Railway weed control vehicle

Abstract

The present invention relates to a railway weed control vehicle. The present invention describes a railway weed control vehicle. Activating (110) at least one weed control unit controls weeds around a railroad track. The railroad track includes rails and sleepers. At least one electrode-based weed control unit is mounted to at least one first location on the vehicle. Sensor data is acquired (120) by at least one sensor. The sensor data relates to at least one location around the railroad track. At least one sensor is mounted to at least one second location on the vehicle. Relative to a forward direction of travel of the vehicle, the at least one second location is forward of the at least one first location. The sensor data is provided (130) to a processing unit. The sensor data is analyzed (140) by the processing unit to identify locations of rail substructure components in addition to the rails and sleepers. The processing unit modifies (150) the operation of one or more of the at least one electrode-based weed control unit, including utilizing at least one of the identified locations of the rail substructure components.

Description

Technical Field

[0001] The present invention relates to a railway weed control vehicle, a weed control method using the railway weed control vehicle, as well as a computer program element and a computer-readable medium.

Background Art

[0002] The general background of the present invention is weed control. Areas around and between railway tracks need to have plants controlled. Such control improves the visibility from the perspective of people inside the train, such as the driver, and also improves the visibility from the perspective of people working on the tracks. Such control can also improve safety. Furthermore, plants can sometimes sever or damage the tracks as well as related signal transmission and communication lines. Control of plants is necessary to mitigate such occurrences. Vegetation management, also called weed control, can require significant time and resources, especially when done manually. There is a need to reduce the environmental impact of chemical sprays frequently used in weed control. An electrode-based weed control technology has been proposed for controlling weeds, where a high voltage is applied between electrodes and current flows from one electrode to the other through the ground and weeds, thereby eradicating the weeds. However, environments where weeds are controlled and that have infrastructure components that can be damaged by such electrode-based weed control units can present difficulties.

Summary of the Invention

Problems to be Solved by the Invention

[0003] It is beneficial to have an improved weed control technology based on electrode-based weed control technology.

[0004] The object of the present invention is achieved by the subject matter of the independent claims, and further embodiments are included in the dependent claims. It should be noted that the aspects and examples of the present invention described below also apply to a railway weed control vehicle, a weed control method using the railway weed control vehicle, as well as a computer program element and a computer-readable medium.

Means for Solving the Problem

[0005] According to the first aspect, - at least one electrode-based weed control unit, - at least one sensor, - a processing unit, A weed control vehicle for railways including these is provided.

[0006] At least one electrode-based weed control unit is mounted at at least one first position of the vehicle. At least one sensor is mounted at at least one second position of the vehicle. With respect to the moving direction of the vehicle forward, at least one second position is in front of at least one first position. By operating at least one weed control unit, weeds surrounding along the railway line are controlled. The railway line includes rails and sleepers. At least one sensor is configured to acquire sensor data regarding at least one location in the vicinity along the railway line. At least one sensor is configured to provide the sensor data to the processing unit. The processing unit is configured to analyze the sensor data to identify the locations of rail infrastructure components in addition to the rails and sleepers. The processing unit is configured to change the operation of one or more of the at least one electrode-based weed control units, including using at least one of the identified locations of the rail infrastructure components.

[0007] In this way, the vulnerable infrastructure components and parts in the railway environment are not damaged by contacting the electrodes of the train's electrode-based weed control unit and / or by the application of high voltage near the parts or components. Therefore, by using sensor data, even in locations where there are vulnerable infrastructure components and parts, appropriate operation is automatically performed through weed control along the railway line using the electrode-based weed control unit, ensuring that such vulnerable parts and components are not damaged, so that weeds can be automatically controlled.

[0008] In one example, changing the operation of one or more electrode-based weed control units includes stopping the operation of one or more electrode-based weed control units.

[0009] In this way, by substantially cutting off the power supply to the electrodes, it is ensured that high voltage and the accompanying current flowing through the ground do not occur at locations where there are vulnerable infrastructure components.

