Apparatus and method for estimating the position of a moving object using a wheel encoder

Abstract

The present invention relates to an apparatus and method for estimating the position of a moving object using a wheel encoder, and more specifically, to an apparatus and method for estimating the position of a moving object according to a road surface using data measured by a wheel encoder. The objective of the present invention is to estimate the position of a moving object using only the data from a wheel encoder.

Description

Technology Field

[0001] The present invention relates to a device and method for estimating the position of a moving object using a wheel encoder, and more specifically, to a device and method for estimating the position of a moving object according to a road surface using data measured by a wheel encoder. Background Technology

[0002] With the advancement of modern industry, smart factories are establishing themselves as a new paradigm in manufacturing. In smart factory environments, various cutting-edge technologies are introduced to maximize efficiency and productivity, and among these, the use of autonomous robots is essential. Autonomous robots possess the potential to perform accurate and repetitive tasks, enabling them to replace human roles, and this remains a field of active research.

[0003] However, for autonomous robots to effectively replace human roles, they must be capable of autonomous movement based on their own judgment, and the core technology enabling this is localization. Localization plays a crucial role in allowing autonomous robots to accurately determine their position within a given environment and navigate along the optimal path to a target location. Since localization directly impacts the tasks assigned to the robot and the achievement of its goals, high accuracy and reliability are required.

[0004] To this end, various sensors are installed in autonomous robots. Sensors installed in autonomous robots include GPS sensors, ultrasonic sensors, infrared sensors, laser sensors, LiDAR sensors, and camera sensors. As such, information regarding the movement environment of autonomous robots is primarily acquired using distance sensors (LiDAR, laser, ultrasonic, infrared, etc.) attached to the robot, or by acquiring information through image processing using vision sensors such as cameras. However, the sensors installed to determine the position of these autonomous robots contribute to increased unit costs and present the problem of requiring a large amount of computation for position estimation. The problem to be solved

[0005] The present invention is intended to solve the problems described above, and the objective of the present invention is to estimate the position of a moving object using only data from a wheel encoder. means of solving the problem

[0007] According to one aspect of the present invention, an apparatus for estimating the position of a moving body including a wheel encoder is disclosed, comprising: a surface selection unit that learns and generates surface information of a road on which the moving body is traveling based on rotation information generated by the wheel encoder; a Kalman filter that removes noise from the rotation information by varying a filtering coefficient according to the surface information; a position estimation unit that generates driving information of the moving body based on the noise-removed rotation information and the surface information; and a position calculation unit that determines the position of the moving body based on the driving information.

[0008] According to an embodiment, a position estimation device for a moving body is disclosed, characterized in that the surface selection unit generates the surface information based on the standard deviation value of the pulse data included in the rotation information.

[0009] According to an embodiment, a position estimation device for a moving body is disclosed, characterized in that the surface selection unit generates surface information by selecting a road with higher friction as the standard deviation value increases.

[0010] According to an embodiment, a position estimation device for a moving body is disclosed, characterized in that the surface selection unit distinguishes between roads with high friction and roads with low friction by setting a threshold value of the standard deviation value.

[0011] According to an embodiment, a position estimation device for a moving body is disclosed, characterized in that the surface selection unit updates the surface information when the standard deviation value exceeds a set threshold.

[0012] According to an embodiment, a position estimation device for a moving body is disclosed, characterized in that the surface selection unit learns surface information based on rotation information using a first artificial intelligence neural network (CNN).

[0013] According to an embodiment, a position estimation device for a moving body is disclosed, characterized in that the surface selection unit learns the surface information through the rotation information measured at the same time and at the same speed on different roads.

[0014] According to an embodiment, a position estimation device for a moving body is disclosed, characterized in that the surface selection unit updates surface information by comparing and analyzing rotation information collected from different roads.

[0015] According to an embodiment, a position estimation device for a moving body is disclosed, characterized in that the driving information of the moving body includes driving distance information and driving direction information of the moving body.

