Method for determining a movement path for a mobile device

Abstract

The invention relates to a method for determining a movement path (130) along which a mobile device (100), in particular a robot, preferably a domestic robot or vacuum cleaner robot, is to move in a surrounding area (120), having the steps of: providing obstacle information which comprises information about the position of an obstacle (140, 1422, 144, 146) that can be overcome by the mobile device, said obstacle information having been determined on the basis of sensor information (202) which has been captured by means of at least one sensor (106) of the mobile device; checking whether additional information relating to the process of overcoming obstacles is available; if additional information is available: determining the movement path on the basis of the additional information; and providing the movement path or information relating to the movement path, in particular in order to navigate the mobile device.

Description

[0001] Description

[0002] title

[0003] Method for determining a movement path for a mobile device

[0004] The present invention relates to a method for determining a movement path in an environment along which a mobile device, in particular a robot, preferably a household or vacuum cleaner robot, is to move, a system for data processing and a computer program for its implementation as well as a mobile device

[0005] Background of the invention

[0006] Mobile devices such as vacuum or floor-mopping robots or other household robots typically move across a surface in an environment to be serviced, such as a home. Sensors can be used to detect the environment, especially obstacles, and navigate based on this.

[0007] Disclosure of the invention

[0008] According to the invention, a method for determining a movement path, a data processing system and a computer program for implementing the method, as well as a mobile device with the features of the independent patent claims are proposed. Advantageous embodiments are the subject of the dependent claims and the following description.

[0009] The invention relates to mobile devices that move or are intended to move in an environment, e.g., on a surface in the environment, and that, e.g., along a specific movement path. A typical example of such a mobile device is a household robot, such as a vacuum and / or floor-mopping robot, or a cleaning robot. Although the invention is described below primarily with reference to household robots, it is equally applicable to other robots or mobile devices that move or are intended to move in an environment on a surface, e.g., lawnmowers, floor or street cleaning devices such as street sweeping robots (or automated street sweepers) and the like, but also other so-called service robots, or other at least partially automated vehicles, such as, for example, passenger transport vehicles or goods transport vehicles (also so-called industrial trucks, e.g.,in warehouses) or other industrial robots.

[0010] For mobile devices such as household robots, movements in the environment (e.g., in the household or apartment) must be carried out in a systematic and planned manner. For this purpose, household robots are equipped with sensors such as lidar sensors or laser scanners (rangefinders), radar sensors, inertial sensors, cameras, ultrasonic sensors, as well as odometry (usually radodometry) or radio localization to perceive their surroundings and, based on corresponding information such as positions, distances, distances, and dimensions of (insurmountable) obstacles, build a map of their environment within which they can ultimately plan their movements, e.g., the systematic vacuuming of an entire apartment (coverage path planning or "coverage problem"). In their environment, these robots typically perceive obstacles such as walls or furniture and enter them into the map. In this way, for example,An area of ​​the ground that is to be covered by the movement of the mobile device or robot can also be determined.

[0011] In addition to insurmountable obstacles such as walls, larger pieces of furniture and the like, there are also surmountable obstacles, e.g. uneven surfaces, door thresholds and the like, which can be overcome or driven over by the mobile device. As has now turned out, however, it is not always sensible for the mobile device to also overcome such surmountable obstacles when moving. While door thresholds (particularly low or otherwise safely surmountable door thresholds) or edges or edges of carpets (particularly vacuumable carpets) should sometimes be overcome in order to clean several rooms or different floor coverings, this can be different for things like the feet of cantilever chairs or lamps or tables or even door thresholds that are too high or objects that cannot be cleaned in any other way (a carpet should not be mopped, for example), and the like.Such surmountable obstacles should often not be overcome because this can lead to problems with the further movement of the mobile device, e.g. due to the mobile device getting stuck, or simply because this is not desired.

[0012] Based on sensor information or sensor data collected by typical sensors of the mobile device, such as the aforementioned lidar sensors, radar sensors, inertial sensors, cameras or odometry, it is usually possible to determine that an obstacle is present that can be overcome. However, a more specific distinction as to which obstacle exactly this is, for example a door threshold or the foot of a table, is often not possible.

[0013] And even if such a distinction were possible, e.g. with sensor information captured by a camera, such a distinction or a classification of the object or obstacle is often not sufficiently accurate to determine the further movement of the mobile device based on it.