[0010] In one example, changing the operation of one or more electrode-based weed units includes determining not to operate one or more electrode-based weed control units.

[0011] Therefore, for example, when the electrode weed control unit passes through an area without weeds, the processing unit can determine based on the sensor data that there are no weeds and the weed control unit should not be operated. And it may encounter an area with weeds, and based on the sensor data, the weed control unit can be normally operated to control the weeds. However, based on the sensor data, the processing unit can determine that there are vulnerable infrastructure components in addition to weeds in that area, and since operating the weed control unit may damage the infrastructure, it can be determined not to operate the weed control unit.

[0012] In one example, changing the operation of one or more electrode-based weed control units includes moving one or more electrode-based weed control units away from at least one of the identified locations.

[0013] In this way, physical contact between the vulnerable underlying structure of the electrode-based weed control unit can be reduced by moving the unit away from the underlying structure components. This movement can be done while the unit is still operating, or it can be done in conjunction with stopping the operation of the unit. The movement can be in a vertical direction to move the unit over the underlying structure components, in a horizontal direction to move the unit around the underlying structure components, or a combination of horizontal and vertical movement. If the movement is horizontal, and the unit remains on or is positioned over the weeds, the operation is maintained in the sense of maintaining the application of high voltage and current, so that these weeds are controlled and weed control becomes efficient.

[0014] In one example, the movement includes vertical movement.

[0015] In one example, the movement includes horizontal movement.

[0016] In one example, each electrode-based weed control unit is movably attached to a vehicle via an associated actuator, and the processing unit is configured to control the actuator to move the associated electrode-based weed control unit.

[0017] In one example, the processing unit is configured to analyze sensor data to identify rail infrastructure components at the identified locations. At least one of the identified locations includes at least one location of the identified rail infrastructure components that is vulnerable to damage by operating the electrode-based weed control unit.

[0018] Thus, for example, when the unit is near the infrastructure components, it is not activated, and / or the unit is moved over or around those components. The change in the operation of the electrode-based weed control technology is determined based on what those components are. Therefore, it is possible to identify the identified infrastructure components that are robust against physical contact and the application of high voltage, and the weed control unit can be operated near the infrastructure components to control weeds. However, it is possible to identify infrastructure components such as cables, electronic systems, or electrical systems that may be damaged by physical contact with the electrodes of the unit and / or the application of high voltage from the unit, and it is possible to make a determination to move the electrodes over the components and / or not to operate the electrodes nearby. However, robust components that will not be damaged may be large enough to damage the electrode-based weed control unit itself. Therefore, in this case, the operation of the unit can also be changed, for example, by moving the unit in the vertical and / or horizontal directions so that the electrodes do not collide with the robust infrastructure components.

[0019] In one example, the sensor data includes image data, and the identification of the rail infrastructure components includes image analysis of the image data.

[0020] In one example, at least one sensor includes one or more of a camera, an IR sensor, a LIDAR sensor, a flexible contact sensor, a radar sensor.

[0021] According to a second aspect, there is provided a weed control method using a railway weed control vehicle, a) operating at least one weed control unit to control weeds in the surroundings along a railway line, the railway line including rails and sleepers, and at least one electrode-based weed control unit being mounted at at least one first position of the vehicle; b) obtaining sensor data regarding at least one location in the vicinity along a railway line by means of at least one sensor, wherein the at least one sensor is mounted at at least one second position of a vehicle, and the at least one second position is in front of the at least one first position with respect to the moving direction of the vehicle towards the front; c) providing the sensor data to a processing unit; d) analyzing the sensor data by the processing unit to identify the location of rail infrastructure components in addition to the rails and sleepers; e) changing the operation of one or more of the at least one electrode-based weed control units, including using at least one of the identified locations of the rail infrastructure components by the processing unit; A weed control method is provided, which includes the above steps.

[0022] In one example, step e) includes stopping the operation of one or more of the electrode-based weed control units.

[0023] In one example, step e) includes moving one or more of the electrode-based weed control units away from at least one of the identified locations.

