Agricultural driving robot

Abstract

The invention relates to an agricultural driving robot (1) having a control device for autonomous navigation between a starting point (3) and a destination (4) along a route, wherein the control device is configured to carry out the following steps: - reading in the starting point (3) and the destination (4) on an environment map; - reading in or determining a plurality of connecting lines (6, 7) and / or at least one connecting area (8) between the starting point (3) and the destination (4); - determining at least two different routes between the starting point (3) and the destination (4) which lead along the predefined connecting lines (6, 7) and / or are each completely within the at least one predefined connecting area (8); and - controlling the driving robot (1) such that the driving robot (1) autonomously drives along the at least two different routes.

Description

[0001] AGRICULTURAL DRIVING ROBOT

[0002] The invention relates to an agricultural driving robot with a control device for autonomous navigation between a starting point and a destination point along a route.

[0003] Many tasks in a barn or farmyard area of ​​a farm involve the transport of materials. For example, animal feeding systems are often used. In a central area, the so-called "kitchen," feed rations are mixed based on various stored basic ingredients as needed and promptly, and then distributed along so-called "feed lanes" for feeding the animals. Another example involves the removal of animal excrement.

[0004] In order to be able to carry out these tasks as autonomously as possible and with minimal personnel input, automated systems and devices have been established for these different applications in the agricultural sector.

[0005] WO 2008 / 097080 A1 discloses an autonomous feeding system for animals, such as cows. A central component of this system is an autonomously driving vehicle with a feed container that can be filled in the aforementioned kitchen. The feed is automatically transported to the unloading points and dispensed there by tipping the feed container.

[0006] Various options are described for the vehicle's movement, for example, a route defined by pre-laid rails. As an alternative, autonomous navigation using sensors or path markers is described. Navigation based on a radio positioning system, such as GPS (Global Positioning System), is also described. To ensure easy installation of such a system and flexible adaptation to changing conditions in a stable or yard area of ​​a farm, a design that is not tied to pre-laid rails or other guidance systems is preferred.

[0007] In order to be able to feed animals efficiently and within the available time, even on a larger farm, for example, feeding robots with filling quantities ranging from several hundred kilograms to several tons are used. To ensure maneuverability within a barn, such agricultural robots are usually equipped with hard tires that are relatively narrow for the weight of the robot. Depending on the number of animals, several trips per day between the kitchen and one or more unloading points are necessary to feed the animals. Over time, this leads to the formation of ruts along the routes of the autonomous agricultural robot, especially on softer ground.It should be noted that due to the heavy weight of the driving robot, even a paved surface is considered a soft surface, in which ruts will develop over time. However, such ruts pose an accident risk for people using the same traffic areas as the driving robot and also lead to undefined driving behavior for the driving robot, even leading to the driving robot swerving in a pronounced rut.

[0008] The problem of rutting is generally known in autonomous vehicles. For example, the publication US 2020 / 0150656 A1 describes an autonomous truck used on construction sites and in mining. This autonomous truck leaves ruts in muddy ground during a single trip. When traveling along the same route again, the route is varied so that the truck does not drive through the same rut again, thus not deepening it, but instead drives slightly offset, widening the resulting rut and thus compensating for it. A camera is used to detect the rut already left behind and drive offset from it.

[0009] This method is therefore well-suited for autonomous vehicles moving on very soft ground, where even a single trip leaves deep ruts. However, the system is unsuitable for preventing the formation of ruts that only develop after frequent travel along the same route, as is the case with the autonomous agricultural robots mentioned above.

[0010] It is therefore an object of the present invention to provide an autonomously driving agricultural robot that prevents the formation of ruts in a stable or farmyard area.

[0011] This problem is solved by an autonomously driving agricultural robot having the features of the independent claim. Advantageous embodiments and further developments are the subject of the dependent claims.

[0012] An autonomously driving agricultural robot of the type mentioned above is characterized by a control system configured to perform the following steps: The starting point and the destination point are read on a map of the environment. Furthermore, a plurality of connecting lines and / or at least one connecting area between the starting point and the destination point are read or determined. At least two different routes between the starting point and the destination point are then determined, which lead along the specified connecting lines and / or each lie entirely within the at least one specified connecting area. The control device controls the robot so that the two routes are driven autonomously by the robot.

[0013] Such an agricultural driving robot can be designed, for example, as a feeding robot, a bedding robot or an excrement collection robot.