[0014] Against this background, a possibility is proposed to circumvent or at least reduce this problem by checking, in addition to obstacle information which comprises information about a position of an obstacle that can be overcome by the mobile device and which has been determined based on sensor information that has been recorded by at least one sensor of the mobile device, e.g. during movement of the mobile device in the environment, but also e.g. while the device is stationary in the environment, whether additional information relating to overcoming obstacles is available. In particular, such additional information has not been determined, or at least not directly, based on sensor information that has been recorded by at least one sensor of the mobile device; this additional information has therefore been provided in another way, e.g. a user input or as semantic information.

[0015] If such additional information is available, the movement path is determined based on the additional information. The movement path or information about it (e.g., boundary conditions of the movement path) is then provided, particularly for navigation of the mobile device.

[0016] Using such additional information can simplify the decision as to whether or how to overcome the surmountable obstacle. For example, certain types of surmountable obstacles may not be overcome, even though they would otherwise be possible, in order to prevent the mobile device from potentially becoming stuck. This also results in less user effort to free stuck mobile devices.

[0017] At this point, it should be mentioned again that it is assumed that an obstacle is detected that is known, or at least can be assumed, to be overcome or driven over by the mobile device. In contrast, the present invention addresses the question of whether such an obstacle can or should actually be overcome or driven over, and, if applicable, the question of how such an obstacle should then be overcome or driven over.

[0018] In one embodiment, if no additional information is available, the movement path is determined based on a stored standard specification relating to overcoming surmountable obstacles. Such a standard specification may, for example, include that an surmountable obstacle should always be overcome. In one embodiment, the additional information comprises at least one of the following additional information: a specification relating to overcoming the obstacle, wherein the specification comprises information about whether and / or how the obstacle should be overcome; one or more metrics relating to overcoming obstacles, wherein it is determinable whether and / or how the obstacle should be overcome based on the one or at least one of the multiple metrics.

[0019] The requirement to overcome the obstacle is, in particular, a specific requirement for the currently relevant obstacle, e.g., in contrast to the aforementioned standard requirement, which generally applies to all or at least a large number of obstacles. Such a specific requirement can, for example, be used to specify that a currently surmountable obstacle, such as the leg of a table or a cantilever chair, should not be overcome. This can, for example, be used to make a targeted exception to the rule for certain obstacles.

[0020] A metric, on the other hand, applies to a plurality of surmountable obstacles. In one embodiment, the one or more metrics relating to overcoming obstacles comprise at least one of the following metrics: a metric that specifies an area in the environment or based on which an area in the environment can be determined. The metric specifies a specification for surmountable obstacles located in the area; this specification relates to overcoming obstacles and includes information about whether and / or how the obstacles should be overcome.

[0021] In contrast to the concrete specification, such a metric applies generally to a large number of surmountable obstacles, but only, for example, if such an obstacle is located in a certain area. For example, a certain area can be defined, e.g. in the form of a rectangle in a room, whereby for all surmountable obstacles that are located in the rectangle, i.e. whose position there is detected, it is specified that these should not be overcome. For example, an area in a dining room can be specified in which it is assumed that there are cantilever chairs with feet, but not always in the same position. Using a metric, it can therefore be specified that the foot of a cantilever chair should not be overcome if it is found in the area.

[0022] However, such an area is not a no-go area, i.e. an area into which the mobile device is not allowed to move at all.

[0023] In one embodiment, the area has been determined by user input, in particular by means of an input device. For example, a user can define the area in the dining room just mentioned, e.g. by selecting it from a map displayed to the user on the input device. In one embodiment, the area is determined or determinable based on a predetermined subdivision of the environment, in particular a transition between rooms. Here, for example, it can be known from a map of the environment that there is a transition between two rooms. Based on this, it can then be concluded that an surmountable obstacle in this area is a door threshold. This can or should be driven over. It is conceivable that how the obstacle is driven over is then also specified here, e.g. only at an at least approximately vertical angle.

[0024] In one embodiment, checking whether additional information relating to overcoming obstacles is present comprises checking whether a specification relating to overcoming the obstacle is present as additional information, wherein the specification comprises information about whether and / or how the obstacle should be overcome. If such a specification is present, it is used as additional information for determining the movement path, i.e. the movement path is determined based on the specification as the additional information. If no such specification is present, a check is carried out as to whether one or more metrics relating to overcoming obstacles are present as additional information, wherein it can be determined based on the one or at least one of the multiple metrics whether and / or how the obstacle should be overcome.If one or more such metrics are present, the movement path is determined based on the one or at least one of the multiple metrics as the additional information.

