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

Abstract

The present invention relates to an apparatus for estimating a position of a moving object by using a wheel encoder, and a method therefor and, more specifically, to: an apparatus for estimating a position of a moving object based on a road surface by using data measured by a wheel encoder; and a method therefor. The purpose of the present invention is to estimate a position of a moving object by using only data of a wheel encoder.

Description

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

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

[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 being introduced to maximize efficiency and productivity, and the use of autonomous robots is essential. Autonomous robots have the potential to perform precise and repetitive tasks, potentially replacing human roles. This area continues to be actively researched.

[0003] However, for autonomous robots to effectively replace humans, they must be capable of autonomous movement based on their own judgment. The key technology enabling this is positional awareness. Positional awareness plays a crucial role in enabling autonomous robots to accurately determine their location within a given environment and navigate optimally to their target location. Because this directly impacts the robot's ability to achieve assigned tasks and objectives, high accuracy and reliability are required.

[0004] To this end, autonomous robots are equipped with various sensors. These sensors include GPS sensors, ultrasonic sensors, infrared sensors, laser sensors, LiDAR sensors, and camera sensors. Information about the autonomous robot's moving environment is primarily obtained using distance sensors (LiDAR, laser, ultrasonic, infrared, etc.) attached to the autonomous robot, or through image processing using vision sensors such as cameras. However, these sensors, which are equipped to determine the location of the autonomous robot, are a factor in increasing the unit price and require a large amount of computation for location estimation.

[0005] The present invention is intended to solve the above-mentioned problems, and the purpose of the present invention is to estimate the position of a moving object using only data from a wheel encoder.

[0006] According to one aspect of the present invention, a device for estimating a position of a moving object including a wheel encoder is disclosed, the device comprising: a surface selection unit for learning and generating surface information of a road on which the moving object is traveling based on rotation information generated from the wheel encoder; a Kalman filter for removing noise from the rotation information by varying a filtering coefficient according to the surface information; a position estimation unit for generating driving information of the moving object based on the rotation information from which the noise has been removed and the surface information; and a position calculation unit for determining the position of the moving object based on the driving information.

[0007] According to an embodiment, a position estimation device for a mobile body is disclosed, characterized in that the surface selection unit generates the surface information based on a standard deviation value of pulse data included in the rotation information.

[0008] According to an embodiment, a device for estimating a position of a moving object is disclosed, characterized in that the surface selection unit generates the surface information by selecting a road having a high frictional force as the standard deviation value is larger.

[0009] According to an embodiment, a device for estimating the position of a moving object is disclosed, characterized in that the surface selection unit sets a threshold value of the standard deviation value to distinguish between a road with high friction and a road with low friction.

[0010] According to an embodiment, a position estimation device for a mobile body is disclosed, characterized in that the surface selection unit updates the surface information when the standard deviation value exceeds a set threshold value.

[0011] According to an embodiment, a device for estimating a position of a moving object is disclosed, characterized in that the surface selection unit learns surface information based on the rotation information using a first artificial intelligence neural network (CNN).

[0012] According to an embodiment, a position estimation device for a moving object 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.

[0013] According to an embodiment, a position estimation device for a mobile body is disclosed, characterized in that the surface selection unit updates surface information by comparing and analyzing the rotation information collected from different roads.

[0014] According to an embodiment, a device for estimating a position of a mobile body is disclosed, characterized in that the driving information of the mobile body includes driving distance information and driving direction information of the mobile body.

[0015] According to an embodiment, a device for estimating a position of a mobile device is disclosed, characterized in that the position estimation unit learns driving information of the mobile device using a second artificial intelligence neural network (CRNN).

[0016] According to another aspect of the present invention, a method for estimating a position of a mobile object including a wheel encoder is disclosed, characterized in that the method comprises the steps of: (a) learning and generating surface information of a road on which the mobile object is traveling based on rotation information generated by the wheel encoder; (b) removing noise from the rotation information by varying a filtering coefficient according to the surface information; (c) generating driving information of the mobile object based on the rotation information from which the noise has been removed and the surface information; and (d) determining the position of the mobile object based on the driving information.

[0017] According to an embodiment, a method for estimating the position of a moving object is disclosed, characterized in that in the step (a), the processor generates the surface information based on a standard deviation value of pulse data included in the rotation information.

[0018] According to an embodiment, a method for estimating the position of a moving object is disclosed, characterized in that the processor generates the surface information by selecting a road with a high friction as the standard deviation value is larger.

[0019] According to an embodiment, a method for estimating the position of a moving object is disclosed, characterized in that the processor sets a threshold value of the standard deviation value to distinguish between a road with high friction and a road with low friction.