[0024] According to another aspect, there is provided a computer program element for controlling the components of the vehicle of the first aspect, which is configured to execute the method according to the second aspect when executed by a processor. Also provided is a computer-readable medium storing this program element.

[0025] Advantageously, the benefits provided by any of the above aspects apply equally to all other aspects, and vice versa.

[0026] The above aspects and examples will become apparent from the embodiments described hereinafter and will be described with reference to these embodiments.

Brief Description of the Drawings

[0027] The exemplary embodiments will be described below with reference to the following drawings.

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Mode for Carrying Out the Invention

[0028] FIG. 1 shows an example of a railway weed control vehicle 10. The vehicle includes at least one electrode-based weed control unit 20, at least one sensor 30, and a processing unit 40. At least one electrode-based weed control unit 20 is mounted at at least one first position of the vehicle 10. At least one sensor 30 is mounted at at least one second position of the vehicle 10. With respect to the forward movement direction of the vehicle 10, at least one second position is in front of at least one first position. By operating at least one weed control unit 20, weeds surrounding along the railway track are controlled. The railway track includes rails and sleepers. At least one sensor 30 is configured to acquire sensor data regarding at least one location around along the railway track. At least one sensor 30 is configured to provide the sensor data to the processing unit 40. The processing unit 40 is configured to analyze the sensor data to identify the locations of rail infrastructure components in addition to the rails and sleepers. The processing unit 40 is configured to change the operation of one or more of the at least one electrode-based weed control units 40, including using at least one of the identified locations of the rail infrastructure components.

[0029] According to one example, changing the operation of one or more electrode-based weed control units includes stopping the operation of the one or more electrode-based weed control units.

[0030] According to one example, changing the operation of one or more electrode-based weed units includes determining not to operate the one or more electrode-based weed control units.

[0031] According to one example, changing the operation of one or more electrode-based weed control units includes moving the one or more electrode-based weed control units away from at least one of the identified locations.

[0032] According to one example, the movement includes vertical movement.

[0033] According to one example, the movement includes horizontal movement.

[0034] According to one example, each electrode-based weed control unit is movably attached to the vehicle via an associated actuator, and the processing unit is configured to control the actuator to move the associated electrode-based weed control unit.

[0035] According to one example, the processing unit is configured to analyze sensor data to identify rail infrastructure components at the identified locations. At least one of the identified locations includes at least one location of the identified rail infrastructure components that is susceptible to damage by operating the electrode-based weed control unit. At least one of the identified locations includes at least one location of the identified rail infrastructure components that may damage the electrode-based weed control unit. At least one of the identified locations includes at least one location of the identified rail infrastructure components that may damage the electrode-based weed control unit when activated.

[0036] According to one example, the sensor data includes image data, and identifying rail infrastructure components includes image analysis of the image data.

[0037] According to one example, at least one sensor includes one or more of a camera, an IR sensor, a LIDAR sensor, a flexible contact sensor, a radar sensor.

[0038] FIG. 2 shows, in basic steps, a weed control method 100 using a railway weed control vehicle. The method 100 includes In an activating step 110, also referred to as step a), activating at least one weed control unit to control weeds surrounding along a railway line, the railway line including rails and sleepers, and at least one electrode-based weed control unit being mounted at at least one first position of the vehicle; In an acquiring step 120, also referred to as step b), acquiring sensor data regarding at least one location in the vicinity along the railway line by at least one sensor, the at least one sensor being mounted at at least one second position of the vehicle, and the at least one second position being in front of the at least one first position with respect to the moving direction of the vehicle forward; In a providing step 130, also referred to as step c), providing the sensor data to a processing unit; In an analyzing step 140, also referred to as step d), analyzing the sensor data by the processing unit to identify the locations of rail infrastructure components in addition to the rails and sleepers; In a changing step 150, also referred to as step e), changing the operation of one or more of the at least one electrode-based weed control units by the processing unit, including using at least one of the identified locations of the rail infrastructure components; and including.

[0039] According to one example, step e) includes stopping the operation of one or more electrode-based weed control units.

