orientation perpendicular to the wall should be carried out.

[0025] The system for data processing according to the invention comprises means for carrying out the method according to the invention or its method steps. For example, in a so-called cloud or cloud environment, the system can be a computer or a server. In the case of an application for a mobile device, trajectory or control information can then be transmitted from the system to the mobile device (for example via a wireless data connection). Likewise, for example, object information can be transmitted from the mobile device to the system. However, it is also conceivable that such a system for data processing is a computer or a control device in such a mobile device.

[0026] The invention also relates to a mobile device configured to obtain and / or determine a trajectory or control information that has been determined according to the method according to the invention and to navigate based on the trajectory or these control information.As mentioned, a system for data processing may also be comprised by the device.

[0027] Preferably, the mobile device has one or more sensors for detecting object information, more preferably a control and / or regulating unit and a drive unit for moving the mobile device along a trajectory, in particular based on the object information and / or other environmental information.

[0028] The mobile device is preferably designed as an at least partially automatically movable vehicle, in particular as a passenger vehicle or a freight vehicle, and / or as a robot, in particular as a household robot, such as a vacuuming and / or mopping robot, a floor or street cleaning device or a lawn mowing robot, and / or as a drone.

[0029] It is also advantageous to implement the method according to the invention in the form of a computer program or computer program product with a program code for executing all method steps, because this leads to particularly low costs, especially when the executed control device is also used for other tasks and therefore always exists. Finally, a machine-readable storage medium is provided, with a computer program as described above stored thereon. Suitable storage media or data carriers for providing the computer program are especially magnetic, optical and electrical memories, such as hard disks, flash memories, EEPROMs, DVDs, etc. It is also possible to download the program via a computer network (Internet, intranet, etc.). Such downloading can be done here either wired or cable-connected or wirelessly (e.g., via a WLAN network, 3G, 4G, 5G or 6G connection, etc.).

[0030] Further advantages and embodiments of the invention are apparent from the description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The invention is schematically illustrated by means of exemplary embodiments in the drawings and is described below with reference to the drawings.

[0032] Figure 1 To explain the invention, a mobile device is schematically shown in a working area.

[0033] Figure 2 The trajectories which have been determined according to a preferred specific embodiment of the present invention are schematically shown.

[0034] Figure 3 A trajectory which has been determined according to a further preferred embodiment of the invention is schematically shown.

[0035] Figure 4 A trajectory which has been determined according to a further preferred embodiment of the invention is schematically shown.

[0036] Figure 5 The sequence of the method according to the invention is schematically shown in a preferred embodiment. DETAILED DESCRIPTION

[0037] exist Figure 12 shows schematically and exemplarily a mobile device 100 in a working area 120 for explaining the present invention. The mobile device 100 is exemplarily a lawnmower robot having a control or regulating unit 102 and a drive unit 104 (with wheels) for moving the lawnmower robot 100, for example, along a trajectory 130.

[0038] Furthermore, the mowing robot 100 has, by way of example, a sensor 106 designed as a camera with a field of view (outlined with dashed lines). For better illustration, the field of view is selected to be relatively small here; in practice, however, the field of view can also be up to 360° (e.g., at least 180° or at least 270°). Object information such as images of objects can be detected by means of the camera 106. Furthermore, the mowing robot can have, for example, a lidar sensor in addition to or instead of a camera.

[0039] The mowing robot 100 also has a system 108 for data processing, such as a control unit, by means of which data can be exchanged with a superordinate system 110 for data processing, for example via a radio connection as described. In the system 110 (for example a server, which can also represent a so-called cloud), for example, trajectories can be determined, which are then transmitted to the system 108 in the mowing robot 100, which is then to follow these trajectories. However, it can also be provided that the trajectories are determined in the system 108 itself or are obtained there in another way. However, instead of trajectories, the system 108 can also, for example, receive control information that has been determined using the trajectories, and based on these control information, the control or regulating unit 102 moves the mowing robot 100 via the drive unit 104 in order to follow the trajectories.

