Information processing apparatus, information processing method, and information processing system

The iToF ranging sensor generates a 3D point cloud and sets a mask area, which solves the control problem of autonomously guiding vehicles into specific locations, and realizes the effect of effectively preventing vehicles from entering without increasing computing resources and power consumption.

CN118922745APending Publication Date: 2024-11-08SONY GROUP CORP +1
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202380029192.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2022-03-29
Filing Date
2023-03-02
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

The prior art is difficult to effectively prevent autonomously guiding vehicles into specific locations without increasing computing resources and power consumption, especially when images are needed to identify, there are problems with reduced reliability of distance measurement and advanced expertise requirements.

Method used

By using iToF ranging sensor to generate a 3D point cloud, and setting the mask area based on the intensity image, smooth filtering is performed to reduce depth error detection, and combining feature shape extraction and virtual roadblock configuration, behavior control of autonomous guidance vehicles is achieved.

Benefits of technology

It realizes control to effectively prevent autonomous guidance of vehicles into specific locations without increasing computing resources and power consumption, reduces the impact of deep mis-checking, reduces the workload of behavior determination, and improves the economics of the system and reliability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118922745A_ABST
    Figure CN118922745A_ABST
Patent Text Reader

Abstract

The present invention can simply and inexpensively implement control for preventing a moving body such as an autonomous guided vehicle from entering a specific position. A mask region setting unit sets, on the basis of an intensity image output from a distance measuring sensor that measures a distance by accumulating reflected light and detecting a phase difference between irradiation light and the reflected light, a mask region in which a three-dimensional point group output from the distance measuring sensor is not smoothed. The smoothing filter processor performs smoothing processing on the three-dimensional point group output from the distance measuring sensor. In this case, the three-dimensional point group in the set mask region is output without smoothing the three-dimensional point group. According to the present invention, in a three-dimensional point group that has undergone smoothing processing, a three-dimensional point group related to depth false detection can be retained only in a desired area, and by using this feature, for example, control for preventing a moving body such as an autonomous guided vehicle from entering a specific position can be realized simply and at low cost.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present technology relates to an information processing device, an information processing method, and an information processing system, and in particular, to an information processing device and the like that can be applied to behavior control of a moving body such as an autonomously guided vehicle. Background Art

[0002] In recent years, autonomous guided vehicles (AGVs) have been active in places such as distribution warehouses and factories. In order to prevent an autonomous guided vehicle from entering a specific location, for example, it is conceivable that the autonomous guided vehicle recognizes the specific location through image recognition so as not to enter the specific location. In this case, it is envisaged that the following problems exist: data collection and machine learning need to be performed in advance, advanced expertise needs to be introduced, high-performance computing devices are required, and power consumption increases. For example, Patent Document 1 discloses that the reliability of the distance measurement value decreases at the boundary between the object and the background.

[0003] Reference List

[0004] Patent Literature

[0005] Patent document 1: International Patent Publication No. 2021 / 176872A. Summary of the invention

[0006] Problems to be solved by the present invention

[0007] An object of the present technology is to easily and inexpensively implement control for preventing a moving body such as an autonomously guided vehicle from entering a specific position.

[0008] Solution to the problem

[0009] The idea of ​​this technology is

[0010] An information processing device comprising

[0011] a mask area setting unit that sets a mask area that does not smooth a 3D point cloud output from a distance measuring sensor that measures a distance by accumulating reflected light and detecting a phase difference between irradiated light and reflected light, based on an intensity image output from the distance measuring sensor, and

[0012] a smoothing filter processor that performs smoothing processing on the 3D point cloud output from the ranging sensor and outputs the 3D point cloud, wherein

[0013] The smoothing filter processor outputs the 3D point cloud of the set mask area as it is without performing smoothing processing.

[0014] In the present technology, a mask area setting unit sets a mask area in which smoothing is not performed on a 3D point cloud output from a ranging sensor based on an intensity image output from the ranging sensor, which measures the distance by accumulating reflected light and detecting a phase difference between the irradiated light and the reflected light. For example, the ranging sensor may include an iToF ranging sensor. Then, a smoothing filter processor performs smoothing processing on the 3D point cloud output from the ranging sensor. In this case, the 3D point cloud of the set mask area is output as is without smoothing processing.

[0015] For example, the mask area setting unit may extract a characteristic shape from the intensity image, and set the mask area corresponding to the area of ​​the extracted characteristic shape. By setting the mask area corresponding to the area of ​​the characteristic shape extracted from the intensity image in this way, a 3D point cloud related to the depth misdetection of the area of ​​the characteristic shape may be used. For example, in the case where a tape having a pattern associated with the characteristic shape is attached to surround a specific location, a virtual roadblock may be configured on the 3D point cloud related to the depth misdetection, and control for preventing a moving body such as an autonomous guided vehicle from entering a specific location may be easily and inexpensively implemented.