[0020] According to an embodiment, a method for estimating a position of a moving object is disclosed, characterized in that the processor updates the surface information when the standard deviation value exceeds a set threshold value.

[0021] According to an embodiment, a method for estimating the position of a moving object is disclosed, characterized in that the processor learns surface information based on the rotation information using a first artificial intelligence neural network (CNN).

[0022] According to an embodiment, a method for estimating the position of a moving object 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.

[0023] According to an embodiment, a method for estimating the position of a moving object is disclosed, characterized in that the processor compares and analyzes the rotation information collected from different roads to update surface information.

[0024] According to an embodiment, a method for estimating the position of a mobile object is disclosed, characterized in that, in the step (c), the driving information of the mobile object includes driving distance information and driving direction information of the mobile object.

[0025] According to an embodiment, a method for estimating the position of a mobile object is disclosed, characterized in that in the step (c), the processor learns driving information of the mobile object using a second artificial intelligence neural network (CRNN).

[0026] According to the present invention, the cost can be reduced by minimizing the number of sensors for estimating the position of a moving object.

[0027] In addition, according to the present invention, the amount of computation of a processor for position estimation can be reduced.

[0028] Additionally, according to the present invention, the location of a moving object can be estimated anywhere regardless of the type of road on which it is driving.

[0029] Fig. 1 is a schematic diagram showing a position estimation device for a mobile body according to an embodiment of the present invention.

[0030] FIGS. 2 to 8 are exemplary diagrams showing examples of a device for estimating a position of a mobile body according to an embodiment of the present invention classifying a road surface.

[0031] Figure 9 is a flowchart showing a method for estimating the position of a mobile object according to an embodiment of the present invention.

[0032] The above-described objects, features, and advantages of the present invention will become more apparent through the following examples taken in conjunction with the accompanying drawings. The specific structural and functional descriptions below are merely illustrative for the purpose of explaining other embodiments of the present invention, and embodiments according to the present invention may be implemented in various forms and should not be construed as limited to the embodiments described in this specification or application. Since embodiments according to the present invention may have 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 present invention to a specific disclosed form, but should be understood to include all modifications, equivalents, and substitutes included in the spirit and technical scope of the present invention. Terms such as first and / or second may be used to describe various components, but the components are not limited to the terms. The above terms are used solely for the purpose of distinguishing one component from another, for example, without departing from the scope of the rights according to the concept of the present invention, a first component may be referred to as a second component, and similarly, a second component may also be referred to as a first component. When a component is referred to as being connected or coupled to another component, it should be understood that it may be directly connected or coupled to the other component, but there may also be other components in between. Conversely, when a component is referred to as being directly connected or coupled to 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, directly between, adjacent to, and directly adjacent to, should be interpreted similarly.The terminology used herein is used solely to describe specific embodiments and is not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly dictates otherwise. It should be understood that the terms "comprise" and "have" used herein indicate the presence of a described feature, number, step, operation, component, part, or combination thereof, and do not preclude the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof. Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention pertains. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning they have in the context of the relevant technology, and shall not be interpreted in an idealized or overly formal sense unless explicitly defined herein. Hereinafter, the present invention will be described in detail by describing a preferred embodiment of the present invention with reference to the accompanying drawings. The same reference numerals in each drawing represent the same parts.

[0033] Fig. 1 is a schematic diagram showing a position estimation device for a mobile body according to an embodiment of the present invention.

[0034] Referring to FIG. 1, a position estimation device (100) of a mobile 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 mobile body may be installed in a mobile body including a wheel encoder (50) and receive rotation information of the wheel from the wheel encoder (50).

[0035] The surface selection unit (110) can learn and generate surface information of a road on which a mobile vehicle is driving based on rotation information generated from a wheel encoder (50) of the mobile vehicle. The surface selection unit (110) can generate surface information based on a standard deviation value of pulse data included in the rotation information. The surface selection unit (110) can generate surface information by selecting a road with a higher friction as the standard deviation value increases. In addition, the surface selection unit (110) can distinguish between a road with a high friction and a road with a low friction by setting a threshold value of 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 by using an artificial intelligence neural network (CNN, Convolutional Neural Network) (hereinafter, referred to as a first artificial intelligence neural network).

[0036] In addition, 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 on 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, such as indoor hallways, sidewalks with board blocks, asphalt roads, unpaved roads, grass, and athletics tracks, and learn surface information of the corresponding roads.