[0025] The above applies to the target and the metrics, but in this embodiment, if there is a specific target for an obstacle, this is given priority.

[0026] In one embodiment, at least some of the additional information is stored in a map of the surroundings. This can be the case, for example, as an annotation in the map. In one embodiment, an obstacle and the additional information are entered into a map of the surroundings. For example, an obstacle that was not previously present in the map can be added when it is detected, making it easier to recognize later. It is also conceivable that an option is then provided for a user to adapt the obstacle and / or the additional information in the map or to remove it again if necessary, e.g. if the user wishes to have different specifications at some point.

[0027] In one embodiment, it is provided that, based on machine learning (e.g., artificial intelligence), it is determined or learned which obstacles could not be overcome; based on this, one or more metrics can then be adjusted, e.g., the learned information can be automatically integrated into a metric.

[0028] A system for data processing according to the invention or a computing unit, e.g. a control device or a control unit of a mobile device, or a server or other computer, is set up, in particular in terms of programming, to carry out a method according to the invention, e.g. in one of the described embodiments.

[0029] The invention also relates to a mobile device such as a household robot, in particular a vacuum and / or floor-mopping robot, a lawnmower, or a floor or street cleaning device. In addition to the aforementioned computing unit or data processing system, the mobile device also has at least one sensor for acquiring sensor information, e.g., a laser scanner. However, the device can also be configured to receive a movement path determined according to a method as mentioned above, or navigation information determined based thereon, and to navigate based thereon.

[0030] The implementation of a method according to the invention in the form of a computer program or computer program product with program code for carrying out all method steps is also advantageous, since this entails particularly low costs, in particular if an executing control unit is also used for other tasks and is therefore already present. Finally, a machine-readable storage medium is provided with a computer program stored thereon as described above. Suitable storage media or data carriers for providing the computer program are, in particular, magnetic, optical and electrical memories, such as hard disks, flash memories, EEPROMs, DVDs, etc. Downloading a program via computer networks (Internet, intranet, etc.) is also possible. Such a download can be wired or cable-based or wireless (e.g. via a WLAN network, a 3G, 4G, 5G or 6G connection, etc.).

[0031] Further advantages and embodiments of the invention will become apparent from the description and the accompanying drawings.

[0032] The invention is illustrated schematically in the drawing using an embodiment and is described below with reference to the drawing.

[0033] Short description of the drawings

[0034] Figure 1 schematically shows a mobile device in one embodiment in an environment.

[0035] Figure 2 shows a schematic flow of a method in one embodiment. Embodiment(s) of the invention

[0036] Figure 1 schematically shows a top view of a mobile device 100 in one embodiment in an environment 120, e.g., a home. By way of example, the environment 120 comprises two rooms 121 and 122.

[0037] The mobile device 100 is, for example, a vacuum cleaner robot with a control or regulating unit 102 and a drive unit 104 (with wheels) for moving the vacuum cleaner robot 100, e.g., along a movement path 130, as well as an end effector 110. Furthermore, the vacuum cleaner robot 100 has, for example, a sensor 106 designed as a lidar sensor with a detection range.

[0038] The environment 120 can be detected by means of the sensor 106, i.e., sensor information can be generated with it. In a scan using the lidar sensor, for example, a set of points, a so-called point cloud, can be generated, where each point indicates a distance of an object at which the laser beam is reflected, from the sensor. This applies in particular to a 3D lidar sensor. In the case of a 2D lidar sensor, which can only scan at a certain height, it can only detect whether or not an obstacle exists at this height. In addition, using such a lidar sensor (also referred to as a laser scanner), for example, an object or obstacle can only be detected above a certain height. This can therefore also be used, for example, to detect or determine whether an obstacle can generally be driven over by the mobile device; this is the case, for example, if the obstacle is only a short height.With other types of sensors, as mentioned above, sometimes in combination, surmountable obstacles can also be detected.

[0039] Furthermore, the robot vacuum cleaner 100 has a computing unit or a system 108 for data processing, e.g., a control unit, by means of which data can be exchanged with a higher-level system 112, e.g., via an indicated radio connection. The control or regulating unit 102 and the system 108 can also be combined. In the system 112, for example, a map and movement paths (or general navigation information) can be determined, which are then transmitted to the system 108 in the robot vacuum cleaner 100, which the latter is then to follow. However, it can also be provided that a map and / or a movement path (or general navigation information) is determined in the system 108 itself or is otherwise received there. Instead of a movement path or the navigation information, the system 108 can, for example,also receive control information determined based on a movement path or the navigation information, and according to which the control or regulating unit 102 can move the robot vacuum cleaner 100 via the drive unit 104 to follow a movement path. The movement path 130 is indicated here only as an example.