[0016] In addition, for example, when the contrast of the region of the characteristic shape is equal to or greater than a threshold value, the mask region setting unit can set the mask region corresponding to the region of the characteristic shape. Therefore, in the case where there is a portion having a similar pattern in addition to the pattern corresponding to the characteristic shape of the tape attached by the user in the environment, the characteristic shape can be prevented from being extracted from the intensity image corresponding to the portion, and an erroneous mask region can be prevented from being set.

[0017] In addition, for example, when the distance from the region of the characteristic shape is less than a threshold value, the mask region setting unit can set the mask region corresponding to the region of the characteristic shape. Therefore, when the distance from the region of the characteristic shape is equal to or greater than the threshold value, it is possible to prevent the mask region associated with the region of the characteristic shape from being set, and the 3D point cloud related to the depth misdetection that is not required for behavior determination can be deleted by smoothing processing, and the workload of behavior determination using the 3D point cloud of a moving body such as an autonomous guided vehicle can be reduced.

[0018] As described above, in the present technology, smoothing processing is performed on the 3D point cloud output from the ranging sensor, a mask area is set based on the intensity image, and the mask area is output without smoothing processing. In the 3D point cloud after the smoothing filter processing, the 3D point cloud related to the depth misdetection can be retained only in the required area, and, for example, by using the 3D point cloud, control for preventing a moving body such as an autonomous guided vehicle from entering a specific position can be easily and inexpensively implemented.

[0019] Note that, for example, the present technology may further include a behavior determiner that sets an entry-prohibited area based on the 3D point cloud output from the smoothing filter processor and determines the behavior of the moving body. In this case, the entry-prohibited area is set by using the 3D point cloud related to the depth misdetection included in the 3D point cloud output from the smoothing filter processor as a virtual roadblock, and control for preventing a moving body such as an autonomous guided vehicle from entering a specific location can be easily and inexpensively implemented.

[0020] Note that another concept of this technology is

[0021] An information processing method comprising

[0022] a mask area setting process for setting a mask area in which a 3D point cloud output from a ranging sensor that measures distance by accumulating reflected light and detecting a phase difference between irradiated light and reflected light, based on an intensity image output from the ranging sensor, and

[0023] The smoothing filter processing process is used to perform smoothing processing on the 3D point cloud output from the ranging sensor and output the 3D point cloud, wherein

[0024] The smoothing filter processing procedure includes outputting the 3D point cloud of the set mask area as it is without performing smoothing processing.

[0025] In addition, another concept of the present technology is

[0026] An information processing system comprising

[0027] Display devices,

[0028] an indicating device for instructing the display device to display a regular pattern, and

[0029] An information processing apparatus that performs distance measurement in an environment including a display device, wherein

[0030] The information processing device includes

[0031] A distance measuring sensor that measures distance by accumulating reflected light and detecting the phase difference between the irradiated light and the reflected light,

[0032] A mask region setting process for extracting a characteristic shape from the intensity image output by the ranging sensor, and setting a mask region for not smoothing the 3D point cloud output by the ranging sensor corresponding to the region of the extracted characteristic shape, and

[0033] a smoothing filter processor that performs smoothing processing on the 3D point cloud output from the ranging sensor and outputs the 3D point cloud, and

[0034] The smoothing filter processor outputs the 3D point cloud of the set mask area as it is without performing smoothing processing.

[0035] The present technology can enable a display device to display a regular pattern in a specific situation in response to an indication of an indication device. For example, the indication device may include a user terminal or a network server. In the case where a regular pattern is displayed on a display device, a 3D point cloud related to depth misdetection can be generated in the area corresponding to the pattern in the 3D point cloud after smoothing filtering, and, for example, by using the 3D point cloud, control for preventing a moving object such as an autonomous guided vehicle from entering a specific position can be performed. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 : is a block diagram showing a configuration example of a moving body system as a first embodiment.

[0037] Figure 2 is a diagram used to describe the intensity image and 3D point cloud output from the iToF sensor.

[0038] Figure 3 is a block diagram showing an example of a drive control device included in an autonomously guided vehicle.

[0039] Figure 4 is a flowchart showing an example of a processing procedure of the drive control device.

[0040] Figure 5 is a flowchart showing another example of the processing procedure of the drive control device.

[0041] Figure 6 : is a block diagram showing a configuration example of a moving body system as a second embodiment.