[0037] The Kalman filter (120) can remove noise from rotation information by varying the filtering coefficient according to surface information. For example, the rotation information has different standard deviation values ​​for each surface, and the Kalman filter (120) can remove noise from rotation information by checking, through the surface information acquired from the surface selection unit (110), on which road the rotation information was measured together with the rotation information, and setting the filtering coefficient value according to the surface information according to a preset standard.

[0038] The position estimation unit (130) can generate driving information of a mobile object based on rotation information and surface information from which noise has been removed. Here, the driving information of the mobile object can include driving distance information and driving direction information of the mobile object. In addition, the position estimation unit (130) can learn the driving information of the mobile object using an artificial intelligence neural network (CRNN, Convolution Recurrent Neural Network) (hereinafter, referred to as a second artificial intelligence neural network). That is, the position estimation unit (130) can generate driving information of the mobile object based on the surface information acquired from the surface selection unit (110) and rotation information from which noise has been removed from the corresponding surface.

[0039] The location calculation unit (140) can determine the location of the moving object based on the driving information of the moving object generated by the location estimation unit (130).

[0040] Figures 2 to 8 are exemplary diagrams showing examples of a device for estimating the position of a mobile body according to an embodiment of the present invention classifying a road surface.

[0041] Referring to FIGS. 2 to 8, rotation information measured by a wheel encoder (50) according to a road surface is shown. Each rotation information represents rotation information measured at the rotation speed of the same wheel for 1 second on a different road.

[0042] As shown in FIGS. 2 to 8, rotation information is different for each road, and based on this, the position estimation device (100) of the moving object can generate surface information.

[0043] The surface selection unit (110) can generate surface information for each road using the standard deviation value of rotation information for each road. In other words, the position estimation device (100) for a mobile object can estimate the position of a mobile object on any road by distinguishing the road on which the mobile object is driving and varying the coefficients of the Kalman filter (130) according to the surface of the road.

[0044] Figure 9 is a flowchart showing a method for estimating the position of a mobile object according to an embodiment of the present invention.

[0045] Referring to FIG. 9, a method for estimating the position of a mobile object according to an embodiment of the present invention may include a step (S310) in which a processor learns and generates surface information, a step (S320) in which noise of rotation information is removed according to the surface information, a step (S33) in which driving information of the mobile object is generated, and a step (S340) in which the position of the mobile object is determined.

[0046] Step (S240) of learning and generating surface information may be performed by a surface selection unit (110) based on rotation information generated by a wheel encoder (50) of the mobile vehicle, to learn and generate surface information of a road on which the mobile vehicle is driving. The surface selection unit (110) may generate surface information based on a standard deviation value of pulse data included in the rotation information. The surface selection unit (110) may generate surface information by selecting a road with a higher friction as the standard deviation value increases. In addition, the surface selection unit (110) may set a threshold value of the standard deviation value to distinguish between roads with high friction and roads with low friction. In this case, the surface selection unit (110) may update the surface information when the standard deviation value exceeds the set threshold value. In addition, the surface selection unit (110) may learn surface information based on rotation information by using an artificial intelligence neural network (CNN, Convolutional Neural Network) (hereinafter referred to as a first artificial intelligence neural network).

[0047] In addition, 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 on 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, such as indoor hallways, sidewalks with board blocks, asphalt roads, unpaved roads, grass, and athletics tracks, and learn surface information of the corresponding roads.

[0048] The step (S320) of removing noise from rotation information according to surface information can remove noise from rotation information by using a Kalman filter (120) to remove noise from rotation information, but varying a filtering coefficient according to surface information. For example, rotation information has different standard deviation values ​​according to each surface, and the Kalman filter (120) can remove noise from rotation information by checking, through surface information obtained from the surface selection unit (110), on which road the rotation information was measured together with the rotation information, and setting a filtering coefficient value according to the surface information according to a preset standard.

[0049] The step (S330) of generating driving information of a mobile object may be performed by a position estimation unit (130) to generate driving information of the mobile object based on rotation information and surface information from which noise has been removed. Here, the driving information of the mobile object may include driving distance information and driving direction information of the mobile object. In addition, the position estimation unit (130) may learn the driving information of the mobile object using an artificial intelligence neural network (CRNN, Convolution Recurrent Neural Network) (hereinafter, referred to as a second artificial intelligence neural network). That is, the position estimation unit (130) may generate driving information of the mobile object based on surface information acquired from the surface selection unit (110) and rotation information from which noise has been removed from the corresponding surface.

[0050] The step (S340) of determining the location of the moving object can be performed by the location calculation unit (140) to determine the location of the moving object based on the driving information of the moving object generated by the location estimation unit (130).