[0016] According to an embodiment, a position estimation device for a moving body is disclosed, characterized in that the position estimation unit learns driving information of the moving body using a second artificial intelligence neural network (CRNN).

[0017] According to another aspect of the present invention, a method for estimating the position of a moving body comprising a wheel encoder is disclosed, wherein the method comprises: a step of a processor learning and generating surface information of a road on which the moving body is traveling based on rotation information generated by the wheel encoder; a step of removing noise from the rotation information by varying a filtering coefficient according to the surface information; a step of generating driving information of the moving body based on the noise-removed rotation information and the surface information; and a step of determining the position of the moving body based on the driving information.

[0018] According to an embodiment, a method for estimating the position of a moving body is disclosed, characterized in that, in step (a), the processor generates the surface information based on the standard deviation value of the pulse data included in the rotation information.

[0019] According to an embodiment, a method for estimating the position of a moving body is disclosed, characterized in that the processor generates surface information by selecting a road with higher friction as the standard deviation value increases.

[0020] According to an embodiment, a method for estimating the position of a moving object is disclosed, characterized in that the processor distinguishes between roads with high friction and roads with low friction by setting a threshold value of the standard deviation value.

[0021] According to an embodiment, a method for estimating the position of a moving body is disclosed, characterized in that the processor updates the surface information when the standard deviation value exceeds a set threshold.

[0022] According to an embodiment, a method for estimating the position of a moving body is disclosed, characterized in that the processor learns surface information based on the rotation information using a first artificial intelligence neural network (CNN).

[0023] According to an embodiment, a method for estimating the position of a moving body is disclosed, characterized in that the processor learns the surface information through the rotation information measured at the same time and at the same speed on different roads.

[0024] According to an embodiment, a method for estimating the position of a moving body is disclosed, characterized in that the processor updates surface information by comparing and analyzing rotation information collected from different roads.

[0025] According to an embodiment, a method for estimating the position of a moving body is disclosed, characterized in that, in step (c), the driving information of the moving body includes driving distance information and driving direction information of the moving body.

[0026] According to an embodiment, a method for estimating the position of a moving object is disclosed, wherein in step (c), the processor learns driving information of the moving object using a second artificial intelligence neural network (CRNN). Effects of the invention

[0027] According to the present invention, costs can be reduced by minimizing the number of sensors for estimating the position of a moving body.

[0028] In addition, according to the present invention, the amount of computation of a processor for position estimation can be reduced.

[0029] In addition, according to the present invention, the location of a moving object can be estimated anywhere regardless of the type of road being traveled on. Brief explanation of the drawing

[0030] FIG. 1 is a configuration diagram showing a position estimation device for a moving body according to an embodiment of the present invention. FIG. 2 is an illustrative diagram showing an example of a position estimation device for a moving object according to an embodiment of the present invention classifying a road surface. FIG. 3 is a flowchart illustrating a method for estimating the position of a moving body according to an embodiment of the present invention. Specific details for implementing the invention

[0031] The objects, features, and advantages of the present invention described above will become more apparent through the following embodiments in connection with the accompanying drawings. The specific structural or functional descriptions below are merely illustrative for the purpose of explaining other embodiments of the concept of the present invention, and embodiments according to the concept of the present invention may be implemented in various forms and should not be interpreted as being limited to the embodiments described in this specification or application. Since embodiments according to the concept of the present invention may be subject to various modifications and may take various forms, specific embodiments are illustrated in the drawings and described in detail in this specification or application. However, this is not intended to limit the embodiments according to the concept of the present invention to specific disclosed forms, and should be understood to include all modifications, equivalents, and substitutions that fall within the spirit and scope of the present invention. Terms such as "first" and / or "second" may be used to describe various components, but said components are not limited to said terms. The above terms may be used solely for the purpose of distinguishing one component from other components, for example, without departing from the scope of rights according to the concept of the present invention, such that the first component may be named the second component, and similarly, the second component may be named the first component. When it is stated that a component is connected to or coupled with another component, it should be understood that it may be directly connected to or coupled with that other component, or that there may be other components in between. On the other hand, when it is stated that a component is directly connected to or directly coupled with another component, it should be understood that there are no other components in between. Other expressions used to describe the relationship between components, such as between, immediately between, adjacent to, and directly adjacent to, should be interpreted in the same way.The terms used in this specification are used merely to describe specific embodiments and are not intended to limit the invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. Terms such as "include" or "have" in this specification are intended to indicate the existence of the described features, numbers, steps, actions, components, parts, or combinations thereof, and should not be understood as precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof. Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which the invention pertains. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this specification. The invention will be described in detail below by describing preferred embodiments of the invention with reference to the accompanying drawings. Identical reference numerals in each drawing indicate identical components.