[0040] Furthermore, a mobile computing system 112 is shown, such as a smartphone or the like, which can exchange data with a superordinate system 110 and / or with a system 108 in the mowing robot, for example via a depicted radio connection.

[0041] Furthermore, a building 140 is shown by way of example and schematically outside the working area 120, which building has, in particular, a wall 142 extending along and parallel to a boundary (here, a wall 142) of the working area 120. Figure 1 In addition, the building 140 has, by way of example, a window 144 in a wall 142, through which, for example, the working area can be seen from the building. The typical viewing axis or viewing direction through the window runs perpendicularly to the wall 142 and therefore also perpendicularly to the mentioned boundary of the working area 120.

[0042] Buildings 140 , walls 142 and windows 144 are exemplarily objects outside the working area 120 , which can be detected by the mowing robot 100 or its camera 106 , ie object information about these objects can be detected.

[0043] The trajectory 130 is only drawn here by way of example. For trajectories which can be created within the scope of the invention in a preferred embodiment, see the subsequent figures.

[0044] exist Figure 2 Schematically shows a trajectory 230 that has been determined according to a preferred embodiment of the present invention. The trajectory 230 should be for example Figure 1 The work area 120 shown in FIG. 1 is determined or has been determined. In addition to the work area 120 , a wall 142 and a window 144 are shown again as objects.

[0045] For example, it can be provided that trajectory 230 should (as far as possible) completely cover working area 120, so that when the mowing robot is moved along trajectory 230 and simultaneously mows the lawn, the lawn in working area 120 (or working area 120 should completely exist as lawn) is completely mowed.

[0046] Here, the trajectory is a line with several sections, which will be explained later. Typically, the trajectory 230 causes the mowing robot to travel to the upper left on the working area 120 (if the mowing robot is not already there), then turn 90° to the right and then zigzag through the working area 120. The trajectory will then continue accordingly at the upper right.

[0047] A typical way of determining or planning this trajectory 230 is to first determine the trajectory segments 231a to 231f. By way of example, these are straight lines running parallel to one another. The spacing between two adjacent trajectory segments is selected, for example, so that it corresponds to or is slightly smaller than the mowing width of the mowing robot. When the mowing robot then follows these trajectory segments 231a to 231f, substantially the entire working area is mowed.

[0048] The trajectory segments 231a to 231f can then be connected or associated with each other so that the trajectory appears as a continuous line along which the mobile device can be moved. A common way to do this is, as in Figure 2 As shown in FIG. 2 , each two adjacent track segments of the track segments 231 a and 231 f are alternately connected again at the other end. Thus, the track 230 is formed as a whole.

[0049] In this case, it is provided that the track segments 231a to 231f, which in this example largely predetermine the mowing direction, are oriented or predetermined according to the orientation of the wall 142 and / or the window 144, more precisely, for example, perpendicularly to the wall 142 or parallel to the viewing direction from the window 144. Furthermore, the track segments 231a to 231f each extend side by side at a predetermined spacing.

[0050] exist Figure 3 Schematically shows a trajectory 330 that has been determined according to another preferred embodiment of the present invention. This trajectory 430 should be for example also Figure 1 The work area 120 shown in FIG. 1 is determined or has been determined. In addition to the work area 120 , a wall 142 and a window 144 are shown again as objects.

[0051] For example, it can be provided that trajectory 330 should (as far as possible) completely cover working area 120, so that when the mowing robot is moved along trajectory 430 and simultaneously mows the lawn, the lawn in working area 120 (or working area 120 should completely exist as lawn) is completely mowed.

[0052] Here, the trajectory is a line with a plurality of sections, which will be explained later. Typically, the trajectory 330 causes the mowing robot to travel to the upper left on the working area 120 (if the mowing robot is not already there) and to zigzag through the working area 120. At the lower left, the trajectory will then be continued accordingly.

