WO2022132008A1

WO2022132008A1 - Method and control device for determining floor condition in a dwelling area

Info

Publication number: WO2022132008A1
Application number: PCT/SE2021/051252
Authority: WO
Inventors: Ilka Klaas
Original assignee: Delaval Holding Ab
Priority date: 2020-12-17
Filing date: 2021-12-14
Publication date: 2022-06-23
Also published as: EP4262370A1

Abstract

The present disclosure generally relates to the field of farming and more specifically it relates to a method and a control device for determining floor condition in a dwelling area. According to a first aspect, the disclosure relates to a computer implemented method for determining floor condition in a dwelling area for a herd of animals. The method comprises obtaining S1, from a walking monitoring system arranged in the dwelling area, walking data indicative of walking characteristics of one or more individual animals located in the dwelling area, and determining S3 the floor condition based on walking characteristics indicated by the obtained walking data. The method enables a farmer to determine the floor condition, whereby the farmer can intervene immediately if floor quality is unacceptable. Consequently, accidents and animal injury may be avoided.

Description

Method and control device for determining floor condition in a dwelling area

Technical field

The present disclosure generally relates to the field of farming and more specifically it relates to a method and a control device for determining floor condition in a dwelling area for a herd of animals. The disclosure also relates to a computer program configured to implement the method and to a computer program product.

Background

When floors of a barn are too hard or slippery, animals will typically adapt by shortening their strides and walk slower than on flooring with good grip on the surface. On slippery flooring animals will typically take shorter strides and put more weight on their toe tip, which increases the risk of lameness, e.g., sole haemorrhages. On slippery floors, animals can also fall and get traumatized. For example, animals in heat with increased activity and jumping on the backs of each other could be in particular danger of slipping and falling and as a result of slippery flooring.

If the reason for the floor being too slippery is the smooth concrete surface, then the floor can be grooved to overcome this. Ultimately, the floor can be replaced with a newer/different floor. If a high amount of manure and urine on the floor is the cause of slipperiness and changed stride pattern, then farmers could adapt their cleaning management of the alleys in the bam to mitigate slipperiness and provide a safer walking. However, to enable taking measures when the floor condition is unacceptable, there is need for a method of determining the floor condition in the bam.

Summary

It is an object of the disclosure to alleviate at least some of the problems mentioned above. Thus, it is an object to provide a method for determining floor condition in a dwelling area such that suitable measures can be taken before animals are affected by poor floor quality.

According to a first aspect, the disclosure relates to a computer implemented method for determining floor condition in a dwelling area for a herd of animals. The method comprises obtaining, from a walking monitoring system arranged in the dwelling area, walking data indicative of walking characteristics of one or more individual animals located in the dwelling area, and determining the floor condition based on walking characteristics indicated by the obtained walking data. The method enables a farmer to determine the floor condition, whereby the farmer can intervene immediately if floor quality is unacceptable. Consequently, accidents and animal injury may be avoided.

In some embodiments, the walking data represent walking characteristics of a group of animals and wherein the individual floor conditions are floor conditions at different points in time. By basing the determination on group behaviour, a more accurate determination of floor conditions may be achieved.

In some embodiments, the individual floor conditions are floor conditions in different parts of the dwelling area. Thereby, the determination based on waking data from one or a few animals is enabled.

In some embodiments, the walking characteristics comprises one or more of: stride length, walking speed, walking rhythm, animals slipping, animals sliding, animals falling. Those are all walking characteristics that may be affected by floor condition and which may therefore be used singly or in combination to determine the floor condition.

In some embodiments, the method comprises detecting a variation among walking characteristics indicated by individual walking data that are expected to indicate similar walking characteristics under similar floor conditions and determining unacceptable floor conditions based on the detected variation. Hence, by monitoring for a change or shift in walking behaviour, altered floor condition may be detected in a simple way. In some embodiments, the variation is a variation among walking characteristics indicated by walking data representing individual parts of the dwelling area. In some embodiments, the variation is a time variation among walking characteristics indicated by walking data representing walking characteristics of a group of animals at different points in time.

