Path planning for a movable robot

Abstract

The invention relates to a method for path planning for a movable robot (10), in which method a map of an environment of the movable robot is provided (S10), which map assigns a distance from a nearest obstacle to each one of different regions of the environment, and in which method at least one path for the movable robot is planned (S20, S35), wherein this path is planned (S35) on the basis of this provided map such that regions are preferred which are assigned a distance from a nearest obstacle that has at least one predefined minimum value, if a distance criterion is met. The invention also relates to a method for operating a movable robot, to a system, to a movable robot and to a computer program (product).

Description

[0001] 120905P524PC 1 / 15 KUKA Deutschland GmbH 2023P00019 WO

[0002] Description

[0003] Path planning for mobile robots

[0004] The present invention relates to a method and system for path planning for a mobile robot, a method for operating the mobile robot, the mobile robot and a computer program or computer program product.

[0005] The object of the present invention is to improve the path planning for mobile robots and / or the operation of mobile robots.

[0006] This task is accomplished by a method having the features of claim 1 or 2.

[0007] Claim 8 is resolved. Claims 9-11 protect a system, a mobile robot, a computer program, or a computer program product for carrying out a method described herein. The dependent claims relate to advantageous embodiments.

[0008] According to one embodiment of the present invention, a method for path planning for a mobile robot provides a map, preferably numerical and / or digitally stored, of the mobile robot's environment, which assigns a distance, preferably one- or multi-dimensional, to the nearest obstacle to the various regions of the mobile robot's environment, particularly in a digital manner. In one embodiment, providing the map comprises creating and / or saving and / or transferring and / or retrieving and / or loading (from and / or into a memory) the map, and / or the method also includes providing or part of providing the map. In a further development, the method includes determining, in particular recognizing, or...Identifying obstacles in an environment, preferably an image of the environment, of the mobile robot and / or determining, in particular calculating, the (respective) distance to the (respective) nearest obstacle and / or assigning (data-technical) these distances to regions of the map, for example in the form of a table, a function or the like. 120905P524PC 2 / 15 KUKA Deutschland GmbH 2023P00019 WO.

[0009] According to one embodiment of the present invention, at least one path for the mobile robot is planned.

[0010] According to one embodiment of the present invention, this route is planned based on the provided map in such a way that regions are preferred, in a further development between a starting region and a target region, in an embodiment from the starting region and / or to the target region, only regions are visited which have a distance to a nearest obstacle that has at least one minimum value, which in one embodiment is variable and / or based on a user input, if a distance criterion is met.

[0011] This allows the probability of maintaining a minimum distance, preferably to maintain a desired and / or safety distance, to be increased as needed (based on the distance criterion) and efficiently (using the provided map), thereby reducing the probability of an unwanted collision of the mobile robot, particularly due to tolerances in its navigation and / or control or the like.

[0012] In one implementation, an intended, or in another implementation pre-planned, path for the mobile robot is checked for potential collisions (of the mobile robot with an obstacle) and / or a potential failure to maintain a specified minimum distance (of the mobile robot) to the nearest obstacle.

[0013] If this check identifies or predicts at least one potential collision and / or at least one potential breach of the specified minimum distance, the distance criterion is met in one iteration and an alternative route is taken based on the provided map, such that regions are given preference, in a further development between a starting region and a target region, in a further development from the starting region and / or to the target region only regions are visited that meet a distance criterion.120905P524PC 3 / 15 KUKA Deutschland GmbH 2023P00019 WO

[0014] is assigned to a nearest obstacle that has at least a specified minimum value, planned, which may in particular include replanning and / or replanning the intended route.

[0015] This allows the probability of compliance with a minimum distance, preferably specified by the minimum value to maintain a desired and / or safety distance, to be increased as needed (due to the verification) and efficiently (using the provided map) in one implementation, thereby reducing the probability of an unwanted collision of the mobile robot, in particular due to tolerances in its navigation and / or control or the like.

[0016] In one version, in further training, the intended path that is checked is planned on the basis of a path length, in a particularly advantageous further training as the shortest path.

[0017] Since the probability of unintentionally getting too close to an obstacle is particularly high when planning routes based on path length, especially the shortest routes, the present invention is particularly advantageous in this regard. However, the intended path being checked can also be planned, or alternatively planned, based on another quality criterion, such as energy consumption, travel time, or the like.

[0018] In one implementation, the intended route is checked for potential collisions and / or a potential violation of a predetermined minimum distance to the nearest obstacle using the provided map. This allows the check to be carried out particularly efficiently.