[0014] The connecting lines or at least one connecting surface between the starting point, which is specified externally, and the destination point, enable the driving robot to vary the respective route within the specified alternatives when navigating at least twice, and usually multiple times, between the starting point and the destination point, without relinquishing control over possible routes. This achieves the maximum possible variation to avoid rutting while simultaneously ensuring the necessary safety and predictability of the routes taken by the driving robot. In the typically confined stable and yard areas, which are also used by people, safety and predictability are essential prerequisites for permitting route variations.

[0015] In an advantageous embodiment of the agricultural driving robot, the plurality of connecting lines and / or the at least one connecting surface are predefined and entered into the environmental map and can be read by the control device. Alternatively or additionally, at least some of the plurality of connecting lines and / or the at least one connecting surface can be determined automatically based on a predefined connecting line and based on predefined boundary conditions. Predetermining the connecting lines or connecting surface(s) allows for maximum individual adaptation to local conditions and thus maximum control over the possible driving routes. Automatic determination simplifies the setup process for the user, yet allows them to influence the possible driving routes via the boundary conditions.

[0016] As a boundary condition, a maximum distance of the connecting lines and / or an edge of the at least one connecting surface from the predefined connecting line can be specified. Furthermore, it can be provided to define at least one non-drivable area as a boundary condition, wherein the connecting lines and / or the at least one connecting surface are then automatically determined such that no section of them lies in the at least one non-drivable area. In this way, the possible travel routes can be influenced via an exclusion criterion, whereby large areas can initially be permitted, which can then be specifically restricted in certain, usually only small, sub-areas. This procedure typically leads to a large number of possible different travel routes.

[0017] The possible routes can run from the starting point to the destination point along one of the connecting lines. However, it is also conceivable that at least two of the connecting lines intersect, and that at least one of the determined routes runs partially along the two intersecting connecting lines. In this way, the total number of possible routes for a given set of connecting lines can be further increased.

[0018] In a further advantageous embodiment of the agricultural driving robot, the determined route is randomly selected by the control device. Alternatively or additionally, it is also possible to select the determined route according to a predefined scheme. Routes can be determined and / or selected using methods supported by artificial intelligence (AI). Neural networks or adaptive algorithms, such as Q-learning, can be used for this purpose.

[0019] In a further advantageous embodiment of the agricultural driving robot, determined and actually driven routes are logged. For the resulting log, not only the route but also the conditions under which the route was driven can be recorded. Such conditions can affect the driving robot itself, in particular its current weight. For this purpose, the driving robot is preferably equipped with a weighing device for determining the load weight, which makes it possible to determine the current total weight of the driving robot at any time based on weighing measurements, and thus the current absolute load on the ground.

[0020] Furthermore, the conditions can include environmental conditions, particularly humidity. The conditions can also relate to the surface on which the robotic vehicle travels, particularly its load capacity and / or susceptibility to rutting. This logged information is then preferably taken into account when determining routes. In this way, the actual relative load on a specific route section can be logged and used as a basis for subsequent route selection.

[0021] The invention is explained in more detail below using exemplary embodiments and figures. The figures show:

[0022] Figure 1 is an oblique view of an example of an autonomous agricultural driving robot; and

[0023] Figures 2-4 each show a schematic representation to illustrate the navigation of a driving robot between a starting point and a destination point.

[0024] Figure 1 shows an example of an autonomously driving agricultural robot 1 in an oblique view. The navigation method described below for planning routes between a starting point and a destination can be carried out, for example, with this driving robot 1.

[0025] In this example, the driving robot 1 is designed as a so-called "feeding robot" that is configured to pick up feed from a dispensing point, mix it automatically, and unload it at one or more feeding stations. It should be noted that the navigation method described below can also be used by driving robots for other agricultural tasks in a stable or farmyard area. The same reference symbols identify the same or similarly acting elements in all figures. For reasons of clarity, not every element in every figure is provided with a reference symbol. In the description, the terms "right" and "left" refer to the respective representation of the figure. The terms "top" and "bottom," on the other hand, refer to the natural orientation of the driving robot. The terms "front" and "rear" refer to a forward direction of travel 2 of the driving robot 1.The forward direction of travel 2, which is indicated in Figure 1 by a directional arrow, represents the main direction of travel of the driving robot 1.