In some embodiments, the determining comprises comparing the obtained walking characteristics with reference data. In some embodiments, the reference data is based on previously recorded walking data of the plurality of animals. In some embodiments, the determining comprises evaluating the obtained walking data using one or more predetermined criteria. Hence, any suitable algorithm of rule may be defined.

In some embodiments, the method comprises performing an action in response to the determining revealing that the floor quality is unacceptable. Thereby, an unacceptable floor condition may be remedied immediately, sometimes even without human interaction. In some embodiments, the action comprises one or more of, initiating a cleaning session, triggering an alert signal, initiating floor monitoring.

According to a second aspect, the disclosure relates to a control device configured to determine a floor condition, the control device being configured to perform the method according to any embodiment of the first aspect.

According to a third aspect, the disclosure relates to a computer program comprising instructions which, when the program is executed by a computer, cause the computer to carry out the method according to the first aspect.

According to a fourth aspect, the disclosure relates to a computer-readable medium comprising instructions which, when executed by a computer, cause the computer to carry out the method according to the first aspect.

Brief description of the drawings

Fig. 1 illustrates an example of a dwelling area.

Fig. 2 illustrates an example walking monitoring system arranged in a dwelling area.

Fig. 3 is a flowchart of the proposed method for determining floor condition in a dwelling area according to the first aspect.

Fig. 4 illustrates different examples of walking data that can be used as a basis for determining a floor condition in a dwelling area.

Fig. 5 illustrates a control device according to the second aspect.

Detailed description

The floor condition of flooring in an area where animals are held (e.g., a concrete or slatted floor in a dairy cow bam) can impact how the animals are walking. When the floor is too hard or too slippery, animals will typically adapt by shortening their stride length. For example, one may see a cow with an arched back without the animal being lame or having hoof lesions when checked in a trimming chute. If several animals within a certain barn group show similar changes to their walking behaviour, this could indicate inadequate condition (or quality) of the flooring. Also, if one and the same animal exhibits different walking behaviour in different areas of the barn, this could indicate inadequate condition (or quality) of the flooring. In addition, on slippery floor, the majority of animals will typically adapt the speed of walking, running and jumping in order to protect themself from falling and injury.

This disclosure is based on the insight that the impact that inadequate floor condition has on animal’s walking characteristics can be utilised to determine the floor condition, e.g., to detect when the floor condition is inadequate. Consequently, suitable measures can readily be taken to remedy an unacceptable floor condition, whereby injuries may be prevented. The floor condition may be performed over time in order to verify that an adjustment performed after an alarm solved the problem.

Fig.1 illustrates a herd of animals 10 in a dwelling area 20, here illustrated as an animal shed containing dairy cows, seen from above. Even though the animals of the illustrated example are cows, the animals 10 may be any arbitrary type of livestock animals, such as dairy animals. However, the herein provided non-limiting examples primarily relate to non-human milk and/or meat producing animals such as cow, goat, sheep, camel, dairy buffalo, yak, etc. Though, even though the proposed solution has been described focusing on dairy cattle, it should be appreciated that it could be used for any kind of livestock that is kept on for example concrete or slatted floor. For example, the solution may be used for beef cattle in winter, beef producing facilities, heifer raising facilities that use activity measurements and location, goats and so on.

Fig. 2 illustrates an example of a walking monitoring system 30 that may be used by the proposed solution. The illustrated walking monitoring system 30 comprises an animal locating system comprising tags 31 , readers 32, a gate monitoring arrangement 35 and a control system 33. In some embodiments, the walking monitoring system 30 also comprises one or more cameras 34. The animal locating system is for example a Real Time Location system, RTLS. An RTLS is a known type of system used to track the location of objects, such as animals 10, in real time using tags 31 (active or passive) attached to animals 10 (e.g., around their necks or in their ears) and readers 32 that receive wireless signals from these tags 31 to determine their locations. In some example, the location of the tags 31 is determined using triangulation techniques or using a GPS arranged in each tag. The wireless communication includes, but is not limited to, a cellular radio, a WiFi radio, a Bluetooth radio, a Bluetooth low energy (BLE) radio, UltraWideBand (UWB) radio or any other appropriate radio frequency communication protocol. The particular number and placement of the readers 32 will depend on the size and shape of a tracking zone, here the dwelling area 20, being monitored.