[0019] In one implementation, the distance criterion is fulfilled, in particular additionally or also, if a distance-maintaining operating mode is selected for route planning in a training course by means of a corresponding user input; in a training course, the procedure includes selecting the 120905P524PC 4 / 15 KUKA Deutschland GmbH 2023P00019 WO

[0020] or switching to distance-maintaining mode based on user input. This allows for advantageous initial path planning, rather than requiring verification of an intended route, while maintaining a desired and / or safety distance. This reduces the time required for path planning, particularly in environments with many and / or closely spaced obstacles.

[0021] In one implementation, the route is planned based on the provided map using an informed search algorithm; in a particularly advantageous further development, using an A* algorithm, if the distance criterion is met.

[0022] Such algorithms have proven to be particularly advantageous for the present application, especially efficient, robust and / or reliable.

[0023] In one version, the route is planned based on the provided map and a route length; in a particularly advantageous further development, with a quality criterion that includes the route length or is reduced with shorter routes under otherwise identical conditions; in another version, the route length is minimized if the distance criterion is met.

[0024] In addition to or as an alternative to path length, a quality criterion used to plan the path based on the provided map (provided the distance criterion is met) can, in one implementation, also include one or more other (path-dependent) quality factors, such as energy consumption and / or travel time, or similar parameters. In another implementation, the quality criterion that includes or depends on path length and / or one or more other quality factors can be used as edge values ​​or costs of a graph. This allows for improvements to the operation of the mobile robot.

[0025] In one implementation, the route is planned based on the provided map in such a way that, between a starting region and a destination region, or in another implementation from the starting region and / or to the destination region, only regions are visited, and in particular may be visited, which (according to the map) have a distance to the nearest obstacle that is at least the distance specified in a 120905P524PC 5 / 15 KUKA Deutschland GmbH 2023P00019 WO

[0026] Execution variables and / or a minimum value specified based on user input.

[0027] In one implementation, the informed search algorithm, in a particularly advantageous further development the A* algorithm, for planning the path between start and end region, in one implementation from the start region and / or to the target region, or its search, is only provided with regions for possible approach or trials, to which (by the map) a distance to a nearest obstacle is assigned that has at least the specified minimum value.

[0028] By ignoring regions that are assigned too small a distance, the procedure can be carried out particularly efficiently.

[0029] In one implementation, the map is generated based on sensor-based detection of the mobile robot's environment (a further development of which utilizes sensors); in another, it is generated based on at least one camera image and / or corresponding image processing, particularly obstacle detection. This allows the process to be carried out with exceptional reliability in one implementation.

[0030] In one implementation, regions of the map are discrete cells and / or nodes of a graph, whose edges can be weighted with corresponding quality criterion values, or in a further development, (partial) path lengths. This allows the process to be carried out particularly efficiently in one implementation.

[0031] According to one embodiment of the present invention, to operate a mobile robot, a path for the mobile robot is planned according to a method described herein and the mobile robot is commanded to follow this planned path.

[0032] According to one embodiment of the present invention, a path planning system for a mobile robot, in particular hardware and / or software-based, is required. 120905P524PC 6 / 15 KUKA Deutschland GmbH 2023P00019 WO

[0033] is technically equipped for carrying out a procedure described herein and / or exhibits:

[0034] Means of providing a map of the mobile robot's environment, assigning a distance to the nearest obstacle to different regions of the environment; and

[0035] Means for planning at least one path for the mobile robot, wherein (these means are set up so that) this path is planned on the basis of this provided map in such a way that regions are preferred, in a further training between a starting region and a target region, in an execution from the starting region and / or to the target region, only regions are visited which have a distance to a nearest obstacle that has at least a specified minimum value, if a distance criterion is met.

[0036] In one version, the system or its means exhibit:

[0037] Means of checking an intended path for the mobile robot, in further training using the provided map, for potential collisions and / or a potential breach of a predetermined minimum distance to a nearest obstacle; and

[0038] Means for planning an alternative route based on the provided map in such a way that regions are given preference, in a further training between a starting region and a target region, in an execution from the starting region and / or to the target region, only regions are visited which are assigned a distance to a nearest obstacle that has at least a specified minimum value, if at least one potential collision and / or at least one potential failure to meet the specified minimum distance is identified during the check.

[0039] In a continuing education program, the system and its resources exhibit the following characteristics:

[0040] Means for planning the intended route, which is checked based on a route length.