[0053] A typical way of determining or planning this trajectory 330 is to first determine the trajectory segments 331a to 331d. By way of example, these are straight lines running parallel to one another. The spacing between two adjacent trajectory segments is selected, for example, so that it corresponds to or is slightly smaller than the mowing width of the mowing robot. When the mowing robot then follows these trajectory segments 331a to 331d, substantially the entire working area is mowed.

[0054] The trajectory segments 431a to 431d can then be connected or associated with each other so that the trajectory appears as a continuous line along which the mobile device can be moved. A common way to do this is to Figure 3 As shown in FIG. 3 , each two adjacent track segments of the track segments 331 a to 331 d are alternately connected again at the other end. Thus, the track 330 is formed as a whole.

[0055] In this case, it is provided that the track segments 331a to 331d, which in this example largely predetermine the mowing direction, are oriented or predetermined according to the orientation of the wall 142 and / or the window 144, more precisely, for example, parallel to the wall 142 or perpendicular to the viewing direction from the window 144. Furthermore, the track segments 331a to 331d each extend side by side at a predetermined spacing.

[0056] exist Figure 4 Schematically shows a trajectory 430 that has been determined according to another preferred embodiment of the present invention. The trajectory 530 should be determined for the working area 420. The working area 420 and Figure 1 The difference of the working area 120 in FIG. 1 is that there is a recess in the working area at the lower right; there should be another object 446, such as a parking lot or another building. In addition, a wall 142 and a window 144 are shown again as objects.

[0057] For example, it can be provided that trajectory 430 should (as far as possible) completely cover working area 420, so that when the mowing robot is moved along trajectory 430 and simultaneously mows the lawn, the lawn in working area 420 (or working area 520 should exist completely as lawn) is completely mowed.

[0058] Here, the trajectory is a line with several sections, which will be explained later. Typically, the trajectory 430 causes the mowing robot to travel to the upper left on the working area 420 (if it is not already there) and to zigzag through the working area 420 (but differently in two different areas). At the lower left, the trajectory will then be continued accordingly.

[0059] A typical way to determine or plan this trajectory 430 is to first determine trajectory segments 431a to 431c and 432a to 432c. Trajectory segments 431a to 431c are, for example, straight lines extending parallel to each other. The spacing between two adjacent trajectory segments is, for example, selected so that the spacing corresponds to or is slightly smaller than the mowing width of the mowing robot. Trajectory segments 433a to 432c are, for example, also straight lines extending parallel to each other. The spacing between two adjacent trajectory segments is, for example, selected so that the spacing corresponds to or is slightly smaller than the mowing width of the mowing robot. However, trajectory segments 431a to 431c have a different orientation from trajectory segments 432a to 432c.

[0060] The track segments 431a to 431c and 432a to 432c can then be connected or associated with each other so that the track appears as a continuous line along which the mobile device can be moved. One possibility for this is to connect every two adjacent track segments of the track segments 431a to 431c on the one hand and 432a to 432c on the other hand alternately at the other end. In addition, the track segment 431c can then be connected to 432a, for example. Thus, the track 430 is then formed as a whole.

[0061] In this case, it is provided that the track segments 431a to 431c are oriented or predetermined according to the orientation of the wall 142 and / or the window 144, more precisely, for example, parallel to the wall 142 or perpendicular to the viewing direction from the window 144. In contrast, the track segments 432a to 432c are oriented or predetermined according to the orientation of the object 446, more precisely, for example, parallel to the object 446 or one side thereof.

[0062] exist Figure 5 The process of the method according to the invention in a preferred embodiment is shown in Figure 2 as well as Figure 1 Also mentioned for Figure 3 and Figure 4 deviations that may be necessary for the trajectory.

[0063] In step 500, object information 502 about a plurality of or possibly all objects within and outside the working area 120 (or 420 if necessary) can first be provided or detected. For this purpose, for example, object information about objects such as buildings 140, walls 142 and windows 142 and other objects not shown here (such as objects 446 or roads, hedges, etc.) can first be detected by means of the camera 106 of the mowing robot 100. It is also conceivable that object information, such as a map with objects, is provided or made available in another way, alternatively or additionally. In this way, for example, a user can provide a previously created map, which is then used.