[0026] The driving robot 1 has two main components, a chassis 100 and a body 110.

[0027] The chassis 100 is preferably universally applicable and can, if necessary, be used together with various functional units. Figure 1 shows only cladding and / or protective elements of the chassis 100, specifically a circumferential apron 102, a front safety bumper 103, and a rear safety bumper 104, as well as one of a total of four wheels, specifically a drive wheel 101. In addition to a further drive wheel located on the same axle as the visible drive wheel 101, there are two swivel wheels hidden beneath the apron 102 in Figure 1. One of the swivel wheels is located at the front and one at the rear of the chassis 100. The swivel wheels are arranged centrally in the lateral direction. In the present exemplary embodiment of a feeding robot, the apron 102 also functions as a feed pusher, which can be used to push together feed that has already been unloaded.

[0028] The structure 110 essentially determines the functionality of the driving robot and thus its intended use within the stable or farm area.

[0029] In the mobile robot 1, which in this case is equipped as a feeding robot, the structure 110 has a feed container 111 as a key component. The feed to be distributed is held in the feed container 111 and can be mixed, if necessary, during filling, in a loading station, and / or during travel using a mixing device not visible in Figure 1. A feed ejector 112 is provided for dispensing the feed, which is moved by means of a conveyor belt. Depending on the direction of travel of the conveyor belt, feed can be dispensed to either side of the feeding robot. The arrangement of the feed container 111 and the feed ejector 112 represent the functional unit of the mobile robot 1, as they provide its specific functionality and thus define it as a feeding robot.

[0030] The structure 110 further comprises a casing, which is made up of a plurality of casing elements, typically casing panels 113. The casing panels 113 can preferably be removed separately to gain access to underlying components and their maintenance or replacement. Externally accessible elements are integrated into the casing, for example, charging contacts 114 and operating and / or display elements on the opposite end face of the driving robot 1 (not visible here). The driving robot 1 is configured to automatically drive into a charging station, where the charging contacts 114 are contacted to recharge batteries or other power storage devices of the driving robot 1.

[0031] Driving robot 1 is also equipped with a navigation system that enables navigation in the stable or farmyard area without permanently installed infrastructure elements such as rails or guide cables. For this purpose, the driving robot is equipped with a number of sensors that are either integrated into the cladding or protrude from the cladding.

[0032] Figure 1 shows two Lidar (Light Detection and Ranging) sensors 115, which are used for object detection to assist navigation. The two Lidar sensors 115 are arranged at the front and rear of the driving robot, respectively. Alternatively or additionally, other 3-dimensional imaging systems can be used, e.g., Time-of-Flight (ToF) cameras or a stereoscopic camera system. Furthermore, it can be provided to arrange an optical camera at the front and, if necessary, at the rear in the direction of travel. The cameras are then used for object or step detection or to provide additional navigation support. The cameras can be tilted downwards, in particular to be able to record and thus monitor the ground area directly in front of the driving robot 1 in both directions of travel (i.e., when driving forward and backward).Furthermore, ultrasonic sensors 116 are distributed around the circumference of the driving robot 1 on the sides in the lower area of ​​the cladding and on the front sides as distance sensors to nearby obstacles.

[0033] Further sensors, not visible here, are mechanical sensors that detect a force acting on one or both of the safety bumpers 103, 104. For this purpose, the respective safety bumper 103, 104 can, for example, be movably mounted, so that when moved against a spring force, one of possibly several sensors is activated. In an alternative embodiment, the safety bumper 103, 104 can be formed in an outer region from an elastically deformable material, in particular a foam, into which a sensor is incorporated, which detects a deformation preferably along the entire edge of the safety bumper 103, 104. In this way, a collision with an obstacle is advantageously dampened and simultaneously detected.

[0034] The driving robot 1 has at least one control device that controls the driving robot's actuators, including drive motors, and reads and evaluates sensor signals. The control device also performs navigation tasks and maintains a stored environmental map, which serves, among other things, to localize the driving robot in its environment. The map is preferably created by the driving robot 1 itself by evaluating the sensor data acquired during various journeys using a so-called SLAM (Simultaneous Localization and Mapping) process. It may be subsequently manually revised and / or supplemented if necessary.