[0032] FIG. 1 is a configuration diagram showing a position estimation device for a moving body according to an embodiment of the present invention.

[0033] Referring to FIG. 1, a position estimation device (100) of a moving body according to an embodiment of the present invention may include a surface selection unit (110), a Kalman filter (120), a position estimation unit (130), and a position calculation unit (140). The position estimation device (100) of a moving body is installed on a moving body including a wheel encoder (50) and can receive rotation information of the wheel from the wheel encoder (50).

[0034] The surface selection unit (110) can learn and generate surface information of the road on which the vehicle is traveling based on rotation information generated by the wheel encoder (50) of the vehicle. The surface selection unit (110) can generate surface information based on the standard deviation value of the pulse data included in the rotation information. The surface selection unit (110) can generate surface information by selecting a road with higher friction as the standard deviation value increases. In addition, the surface selection unit (110) can distinguish between roads with high friction and roads with low friction by setting a threshold value for the standard deviation value. At this time, the surface selection unit (110) can update the surface information when the standard deviation value exceeds the set threshold value. In addition, the surface selection unit (110) can learn surface information based on rotation information using an artificial intelligence neural network (CNN, Convolutional Neural Network) (hereinafter referred to as the first artificial intelligence neural network).

[0035] Additionally, the surface selection unit (110) can learn surface information through rotation information measured at the same time and at the same speed on different roads. The surface selection unit (110) can update surface information by comparing and analyzing rotation information collected from different roads. For example, the surface selection unit (110) can collect rotation information at the same time and at the same speed on roads with different surface friction forces, such as indoor corridors, sidewalks paved with paving blocks, asphalt roads, unpaved roads, grass, and athletic tracks, and learn surface information of the roads.

[0036] The Kalman filter (120) removes noise from rotation information, and can remove noise from rotation information by varying the filtering coefficient according to surface information. For example, rotation information has different standard deviation values ​​depending on each surface, and the Kalman filter (120) can remove noise from rotation information by checking, along with the rotation information, which road the rotation information was measured on using surface information obtained from the surface selection unit (110), and setting a filtering coefficient value according to the surface information according to a preset standard.

[0037] The position estimation unit (130) can generate driving information of a moving body based on noise-removed rotation information and surface information. Here, the driving information of the moving body may include driving distance information and driving direction information of the moving body. Additionally, the position estimation unit (130) can learn the driving information of the moving body using an artificial intelligence neural network (CRNN, Convolution Recurrent Neural Network) (hereinafter, the second artificial intelligence neural network). That is, the position estimation unit (130) can generate driving information of the moving body based on surface information obtained from the surface selection unit (110) and noise-removed rotation information from the corresponding surface.

[0038] The position calculation unit (140) can determine the position of the moving body based on the driving information of the moving body generated by the position estimation unit (130).

[0039] FIG. 2 is an illustrative diagram showing an example of a position estimation device for a moving object according to an embodiment of the present invention classifying a road surface.

