Transport vehicle system

Abstract

To provide a carrier system capable of supporting smooth traveling of a carrier.SOLUTION: The transport vehicle system 10 includes the setting unit 14 that sets, for each pixel constituting the image data of the map representing the real environment, the highest value of the evaluation value indicating the likelihood of the self-position estimation of the transport vehicle assumed in the pixel as the first evaluation value, the calculation unit 15 that calculates the evaluation value at the current position of the transport vehicle placed in the real environment as the second evaluation value, and the determination unit 16 that determines whether or not the map is correct based on the difference between the first evaluation value and the second evaluation value.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to a guided vehicle system. [Background technology]

[0002] Some guided vehicles, such as autonomous guided vehicles, have the function of estimating their own position while traveling. Guided vehicles with such a function estimate their own position based on the detection results of surrounding objects by the guided vehicle and a map stored in the guided vehicle. Patent Document 1 listed below discloses a technology for estimating the self-position of a moving body, including a guided vehicle, using a map showing the positions of obstacles in the moving area of ​​the moving body. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-18639 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the positions and number of obstacles shown on the stored map may change. If the positions and number of obstacles change, the map used for self-location estimation will differ from the actual environment in which the vehicle is traveling, which can cause problems for the autonomous driving of the vehicle.

[0005] Therefore, an object of the present invention is to provide a guided vehicle system that can support the smooth running of a guided vehicle. [Means for solving the problem]

[0006] A transport vehicle system according to one aspect of the present disclosure includes a setting unit that sets, for each pixel constituting image data of a map representing a real environment, the highest value of an evaluation value indicating the likelihood of the transport vehicle's self-position estimation expected at that pixel as a first evaluation value, a calculation unit that calculates, as a second evaluation value, an evaluation value at the current position of the transport vehicle placed in the real environment, and a determination unit that determines whether the map is correct based on the difference between the first evaluation value and the second evaluation value.

[0007] According to this aspect, by comparing the first evaluation value set as the theoretical maximum value for each pixel of the map with the second evaluation value calculated at the current position of the transport vehicle placed in the real environment, if there is a discrepancy between the two, it is possible to determine that there is a discrepancy between the map and the real environment, i.e., that there is an error in the map.

[0008] In the above aspect, the system further includes a screen generation unit that generates an evaluation screen in which a color associated with the first evaluation value is superimposed on a map based on the first evaluation value, and the screen generation unit may regenerate the evaluation screen based on the difference between the first evaluation value and the second evaluation value if the determination unit determines that the map is incorrect.

[0009] According to this aspect, if there is a discrepancy between the first evaluation value and the second evaluation value, an evaluation screen can be regenerated based on the difference, and the user can be informed through the generated evaluation screen that there is an error in the map.

[0010] In the above aspect, when the judgment unit judges that the map is incorrect, the screen generation unit may change the color superimposed on the part of the map judged to be incorrect to a color that allows the user to distinguish that the map is incorrect, and re-generate the evaluation screen.

[0011] According to this aspect, the user can visually understand that the map is incorrect by looking at the color superimposed on the map.

[0012] In the above aspect, when changing the color to be superimposed on the portion determined to be incorrect, the screen generating unit may change the color to a more noticeable color as the difference between the first evaluation value and the second evaluation value increases.

[0013] According to this aspect, the user can visually grasp the extent of the error in the map by distinguishing the colors superimposed on the map.

[0014] In the above aspect, the calculation unit may calculate the second evaluation value by determining whether the distance to the object measured by the laser emitted from the transport vehicle and the distance from the pixel on the map corresponding to the current position of the transport vehicle to the obstacle on the map are within the same range, for each of the lasers emitted from the transport vehicle.

[0015] According to this aspect, when calculating the second evaluation value indicating the likelihood of self-position estimation of a transport vehicle placed in a real environment, it is possible to use all lasers emitted from the transport vehicle, thereby improving the calculation accuracy of the second evaluation value.

[0016] In the above aspect, the calculation unit may calculate the second evaluation value by dividing the number determined to be within the equivalent range by the total number of lasers emitted from the transport vehicle.

[0017] According to this aspect, it is possible to estimate the self-position based on the proportion of the total number of lasers emitted that are determined to be within the same range as the distance measured in the real environment and the distance measured on the map. [Effects of the Invention]

[0018] According to the present invention, it is possible to provide a guided vehicle system that can support the smooth running of a guided vehicle. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a schematic diagram of a guided vehicle included in a guided vehicle system according to an embodiment of the present invention, viewed from directly above. [Figure 2]FIG. 1 is a block diagram showing an example of the configuration of a guided vehicle system. [Figure 3] FIG. 10 is a diagram illustrating an example of an evaluation screen. [Figure 4] 10 is a flowchart illustrating an example of processing executed in the guided vehicle system. DETAILED DESCRIPTION OF THE INVENTION

[0020] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS A preferred embodiment of the present invention will be described with reference to the accompanying drawings. In the drawings, components with the same reference numerals have the same or similar configurations.