[0035] In addition, the control device is equipped with or coupled to communication interfaces, in particular for wireless communication. The communication interfaces serve, for example, to connect to a higher-level operations management system that coordinates the use of the driving robot 1. Furthermore, the communication interfaces can be used to control the driving robot 1 using a remote control.

[0036] Figure 2 shows a section of a two-dimensional map used by the driving robot 1 for navigation as part of its SLAM navigation method. The map is also referred to as an environmental map and is a digital image of the environment in which the driving robot 1 moves. The section shown in Figure 2 is, for example, part of a larger map of the agricultural operation on which the driving robot 1 is deployed. Typically, the map used by the driving robot 1 comprises a large number of points connected by predefined connecting lines, also called routes or route sections.

[0037] The various points can be approached by the driving robot 1 or can be associated with specific actions that the driving robot 1 performs after approaching the point. Such actions include, for example, requesting feed quantities to be added and / or dispensing feed quantities, or similar actions. Navigation of the driving robot 1 typically occurs along the routes connecting the points.

[0038] Figure 2 shows only two such points, a starting point 3 and a destination point 4, as examples. A non-driveable area 5 is drawn directly between the starting point 3 and the destination point 4. This area was, for example, recognized as a non-driveable obstacle by the driving robot 1 itself during exploration of the surroundings and entered into the surroundings map, or was manually specified during post-processing of the surroundings map.

[0039] Furthermore, the plan in Figure 2 shows a predefined connecting line 6 that connects the starting point 3 and the destination point 4 and represents a possible route for the driving robot 1. In this example, the connecting line consists of two straight sections to bypass the non-drivable area 5. The route along the connecting line 6 is also referred to as the original route 6 for ease of naming.

[0040] According to a first exemplary embodiment of a method according to the invention, a number of further connecting lines 7 are specified in the plan shown in Figure 2 in addition to the original route 6. Purely by way of example, three further connecting lines 7 are shown in the illustration in Figure 2, whereby this number is preferably larger in an implementation of the method according to the invention and is chosen as such here solely for reasons of better representation. Routes along each of the further connecting lines 7 represent alternative routes to the original route and are therefore also referred to as alternative routes 7 for the sake of simplicity.

[0041] According to the invention, during successive journeys between the starting point 3 and the destination point 4, the driving robot 1 varies the route actually traveled by preselecting either the original route 6 or one of the possible alternative routes 7. For example, before each journey from the starting point 3 to the destination point 4, a route can be randomly selected from the set of available connecting lines 6, 7. The selection of different routes in successive journeys prevents the driving robot 1 from driving its wheels, e.g., the drive wheels 101, into ruts in the ground in the stable or yard area.

[0042] In the example shown in Figure 2, the connecting lines 6, 7 run essentially parallel to each other. Intersecting connecting lines 6, 7 can also be specified, whereby the driving robot 1 can lay the route in sections along different connecting lines 6, 7. At an intersection point or at several intersection points, the route then changes from one of the connecting lines 6, 7 to another. In this way, the variety of different routes can be further increased.

[0043] The additional connecting lines 7 can be manually entered in a manual revision of the environmental map used by the driving robot 1 for navigation. It is also conceivable that the additional connecting lines 7 are pre-entered into the plan of the driving robot 1 using an automatic algorithm. Boundary conditions can be specified, for example, that the maximum permissible deviation from the original route 6 is limited and that non-driveable areas 5 are taken into account.

[0044] In Figure 3, another connecting line 6 (original route 6) is shown in the same way as in Figure 2 and for the same arrangement of starting point 3, destination point 4 and non-driveable area 5.

[0045] In this exemplary embodiment, no further connecting lines 7 are predefined or determined as possible routes; instead, a connecting surface 8 is specified, which connects the starting point 3 and the destination point 4 as a continuous surface. Within the connecting surface, the driving robot 1 independently determines routes to be traveled between the starting point 3 and the destination point 4, for example, randomly, with the proviso that the routes lie entirely within the area of ​​the connecting surface 8.

[0046] In the illustrated embodiment, the connecting surface 8 is generated automatically by specifying a distance d based on the original route 6. The connecting surface 8 is defined such that its edges lie within a strip with half the width of the distance d from the original route 6. In alternative embodiments, comparable specifications for the automatic determination of the connecting surface 8 are conceivable, for example, that its edge occupies the maximum distance d from the original route 6. Further boundary conditions can be taken into account, for example, that the non-driveable area 5 is to be excluded from the connecting surface 8.