[0064] With the aid of object information 502, one or more objects can then be selected and provided in step 510 from all objects present therein. This can be achieved, for example, by classifying the objects with the aid of algorithm 504. By way of example, these objects would be walls 142 and windows 144. Object information 512 is then provided for these objects, which object information can be part of object information 502, for example. These selected objects, namely walls 142 and windows 144, are therefore to be taken into account for the determination of the trajectory. Figure 4 In the trajectory, for example, object 446 should also be selectable.

[0065] However, it is alternatively (or additionally) conceivable to determine a plurality of dominant objects from all objects present therein based on object criteria 505 , in particular by means of classification. This can be achieved, for example, via a hierarchical list which specifies which types of objects are considered relevant for later determining the orientation of the trajectory segment.

[0066] In step 506, information about these dominant objects can then be provided, for example also by means of an output on a user interface. It can then be displayed to the user, for example on computing system 112, which objects are under consideration. The user can then, for example, select one of them, such as window 144. In step 508, information about the object selected from the plurality of dominant objects is then obtained. Window 144 is then used as the selected object.

[0067] In step 520, the orientation of one or more of the selected objects is then determined, for example by means of image analysis or classification, more precisely based on the object information 512. By way of example, orientation 522 is determined only for wall 142. This orientation is in particular the orientation of wall 142 (or an object in general) in the environment, in particular relative to work area 120. For example, for this purpose, the location, position, orientation of wall 142 in a virtual map of the environment, which also contains the location, position, orientation of work area 120, can be determined.

[0068] In step 530, trajectory 230 is then determined. For this purpose, an orientation 532 is predefined for each of trajectory segments 231a to 231f, which depends on orientation 522 of wall 142 according to orientation criterion 534. In the example shown, orientation criterion 534 predetermines that the trajectory segment should be perpendicular to orientation 522 of wall 142.

[0069] If window 144 is used as the object instead of wall 142 here, the orientation of the trajectory segment can be determined based on the orientation of the window. The orientation criterion can be, for example, an orientation parallel to the viewing direction of window 144 or perpendicular to window 144 (or its front side) in order to obtain the same trajectory 230.

[0070] exist Figure 3 In the case of , the targeting criteria are also different. Figure 4 In the case of a , for example, different orientation criteria exist for different objects and trajectory segments.

[0071] It is also conceivable that information about a plurality of trajectory segments is provided in step 536, for example also by means of an output on a user interface. It is then possible to display to the user, for example, on the computing system 112: which possible trajectory segments are under consideration. For example, the user may be advised Figure 2 and Figure 3 The user can then select one of them, for example. In step 538, information about the trajectory segment is then obtained and then used.

[0072] In step 540, trajectory 230 is then provided for use by a control or regulating unit of the mobile device, in particular for controlling the mobile device along trajectory 230. For this purpose, control information 552 for moving the mobile device can first be determined in step 550 based on the trajectory and then provided.

Claims

1. A method for determining a trajectory (230, 330, 430) for a mobile device (100), in particular an at least partially automatically moving vehicle and / or a robot, preferably a mowing robot, in particular for obtaining a structured orientation of the trajectory (230), along which the mobile device (100) is to be moved in a working area (120, 420), the method comprising: providing (510) object information (312) about one or more selected objects (142, 144), the objects being selected from a plurality of objects within and / or outside the work area (120), determining (520) an orientation (522) of the one selected object, at least one of the plurality of selected objects (142, 144), or at least a plurality of the plurality of selected objects (142, 144) based on the object information (512), determining (530) the trajectory (230, 330, 430), wherein an orientation (522) is respectively predetermined for one or more trajectory segments (231a-231f, 331a-331d, 431a-431c, 432a-432c) of the trajectory, the orientation depending on at least one orientation criterion (534) on the orientation (522) of the one selected object, at least one of the plurality of selected objects (142, 144) or at least a plurality of the plurality of selected objects (142, 144), and The trajectory (230, 330, 430) is provided (540) for use by a control or regulating unit (102) of the mobile device, in particular for controlling the mobile device along the provided trajectory (230, 330, 430).