[0042] Figure 7 is a block diagram showing an example of a drive control device, an indication device, and a display apparatus included in an autonomously guided vehicle.

[0043] Figure 8 is a block diagram showing a hardware configuration example of a computer. DETAILED DESCRIPTION

[0044] Hereinafter, a mode for carrying out the present invention (hereinafter referred to as "embodiment") will be described. Note that the description will be made in the following order.

[0045] 1. First Implementation

[0046] 2. Second Implementation

[0047] 3. Modification.

[0048] <1. First Embodiment>

[0049] [Configuration of mobile system]

[0050] Figure 1 A configuration example of a moving body system 10 as a first embodiment is shown. The moving body system 10 includes an autonomous guided vehicle (transport robot) 100 as a moving body and a black-and-white striped tape 200 attached to a floor surface.

[0051] The tape 200 is attached to surround the portion that the autonomous guided vehicle 100 is prevented from entering. Note that the pattern of the tape 200 is not limited to the black and white stripe pattern, and may be a yellow and black stripe pattern, and may be a stripe pattern using colors with a contrast difference. In addition, the pattern of the tape 200 is not limited to the stripe pattern, and may be any regular pattern, for example, may be a dot pattern, a zigzag pattern, a wave pattern, etc.

[0052] The autonomous guidance machine 100 includes an indirect time-of-flight (iToF) sensor as a distance measuring sensor. The iToF sensor is a distance measuring sensor that measures the distance by accumulating reflected light and detecting the phase difference between the irradiated light and the reflected light. Note that although a distance measuring sensor that measures the distance based on a similar principle may be provided instead of the iToF sensor, the following description will be made based on the assumption that the iToF sensor is provided.

[0053] In the iToF sensor, depth misdetection may occur in high contrast portions of the intensity image. In addition, it is known that this phenomenon occurs due to the measurement principle of iToF, that is, a large change in the confidence value during phase measurement, and the faster the moving speed of the autonomous guided vehicle 100, the more obvious this phenomenon is.

[0054] Figure 2 (a) shows an example of an intensity image output from the iToF sensor when measuring the distance to the area to which the band 200 is attached. The intensity image represents the intensity of the light detected by the iToF sensor (image sensor), and as the detected light becomes stronger, the intensity becomes brighter. In addition, the intensity image may be referred to as a confidence image. The intensity image represents the reliability of the 3D point cloud of each unit output from the iToF sensor, and the brighter the intensity image, the higher the confidence value (reliability).

[0055] exist Figure 2 In the intensity image shown in (a), a black and white shape (pattern) corresponding to the black and white stripe pattern of the belt 200 exists as a characteristic shape, a high contrast portion exists in the region of the characteristic shape, and depth misdetection occurs in this portion. Figure 2 (b) shows an example of a 3D point cloud corresponding to the black and white stripe pattern of the tape 200, and in which a depth misdetection occurs. Figure 2 (c) shows the floor viewed from the side Figure 2 (b) shows the 3D point cloud. It can be seen that the point cloud protrudes from the floor surface, but in fact there should be nothing there.

[0056] Back again Figure 1 In the above, the autonomous guided vehicle 100 recognizes a point protruding from the floor surface due to the depth misdetection occurring in the area to which the belt 200 is attached as a virtual roadblock (an obstacle that does not actually exist), and determines a behavior to avoid collision with the virtual roadblock. As a result, the autonomous guided vehicle 100 is prevented from entering the position surrounded by the belt 200. That is, the autonomous guided vehicle 100 performs control to prevent entering the position surrounded by the belt 200.

[0057] Figure 3 An example of a drive control device 110 included in the autonomous guided vehicle 100 is shown. The drive control device 110 includes an iToF sensor (iToF camera) 111, a smoothing filter processor 112, a behavior determiner 113, a drive controller 114, a feature detector 115, and a mask region extractor 116.

[0058] As is known, the iToF sensor 111 images the environment and measures the distance of each pixel, and outputs an intensity image and a 3D point cloud.

[0059] The smoothing filter processor 112 performs smoothing processing on the 3D point cloud (3D point cloud data) output from the iToF sensor 111 and outputs the 3D point cloud. Here, the smoothing processing is not only a simple averaging processing, but also a noise removal processing such as a low-pass filter or a Kalman filter. Through this smoothing processing, the erroneous points caused by the depth misdetection included in the 3D point cloud output from the iToF sensor 111 are deleted.