[0040] Furthermore, the robot vacuum cleaner 100 optionally has an inertial sensor 107; multiple inertial sensors are also conceivable. In one embodiment, an inertial sensor or inertial measuring unit can, for example, combine a 3D rotation rate sensor (gyroscope) with a 3D linear acceleration sensor (accelerometer).

[0041] The robot vacuum cleaner 100 is located on a surface 125, a floor, of room 121. In room 121, a table 145 and two cantilever chairs 141, 143 are shown, by way of example, with the cantilever chair having a base 142 and the cantilever chair having a base 144. The table 145 has a base 146. In this context, it should be noted that the robot vacuum cleaner 100 is shown enlarged compared to the table and the cantilever chairs. Furthermore, a transition in the form of a floor threshold or door threshold 140 is present between rooms 121 and 122.

[0042] Both the floor threshold 140 and the feet 142, 144 of the cantilever chairs and 146 of the table are now obstacles that can be overcome, ie the robot vacuum cleaner 100 can drive over them. However, while it is desired, for example, that the robot vacuum cleaner 100 drives over the floor threshold 140, the robot vacuum cleaner 100 should not drive over the feet 142, 144, 146 in order to avoid potentially getting stuck. Figure 2 shows a schematic sequence of a method in one embodiment. The method is used generally for determining a movement path and, in particular, also for navigating a mobile device such as the robot vacuum cleaner according to Figure 1.

[0043] For this purpose, it can initially be assumed that the mobile device or the robot vacuum cleaner is moving on the floor in the surrounding area. In a step 200, sensor information 202 is acquired using the sensor of the mobile device, based on which obstacle information 206 is then determined in step 204. The obstacle information 206 comprises information about a position of an obstacle that can be overcome by the mobile device, e.g., one of the feet 142, 144, 146 or the door threshold 140.

[0044] In step 208, this obstacle information 206 is provided. This can be done, for example, in the computing unit 108 of the robot vacuum cleaner, or, for example, in the higher-level system 110.

[0045] In a step 210, it is then checked whether additional information 212 relating to overcoming obstacles is present. For example, in step 214, it can first be checked whether a specification 216 relating to overcoming the obstacle is present as additional information, wherein the specification 216 comprises information about whether and / or how the obstacle should be overcome. If such a specification 216 is present, the movement path is determined in step 218 based on the specification as the additional information and provided in step 220, e.g., for further navigation of the robot vacuum cleaner.

[0046] This can be the case, for example, for the table 145 or its base 146. A user can, for example, have entered a corresponding specification in a map of the environment to which the robot vacuum cleaner or an executing system has access. This is useful, for example, if the table has a fixed position in the room. If, however, no such specification exists, a check is carried out in step 222 to determine whether one or more metrics 224 relating to overcoming obstacles are available as additional information, wherein, based on the one or at least one of the multiple metrics, it can be determined whether and / or how the obstacle should be overcome.

[0047] If one or more such metrics are present, the movement path is determined in step 226 based on the one or at least one of the several metrics as the additional information and provided in step 228, e.g. for further navigation of the robot vacuum cleaner.

[0048] This can be the case, for example, for the cantilever chairs 141, 143 or their feet 142, 144. For this purpose, a user can, for example, have entered a corresponding area, as designated 150 in Figure 1, in a map of the environment to which the robot vacuum cleaner or an executing system has access, as well as the metric which specifies that surmountable obstacles located in area 150 should not be driven over. This is useful, for example, because cantilever chairs or chairs in general, unlike tables, for example, do not have a fixed position in the room. However, it is also conceivable that one or more others are defined within an area with different metrics; in this case, the foot of the table could, for example, be in a different area than the chairs.

[0049] However, if there were no specification for the table or its base, for example, this metric would also apply to the table or its base if the table is located in the area 150 - as is the case in Figure 1.

[0050] However, this can also be the case, for example, for the door threshold 140. In this case, however, no specific area is directly specified by a user; rather, an area 151 can be determined based on a predefined subdivision of the environment, in particular a transition between rooms 121 and 122.