In some embodiments the tags 31 comprise orientation sensors configured to generate data indicative of the orientation of the tag 31 , such as a three-axis accelerometer assembly or a gyro assembly. The tags 31 may also include other sensors or components.

The cameras 34 are arranged to monitor the dwelling area. In particular the camera is arranged to monitor animals 10 in the dwelling area 20 and their poses. For example, images are captured by the camera 34, from which it is possible to determine the animals’ head positions, back positions and/or spine positions. In some embodiments, the images, or a combination of sequentially captured images, enables determining animal activities, such as animals slipping, animals sliding, animals falling and animals stumbling.

The gate monitoring arrangement 35 is configured to monitor when an animal passes any gate 21 (Fig. 1 ) or another passage in the dwelling area 20. The gates 21 may define floor compartments. The gate monitoring arrangement 35 is configured to detect when an animal moves through a gate for example from floor compartment A to floor compartment B. This is for example done by reading data from the tags 31 when the animals are passing through the gates 21 . This is particularly relevant to keep track of where, i.e. , in which compartment, the animals are in embodiments when there is no other means such as GPS or triangulation available to position the tags 31 . It must be appreciated that the walking monitoring system 30 could be more or less simple. In principle information about the animal’s pose and/or walking speed may be sufficient. Hence, in an example embodiment only data from orientation sensors attached to one or more animals and from a gate monitoring arrangement 35 are used for determining the floor condition. In another embodiment, only data from a RTLS which may already be installed in the dwelling area for other purposes is used.

The control system 33 is configured to receive data from the tags 31 and readers 32. In some embodiments, control system 33 is configured to receive data from the one or more cameras 34 and/or from the gate monitoring arrangement 35. When the walking monitoring system 30 is in use, the location of each tag 31 is tracked within the dwelling area 20 using multi-lateration techniques known in the art, for example using Time Difference of Arrival (TDOA) and Received Signal Strength Indicator (RSSI) techniques. To this end, data from the readers 32 is supplied to a control system 33 that determines, in real-time basis, the instantaneous position of each tag 31 in the dwelling area 20. The control system 33 may be implemented as a computer-based system that is capable of executing computer applications (for example, software programs). An exemplary application of the control system 33 includes a real-time location function, configured to determine a two-dimensional position of the tag 31 within the dwelling area 20. The control system 33 may for example use triangulation of data provided by three or more readers 32 to determine the location of the tags 31 .

The control system 33 is configured to determine a movement of the tags 31 , including for example direction of movement and amount of movement. In some embodiments, the control system 33 is configured to determine an orientation of the tag 31 . In some embodiments, the control system 33 is configured to determine walking characteristics of an animal 10 wearing the tag 31 based on the location, movement and orientation of the animal's tag within the dwelling area 20. As an example, stride length, walking speed and walking rhythm may be determined.

The control system 33 also may have one or more communications interfaces. The communications interfaces may include for example, a modem and/or a network interface card. The communications interfaces enable the control system 33 to communicate with other control devices, e.g., with a control device 100 configured to implement the solution proposed herein. In some embodiments, the control system 33 comprises a control device 100 configured to implement the proposed solution. In other words, the control device 100 that will be further explained in Fig. 5 is in some embodiments an integral part of the control system 33. The communications interface also enables the control system 33 to receive messages and data from the readers 32, cameras 34 and from the gate monitoring arrangement 35 and possibly also directly from the tags 31. The data may be received either directly or via another communications network. The communications network may be any network platform and may include multiple network platforms. Exemplary network platforms include, but are not limited to, a WiFi network, a cellular network, etc.

The proposed solution will now be described in further detail with reference to the flow chart of Fig. 3 and the dwelling area 20 of Figs. 1 and 2. The flow chart in Fig. 3 illustrates the proposed method for determining floor condition in a dwelling area for a herd of animals. The method is for example performed continually while animals are dwelling in the bam. In such a situation the floor condition may shift for example because it needs cleaning or alternatively because of wear, or for any other reason. Other reasons could for example be broken parts or obstacles of the floor, such as a broken boards or metal pieces sticking out from a fence. Such obstacles may herein also be considered bad floor condition.