[0060] Based on the 3D point cloud (3D point cloud data) output from the smoothing filter processor 112, the behavior determiner 113 confirms the situation around the autonomous guided vehicle 100 and determines the behavior of the autonomous guided vehicle 100. In this case, if there is an obstacle, an entry prohibition area is set, and a moving speed and a moving route are calculated to avoid a collision. Based on the determination of the behavior determiner 113, the drive controller 114 controls the operation of the drive system of the autonomous guided vehicle 100 so that it moves, for example, based on the calculated moving speed and moving route.

[0061] The feature detector 115 extracts a feature shape from the intensity image (intensity image data) output by the smoothing filter processor 112. In this case, the feature detector 115 extracts a feature shape based on the feature shape data. The feature shape is a black and white shape corresponding to the black and white stripe pattern of the belt 200.

[0062] The mask region extractor 116 sets a region where the 3D point cloud is not smoothed, that is, a mask region, corresponding to the region of the characteristic shape extracted by the feature detector 115. In this case, the three-dimensional region is set as the mask region to include the point cloud corresponding to the region of the extracted characteristic shape.

[0063] The mask region extractor 116 notifies the smoothing filter processor 112 of the mask region. The smoothing filter processor 112 outputs the 3D point cloud of the mask region as it is without performing smoothing processing, and outputs the 3D point cloud of the region other than the mask region after performing smoothing processing.

[0064] exist Figure 3 In the driving control device 110 shown in FIG. 1 , the feature detector 115 extracts the intensity image corresponding to the band 200 (see FIG. 2 ) from the intensity image output by the iToF sensor 111. Figure 1 ) as a characteristic shape, the mask area extractor 116 sets a mask area corresponding to the characteristic shape, and the smoothing filter processor 112 performs smoothing processing on the 3D point cloud output from the iToF sensor 111 except the mask area.

[0065] Therefore, the 3D point cloud output from the smoothing filter processor 112 includes points protruding from the floor surface due to the depth misdetection occurring in the area to which the belt 200 is attached. Therefore, in the behavior determiner 113, the points protruding from the floor surface included in the 3D point cloud are identified as virtual roadblocks (obstacles that do not actually exist), an entry prohibition area is set to avoid collision with the points, and a moving speed and a moving route are calculated. Then, the drive controller 114 controls the operation of the drive system of the autonomous guided vehicle 100 so as to move based on the moving speed and the moving route calculated by the behavior determiner 113. Therefore, the autonomous guided vehicle 100 is prevented from entering a position surrounded by the belt 200.

[0066] Note that it is also conceivable that the mask region extractor 116 sets the mask region when the contrast of the region of the extracted characteristic shape is equal to or greater than the threshold value, rather than setting the mask region corresponding to all regions of the characteristic shape extracted by the feature detector 115. Therefore, in the case where there is a portion having a similar pattern in the environment in addition to a pattern corresponding to the characteristic shape of the band 200 attached by the user, it is possible to prevent the characteristic shape from being extracted from the intensity image corresponding to the portion, and it is possible to prevent an erroneous mask region from being set.

[0067] Furthermore, it is also conceivable that the mask region extractor 116 sets the mask region corresponding to the region of the characteristic shape when the distance to the region of the characteristic shape is less than the threshold value, rather than setting the mask region corresponding to all regions of the characteristic shape extracted by the feature detector 115. Therefore, when the distance to the region of the characteristic shape is equal to or greater than the threshold value, the mask region associated with the region of the characteristic shape can be prevented from being set, and the 3D point cloud associated with the depth misdetection can be deleted through smoothing, which is far away from the pasting position of the tape 200 and does not need to be determined, and the workload of the behavior determiner 113 using the 3D point cloud for behavior determination can be reduced.

[0068] Figure 4 The flowchart shows Figure 3 An example of the processing procedure of the drive control device 110 is shown. First, in step ST1, the drive control device 110 starts the processing. Next, the drive control device 110 reads the contrast threshold value Cth from the storage medium in step ST2, and reads the feature data from the storage medium in step ST3.

[0069] Next, in step ST4, the drive control device 110 acquires an intensity image of a specific frame from the iToF sensor 111. Note that the intensity image and the 3D point cloud are output from the iToF sensor 111 at, for example, 30 frames per second.

[0070] Next, in step ST5 , the drive control device 110 extracts a characteristic shape from the intensity image acquired in step ST4 based on the characteristic data read in step ST3 .

[0071] Next, in step ST6, the drive control device 110 determines whether there is a characteristic shape. If there is a characteristic shape, in step ST7, the drive control device 110 extracts the contrast Co of the region of the characteristic shape extracted in step ST5. The contrast Co is the difference between the maximum brightness and the minimum brightness in the characteristic shape region.