[0051] If no such metric is present, ie if no additional information is available, the movement path is determined in step 230 based on a standard specification 232 and provided in step 234, e.g. for further navigation of the vacuum cleaner robot.

[0052] If a metric is present or if the default setting is used, the obstacle, in particular its position, as well as any additional information, can also be entered into a map 238 of the environment in step 236; this can later be changed or adapted by a user, for example.

[0053] In this context, it should also be mentioned that when a surmountable obstacle is overcome or driven over, a more precise determination or classification of the obstacle can also be made, e.g., for entry on the map. For this purpose, additional sensors on the mobile device, such as inertial sensors, lift-up sensors, or bumper sensors, as well as the sensor data obtained from them, can be used.

Claims

Claims 1. A method for determining a movement path (130) in an environment (120) along which movement path a mobile device (100), in particular a robot, preferably a household or vacuum cleaner robot, is to move, comprising: Providing (208) obstacle information (206) comprising information about a position of an obstacle (140, 142, 144, 146) that can be overcome by the mobile device, wherein the obstacle information has been determined based on sensor information (202), wherein the sensor information has been detected by means of at least one sensor (106) of the mobile device; Checking (210) whether additional information (212) regarding overcoming obstacles is available; if additional information is available: determining (218, 226) the movement path based on the additional information; and Providing (220, 228, 234) the movement path or information concerning the movement path, in particular for navigation of the mobile device.

2. The method according to claim 1 , further comprising, if no additional information is available: Determining (232) the movement path based on a stored standard specification (230) relating to overcoming surmountable obstacles.

3. The method according to claim 1 or 2, wherein the additional information comprises at least one of the following additional information: a specification (216) relating to overcoming the obstacle, wherein the specification comprises information about whether and / or how the obstacle should be overcome; one or more metrics (224) relating to overcoming obstacles, wherein it is determinable whether and / or how the obstacle should be overcome based on the one or at least one of the multiple metrics.

4. The method according to claim 1 or 2, wherein checking whether additional information concerning overcoming obstacles is available comprises: Checking (214) whether a specification (216) relating to overcoming the obstacle is present as additional information, wherein the specification comprises information about whether and / or how the obstacle is to be overcome; if such a specification is present: determining (218) the movement path based on the specification as the additional information; if none is present: checking (222) whether one or more metrics (224) relating to overcoming obstacles are present as additional information, wherein based on the one or at least one of the multiple metrics it is determinable whether and / or how the obstacle is to be overcome; and if one or more such metrics are present: determining (226) the movement path based on the one or at least one of the multiple metrics as the additional information.

5. The method according to claim 3 or 4, wherein the one or more metrics relating to overcoming obstacles comprise at least one of the following metrics: a metric (224) which indicates an area (150) in the environment or based on which an area in the environment can be determined, and wherein the metric specifies a specification relating to overcoming obstacles for overcoming obstacles located in the area, which specification comprises information about whether and / or how the obstacles are to be overcome; 6. The method according to claim 5, wherein the area has been determined by a user input, in particular by means of an input device, or wherein the area is determined or determinable based on a predetermined subdivision of the environment, in particular a transition between rooms.

7. Method according to one of the preceding claims, wherein at least part of the additional information is stored in a map of the surroundings.

8. Method according to one of the preceding claims, further comprising: entries (236) of the obstacle and the additional information in a map (238) of the surroundings.

9. The method according to any one of the preceding claims, wherein the at least one sensor of the mobile device comprises one or more of the following sensors: a lidar sensor (106), a radar sensor, an inertial sensor, an odometry, a camera, an ultrasonic sensor, a radio localization sensor.

10. A data processing system comprising means for carrying out the method according to any one of the preceding claims.

11. A mobile device (100) having at least one sensor for acquiring sensor information, and wherein the mobile device comprises a system according to claim 10 and / or is configured to receive a movement path determined according to a method according to any one of claims 1 to 9, or navigation information determined based thereon, and to navigate based thereon.

12. Mobile device (100) according to claim 11, which is designed as a household robot, in particular a vacuum and / or wiping robot, or as a floor or Street cleaning device or as a lawnmower or as a service robot or as an industrial robot.

13. A computer program comprising instructions which, when executed by a computer, cause the program to carry out the method steps of a method according to any one of claims 1 to 9 when executed on the computer.

14. A computer-readable storage medium on which the computer program according to claim 13 is stored.

Images