The method may be implemented as a computer program comprising instructions which, when the program is executed by a computer (for example a processor 101 in the control device 100 (Figs. 2 and 4)), cause the control device 100 to carry out the method. According to some embodiments the computer program is stored in a computer-readable medium (for example a memory or a compact disc) that comprises instructions which, when executed by a computer, cause the computer to carry out the method.

In order to determine the floor condition, the method may comprise a number of steps S1 -S4. However, some of these steps are optional, which is illustrated with dashed lines, and may be performed in none or in solely some embodiments. Further, the described steps may be performed in a different chronological order than the numbering suggests. The method comprises obtaining S1 walking data from a walking monitoring system 30 arranged in the dwelling area 20. Walking data is data that is collected by devices that monitor movement of the animals. The walking data may be collected by devices attached to leg, neck or ear of an animal. Alternatively, the walking data may be collected by other devices in the dwelling area 20, such as cameras 34 or a gate monitoring arrangement 35. The walking data may be obtained from the walking monitoring system 30 using wired or wireless communication. Alternatively, if the method is performed in the control system 33 of the walking monitoring system 30 the walking data may be directly obtained by e.g., reading the data from a memory or similar. If the method is performed remotely from the walking monitoring system, then the walking data may be received via a communication network.

The walking data is indicative of walking characteristics of one or more individual animals 10 located in the dwelling area 20. Examples of walking characteristics that are indicated by the walking data include stride length, walking speed, walking rhythm, an animal slipping, an animal sliding, animals falling, animals stumbling, head position, head movement, back position.

For example, walking data may comprise location data and accelerometer data. From location data it is possible to calculate walking speed. Furthermore, the stride length (i.e., the length of steps) can be determined by combining speed and accelerometer data. In some embodiments, specific key performance indicators, KPIs, defining acceptable walking characteristics may be defined. For example, walking speed patterns and stride patterns measured by the walking monitoring system can be used to create group level KPIs that can be monitored over time.

The walking data to be used as a basis for determining the floor condition should typically be selected to make it possible to differentiate between individual problems related to one animal 10 and unacceptable (e.g., slippery) flooring. There are different ways of selecting the walking data that do all achieve the goal of enabling determination of the floor condition. For example, walking data may be collected from a plurality of animals, in different parts of the bam and/or at different points in time. There are different possibilities, that will now be explained with some examples illustrated in Fig. 4. The diagrams of Fig. 4 illustrate walking data collected at different points in time (x-axis) and in different parts of the dwelling area (y-axis). In the diagrams walking data representing a group is indicated with a thicker line.

In a first example (illustrated in the upper left diagram of Fig. 4), walking data is collected from an animal walking in two zones (A & B) at different points in time. The animal is expected be able to move between the zones A, B, which is indicated by the arrow. Changes in walking behaviour of the individual in these two zones is analysed over time. A deteriorated walking behaviour in one of the zones (e.g., zone B over time) in relation to zone A indicate floor problems in one of the zones. Data can then be analysed to check where the problem is as will be explained below. In other words, in some embodiments walking data represent different points in time and different parts of the dwelling area 20. This first example is applicable to one single animal, but higher quality in determination is achieved if applied to a group of animals.

In a second example (illustrated in the upper right diagram of Fig. 4), walking data represent a group of animals walking in one single zone (here zone B). Change in walking behaviour of a group of animals is studied over time. A change of walking behaviour on group level is an indicator of floor problems. In other words, in some embodiments the walking data represent walking characteristics of a group of animals at different points in time.

In a third example (lower diagram), the walking data represent walking characteristics at one point in time in two groups of animals walking in two different zones (A & B) that have similar flooring. If a group of animals in zone B behave differently than in zone A, this indicates floor problems in one of the areas. Data can then be analysed to check where the problem is as will be explained below. In other words, in some embodiments the walking data represent a group of animals and walking characteristics at one points in time, but in different parts of the dwelling area 20.