[0021] FIG. 1 is a schematic diagram of a transport vehicle 1 according to an embodiment, viewed from directly above. The transport vehicle 1 is an autonomously traveling device, and may be, for example, a transport platform that transports luggage or the like placed on the vehicle body, or a transport robot that transports luggage or the like. In this embodiment, a case will be described where the transport vehicle 1 is an autonomous transport platform, for example. The transport vehicle 1 can move in all directions 360 degrees automatically or manually.

[0022] The transport vehicle 1 is equipped with two sensors 2a and 2b. The sensors 2a and 2b are sensors that measure the distance to an object, and include, for example, a laser scanner, a TOF (Time Of Flight) sensor, and a LiDAR (Light Detection and Ranging) sensor. In this embodiment, a case will be described in which the sensors 2a and 2b are laser scanners that can scan a range of 270 degrees with laser light.

[0023] 1, the scanning range Ra of sensor 2a and the scanning range Rb of sensor 2b partially overlap, and by combining the two scanning ranges Ra and Rb, it is possible to scan the entire periphery of the transported vehicle 1. This makes it possible to detect objects such as obstacles that may exist around the transported vehicle 1 (in all directions).

[0024] The number of sensors mounted on the transport vehicle 1 is not limited to two, but may be one, or three or more. It is sufficient that the mounted sensors can detect obstacles present in all directions in which the transport vehicle 1 can move.

[0025] An example of the configuration of a guided vehicle system 10 according to this embodiment will be described with reference to Fig. 2. The guided vehicle system 10 includes, for example, a guided vehicle 1 and a management device (not shown). The management device is an information processing device that can be used by a user who manages the guided vehicle 1, and has a processor. The management device may be, for example, a server device, a personal computer, a tablet terminal, or the like.

[0026] The transport vehicle system 10 includes, for example, a memory unit 11, a communication unit 12, a display unit 13, a setting unit 14, a calculation unit 15, a determination unit 16, and a screen generation unit 17. Each of these units may be incorporated into the transport vehicle 1 having a processor, may be incorporated into a management device, or may be incorporated separately into the transport vehicle 1 and the management device.

[0027] The storage unit 11 stores programs and various information used by executing the programs. The programs stored in the storage unit 11 are executed by a processor, whereby the functions of the respective units of the guided vehicle system 10 are realized.

[0028] Here, the various types of information stored in the storage unit 11 may include map information of the inside of a factory where the transport vehicle 1 travels. The map information may be map information that enables SLAM (Simultaneous Localization and Mapping).

[0029] The communication unit 12 controls communications between devices within the system and with external devices.

[0030] The display unit 13 is a display device for presenting information to the user.

[0031] The setting unit 14 sets a first evaluation value for each pixel constituting image data of a map representing a real environment such as a factory. As the first evaluation value to be set, it is preferable to use the theoretically highest value (maximum value) among the evaluation values ​​indicating the likelihood of self-position estimation of the guided vehicle 1 assumed for that pixel. The evaluation value indicates the likelihood of self-position estimation of the guided vehicle 1 placed in the real environment corresponding to the map. The evaluation value that is the premise of the first evaluation value is calculated, for example, by the processor of the guided vehicle system 10 according to the following procedure (1).

[0032] Step (1): The processor sequentially and repeatedly executes the following steps (1-1) to (1-3) for each pixel on the map. Here, the pixels to be processed are pixels identified based on map information, and are, for example, pixels on the map where the guided vehicle 1 can be present. Therefore, pixels on the map that correspond to obstacles (including walls and objects) are excluded from the pixels to be processed.

[0033] Step (1-1): The position of the target pixel is assumed to be the center position of the guided vehicle 1, and a set number of virtual lasers are virtually emitted on the map from the target pixel. Here, the virtual lasers are emitted only for a distance corresponding to the detectable range of the actual guided vehicle 1. The number of virtual lasers set may be one or more.

[0034] Step (1-2): Of the virtually emitted virtual lasers, the number of virtual lasers that reach obstacles in the map information is calculated.

[0035] Step (1-3): Calculate an evaluation value for the target pixel based on the number of virtual lasers that have reached the obstacle and the total number of virtual lasers. Specifically, calculate the evaluation value by dividing the "number of virtual lasers that have reached the obstacle" by the "total number of virtual lasers emitted from the target pixel."

[0036] The calculation unit 15 calculates an evaluation value at the current position of the guided vehicle 1 placed in the real environment as the second evaluation value. The current position of the guided vehicle 1 placed in the real environment is preferably identified by a method of estimating its own position, such as odometry. The calculation unit 15 calculates the second evaluation value, for example, by the following steps (2) to (4).