[0047] Finally, Figure 4 shows a third embodiment comparable to Figures 2 and 3. Again, the starting point 3, the destination 4, and the non-driveable area 5 are specified in the same way as in the previous embodiments. An original route 6 connecting the starting point 3 and destination 4 is also indicated.

[0048] In this exemplary embodiment, as in Figure 3, a connecting surface 8 is defined within which the driving robot 1 independently determines its route, varying it as diversely as possible from trip to trip. However, in this exemplary embodiment, the connecting surface 8 is not automatically determined by an algorithm based on the original route 6, but is freely defined in advance by the user. It is also possible to define more than one connecting surface 8 connecting the starting and destination points 3, 4.

[0049] It is also conceivable to combine connecting lines and connecting surfaces one after the other. In certain sections, the driving robot 1 then has the option of freely planning its route within the connecting surface, while in other sections it must follow a connecting line that it can select from a set of predefined connecting lines. It can also be provided that only one connecting line is defined in a section, which must then be selected for that section of the route.

[0050] In all three exemplary embodiments, it can be provided that the same connecting lines 6, 7 or the same connecting surfaces 8 are used not only for a journey from the starting point 3 to the destination point 4, but also for a journey in the opposite direction, i.e. from the destination point 4 to the starting point 3. Alternatively, it can also be provided to use different connecting lines 6, 7 or connecting surfaces 8 for different directions. This can be useful, for example, in cases in which the driving robot 1 travels in both directions under different conditions, e.g. fully loaded and therefore heavier in one direction (away from the kitchen) and emptied and therefore lighter in the opposite direction (towards the kitchen). As already mentioned, it can be provided in all three exemplary embodiments that the route actually traveled is randomly selected from the set of possible routes.Alternatively, it is also conceivable that the actual route is selected from the pool of possible routes according to a predefined pattern from trip to trip. For example, a distance can be defined by which successively driven routes are offset laterally.

[0051] In an advantageous embodiment, the driving robot 1 logs how often and, if applicable, at what time and under which conditions the various routes are actually traveled. An even distribution can then be achieved by selecting routes that have not yet been traveled and are more likely to be selected. Conditions prevailing when traveling the possible routes can be recorded and taken into account. For example, the driving robot 1 designed as a feeding robot generally has a weighing device with which the payload in the feed container 111 can be recorded. From the payload determined during the weighing, the driving robot 1 can determine its current total weight and thus weight the route taken in its log.

[0052] It is also conceivable, for example, that for outdoor journeys, consideration may be given to whether the ground is dry or wet from current or previous rain, which also impacts the load for the corresponding route section during a journey. The selection of possible routes then takes into account not only an equal distribution with regard to the number of journeys made, but also an equal distribution with regard to the load on the ground along the respective route.

[0053] Furthermore, the extent to which a route or a specific route section is susceptible to certain loads or to certain loads under certain conditions (weight of the driving robot 1; environmental or ambient conditions such as wet / dry) can also be taken into account. Thus, the actual relative load of a specific route section is recorded and used as the basis for subsequent route selection.

[0054] In one embodiment, route selection and ensuring even load distribution across route sections can be achieved using deterministic algorithms. Alternatively or additionally, route selection and the avoidance of uneven load distribution across route sections can also be performed using artificial intelligence. For example, a neural network can be used, trained using available routes and information on the load capacity of route sections, possibly taking environmental conditions and load conditions into account. Instead of neural networks, adaptive algorithms, such as Q-learning, can also be used.

[0055] Furthermore, it can additionally be provided to take into account the currently recorded condition of the ground when selecting the routes. The ground can, for example, be imaged by a camera attached to the driving robot 1 and the condition can be determined by evaluating the image. The evaluation can also be carried out with the support of AI. The camera used can in particular be a 3-dimensional camera or camera system, e.g. a ToF camera or a stereoscopic camera system. Alternatively, 1- or 2-dimensional distance measuring systems, e.g. ultrasonic sensors, can be used to image the ground. Information from a lidar system, e.g. the lidar sensors 115 used for navigation, can also be used to determine the condition of the ground.