All these examples illustrate situations when the obtained walking data are expected to indicate similar walking characteristics as long as the individual floor conditions are the same (or similar) over time t and/or in the different parts A, B. However, if the individual floor conditions differ from each other the walking data are expected to differ from each other to a certain extent. If the walking data would instead be indicative of walking characteristics of one single animal walking on the same floor e.g., Zone A, then a change in walking characteristics may also be caused by an issue with the animal, which is out of scope for this disclosure. Hence, such walking data would provide false alarms when determining floor conditions based on walking behaviour.

In other words, one way to avoid false alarms caused by a problem related to an individual animal 10 is to study the walking characteristics of the animals on group level. Hence, in some embodiments, the walking data represent walking characteristics of a group of animals and wherein the individual floor conditions are floor conditions at different points in time. In this way it is possible to ignore deviating behaviour of single individuals.

Another way to avoid false alarms cause by a problem related to an individual animal is to study the same animal but in different places or zones, as an animal having an individual problem would typically show a deviating behaviour on all these places. Hence, by letting one or more animals walk on for example different parts of a floor (which parts may or may not have different floor qualities), it is possible to differentiate an unacceptable floor condition in one part from a problem related to an individual animal. In other words, one may look at how animals move in one area and compare that with how the animal moves in another area. Stated differently, in some embodiments, the individual floor conditions are floor conditions in different parts of the dwelling area. Parts of the floor are e.g., individual alleys, sections, corridors (or paths) e.g., leading to a milking area, waiting areas, milking yards etc. The same principle may of course be applied on group level for even better accuracy.

Walking data may be studied in different ways. One possibility is look for shifts in walking characteristics. In other words, in some embodiments, the method comprises detecting S2 a variation among walking characteristics indicated by individual walking data that are expected to indicate similar walking characteristics under similar floor conditions. The variation is for example a variation among walking characteristics indicated by walking data representing individual parts of the dwelling area 20. In other examples, the variation is a time variation among walking characteristics indicated by walking data representing walking characteristics of a group of animals 10 at different points in time.

The method further comprises determining S3 the floor condition based on walking characteristics indicated by the obtained walking data. There are a multitude of different ways of analysing the walking characteristics to determine the floor condition. In principle, an algorithm is applied that detects a change in walking characteristics in comparison to an expected value. This comparison may be performed by determining walking characteristics on group level and then making the comparison on group level. Alternatively, the comparison is made per individual and the floor condition is then based on the combined results. Then deviation in walking characteristics of one or a few animals are typically ignored and considered due to issues in the individual animals, rather than in the floor condition.

One way is to monitor the walking characteristics for changes in time or space. A significant shift in walking characteristics of a group of animals could be caused by altered floor conditions. Different parameters may be defined to define a size of a shift corresponding to e.g., unacceptable floor conditions. In other words, in some embodiments, the determining S3 comprises determining S3a unacceptable floor conditions based on the detected variation. For example, one can monitor whether the length of the steps is constant or changes over time. If the steps become shorter in a group of animals, this indicates the floors might be slippery and the animals stand more on the tip of their toes while walking.

In addition to (or as an alternative to) step length, it is possible to analyse the walking speed. If the floor is too slippery, animals will start to move slower to avoid falls and injury. For example, if the average walking speed decreases with more than for example 20% or 2 km/h the floor quality may be considered unacceptable. In another example, the floor condition may be considered unacceptable in a certain area if the average stride length in the certain area deviates with more than for example 10 %, in comparison with another area having a similar flooring. In another example, the floor condition is considered unacceptable if a certain walking KPI representing a group of animals (defined based on a variety of walking characteristics) decreases more than 20%. These parameters will of course depend on the surface and the type of animals etc.

Accuracy of the determining may be improved by analysing behaviour of certain groups of animals. For example, monitoring deviant behaviour of animals in heat could improve the accuracy of the determining, because animals in heat have increased activity and may express lower activity in the peaks when floors are slippery than on good conditions. Alternatively, animals in heat are filtered out from the walking data, in order to have a larger group of animals with more consistent walking (movement) behaviour. For example, animals being afraid of falling may restrict their mounting behaviour, which could be detected by a change in head positions above the animal typical height while standing.