[0072] Next, in step ST8, the drive control device 110 determines whether the contrast Co is equal to or greater than the contrast threshold Cth read in step ST2. When the contrast Co is equal to or greater than the contrast threshold Cth, the drive control device 110 sets an area where the 3D point cloud is not smoothed, i.e., a mask area, corresponding to the area of ​​the characteristic shape in step ST9.

[0073] Next, the drive control device 110 proceeds to the process of step ST10. When there is no characteristic shape in the above-mentioned step ST6, or when the contrast Co is not equal to or greater than the contrast threshold value Cth in step ST8, the process immediately proceeds to the process of step ST10. In step ST10, the drive control device 110 acquires a 3D point cloud of a frame corresponding to the intensity image of the specific frame acquired in step ST4 from the iToF sensor 111.

[0074] Next, in step ST11, the drive control device 110 performs smoothing processing on the 3D point cloud acquired in step ST10. In this case, when the mask area is set in step ST9, the smoothing processing is not performed on the 3D point cloud of the mask area.

[0075] Next, in step ST12, the drive control device 110 confirms the situation around the autonomous guided vehicle 100 based on the smoothed 3D point cloud, determines the behavior of the autonomous guided vehicle 100, and calculates the moving speed and moving route of the autonomous guided vehicle 100. In this case, when a point protruding from the floor surface due to depth misdetection is included in the 3D point cloud, the point is identified as a virtual roadblock (an obstacle that does not actually exist), the behavior is determined to avoid collision with the point, and the moving speed and moving route are calculated. In addition, in step ST12, the drive control device 110 controls the operation of the drive system of the autonomous guided vehicle 100 so that it moves based on the calculated moving speed and moving route.

[0076] After the process of step ST12, the drive control device 110 returns to the process of step ST4 and repeats the process similar to the above for the intensity image and 3D point cloud in the next frame. Note that the repetition cycle of the process may not be performed on a frame-by-frame basis but may be performed in a longer cycle.

[0077] Figure 5 The flowchart shows Figure 3 Another example of the processing procedure of the drive control device 110 is shown. Figure 5 In, with Figure 4 Steps corresponding to the steps in are assigned the same reference numerals.

[0078] exist Figure 5 In the processing procedure shown in the flowchart of , after the processing of step ST2, the drive control device 110 reads the distance threshold value Lth from the storage medium in step ST13, and then moves to the processing of step ST3.

[0079] In addition, Figure 5In the processing process shown in the flowchart, when the contrast Co is equal to or greater than the contrast threshold Cth in step ST8, the drive control device 110 extracts the distance Lo to the area of ​​the characteristic shape in step ST14. Next, in step ST15, the drive control device 110 determines whether the distance Lo is equal to or greater than the distance threshold Lth.

[0080] Then, when the distance Lo is not equal to or greater than the distance threshold Lth, the drive control device 110 proceeds to the process of step ST9, and when the distance Lo is equal to or greater than the distance threshold Lth, the drive control device 110 proceeds to the process of step ST10 without setting a mask area.

[0081] exist Figure 4 In the processing shown in the flowchart of , when a characteristic shape exists in the intensity image and the contrast Co is equal to or greater than the contrast threshold Cth, a mask area is set corresponding to the area of ​​the characteristic shape. Figure 5 In the processing process shown in the flowchart, when there is a characteristic shape in the intensity image, the contrast Co of the area of ​​the characteristic shape is equal to or greater than the contrast threshold Cth, and the distance Lo of the area of ​​the characteristic shape is not equal to or greater than the distance threshold Cth, a mask area is set corresponding to the area of ​​the characteristic shape.

[0082] As mentioned above, in Figure 1 In the moving body system 10 shown, the autonomous guided vehicle 100 recognizes a point protruding from the floor surface due to a depth misdetection occurring in the area to which the belt 200 is attached as a virtual roadblock (an obstacle that does not actually exist), determines a behavior to avoid collision with the point, calculates a moving speed and a moving route, and controls the operation of the drive system. Therefore, the autonomous guided vehicle 100 can be prevented from entering a position surrounded by the belt 200. That is, by simply attaching the belt 200 around a position to which it is desired to prevent the autonomous guided vehicle 100 from entering, it is possible to easily and inexpensively prevent the autonomous guided vehicle 100 from entering the position.

[0083] In this case, compared with the case where a specific position is recognized by image recognition and control is performed so as not to enter the specific position, data collection and machine learning are not required in advance, a high-performance computing device is not required, power consumption can be suppressed, and control to prevent the autonomous guided vehicle 100 from entering the specific position can be easily and inexpensively implemented. In addition, in this case, the belt 200 affixed to the floor has no physical unevenness for a person, and is safe because there is no risk of tripping during travel.