[0041] In one version, the system or its means exhibit:

[0042] Means of selecting a distance-maintaining operating mode for path planning to meet the distance criterion. 120905P524PC 7 / 15 KUKA Deutschland GmbH 2023P00019 WO

[0043] In one embodiment, the means for planning at least one path for the mobile robot is configured to plan the path using an informed search algorithm, in particular an A* algorithm, and / or on the basis of a path length, such that regions are preferred which are assigned a distance to a nearest obstacle that has at least a predetermined minimum value if the distance criterion is met.

[0044] In one embodiment, the means for planning at least one path for the mobile robot is configured to plan the path based on the provided map in such a way that, between a starting region and a target region, or in one embodiment from the starting region and / or to the target region, only regions are visited that have a distance to the nearest obstacle that has at least the specified minimum value, if the distance criterion is met.

[0045] In one version, the system or its means exhibit:

[0046] Means of providing the map based on a, in particular sensory, detection of the mobile robot's environment.

[0047] According to one embodiment of the present invention, a mobile robot is equipped, in particular in terms of hardware and / or software, especially programming, to carry out a method described herein and / or has a system described herein.

[0048] A system and / or means according to the present invention can be configured in hardware and / or software, in particular comprising at least one processing unit, preferably a microprocessor unit (CPU), graphics card (GPU), or the like, preferably connected to a memory and / or bus system via data or signals, and / or comprising one or more programs or program modules. The processing unit can be configured to execute instructions implemented as a program stored in a memory system, to acquire input signals from a data bus, and / or to output signals.

[0049] to provide a data bus. A storage system can have one or more, in particular different, storage media, in particular optical, magnetic, solid-state and / or other non-volatile media. The program can be designed in such a way that it embodies or is capable of executing the procedures described herein, so that the processing unit can execute the steps of such procedures and thus, in particular, plan at least one path for the mobile robot or operate the mobile robot. A computer program product can, in one embodiment, have a storage medium, in particular a computer-readable and / or non-volatile one, for storing a program or instructions, or with a program or instructions stored thereon. In one embodiment, the execution of this program or these instructions by a system or...a control system, in particular a computer or an arrangement of several computers, the system or the control system, in particular the computer(s), for carrying out a procedure described herein or one or more of its steps, or the program or instructions for this purpose are set up.

[0050] In one embodiment, one or more, in particular all, steps of the procedure are fully or partially computer-implemented, or one or more, in particular all, steps of the procedure are fully or partially automated, in particular by the system or its means.

[0051] Further advantages, features, and advantageous embodiments of the present invention will become apparent from the dependent claims and the exemplary embodiments. These are shown, in part schematically:

[0052] Fig. 1 : a method for operating a mobile robot according to an embodiment of the present invention;

[0053] Fig. 2: the mobile robot; and

[0054] Fig. 3: A card provided according to the procedure. 120905P524PC 9 / 15 KUKA Deutschland GmbH 2023P00019 WO

[0055] Fig. 1 shows a method for operating a mobile robot 10 according to an embodiment of the present invention, comprising a (method for) path planning for the mobile robot according to an embodiment of the present invention.

[0056] The robot 10 (see Fig. 2) has a controller 11 for operating the robot and, in one version, for path planning. In a modified version, the path planning can also be carried out by an external computer 11' and communicated to the controller 11. The robot 10 also has at least one camera 12 for sensory perception of the robot's environment.

[0057] In step S10, a map of the environment is generated, for example using camera 12. Obstacles Hi and H2 are identified on this map, and corresponding regions, such as cells or nodes of a graph, are marked as occupied. Furthermore, the map, which is schematically illustrated in Fig. 3, assigns a distance to the nearest obstacle to different regions of the environment, such as different cells or nodes of the graph.

[0058] This is illustrated by example in Fig. 3: the regions located at the edge (obstacle Hi) and the regions immediately adjacent to obstacle H2 are assigned the distance (value) “1”, regions that are further away from the edge and obstacle H2 are assigned the corresponding distance (value) “2” or “3”.

[0059] In step S20, an intended path W1 is planned as the shortest path from a starting region S to a target region Z in a manner known per se, as shown in Fig.

[0060] 3 is indicated schematically.

[0061] In step S30, this intended path W1 is checked for potential collisions. If no potential collision is detected (S30: "N"), the mobile robot is commanded to follow this path (Fig. 1: step S40).

[0062] If a potential collision is detected (S30: “Y”), an alternative route W* is planned based on the provided map such that, from a starting region S to a destination region Z, only regions are (or may be) visited, and thus regions120905P524PC 10 / 15 KUKA Deutschland GmbH 2023P00019 WO

[0063] Preferred are those to which a distance to the nearest obstacle is assigned that has at least a predetermined minimum value, in the exemplary embodiment (at least) the distance (value) “2” (Fig.