[0037] Step (2): The calculation unit 15 distributes particles at predetermined intervals within a predetermined range including the identified current position of the transport vehicle 1. The predetermined range and predetermined intervals are preferably set to a range within which the transport vehicle 1 may exist, taking into consideration an estimation error in the current position, and to an interval that can reduce the influence of the error.

[0038] Step (3): The calculation unit 15 sequentially and repeatedly executes the following steps (3-1) to (3-4) for each particle to calculate an evaluation value for each particle.

[0039] Step (3-1): A set number of lasers are emitted from the sensors 2a and 2b of the transport vehicle 1, and the distance to the object measured for each laser is obtained.

[0040] Step (3-2): A set number of virtual lasers are virtually emitted from the pixel on the map corresponding to the target particle, and the distance to obstacles (including walls and objects) in the map information is calculated for each virtual laser.

[0041] Step (3-3): For each pair of a corresponding laser and a virtual laser, the distance acquired in step (3-1) is compared with the distance calculated in step (3-2), and the number of pairs for which the distances are within the same range is calculated. Here, it is preferable to determine whether or not the distances are within the same range by setting a predetermined error taking into account errors that occur when measuring the distance, and to determine that the distances are within the same range if the difference between the distances is within the predetermined error range.

[0042] Step (3-4): Calculate an evaluation value for the target particle based on the number of pairs determined to be within the equivalent range and the total number of lasers. Specifically, the evaluation value is calculated by dividing the "number of pairs determined to be within the equivalent range" by the "total number of lasers irradiated from sensors 2a and 2b."

[0043] Step (4): The calculation unit 15 determines the highest evaluation value among the evaluation values ​​of each particle calculated in the above step (3-4) as a second evaluation value. The particle corresponding to this second evaluation value becomes a candidate for the self-position of the guided vehicle 1 placed in the real environment.

[0044] The determination unit 16 compares the second evaluation value calculated by the calculation unit 15 with the first evaluation value set for the pixel of the map. If the difference between the second evaluation value and the first evaluation value exceeds a predetermined threshold, the determination unit 16 determines that the map is incorrect, that is, that there is an error in the map.

[0045] Here, it is preferable that the calculation unit 15 calculates the second evaluation value when the guided vehicle 1 is test driving in the real environment. This is because the accuracy of the map can be confirmed during the test driving stage before the actual driving, and errors can be corrected before the actual driving. Note that whether or not to calculate the second evaluation value may be determined using, for example, the driving mode. In this case, a test driving mode and an actual driving mode may be provided as the driving mode, and the second evaluation value may be calculated when the driving mode is the test driving mode.

[0046] The screen generator 17 generates an evaluation screen in which a color associated with the first evaluation value is superimposed on the map based on the first evaluation value set for each pixel of the map. A heat map technique can be used as a method for superimposing a color on the map. This makes it easy to visually check on the map areas where the evaluation value indicating the likelihood of self-location estimation is high and low. Therefore, by looking at the evaluation screen, the user can easily distinguish areas where self-location estimation is sufficiently possible and areas where it is difficult.

[0047] For example, in areas with surrounding obstacles or walls, the evaluation value tends to be high, and areas with high evaluation values ​​can be determined to be areas where self-location estimation is sufficiently possible. On the other hand, in areas without surrounding obstacles or walls, the evaluation value tends to be low, and areas with low evaluation values ​​can be determined to be areas where self-location estimation is difficult.

[0048] When the determination unit 16 determines that there is an error in the map based on the difference between the second evaluation value and the first evaluation value, the screen generation unit 17 changes the color superimposed on the portion determined to have an error to a color that allows the user to distinguish that there is an error, and generates the evaluation screen again. The larger the difference between the second evaluation value and the first evaluation value, the more noticeable the color may be changed. This allows the user to visually distinguish errors in the map by looking at the evaluation screen. Examples of errors in the map include when an object that was on the map has moved or when a new object has been placed.

[0049] Figure 3 shows an example of an evaluation screen 3 that displays evaluation values ​​as a heat map on a map, and displays locations 3a that have been determined to contain errors on the map. On the evaluation screen 3, the locations 3a that have been determined to contain errors on the map are displayed in a darker color than the other locations. This allows the user to easily identify the locations 3a that contain errors on the map.

[0050] An example of processing executed in the guided vehicle system 10 according to the embodiment will be described with reference to Fig. 4. Here, it is assumed that before executing this processing, a first evaluation value is set for each pixel of a map representing the real environment in which the guided vehicle 1 travels.

[0051] First, the calculation unit 15 identifies the current position of the guided vehicle 1 placed in the real environment (step S101).