2. The method according to claim 1, wherein the trajectory (230, 330, 430) is determined so that it includes a plurality of trajectory segments (231a-231f, 331a-331d, 431a-431c, 432a-432c) extending side by side at predetermined intervals.

3. The method according to claim 1 or 2, further comprising: A plurality of trajectory segments (431a-431c, 432a-432c) are determined based on the orientation (322) of the one selected object, at least one of the multiple selected objects, or at least multiple of the multiple selected objects, wherein the multiple trajectory segments have different orientations from each other.

4. The method according to claim 3, further comprising: providing (536) information about the plurality of different trajectory segments, and obtaining (538) information about at least one selected trajectory segment of the plurality of trajectory segments, Therein, the at least one selected trajectory segment is used for the trajectory.

5. The method according to any one of the preceding claims, further comprising: determining the one or more selected objects from the plurality of objects by means of an algorithm (504), in particular by means of a classification of the plurality of objects, and The determined one or more selected objects are provided.

6. The method according to any one of the preceding claims, further comprising: Based on at least one object criterion (505), a plurality of dominant objects are determined from the plurality of objects, in particular by means of a classification.

7. The method according to claim 6, further comprising: providing (506) information about the plurality of dominant objects, and obtaining (508) information about one or more objects selected from the plurality of dominant objects, The one or more selected objects are determined based on the obtained information.

8. The method according to claim 6 or 7, further comprising: providing information about the plurality of dominant objects and information about at least one trajectory segment, obtaining information about a change of the at least one trajectory segment and / or about at least one orientation criterion, and The trajectory is determined based on the obtained information.

9. The method according to any of the preceding claims, wherein the one or more selected objects (140, 142, 144, 446) include at least one of the following: -building, -wall, -window, -Door, -hedge, - roads, and -PARKING LOT.

10. The method according to any one of the preceding claims, wherein the object information comprises and / or is based on at least one of the following: - images of the one or more selected objects, a pre-given map having the one or more selected objects, and - Position and / or distance information about the one or more selected objects.

11. The method according to any of the preceding claims, wherein the object information is detected by means of one or more sensors (106), in particular image sensors and / or lidar sensors, of the mobile device (100).

12. The method according to any one of the preceding claims, further comprising: Based on the trajectory (230), determining (350) control information (352) for moving the mobile device (100), and The control information is provided and the mobile device is controlled, in particular based on the control information.

13. A system (108, 110) for data processing, comprising means for performing the method according to any of the preceding claims.

14. A mobile device (100) comprising a system (108) according to claim 13, or configured to obtain and / or determine a trajectory (230, 330, 430) or control information (352) determined according to a method according to any one of claims 1 to 12, The mobile device (100) is configured to navigate based on the trajectory (230, 330, 430) or the control information (352).

15. The mobile device (100) according to claim 14 has one or more sensors (106) for detecting the object information (302, 312), and more preferably has a control or regulation unit (102) and a drive unit (104) for moving the mobile device (100) along the trajectory (230, 330, 430s), in particular based on the object information and / or other environmental information.

16. The mobile device (100) according to claim 14 or 15 is configured as a vehicle that moves at least partially automatically, in particular as a passenger vehicle or a freight vehicle, and / or as a robot, in particular as a household robot, such as a vacuuming and / or mopping robot, a floor or street cleaning device or a lawn mowing robot, and / or as a drone.

17. A computer program comprising instructions which, when executed on a computer, cause the computer to perform the method steps of the method according to any one of claims 1 to 12 when the computer program is executed by the computer.

18. A computer-readable storage medium having stored thereon the computer program according to claim 17.

Images