[0040] In one example, step e) includes determining not to activate one or more electrode-based weed control units.

[0041] According to one example, step e) includes moving one or more electrode-based weed control units away from at least one of the identified locations.

[0042] In one example, the movement includes vertical movement.

[0043] In one example, the movement includes horizontal movement.

[0044] In one example, each electrode-based weed control unit is movably attached to the vehicle via an associated actuator, and the processing unit is configured to control the actuator to move the associated electrode-based weed control unit.

[0045] In one example, step d) includes analyzing sensor data to identify rail infrastructure components at the identified locations, and at least one of the identified locations includes at least one location of an identified rail infrastructure component that is susceptible to damage by activating an electrode-based weed control unit.

[0046] In one example, at least one sensor includes a camera, the sensor data includes image data acquired by the camera, and identifying the rail infrastructure components includes image analysis of the image data.

[0047] In one example, at least one sensor includes one or more of a camera, an IR sensor, a LIDAR sensor, a flexible contact sensor.

[0048] Hereinafter, the weed control vehicle and the weed control method using the vehicle will be described in more detail with reference to FIGS. 3 to 5.

[0049] FIG. 3 shows an example of a number of weed control units in the form of high-voltage electrode pairs. The electrode pairs are provided to form individual electrode-based weed control units, and a high voltage can be applied between the electrodes forming a pair of electrodes. When the electrode pair is activated, current flows from one electrode to the other through the ground including weeds and the roots of the weeds. One of the shown sub-units can have one electrode pair, or can actually have a number of electrode pairs in order to provide such high-voltage-based weed control with higher resolution in a smaller spatial range. The high voltage can be applied in DC mode for a certain period and in AC mode for a certain period. The electrodes have flexible end portions in the form of metal tapes or wires that contact the ground flexibly near (or at) the ground, not shown. However, during normal operation, the robust structural parts of the electrodes are very close to the ground and may hit and damage the vulnerable railway infrastructure components, and may also damage such components by operating on or near certain vulnerable infrastructure components.

[0050] Figure 4 shows a detailed example of a railway weed control vehicle. Figure 4 shows two images of the railway weed control vehicle, with the left image showing the vehicle at an earlier time than the right image. The railway weed control vehicle is traveling along a railway line and is observed from the side in Figure 4. The railway weed control vehicle is moving forward, i.e., from left to right in Figure 4. A number of sensors are mounted on the front of the vehicle. These sensors detect the ground and make it possible to determine whether it is about to encounter a vulnerable infrastructure component or a component that could damage the electrodes if the electrodes are in the standby state for operation. A number of touch detectors that spread across the front of the vehicle and laterally on both sides physically contact the articles, a number of cameras acquire images of both sides of the track across the width of the track, and the images are analyzed by an image processing algorithm. This sensor data is processed to identify the infrastructure components encountered and determine their height above from their size and position on the track. There are a number of electrode-based weed control units under the vehicle and on both sides of the vehicle, which, when activated, control weeds as described above. In the left image, image analysis and contact analysis detect that the electrodes will encounter infrastructure that could be damaged by touching and / or operating near the components, and / or infrastructure that could damage the electrodes. In the left image, there are weeds under the vehicle and around the vehicle (not shown), and the electrodes are activated to control the weeds by passing a high-potential current through the ground containing the roots of plants and weeds. In the right image, the vehicle is moving forward, but based on the analyzed sensor data, the vehicle's processing unit changes the operation of the electrode-based weed control units that would encounter the infrastructure components by lifting the electrodes above the infrastructure components with actuators, and at the same time stops the operation of the electrodes.

[0051] Continuing with Figure 4, the railway weed control train has a GPS unit that identifies the location of the train. The location of the train can be enhanced by information obtained by image processing and / or information based on movement resulting from knowledge of the train's speed, and / or using an inertial navigation-based sensor. Thus, at any given time, the processing unit of the weed control train knows which part of the ground the electrode-based weed control unit is located above.