[0040] Referring to FIG. 2, rotation information measured by a wheel encoder (50) according to the road surface is shown. Each rotation information represents rotation information measured at the same wheel rotation speed for 1 second on different roads.

[0041] As shown in FIG. 2 (a) to (g), rotation information is different for each road, and based on this, the position estimation device (100) of the moving body can generate surface information.

[0042] The surface selection unit (110) can generate surface information for each road using the standard deviation value of rotation information for each road. That is, the moving body position estimation device (100) can distinguish the road on which the moving body is traveling and estimate the position of the moving body on any road by varying the coefficients of the Kalman filter (130) according to the surface of the road.

[0043] FIG. 3 is a flowchart illustrating a method for estimating the position of a moving body according to an embodiment of the present invention.

[0044] Referring to FIG. 3, a method for estimating the position of a moving body according to an embodiment of the present invention may include a step of a processor learning and generating surface information (S310), a step of removing noise from rotation information based on the surface information (S320), a step of generating driving information of the moving body (S33), and a step of determining the position of the moving body (S340).

[0045] In the step of learning and generating surface information (S240), the surface selection unit (110) can learn and generate surface information of the road on which the vehicle is traveling based on rotation information generated from the wheel encoder (50) of the vehicle. The surface selection unit (110) can generate surface information based on the standard deviation value of the pulse data included in the rotation information. The surface selection unit (110) can generate surface information by selecting a road with higher friction as the standard deviation value increases. Additionally, the surface selection unit (110) can distinguish between roads with high friction and roads with low friction by setting a threshold value for the standard deviation value. At this time, the surface selection unit (110) can update the surface information if the standard deviation value exceeds the set threshold value. Additionally, the surface selection unit (110) can learn surface information based on rotation information using an artificial intelligence neural network (CNN, Convolutional Neural Network) (hereinafter referred to as the first artificial intelligence neural network).

[0046] Additionally, the surface selection unit (110) can learn surface information through rotation information measured at the same time and at the same speed on different roads. The surface selection unit (110) can update surface information by comparing and analyzing rotation information collected from different roads. For example, the surface selection unit (110) can collect rotation information at the same time and at the same speed on roads with different surface friction forces, such as indoor corridors, sidewalks paved with paving blocks, asphalt roads, unpaved roads, grass, and athletic tracks, and learn surface information of the roads.

[0047] The step (S320) of removing noise from rotation information according to surface information involves a Kalman filter (120) removing noise from rotation information, wherein the filtering coefficient is varied according to surface information to remove noise from rotation information. For example, rotation information has different standard deviation values ​​depending on each surface, and the Kalman filter (120) can remove noise from rotation information by checking, along with the rotation information, which road the rotation information was measured on using surface information obtained from the surface selection unit (110), and setting a filtering coefficient value according to surface information based on a preset standard.

[0048] In the step (S330) of generating driving information of a moving body, the position estimation unit (130) may generate driving information of the moving body based on noise-removed rotation information and surface information. Here, the driving information of the moving body may include driving distance information and driving direction information of the moving body. Additionally, the position estimation unit (130) may learn the driving information of the moving body using an artificial intelligence neural network (CRNN, Convolutional Recurrent Neural Network) (hereinafter, the second artificial intelligence neural network). That is, the position estimation unit (130) may generate driving information of the moving body based on surface information obtained from the surface selection unit (110) and noise-removed rotation information from the corresponding surface.

[0049] The step of determining the position of the moving body (S340) allows the position calculation unit (140) to determine the position of the moving body based on the driving information of the moving body generated by the position estimation unit (130).