Another way to determine the floor condition is to compare the walking characteristics with reference data. For example, a KPI representing a group of animals (defined based on for example walking speed, stride length and head position) may be compared with a predefined reference value. In other words, in some embodiments, the determining S3 comprises comparing S3b the obtained walking characteristics with reference data.

The reference data may also be previously recorded data. For example, the reference data is an average walking characteristic. Then the floor condition is determined based on a deviation from an average walking characteristic. The reference data may also be based on walking data recorded under controlled floor conditions. In some embodiments, the reference data is based on previously recorded walking data of the plurality of animals. For example, the reference data represent animals walking on floor having an acceptable or “good” condition. One or more thresholds may then be defined which define an acceptable deviation from these thresholds. Thus, in some embodiments, the reference data is based on previously recorded walking data of the plurality of animals.

More or less advanced analysis may be developed to determine S3 the floor condition. In some embodiments, the determining S3 comprises evaluating the obtained walking data using one or more predetermined criteria. The predetermined criteria are for example a rule or an algorithm. For example, an algorithm combining walking data on group level may be used. For example, walking data such as average walking speed (or walking speed pattern) in the whole group; heat activity pattern and mounting behaviour in animals in heat, could be a valuable indicator of unacceptable flooring quality in such an algorithm.

For better understanding of the solution some example criteria will now be described. These criteria could be used singly or in combination. The criteria could be applied to a single animal, but more accurate determining of floor quality is expected when applied to a group of animals. In some embodiments, the one or more predetermined criteria comprises that the floor condition is considered unacceptable when the walking characteristics of a certain amount of the plurality of animals deviate from corresponding reference data. In some alternative embodiments, the one or more predetermined criteria comprises that the floor condition is considered unacceptable when the walking characteristics in a certain part of the dwelling area deviate from corresponding reference data.

As mentioned above, animals will typically shorten their strides and walk slower than on flooring with good grip. Hence, a stride length below a reference value is an indication of unacceptable floor quality. Hence, in some embodiments, the floor quality is considered unacceptable when the stride length of a certain number of animals and/or in a certain part of the dwelling area fall below a stride length reference value.

A stride pattern is an animal’s pattern of walking. Walking involves balance and coordination of muscles so that the animal body is propelled forward in a rhythm, called the stride. An abnormal stride pattern may be caused by an unacceptable floor condition. Hence, in some embodiments, the floor quality is considered unacceptable when a stride pattern of a certain number of animals and/or in a certain part of the dwelling area or deviate to a certain amount from a stride reference pattern. In contrast, if the steps become shorter in combination with a deviating walking rhythm the animals might be lame.

Another possibility is to analyse walking speed. In some embodiments, the floor quality is considered unacceptable upon the walking speed of a certain number of animals and/or in a certain part of the dwelling area falling below a walking speed reference value. Alternatively, a walking speed pattern defining variations in walking speed in time and/or space may be analysed. There may be variations in walking speed e.g., during different times of the day and/or in different parts of the dwelling area. For example, the animals generally walk slower in narrow passages. Expected walking behaviour may be expressed as a walking speed pattern. In some embodiments, the floor quality is considered unacceptable upon the walking speed pattern of a certain number of animals and/or in a certain part of the dwelling area deviating to a certain amount from a reference walking speed pattern.

Incidents of falling or stumbling may also be counted. In some embodiments, the floor quality is considered unacceptable upon the stumbling or slipping frequency of a certain number of animals and/or in a certain part of the dwelling area 20 falling below, and/or in a certain part of the dwelling area exceeding, a reference value.

Another possibility is to monitor the animals head positions. A cow will for example normally hold her head slightly below the back line. When the cow is walking the head only moves a little. If floor condition is bad cows may lower or bob their heads. In some embodiments, the floor quality is considered unacceptable upon the head position of a certain number of animals 10 and/or in a certain part of the dwelling area 20 falling below a reference head position. A reference head position is e.g., that the head is at least partly positioned above the spine of the animal.