[0056] Based on the condition, for example, statements can be made about possibly already formed or emerging ruts, so that existing or emerging ruts are no longer or at least less frequently traveled again to prevent them from becoming further deepened. The condition can also include the degree of moisture in the subsoil, which may influence its load-bearing capacity. Reference symbol

[0057] 1 driving robot

[0058] 2 direction of travel

[0059] 3 Starting point

[0060] 4 Destination point

[0061] 5 non-driveable area

[0062] 6 Connecting line (original route)

[0063] 7 Connecting line (alternative route)

[0064] 8 Connecting surface

[0065] 100 chassis

[0066] 101 Drive wheel

[0067] 102 Apron feed pusher

[0068] 103 front safety bumper

[0069] 104 rear safety bumper

[0070] 110 Structure

[0071] 111 feed containers

[0072] 112 Feed ejection

[0073] 113 cladding panels

[0074] 114 charging contacts

[0075] 115 Lidar sensor

[0076] 116 Ultrasonic sensor

Claims

Claims 1. Agricultural driving robot (1) with a control device for autonomous navigation between a starting point (3) and a destination point (4) along a route, characterized in that the control device is designed to carry out the following steps: - Reading the starting point (3) and the destination point (4) on a map of the surrounding area; - reading in or determining a plurality of connecting lines (6, 7) and / or at least one connecting surface (8) between the starting point (3) and the target point (4); - determining at least two different routes between the starting point (3) and the destination point (4), which lead along one of the predetermined connecting lines (6, 7) and / or which each lie completely within the at least one predetermined connecting area (8); and - Controlling the driving robot (1) to autonomously travel the at least two different routes by the driving robot (1).

2. Agricultural driving robot (1) according to claim 1, wherein the plurality of connecting lines (6, 7) and / or the at least one connecting surface (8) are predetermined and entered in the environmental map.

3. Agricultural driving robot (1) according to claim 1 or 2, wherein a part of the plurality of connecting lines (7) and / or the at least one connecting surface (8) is automatically determined by the control device on the basis of a predetermined connecting line (6) and on the basis of predetermined boundary conditions.

4. Agricultural driving robot (1) according to claim 3, wherein a maximum distance of the connecting lines (7) and / or an edge of the at least one connecting surface (8) from the predetermined connecting line (6) is specified as a boundary condition.

5. Agricultural driving robot (1) according to claim 3 or 4, in which at least one non-drivable area (5) is specified as a boundary condition, wherein the connecting lines (7) and / or the at least one connecting surface (8) are determined such that no section of them lies in the at least one non-drivable area (5).

6. Agricultural driving robot (1) according to one of claims 1 to 5, wherein at least one of the determined routes runs from the starting point (3) to the destination point (4) along one of the connecting lines (6, 7).

7. Agricultural driving robot (1) according to one of claims 1 to 6, in which at least two of the connecting lines (6, 7) intersect and in which at least one of the determined routes runs in sections on the two intersecting connecting lines (6, 7).

8. Agricultural driving robot (1) according to one of claims 1 to 7, wherein the determined route is randomly selected by the control device.

9. Agricultural driving robot (1) according to one of claims 1 to 8, wherein the determined route is selected by the control device according to a predetermined scheme.

10. Agricultural driving robot (1) according to one of claims 1 to 9, in which routes are determined and / or selected by the control device with the aid of KI methods.

11. Agricultural driving robot (1) according to one of claims 1 to 10, in which determined and actually driven routes are logged by the control device.

12. Agricultural driving robot (1) according to claim 11, wherein the protocol records conditions under which the route is driven.

13. Agricultural driving robot (1) according to claim 12, wherein the conditions relate to the driving robot (1), in particular its respective current weight.

14. Agricultural driving robot (1) according to claim 13, comprising a weighing device for determining a load weight.

15. Agricultural driving robot (1) according to claim 14, wherein the control device is configured to determine the current weight of the driving robot (1) on the basis of weighings by the weighing device.

16. Agricultural driving robot (1) according to claim 12 to 15, wherein the conditions are ambient conditions, in particular humidity.

17. Agricultural driving robot (1) according to one of claims 12 to 16, wherein the conditions relate to a surface on which the driving robot (1) travels, in particular a load-bearing capacity and / or susceptibility with regard to the formation of ruts.

18. Agricultural driving robot (1) according to one of claims 11 to 17, wherein the control device is configured to take the logged information into account when determining the routes.

19. Agricultural driving robot (1) according to one of claims 1 to 18, designed as a feeding robot, as a bedding robot or as an excrement collecting robot.

Images