[0052] As described above, the GPS coordinates of the weeds can be provided to the weed control train, and the weed control train uses its own GPS unit to activate the electrodes when necessary. However, the images obtained by the railway weed control camera and used for identifying infrastructure components are also analyzed. When weeds are present, the location of the weeds and what types of weeds they are can be identified. Thus, the images are provided to the processing unit, which processes the images to determine if weeds are present and what those weeds are. If present, the location on the ground can be identified. Then, as the train moves forward, the electrodes can be activated to eliminate the weeds, and depending on what types of weeds are identified, the electrodes can perform different operations. By analyzing this image to identify infrastructure components as well, the operation of the unit can be modified so that these components are not damaged and / or the electrodes are not damaged. Thus, in addition to making a determination to modify the operation so as not to damage the infrastructure around the railway line and / or not to damage the electrode-based weed control unit, the weed types can be identified by image analysis, and this can be used to vary the current and / or voltage applied to eliminate different types of weeds encountered. This allows weeds that are easier to eliminate to be reliably controlled at a lower power setting than weeds that are more difficult to control.

[0053] Regarding image processing for determining the presence of weeds, the processing unit analyzes an image to identify regions in the image where plants are found. Plants can be detected based on the shape of multiple features in the acquired image. For example, edge detection software is used to draw the outer perimeters of multiple objects and the outer perimeters of multiple features within the outer perimeter of the object itself. A database of plant images can be used to assist in determining whether features in the image are related to plants using trained machine learning algorithms such as artificial neural networks or decision tree analysis. The camera can acquire a multispectral image, which is an image having information regarding the colors in the image, and this image can be used alone or in combination with feature detection to identify where plants are found in the image. Similarly, trained machine learning algorithms are used to identify infrastructure components, and a touch sensor helps with this identification by providing information regarding the actual dimensions of the components.

[0054] Regarding the weed detection machine learning analyzer, images of specific weeds are acquired along with information related to the size of the weeds being used. Information related to the geographical location where such weeds are found in the world, and information related to the season when the weeds are found, including the time when the flowers are in full bloom, can be tagged to this image. Also, the name of the weed can be tagged to the weed image. And the machine learning analyzer can be based on an artificial neural network or a decision tree analyzer, but is trained with ground-truthed acquired images. In this way, new images of plants are presented to the analyzer, and such images can be tagged with relevant timestamps such as the season, and geographical locations such as Germany and South Africa. However, the analyzer identifies a specific type of weed in the image from a comparison between the image of the weed found in the new image and the images of different weeds used in training, and the size of the weed and where and when the weed grows can also be considered. Therefore, the specific location on the ground and the size of that weed species in the environment can be identified. The machine learning algorithm for infrastructure component detection and identification is similarly trained based on images of components found around railway lines and can be trained using images of animals such as cats, dogs, and rabbits so that actions can be taken to reduce the risk of animals being electrocuted, thereby providing the greatest possible animal welfare. Other types of sensors and image processing can be used to detect and identify weeds, and other types of sensors and image processing can be used to detect and identify railway infrastructure components, such as processing data from radar- and LIDAR-based sensor systems. A touch sensor can be used to enhance image processing and can be useful when a robust component is in a clump of weeds and cannot be imaged. For example, a large metal mass may be on the track and weeds may grow around and on it. And identification can be performed using camera image processing, and in some cases, detection and identification of metal objects can be performed by processing LIDAR images.However, a simple method is provided to determine, by means of a touch sensor, whether there is an object that would damage the electrode, and appropriate operations can be performed, such as lifting the electrode over the object and / or lifting the electrode to one side of the object. When moving the electrode-based weed control unit, the electrode-based weed control unit can also stop operating.