[0064] 1: Step S35). For this purpose, only the corresponding regions with sufficient distance (value) are provided to an A* algorithm as regions (of a corresponding graph) for approaching or searching.

[0065] The mobile robot is then commanded to travel along this path W* (Fig. 1: step S40).

[0066] In the present disclosure, "has an X" does not generally imply an exhaustive list, but is a shorthand for "has at least one X" and also includes "has two or more X" as well as "has Y in addition to X". Although exemplary implementations were explained in the preceding description, it should be noted that a multitude of variations are possible. For example, in step S30, it can alternatively be checked whether a distance-maintaining operating mode is selected as a result of a corresponding user input. Furthermore, it should be noted that the exemplary implementations are merely examples and are not intended to restrict the scope of protection, the applications, or the structure in any way.Rather, the preceding description provides the skilled person with a guideline for implementing at least one exemplary embodiment, whereby various modifications, particularly with regard to the function and arrangement of the described components, can be made without leaving the scope of protection as defined by the claims and these equivalent combinations of features. 120905P524PC 11 / 15 KUKA Deutschland GmbH.

[0067] 2023P00019 WO

[0068] List of reference signs

[0069] 10 mobile robots

[0070] 11 Control

[0071] 11' Computer

[0072] 12 Camera

[0073] Hi, H2 obstacle

[0074] S Start region

[0075] Which shortest route

[0076] W* planned route

[0077] Target region Z

Claims

120905P524PC 12 / 15 KUKA Deutschland GmbH 2023P00019 WO Patent claims 1. Method for path planning for a mobile robot (10), wherein: a map of the mobile robot's environment, which assigns a distance to the nearest obstacle to different regions of the environment, is provided (S10); and at least one path for the mobile robot is planned (S20, S35); this path is planned on the basis of this provided map in such a way that regions are preferred which are assigned a distance to a nearest obstacle which has at least a specified minimum value (S35), if a distance criterion is met.

2. The method according to claim 1, characterized in that: an intended path for the mobile robot is checked for potential collisions and / or a potential breach of a specified minimum distance to the nearest obstacle (S30); and An alternative route is planned based on the provided map in such a way that regions are given preference which are assigned a distance to the nearest obstacle which has at least a specified minimum value (S35), if at least one potential collision and / or at least one potential failure to maintain the specified minimum distance is identified during the review.

3. Method according to claim 2, characterized in that: the intended route, which is being checked, is planned based on a route length; and / or The verification will be carried out using the provided card.

4. Method according to one of the preceding claims, characterized in that the distance criterion is met if a distance-maintaining operating mode is selected for path planning.

5. Method according to one of the preceding claims, characterized in that the path is based on the provided map. 120905P524PC 13 / 15 KUKA Deutschland GmbH 2023P00019 WO - using an informed search algorithm, in particular an A* algorithm; and / or - based on a path length It will be planned if the distance criterion is met.

6. Method according to one of the preceding claims, characterized in that the route is planned on the basis of the provided map in such a way that only regions are visited between a starting region (S) and a destination region (Z) which have a distance to a nearest obstacle that has at least the specified minimum value.

7. Method according to one of the preceding claims, characterized in that: the map is provided based on a, in particular sensory, assessment of the mobile robot's environment; and / or Regions of the map are discrete cells and / or nodes of a graph.

8. Method for operating a mobile robot (10), wherein: a path for the mobile robot is planned according to a method according to one of the preceding claims; and the mobile robot is commanded to travel along this planned route (S40).

9. Path planning system for a mobile robot (10) which is configured and / or comprises a method according to any one of the preceding claims 1-7: Means of providing a map of the mobile robot's environment, assigning a distance to the nearest obstacle to different regions of the environment; and Means for planning at least one path for the mobile robot, wherein this path is planned on the basis of this provided map in such a way that regions are preferred which are assigned a distance to a nearest obstacle that has at least a predetermined minimum value, if a distance criterion is met. 120905P524PC 14 / 15 KUKA Deutschland GmbH 2023P00019 WO 10. Mobile robot (10) configured to perform a method according to claim 8 and / or comprising a system according to claim 9.

11. Computer program or computer program product, wherein the computer program or computer program product, in particular stored on a computer-readable and / or non-volatile storage medium, contains instructions which, when executed by one or more computers or a system according to claim 9 or 10, cause the computer(s) or system to perform a method according to any one of claims 1 to 8.

Images