[0052] Next, the calculation unit 15 distributes the particles at predetermined intervals within a predetermined range including the identified current position of the transportation vehicle 1 (step S102).

[0053] Next, the calculation unit 15 causes the sensors 2a and 2b of the transport vehicle 1 to emit a set number of lasers, and acquires the distance to the object measured for each laser (step S103).

[0054] Next, the calculation unit 15 virtually emits a set number of virtual lasers on the map from a pixel on the map corresponding to one particle to be processed this time among the distributed particles, and calculates the distance to an obstacle in the map information for each virtual laser (step S104).

[0055] Next, the calculation unit 15 compares the distance obtained in step S103 with the distance calculated in step S104 for each pair of corresponding laser and virtual laser, and calculates the number of pairs for which both distances are in the same range (step S105).

[0056] Next, the calculation unit 15 calculates an evaluation value for the particle to be processed based on the number of sets calculated in step S105 and the total number of lasers (step S106).

[0057] Next, the calculation unit 15 determines whether or not the processing for all particles distributed in the above step S102 has been completed (step S107). If this determination is NO (step S107; NO), the calculation unit 15 shifts the processing to the above step S103 to execute the processing for the next particle.

[0058] If it is determined in step S107 that the processing for all particles has been completed (step S107; YES), the calculation unit 15 calculates the highest evaluation value among the evaluation values ​​of each particle calculated in step S106 as a second evaluation value (step S108). This second evaluation value becomes a candidate for the self-position of the transported vehicle 1.

[0059] Next, the determination unit 16 compares the second evaluation value calculated in step S108 with the first evaluation value set for the pixel on the map corresponding to the current position of the guided vehicle 1 (step S109).

[0060] Next, the screen generator 17 generates a heat map evaluation screen again based on the result of the comparison in step S109 (step S110).

[0061] As described above, the guided vehicle system 10 according to the embodiment compares the first evaluation value set as the theoretical maximum value for each pixel of the map with the second evaluation value calculated at the current position of the guided vehicle placed in the real environment, and if there is a discrepancy between the two, it is possible to determine that there is a discrepancy between the map and the real environment, that is, that there is an error in the map.Then, the color superimposed on the part determined to have an error in the map can be changed to a color that is distinguishable by the user, and the evaluation screen can be generated again.

[0062] This allows the user to see the evaluation screen and understand that there is an error in the map, and to correct the error to suit the actual environment.

[0063] Therefore, the guided vehicle system 10 according to the embodiment can support the smooth running of the guided vehicle 1.

[0064] It should be noted that the present invention is not limited to the above-described embodiment, and can be embodied in various other forms without departing from the spirit of the present invention. Therefore, the above-described embodiment is merely illustrative in all respects and should not be interpreted as being limiting. [Explanation of symbols]

[0065] 1...Transportation vehicle, 2a, 2b...Sensor, 3...Evaluation screen, 10...Transportation vehicle system, 11...Memory unit, 12...Communication unit, 13...Display unit, 14...Setting unit, 15...Calculation unit, 16...Determination unit, 17...Screen generation unit

Claims

1. a setting unit that sets, for each pixel constituting image data of a map representing a real environment, a maximum value of evaluation values ​​indicating a likelihood of a self-position estimation of the guided vehicle assumed at the pixel as a first evaluation value; a calculation unit that calculates the evaluation value at a current position of the transport vehicle placed in the real environment as a second evaluation value; a determination unit that determines whether the map is correct based on a difference between the first evaluation value and the second evaluation value; A transport vehicle system comprising:

2. a screen generation unit that generates an evaluation screen in which a color associated with the first evaluation value is superimposed on the map based on the first evaluation value, the screen generation unit generates the evaluation screen again based on a difference between the first evaluation value and the second evaluation value when the determination unit determines that the map is incorrect. The transport vehicle system according to claim 1 .

3. When the determination unit determines that the map is incorrect, the screen generation unit changes the color to be superimposed on the portion of the map determined to be incorrect to a color that allows a user to distinguish that the map is incorrect, and generates the evaluation screen again. The transport vehicle system according to claim 2 .

4. When changing the color to be superimposed on the portion determined to be incorrect, the screen generation unit changes the color to a more noticeable color as the difference between the first evaluation value and the second evaluation value increases. The transport vehicle system according to claim 3 .

5. the calculation unit determines whether a distance to an object measured by a laser irradiated from the transport vehicle and a distance from the pixel on the map corresponding to the current position of the transport vehicle to an obstacle on the map are within an equivalent range, the number of times corresponding to the number of lasers irradiated from the transport vehicle, and calculates the second evaluation value. The transport vehicle system according to claim 1 .

6. the calculation unit calculates the second evaluation value by dividing the number determined to be within the equivalent range by the total number of lasers emitted from the transport vehicle. The transport vehicle system according to claim 5.

Images