Animals, such as cows, normally have a regular walking rhythm in all four legs and walk confidently with a fluid motion, if the floor condition is bad the rhythm may be interrupted and become uneven. In some embodiments, the floor quality is considered unacceptable upon the walking rhythm of a certain number of animals and/or in a certain part of the dwelling area deviating to a certain amount from a reference walking rhythm.

An unacceptable (i.e., “bad”) floor condition may e.g., be caused by wear, other deterioration or need for cleaning. In some embodiments an alarm is generated, when farmers need to intervene to improve flooring quality, because the floor quality is unacceptable. Alternatively, in some embodiments an appropriate action is automatically triggered without human interaction. Stated differently, in some embodiments, the method comprises performing S4 an action in response to the determining S3 revealing that the floor quality is unacceptable.

In some embodiments, the action comprises for example initiating triggering an alert signal. For example, a message, such as an SMS, is sent to predefined user (e.g., the farmer). The alarm signal may alternatively be an audible signal, a visual signal (a lamp is lightened) or any signal perceptible by a human being. The farmer may then take appropriate actions to remedy the unacceptable quality.

In some embodiment an action is automatically triggered. For example, a cleaning session is started. An automatic cleaning session is for example performed by a cleaning robot or an automated manure scraper. Other actions may also be triggered. For example, rinsing, heating, cooling and surface treatment are actions that may be automatically performed by autonomous agricultural equipment.

Fig. 5 illustrates a control device 100 for determining floor condition in a dwelling area 20 for a herd of animals 10 in more detail. In some embodiments, the control device 100 is included in the walking monitoring system 33. The control device 100 should be considered as a functional unit, which may be implemented by one or several physical units. The control device 100 comprises hardware and software. The hardware is for example various electronic components on a for example a Printed Circuit Board, PCB. The most important of those components is typically a processor 101 for example a microprocessor, along with a memory 102 for example EPROM or a Flash memory chip. The software (also called firmware) is typically lower-level software code that runs in the microcontroller. The control device 1000 comprises a communication interface, for example I/O interface or other communication bus, for communicating with the walking monitoring system 50.

The control device 100 also may have one or more communications interfaces. The communications interfaces may include for example, a modem and/or a network interface card. Also, the communications interface enables the control device 100 to receive messages and data from the readers 32 or directly from the tags 31 either directly or via another communications network. The communications network may be any network platform and may include multiple network platforms. Exemplary network platforms include, but are not limited to, a WiFi network, a cellular network, etc. Hence, the control device 100 may be remotely arranged in relation to the walking monitoring system 30 and the dwelling area 20.

The control device 100, or more specifically a processor 101 of the control device 100, is configured to perform all aspects of the method for determining floor condition in a dwelling area 20 for a herd of animals 10. This is typically done by running computer program code stored in the memory 102, in the processor 101 of the control device 100. Hence, the control device 100 is configured to determine a floor condition in the dwelling area 20.

More particularly, the control device 100 is configured to obtain, from a walking monitoring system 30 arranged in the dwelling area 20, walking data indicative of walking characteristics of one or more individual animals 10 located in the dwelling area 20, and to determine the floor condition based on the obtained walking data.

In some embodiments, the control device 100 is also configured to performing S4 an action in response to the determining (S3) revealing that the floor quality is unacceptable.

The terminology used in the description of the embodiments as illustrated in the accompanying drawings is not intended to be limiting of the described method, control device or computer program. Various changes, substitutions and/or alterations may be made, without departing from disclosure embodiments as defined by the appended claims.

The term “or” as used herein, is to be interpreted as a mathematical OR, that is, as an inclusive disjunction; not as a mathematical exclusive OR (XOR), unless expressly stated otherwise. In addition, the singular forms "a", "an" and "the" are to be interpreted as “at least one”, thus also possibly comprising a plurality of entities of the same kind, unless expressly stated otherwise. It will be further understood that the terms "includes", "comprises", "including" and/ or "comprising", specifies the presence of stated features, actions, integers, steps, operations, elements, and/ or components, but do not preclude the presence or addition of one or more other features, actions, integers, steps, operations, elements, components, and/ or groups thereof. A single unit such as for example a processor may fulfil the functions of several items recited in the claims.