[0055] Since the weed control train identifies the locations and types of weeds on its own from the acquired images, it is not necessary to identify the exact geographical positions of the weeds. Also, since the weed control train identifies the locations and types of infrastructure components on its own from the acquired images, it is not necessary to identify the exact geographical positions of the components. Rather, based on the knowledge of the forward movement (its speed) of the weed control train, in addition to the relative distance between the sensor (e.g., camera) and the electrode-based weed control unit, when weeds / components are found and identified, the electrode-based weed control unit can later be activated at that location to control the weeds, or the operation can be changed so that the vulnerable infrastructure components are not damaged. Thus, for example, in a train traveling at 25 m / s where it takes a total of 0.2 s, 0.4 s, or 0.8 s for the processing time and to prepare the electrode-based weed control unit to operate, the camera needs to be separated from the electrode-based weed control technology unit by 5 m, 10 m, or 20 m in front of the train, relative to its speed. By reducing the speed of the train, the distance interval can be decreased. Further, the camera acquiring the images can have a very short exposure time so that image smear due to the movement of the train during the exposure time is minimized. This can be achieved by various means, including the use of a camera with a short exposure time, or the use of short-pulse illumination using, for example, lasers or LEDs in combination with, for example, filters. However, the train can use a GPS system and / or an inertial navigation system, and / or image analysis to identify the exact geographical positions of the weeds and infrastructure components, and the electrode-based weed control unit can have related location identification means such as a GPS system and / or an inertial navigation system and / or an image-based system that can be used to provide the exact position of the unit. Thus, the leading passenger car of the train can have a camera that acquires images that can identify and locate infrastructure components and weeds in conjunction with GPS data, and the rear passenger cars of the train, which may be located tens or hundreds of meters behind the leading passenger car, can have weed control units.And even if the train goes up and down the slope, becoming shorter or longer, the electrode-based weed control unit can still use GPS data to operate at the correct position to control weeds, or can change its operation so as not to damage the infrastructure components.

[0056] Figure 5 shows examples of vulnerable infrastructure components around the railway line, and the railway weed control train currently being described can use the electrode-based weed control unit to perform control without damaging these infrastructure components.

[0057] Image processing that enables the identification of weed species (types of infrastructure components) through analysis From this, specific examples will be described regarding how the image is processed to enable the identification of the types of weeds (infrastructure components), and how it is determined to be suitable for image processing. 1. A digital image of the weeds (infrastructure components), especially a color image, is taken. 2. Areas within the digital image having pre-specified colors and textures are outlined within the boundary contour. Typically, one contour may be expected for one weed plant (infrastructure component). Such a detection or determination process detects the boundaries of relevant areas of the digital image. During this process, at least one contoured area containing pixels related to the weeds (infrastructure components) is created within the boundary contour. However, when the infrastructure component has sub-components and the weeds have different sub-parts, areas with two or more contours may be identified. 3. It is determined whether the boundary contour covers a sufficiently large area, and the sharpness (degree of focus) of the image data within the boundary contour is determined. This ensures that there is sufficient image data to first identify the type of weed (type of infrastructure component), and then it is judged that the minimum quality of the digital image will be met so that the type of weed (type of infrastructure component) can be determined. 4. If both criteria of 3) are met, the digital image, specifically the digital image within the boundary contour, is sent to the processing unit for image analysis by the artificial neural network, and the weed type (type of basic structural component) is identified as described above.

[0058] In another exemplary embodiment, there is provided a computer program or computer program element characterized in that it is configured to execute the method steps of the method according to one of the foregoing embodiments on a suitable system.

[0059] Therefore, the computer program element may be stored in a computer unit, which may also be part of one embodiment. This computer unit may be configured to execute or cause to execute the steps of the method described above. Further, this computer unit may be configured to operate the device and / or components of the system described above. The computer unit can be configured to operate automatically and / or to execute user instructions. The computer program may be loaded into the working memory of the data processing device. The data processing device may thus be capable of executing the method according to one of the foregoing embodiments.

[0060] This exemplary embodiment of the present invention is directed to both a computer program that uses the present invention from the beginning and a computer program that changes an existing program to a program that uses the present invention by an update.

[0061] Furthermore, the computer program element may be able to provide all the steps necessary to implement the procedure of the exemplary embodiment of the method described above.

[0062] According to a further exemplary embodiment of the present invention, a computer readable medium is provided, such as a CD-ROM, USB stick or the like, on which are stored the computer program elements described in the previous paragraphs.