[0084] <2. Second Embodiment>

[0085] [Configuration of mobile system]

[0086] Figure 6 FIG. 2 shows a configuration example of a moving body system 20 as a second embodiment. Figure 6 In, with Figure 1 Corresponding parts in FIG. 1 are denoted by the same reference numerals, and detailed descriptions of these parts are appropriately omitted. The moving body system 20 includes an autonomous guided vehicle (transport robot) 100 as a moving body and a display device 300 embedded in a floor surface.

[0087] The display device 300 includes a liquid crystal display panel, etc. In response to an instruction from an instruction device (eg, a user terminal or a network server), the display device 300 displays a band-shaped black and white stripe pattern 310 so as to be in the same manner as in the above Figure 1 This display is similar to the state in which the black and white pattern tape 200 is pasted on the floor surface in the moving body system 10 in FIG. This display is performed when it is desired to prevent the autonomous guided vehicle 100 from entering a position surrounded by the band-like black and white stripe pattern 310.

[0088] Note that the pattern displayed on the display device 300 is not limited to the black and white stripe pattern, and may be a yellow and black stripe pattern, and may be a stripe pattern using colors with a contrast difference. In addition, the pattern displayed on the display device 300 is not limited to the stripe pattern, and may be any regular pattern, and for example, may be a dot pattern, a zigzag pattern, a wave pattern, etc.

[0089] In a state where a band-shaped black and white stripe pattern 310 is displayed on the display device 300, similar to the above Figure 1 In the moving body system 10 in FIG. 1 , the autonomous driving vehicle 100 recognizes a point protruding from the floor surface due to a depth misdetection occurring in the area of ​​the band-shaped black and white stripe pattern 310 displayed on the display device 300 as a virtual roadblock (an obstacle that does not actually exist), and determines a behavior for avoiding a collision with the virtual roadblock. As a result, the autonomous guided vehicle 100 is prevented from entering a position surrounded by the band-shaped black and white stripe pattern 310. That is, the autonomous guided vehicle 100 performs control for preventing entry into a position surrounded by the band-shaped black and white stripe pattern 310.

[0090] Figure 7 1 shows an example of a drive control device 110, a display device 300, and an indication device 350 included in an autonomous guided vehicle 100. The indication device 350 indicates the display device 300 to display a band-shaped black and white stripe pattern 310. Although detailed description is omitted, the drive control device 110 is similar to the above-mentioned reference numeral 310. Figure 3 The invention is configured in a similar manner and operates in a similar manner as described above.

[0091] As mentioned above, in Figure 6In the illustrated moving body system 20, the autonomous guided vehicle 100 recognizes a point protruding from the floor surface due to a depth misdetection occurring in the area of ​​the band-shaped black and white stripe pattern 310 displayed on the display device 300 as a virtual roadblock (an obstacle that does not actually exist), determines a behavior to avoid collision with the point, calculates a moving speed and a moving route, and controls the operation of the drive system. Therefore, by displaying the band-shaped black and white stripe pattern 310 on the display device 300 under certain conditions, it is possible to prevent the autonomous guided vehicle 100 from entering a position surrounded by the band-shaped black and white stripe pattern 310.

[0092] Note that in the above description, an example has been described in which the band-like black and white stripe pattern 310 is displayed by the display device 300 (for example, including a liquid crystal display panel). Alternatively, it is also conceivable to perform similar display by other display devices such as a display device in which a plurality of LEDs are arranged.

[0093] [Processing by computer software]

[0094] Above Figure 4 and Figure 5 The processing shown in the flowchart can be performed by hardware or by software. In the case of performing a series of processing by software, the program constituting the software is installed from a recording medium to, for example, a computer built into dedicated hardware or a general-purpose computer capable of performing various functions by installing various programs.

[0095] Figure 8 4 is a block diagram showing an example of a hardware configuration of a computer 400. The computer 400 includes a CPU 401, a ROM 402, a RAM 403, a bus 404, an input / output interface 405, an input unit 406, an output unit 407, a memory 408, a driver 409, a connection port 410, and a communication unit 411. Note that the hardware configuration shown here is an example, and some components may be omitted. In addition, components other than those shown here may be included.

[0096] The CPU 401 functions as a calculation processing device or a control device, and controls all or part of the operations of the components based on various programs recorded in the ROM 402 , the RAM 403 , the storage 408 , or the removable recording medium 501 , for example.

[0097] The ROM 402 is a device that stores programs to be read by the CPU 401, data to be used for calculations, etc. The RAM 403 temporarily or permanently stores, for example, programs to be read by the CPU 401, various parameters that appropriately change when executing the programs, and the like.