[0050] Although preferred embodiments of the present invention have been described above, the embodiments disclosed in the present invention are intended only to illustrate, not to limit, the technical scope of the present invention. Accordingly, the technical scope of the present invention includes not only each disclosed embodiment but also combinations of the disclosed embodiments, and furthermore, the scope of the technical scope of the present invention is not limited by such embodiments. In addition, a person skilled in the art to which the present invention pertains can make numerous changes and modifications to the present invention without departing from the spirit and scope of the appended claims, and all such appropriate changes and modifications should be deemed to fall within the scope of the present invention as equivalents. Explanation of the symbols

[0051] 50 : Wheel encoder 100: Position estimation device 110 : Surface selection section 120 : Kalman filter 130 : Position estimation section 140 : Position calculation unit

Claims

Claim 1 A device for estimating the position of a moving body including a wheel encoder, comprising: a surface selection unit that learns and generates surface information of a road on which the moving body is traveling based on rotation information generated by the wheel encoder; a Kalman filter that removes noise from the rotation information by varying a filtering coefficient according to the surface information; a position estimation unit that generates driving information of the moving body based on the noise-removed rotation information and the surface information; and a position calculation unit that determines the position of the moving body based on the driving information; wherein the surface selection unit generates the surface information based on the standard deviation value of pulse data included in the rotation information, wherein the surface information is generated by selecting a road with higher friction as the standard deviation value increases, and learns the surface information based on the rotation information using a first artificial intelligence neural network (CNN), and learns the surface information through the rotation information measured at the same time and at the same speed on different roads including at least one of an indoor corridor, a sidewalk paved with paving blocks, an asphalt road, an unpaved road, grass, and a running track. Claim 2 delete Claim 3 delete Claim 4 A device for estimating the position of a moving body according to claim 1, wherein the surface selection unit distinguishes between roads with high friction and roads with low friction by setting a threshold value of the standard deviation value. Claim 5 A device for estimating the position of a moving body according to claim 4, wherein the surface selection unit updates the surface information when the standard deviation value exceeds a set threshold. Claim 6 delete Claim 7 delete Claim 8 A position estimation device for a moving body according to claim 1, wherein the surface selection unit updates surface information by comparing and analyzing rotation information collected from different roads. Claim 9 A position estimation device for a moving body according to claim 1, wherein the driving information of the moving body includes driving distance information and driving direction information of the moving body. Claim 10 A position estimation device for a moving body according to claim 1, wherein the position estimation unit learns driving information of the moving body using a second artificial intelligence neural network (CRNN). Claim 11 A method for estimating the position of a moving body including a wheel encoder, comprising: a step in which a processor learns and generates surface information of a road on which the moving body is traveling based on rotation information generated by the wheel encoder; (b) a step in which a filtering coefficient is varied according to the surface information to remove noise from the rotation information; (c) a step in which driving information of the moving body is generated based on the rotation information from which noise has been removed and the surface information; and (d) a step in which the position of the moving body is determined based on the driving information; wherein, in step (a), the processor generates the surface information based on the standard deviation value of pulse data included in the rotation information, wherein the surface information is generated by selecting a road with higher friction as the standard deviation value increases, and learns the surface information based on the rotation information using a first artificial intelligence neural network (CNN), and learns the surface information through the rotation information measured at the same time and at the same speed on different roads including at least one of an indoor corridor, a sidewalk paved with paving blocks, an asphalt road, an unpaved road, grass, and a running track. Claim 12 delete Claim 13 delete Claim 14 A method for estimating the position of a moving body according to claim 11, wherein the processor distinguishes between roads with high friction and roads with low friction by setting a threshold value of the standard deviation value. Claim 15 A method for estimating the position of a moving body according to claim 14, wherein the processor updates the surface information when the standard deviation value exceeds a set threshold. Claim 16 delete Claim 17 delete Claim 18 A method for estimating the position of a moving body according to claim 11, wherein the processor updates surface information by comparing and analyzing rotation information collected from different roads. Claim 19 A method for estimating the position of a moving body according to claim 11, wherein in step (c) above, the driving information of the moving body includes driving distance information and driving direction information of the moving body. Claim 20 A method for estimating the position of a moving body, characterized in that, in step (c) above, the processor learns the driving information of the moving body using a second artificial intelligence neural network (CRNN).

Images