[0063] A computer program may be supplied together with or as part of other hardware, stored on and / or distributed on a suitable medium, such as an optical storage medium or a semiconductor medium, or in other forms, such as via the Internet or other wired or wireless telecommunications systems.

[0064] However, the computer program may also be presented via a network, such as the World Wide Web, from which it can be downloaded into the working memory of a data processing device. According to a further exemplary embodiment of the invention, a medium is provided for downloading computer program elements arranged to carry out a method according to one of the aforementioned embodiments of the invention.

[0065] It should be noted that the embodiments of the present invention are described with respect to different subject matters. In particular, some embodiments are described with respect to method claims, while other embodiments are described with respect to apparatus claims. However, a person skilled in the art will infer from the above and following description that, unless otherwise indicated, any combination of features belonging to one subject matter, as well as any combination of features related to different subject matters, is considered to be disclosed by the present application. However, all features can be combined to provide synergistic effects that go beyond the simple sum of the features.

[0066] Although the present invention has been illustrated and described in the drawings and the foregoing description, such drawings and description should be considered illustrative or exemplary and not restrictive. The present invention is not limited to the disclosed embodiments. Other variations of the disclosed embodiments can be understood and achieved by those skilled in the art by considering the drawings, the present disclosure, and the dependent claims when practicing the claimed invention.

[0067] In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality. A single processor or other unit may perform the functions of several items recited in the claims. Even if certain means are recited in mutually different dependent claims, this fact alone does not indicate that a combination of these means cannot be used advantageously. Any reference signs in the claims should not be construed as limiting the scope of the claims.

Claims

1. At least one electrode-based weed control unit (20); At least one sensor (30); A railway weed control vehicle (10) comprising a processing unit (40), wherein The at least one electrode-based weed control unit is mounted at at least one first position of the vehicle; The at least one sensor is mounted at at least one second position of the vehicle, and the at least one second position is in front of the at least one first position with respect to the forward movement direction of the vehicle; By operating the at least one weed control unit, weeds surrounding along a railway track including rails and sleepers are controlled; The at least one sensor is configured to acquire image data regarding at least one location around along the railway track; The at least one sensor is configured to provide the image data to the processing unit; The processing unit is configured to analyze the image data to identify locations of rail infrastructure components that can be damaged by the electrode-based weed control unit in addition to the rails and the sleepers, and to identify weed species; The processing unit is configured to stop the operation of one or more of the electrode-based weed control units at at least one of the identified locations of the rail infrastructure components, and to set the power applied to the electrode-based weed control unit according to the weed species; The change in the operation of the one or more electrode-based weed control units includes the movement of the one or more electrode-based weed control units away from at least one of the identified locations; The movement includes horizontal movement under the vehicle; A railway weed control vehicle (10).

2. A weed control method (100) using a railway weed control vehicle, comprising: a) Operating at least one weed control unit to control weeds surrounding along a railway track (110), the railway track including rails and sleepers, and the at least one electrode-based weed control unit being mounted at at least one first position of the vehicle; b) obtaining (120) image data regarding at least one location in the vicinity along the railway line by means of at least one sensor, wherein the at least one sensor is mounted at at least one second position of the vehicle, and the at least one second position is in front of the at least one first position with respect to the forward movement direction of the vehicle; c) providing (130) the image data to a processing unit; d) analyzing (140) the image data by the processing unit to identify the location of rail infrastructure components that can be damaged by the electrode-based weed control unit in addition to the rails and the sleepers, and to identify the weed species; e) stopping, by the processing unit, the operation of one or more of the at least one electrode-based weed control units at at least one of the identified locations of the rail infrastructure components, and setting the power applied to the electrode-based weed control unit according to the weed species (150), including: The stopping of the operation of the one or more electrode-based weed control units includes the movement of the one or more electrode-based weed control units away from at least one of the identified locations; The movement includes horizontal movement under the vehicle; Method. Claim 3 A computer program for controlling a railway weed control vehicle, configured to execute the method according to claim 2 when executed by a processor.

Images