[0098] The CPU 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. Furthermore, various components are connected to the bus 404 via an interface 405.

[0099] For example, a mouse, a keyboard, a touch panel, a button, a switch, a lever, or the like is used as the input unit 406. Furthermore, as the input unit 406, a remote controller capable of transmitting a control signal by using infrared rays or other radio waves may be used.

[0100] The output unit 407 is a device capable of visually or audibly notifying the user of the acquired information, for example, a display device such as a cathode ray tube (CRT), LCD or organic EL, an audio output device such as a speaker or headphones, a printer, a mobile phone or a fax machine.

[0101] The memory 408 is a device for storing various types of data. For example, a magnetic storage device such as a hard disk drive (HDD), a semiconductor storage device, an optical storage device, a magneto-optical storage device, or the like is used as the memory 408 .

[0102] The drive 409 is a device that reads information recorded in the removable recording medium 501 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, for example, or writes information in the removable recording medium 501 .

[0103] The removable recording medium 501 is, for example, a DVD medium, a Blu-ray medium, an HD-DVD medium, various types of semiconductor storage media, etc. Of course, the removable recording medium 501 may be, for example, an IC card mounted with a non-contact IC chip, an electronic device, etc.

[0104] The connection port 410 is, for example, a port for connecting an external connection device 502, such as a universal serial bus (USB) port, an IEEE1394 port, a small computer system interface (SCSI), an RS-232C port, or an optical audio terminal. The external connection device 502 is, for example, a printer, a portable music player, a digital camera, a digital video camera, an IC recorder, etc.

[0105] The communication unit 411 is a communication device for connecting to the network 503, for example, a communication card for a wired or wireless LAN, Bluetooth or wireless USB (WUSB), a router for optical communication, a router for an asymmetric digital subscriber line (ADSL), a modem for various communications, etc.

[0106] Note that the program executed by the computer may be one in which processing is performed time-sequentially in the order described in this specification, or may be one in which processing is performed in parallel or at necessary timing (such as when a call is made).

[0107] <3. Modification>

[0108] Note that the preferred embodiments of the present disclosure have been described in detail with reference to the accompanying drawings, but the technical scope of the present disclosure is not limited to these examples. Obviously, a technician with ordinary knowledge in the technical field of the present disclosure can implement various types of changed or modified examples within the scope of the technical concept recorded in the claims, and such examples will also be naturally understood to belong to the technical scope of the present disclosure.

[0109] In addition, the effects described in this specification are merely exemplary or illustrative, and not restrictive. That is, in addition to or in place of the above effects, the technology of the present disclosure may also exhibit other effects that are obvious to those skilled in the art based on the description of this specification.

[0110] Furthermore, the present technology may also have the following configurations.

[0111] (1) An information processing device comprising:

[0112] a mask area setting unit that sets a mask area where a 3D point cloud output from a distance measuring sensor that measures a distance by accumulating reflected light and detecting a phase difference between irradiated light and the reflected light, based on an intensity image output from the distance measuring sensor; and

[0113] a smoothing filter processor that performs the smoothing process on the 3D point cloud output from the ranging sensor and outputs the 3D point cloud, wherein

[0114] The smoothing filter processor outputs the 3D point cloud of the set mask area as it is without performing the smoothing process.

[0115] (2) In the information processing device according to (1),

[0116] The mask region setting unit extracts a characteristic shape from the intensity image and sets a mask region corresponding to a region of the extracted characteristic shape.

[0117] (3) In the information processing device according to (2),

[0118] When the contrast of the region of the characteristic shape is equal to or greater than a threshold value, the mask region setting unit sets a mask region corresponding to the region of the characteristic shape.

[0119] (4) In the information processing device according to (2) or (3),

[0120] When the distance from the region of the characteristic shape is less than a threshold, the mask region setting unit sets a mask region corresponding to the region of the characteristic shape.

[0121] (5) The information processing device according to any one of (1) to (4), further comprising

[0122] A behavior determiner sets an entry-prohibited area based on the 3D point cloud output from the smoothing filter processor and determines a behavior of the moving body.

[0123] (6) In the information processing device according to any one of (1) to (5),

[0124] The distance measuring sensor includes an iToF distance measuring sensor.

[0125] (7) An information processing method, comprising:

[0126] a mask area setting process for setting a mask area for not smoothing a 3D point cloud output from the distance measuring sensor based on an intensity image output from the distance measuring sensor, the distance measuring sensor measuring distance by accumulating reflected light and detecting a phase difference between irradiated light and the reflected light; and

[0127] a smoothing filter processing process for performing the smoothing process on the 3D point cloud output from the ranging sensor and outputting the 3D point cloud, wherein

[0128] The smoothing filter processing includes outputting the 3D point cloud of the set mask area as it is without performing the smoothing processing.