[0051] Although preferred embodiments of the present invention have been described above, the embodiments disclosed in the present invention are not intended to limit the technical spirit of the present invention, but rather to explain it. Therefore, the technical spirit of the present invention includes not only each disclosed embodiment but also a combination of disclosed embodiments, and further, the scope of the technical spirit of the present invention is not limited by these embodiments. In addition, those 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 considered as equivalents and falling within the scope of the present invention.

[0052] [Explanation of symbols]

[0053] 50: Wheel encoder

[0054] 100: Position estimation device

[0055] 110: Surface selection section

[0056] 120: Kalman filter

[0057] 130: Location estimation unit

[0058] 140: Position operation unit

Claims

1. In a device for estimating the position of a moving object including a wheel encoder, A surface selection unit that learns and generates surface information of a road on which the mobile device is driving based on rotation information generated from the wheel encoder; A Kalman filter that removes noise from the rotation information by varying the filtering coefficient according to the surface information; A position estimation unit that generates driving information of the mobile body based on the rotation information and the surface information from which the noise has been removed; and A position calculation unit that determines the position of the moving object based on the driving information; A position estimation device for a moving object characterized by:

2. In paragraph 1, The above surface selection section, Generating the surface information based on the standard deviation value of the pulse data included in the rotation information A position estimation device for a moving object characterized by:

3. In paragraph 2, The above surface selection section, The larger the standard deviation value, the higher the frictional force is selected as the road, and the surface information is generated. A position estimation device for a moving object characterized by:

4. In paragraph 3, The above surface selection section, Setting a threshold for the above standard deviation value to distinguish between roads with high and low friction A position estimation device for a moving object characterized by:

5. In paragraph 4, The above surface selection section, If the above standard deviation value exceeds the set threshold, updating the surface information A position estimation device for a moving object characterized by:

6. In paragraph 3, The above surface selection section, Learning surface information based on the rotation information using the first artificial intelligence neural network (CNN) A position estimation device for a moving object characterized by:

7. In paragraph 6, The above surface selection section, Learning the surface information through the rotation information measured at the same time and at the same speed on different roads. A position estimation device for a moving object characterized by:

8. In paragraph 7, The above surface selection section, Updating surface information by comparing and analyzing the rotation information collected from different roads. A position estimation device for a moving object characterized by:

9. In paragraph 1, The driving information of the above mobile device is: Including driving distance information and driving direction information of the above moving object A position estimation device for a moving object characterized by:

10. In paragraph 1, The above location estimation unit, Learning driving information of the above-mentioned mobile device using a second artificial intelligence neural network (CRNN) A position estimation device for a moving object characterized by:

11. A method for estimating the position of a moving object including a wheel encoder, The processor, (a) a step of learning and generating surface information of a road on which the mobile body is driving based on rotation information generated from the wheel encoder; (b) a step of removing noise from the rotation information by varying the filtering coefficient according to the surface information; (c) a step of generating driving information of the moving object based on the rotation information and the surface information from which the noise has been removed; and (d) a step of determining the location of the moving object based on the driving information; A method for estimating the position of a moving object characterized by .

12. In paragraph 11, In the above step (a), the processor, Generating the surface information based on the standard deviation value of the pulse data included in the rotation information A method for estimating the position of a moving object characterized by .

13. In paragraph 12, The above processor, The larger the standard deviation value, the higher the frictional force is selected as the road, and the surface information is generated. A method for estimating the position of a moving object characterized by .

14. In paragraph 13, The above processor, Setting a threshold for the above standard deviation value to distinguish between roads with high and low friction A method for estimating the position of a moving object characterized by .

15. In paragraph 14, The above processor, If the above standard deviation value exceeds the set threshold, updating the surface information A method for estimating the position of a moving object characterized by .

16. In paragraph 13, The above processor, Learning surface information based on the rotation information using the first artificial intelligence neural network (CNN) A method for estimating the position of a moving object characterized by .

17. In paragraph 16, The above processor, Learning the surface information through the rotation information measured at the same time and at the same speed on different roads. A method for estimating the position of a moving object characterized by .

18. In paragraph 17, The above processor, Updating surface information by comparing and analyzing the rotation information collected from different roads. A method for estimating the position of a moving object characterized by .

19. In paragraph 11, In the above step (c), the driving information of the mobile device is: Including driving distance information and driving direction information of the above moving object A method for estimating the position of a moving object characterized by .

20. In paragraph 11, In the above step (c), the processor, Learning driving information of the above-mentioned mobile device using a second artificial intelligence neural network (CRNN) A method for estimating the position of a moving object characterized by .

Images