Claims

1 . A computer implemented method for determining floor condition in a dwelling area (20) for a herd of animals (10), the method comprising:

- obtaining (S1 ), from a walking monitoring system (30) arranged in the dwelling area (20), walking data indicative of walking characteristics of one or more individual animals (10) located in the dwelling area (20), and determining (S3) the floor condition based on walking characteristics indicated by the obtained walking data.

2. The method of claim 1 , wherein the walking data represent walking characteristics of a group of animals.

3. The method of claim 1 or 2, wherein the walking data indicative of walking characteristics in different parts of the dwelling area (20).

4. The method of any one of the preceding claims, wherein the walking characteristics comprises one or more of: stride length, walking speed, walking rhythm, animals slipping, animals sliding, animals falling, animals stumbling, head position, back position.

5. The method of any one of the preceding claims, wherein the method comprises detecting (S2) a variation among walking characteristics indicated by individual walking data that are expected to indicate similar walking characteristics under similar floor conditions and determining (S3a) unacceptable floor conditions based on the detected variation.

6. The method of claim 5, wherein the variation is a variation among walking characteristics indicated by walking data representing individual parts of the dwelling area (20).

7. The method of claim 5 or 6, wherein the variation is a time variation among walking characteristics indicated by walking data representing walking characteristics of a group of animals (10) at different points in time. The method of any one of the preceding claims, wherein the determining (S3) comprises comparing (S3b) the obtained walking characteristics with reference data. The method of any one of the preceding claims, wherein the determining (S3) comprises evaluating the obtained walking data using one or more predetermined criteria. The method of claim 9, wherein the reference data is based on previously recorded walking data of the plurality of animals. The method of claim 9 or 10, wherein one or more predetermined criteria comprises that the floor condition is considered unacceptable when the walking characteristics of a certain amount of the plurality of animals /or in a certain part of the dwelling area (20) deviates from corresponding reference data. The method of any one of claims 9 to 11 , wherein the floor quality is considered unacceptable upon at least one of the following predetermined criteria being fulfilled:

- the stride length of a certain number of animals and/or in a certain part of the dwelling area falling below a stride length reference value or upon stride pattern deviating to a certain amount from a stride reference pattern,

- the walking speed of a certain number of animals and/or in a certain part of the dwelling area falling below falling below a walking speed reference value or upon a walking speed pattern deviating to a certain amount from a walking speed reference pattern,

- the stumbling or slipping frequency of a certain number of animals and/or in a certain part of the dwelling area (20) exceeding a reference value, - the head position of a certain number of animals and/or in a certain part of the dwelling area falling below being below a reference head position and

- the walking rhythm of a certain number of animals and/or in a certain part of the dwelling area falling below deviating to a certain amount from a reference walking rhythm.

13. The method of any one of the preceding claims, wherein the walking monitoring system comprises one or more of; an animal locating system, accelerometers attached to the animals and one or more cameras arranged to monitor the dwelling area.

14. The method of any one of the preceding claims comprising:

- performing (S4) an action in response to the determining (S3) revealing that the floor quality is unacceptable.

15. The method of claim 14, wherein the action comprises one or more of, initiating a cleaning session, triggering an alert signal, initiating floor monitoring.

16. A computer program comprising instructions which, when the program is executed by a computer, cause the computer to carry out the method according to any one of claims 1 to 15.

17. A computer-readable medium comprising instructions which, when executed by a computer, cause the computer to carry out the method according to any one of claims 1 to 15.

18. A control device (100) for determining floor condition in a dwelling area (20) for a herd of animals (10), wherein the control device (100) is configured to:

- obtain, from a walking monitoring system (30) arranged in the dwelling area (20), walking data indicative of walking characteristics of one or more individual animals (10) located in the dwelling area (20), and

- determine the floor condition based on the obtained walking data.

19. The control device (100) according to claim 18, wherein the control device

(100) is configured to perform the method of any one of claims 1 to 15

21