[0129] (8) An information processing system comprising:

[0130] Display devices;

[0131] an indicating device, the indicating device instructing the display device to display a regular pattern; and

[0132] An information processing apparatus that performs distance measurement in an environment including the display device, wherein

[0133] The information processing device comprises

[0134] a distance measuring sensor that measures distance by accumulating reflected light and detecting a phase difference between irradiated light and the reflected light,

[0135] a mask region setting unit that extracts a characteristic shape from the intensity image output by the ranging sensor and sets a mask region that does not perform smoothing on the 3D point cloud output by the ranging sensor, corresponding to a region of the extracted characteristic shape; and

[0136] a smoothing filter processor that performs smoothing processing on a 3D point cloud output from the ranging sensor and outputs the 3D point cloud;

[0137] The smoothing filter processor outputs the 3D point cloud of the set mask area as it is without performing the smoothing process.

[0138] (9) In the information processing system according to (8),

[0139] The indicating device includes a user terminal or a network server.

[0140] (10) In the information processing device according to (8) or (9),

[0141] The distance measuring sensor includes an iToF distance measuring sensor.

[0142] Reference Mark List

[0143] 10, 20 mobile system

[0144] 100 autonomous guided vehicles

[0145] 110 drive control device

[0146] 111iToF sensor

[0147] 112 smoothing filter processor

[0148] 113 Behavior Determiner

[0149] 114 drive controller

[0150] 115 Feature Detector

[0151] 116 Mask area setting unit

[0152] 200 belts

[0153] 300 display devices

[0154] 310 striped black and white pattern

[0155] 350 indicating device.

Claims

1. An information processing device, comprising: a mask area setting unit that sets a mask area where a 3D point cloud output from a distance measuring sensor that measures a distance by accumulating reflected light and detecting a phase difference between irradiated light and reflected light, based on an intensity image output from the distance measuring sensor; and a smoothing filter processor that performs smoothing processing on the 3D point cloud output from the ranging sensor and outputs the 3D point cloud, wherein The smoothing filter processor outputs the 3D point cloud of the set mask area as it is without performing smoothing processing thereon.

2. The information processing device according to claim 1, wherein The mask region setting unit extracts a characteristic shape from the intensity image and sets the mask region corresponding to a region of the extracted characteristic shape.

3. The information processing device according to claim 2, wherein When the contrast of the region of the characteristic shape is equal to or greater than a threshold value, the mask region setting unit sets the mask region corresponding to the region of the characteristic shape.

4. The information processing device according to claim 2, wherein When the distance from the region of the characteristic shape is less than a threshold, the mask region setting unit sets the mask region corresponding to the region of the characteristic shape.

5. The information processing device according to claim 1, further comprising A behavior determiner sets an entry-prohibited area based on the 3D point cloud output from the smoothing filter processor and determines a behavior of the moving body.

6. The information processing device according to claim 1, wherein The distance measuring sensor includes an iToF distance measuring sensor.

7. An information processing method, comprising: a mask area setting process of setting a mask area in which a 3D point cloud output from a distance measuring sensor that measures distance by accumulating reflected light and detecting a phase difference between irradiated light and reflected light is not smoothed, based on an intensity image output from the distance measuring sensor; and a smoothing filter processing process, which performs a smoothing process on the 3D point cloud output from the ranging sensor and outputs the 3D point cloud, wherein During the smoothing filter processing, the 3D point cloud of the set mask area is outputted as it is without performing smoothing processing thereon.

8. An information processing system comprising: Display devices; an indicating device, the indicating device instructing the display device to display a regular pattern; as well as An information processing apparatus that performs distance measurement in an environment including the display device, wherein The information processing device comprises a distance measuring sensor that measures distance by accumulating reflected light and detecting a phase difference between irradiated light and reflected light, a mask region setting unit that extracts a characteristic shape from the intensity image output by the ranging sensor and sets a mask region for not smoothing the 3D point cloud output by the ranging sensor, corresponding to a region of the extracted characteristic shape; and a smoothing filter processor that performs smoothing processing on the 3D point cloud output from the ranging sensor and outputs the 3D point cloud; The smoothing filter processor outputs the 3D point cloud of the set mask area as it is without performing smoothing processing thereon.

9. The information processing system according to claim 8, wherein The indicating device is a user terminal or a network server.

10. The information processing system according to claim 8, wherein The distance measuring sensor includes an iToF distance measuring sensor.

Citation Information

Patent Citations

  • Information display control method, information display control device, and program

    WO2021176872A1