Control device, control method, and control program

Abstract

A control device (102) is provided with a map update unit (80). In a map to be updated that shows areas to be classified, when, as a confidence level that is an index corresponding to the likelihood of an area being a travelable area, a value indicating an other area is set for each area, the map update unit (80) updates the confidence level corresponding to an other area located between a target classified area and a target location to a target update value. Each target classified area is an area that has been found on the basis of the results of measurement of the surroundings of a second autonomous traveling body by a second sensor with which the second autonomous traveling body is provided when the second autonomous traveling body is traveling in a target location on a second travel route, the target classified area being classified as either a travelable area or a travel-prohibited area in the map to be updated. The target update value is a value corresponding to the distance between an other area and a target classified area, and depends on whether the target classified area is a travelable area or a travel-prohibited area.

Description

Control device, control method, and control program

[0001] The present disclosure relates to a control device, a control method, and a control program.

[0002] Patent Literature 1 discloses a technology for creating a map for an autonomous mobile robot. In this technology, a base map is created that includes position information of objects that may become obstacles during autonomous driving, and the autonomous mobile robot drives autonomously based on the created base map. The autonomous mobile robot uses sensors mounted on the autonomous mobile robot to detect objects that may become obstacles during autonomous driving. No-travel areas corresponding to the detected objects are reflected in the base map.

[0003] Japanese Patent Application Laid-Open No. 2019-204336

[0004] Autonomous robots generally have a map for estimating their own location. Additionally, providing an autonomous robot with a map showing drivable areas to prevent the robot from entering prohibited areas can prevent unexpected accidents. The technology disclosed in Patent Document 1 detects obstacles and sets prohibited areas without limiting the type of sensor. This technology assumes that obstacles can be detected using sensors. When detecting obstacles using a sensor that emits electromagnetic waves, a type of sensor commonly used in autonomous robots, it is conceivable to determine height based on the distance value measured by the sensor. However, when using a sensor outdoors, it is difficult to accurately distinguish between drivable areas and prohibited areas based on distance values ​​alone. Therefore, conventional technology has the problem of excessively setting prohibited areas. As a specific example, it is difficult to accurately classify an area consisting of an asphalt road, a gravel road, and a lawn into drivable areas and prohibited areas based on distance values ​​alone. The present disclosure aims to reduce the number of excessively set no-travel areas by integrating multiple pieces of information to distinguish between drivable areas and no-travel areas in a technology for creating maps for autonomous robots using a type of sensor that emits electromagnetic waves.

[0005] The control device according to the present disclosure is configured to: when, in an update target map showing a classification target area, each area within a portion of the classification target area is classified as either a drivable area or a prohibited area based on a first driving trajectory, which is the driving trajectory when a first autonomous vehicle travels within the classification target area, and a result of measurement of the periphery of the first autonomous vehicle by a first sensor provided on the first autonomous vehicle when the first autonomous vehicle travels along the first driving trajectory, and when each area within the classification target area that is not classified as either the drivable area or the prohibited area is designated as a first unclassified area, a value indicating that the first unclassified area is neither the drivable area nor the prohibited area is set as a reliability that is an index corresponding to the possibility that the first unclassified area is the drivable area; The map update unit is configured to update the reliability of target classified areas, which are areas discovered based on the results of measurements of the surroundings of the second autonomous vehicle by a second sensor equipped on the second autonomous vehicle when the second autonomous vehicle is traveling at a target point on the second traveling path, and second unclassified areas, which are areas that exist between the target point and are not classified as either the drivable area or the drivable area in the update target map, to a target update value that is a value corresponding to the distance between the second unclassified area and the target classified area and that is a value corresponding to whether the target classified area is the drivable area or the drivable area.

[0006] According to the present disclosure, a map update unit updates the reliability of each area between the target point and the classified area map based on the measurement results of the second sensor when the second autonomous vehicle is traveling through the target point on the second traveling trajectory, in accordance with the distance between each area and the target classified area. Here, the reliability is an index corresponding to the likelihood that the area is a drivable area. The second sensor may be a sensor that emits electromagnetic waves. Therefore, according to the present disclosure, in a technology for creating a map for an autonomous robot using a sensor that emits electromagnetic waves, by integrating multiple pieces of information to distinguish between drivable areas and prohibited areas, the number of excessively set prohibited areas can be reduced.

[0007] 1 is a diagram showing an example of the configuration of a map generation system 90 according to the first embodiment. FIG. 2 is a diagram showing an example of the configuration of a map generation system 90 according to the first embodiment. FIG. 3 is a diagram showing an example of the configuration of a map generation system 90 according to the first embodiment. FIG. 4 is a diagram showing an example of the hardware configuration of a control device 100 according to the first embodiment. A flowchart showing the operation of the control device 100 according to the first embodiment. A diagram explaining processing in a data collection phase according to the first embodiment. A flowchart showing the operation of the control device 101 according to the first embodiment. A diagram explaining processing in a map creation phase according to the first embodiment. A flowchart showing the operation of the control device 101 according to the first embodiment. A flowchart showing the operation of the control device 101 according to the first embodiment. A diagram explaining processing in a map creation phase according to the first embodiment. A flowchart showing the operation of the control device 102 according to the first embodiment. A diagram explaining processing in a map update phase according to the first embodiment. A diagram explaining processing in a map update phase according to the first embodiment. A diagram explaining processing in a map update phase according to the first embodiment. A diagram explaining processing in a map update phase according to the first embodiment. A diagram showing an example of the hardware configuration of a control device 100 according to a variation of the first embodiment.

[0008] In the description of the embodiments and the drawings, the same elements and corresponding elements are given the same reference numerals. The description of elements given the same reference numerals will be omitted or simplified as appropriate. Arrows in the drawings mainly indicate the flow of data or the flow of processing. Furthermore, "unit" may be read as "circuit," "step," "procedure," "process," or "circuitry" as appropriate.

[0009] Embodiment 1. Hereinafter, embodiment 1 will be described with reference to the drawings. In embodiment 1, a data collection phase, a map creation phase, and a map update phase are each realized. ***Description of Configuration*** <Data Collection Phase> FIG. 1 is a block diagram corresponding to an example configuration of a map generation system 90 that realizes the data collection phase. In the data collection phase, the controller 300 controls the autonomous vehicle 1 to pass through a drivable area, while the purpose is to store data obtained from the sensor 200. The drivable area is an area in which the autonomous vehicle can travel. Each autonomous vehicle may be an autonomous vehicle robot.

[0010] The autonomous vehicle 1 includes a housing 2, a control device 100, and a sensor 200. The autonomous vehicle 1 corresponds to a first autonomous vehicle, and is controlled by a controller 300. Each control device corresponds to a map creation device.

[0011] The housing 2 has drive wheels and a power source. As a specific example, the drive wheels are four wheels, and the power source is battery-driven.

[0012] The control device 100 has a data collection function and includes a travel control unit 10 , a manual control unit 20 , a data acquisition unit 30 , and a storage unit 40 .

[0013] The driving control unit 10 controls the driving of the autonomous vehicle 1 in response to a signal sent from the manual control unit 20 .

[0014] The manual control unit 20 monitors the signals sent from the controller 300, interprets how the autonomous vehicle 1 should move based on the monitoring results, and outputs the interpretation results to the driving control unit 10.

[0015] The data acquisition unit 30 interprets the signal sent from the sensor 200 to derive the distance value and the reflection intensity, and stores information indicating the derived distance value and reflection intensity in the storage unit 40.

[0016] The storage unit 40 has a function of storing various information, and is realized by a storage device such as a hard disk, etc. The storage unit 40 is mainly used to store distance values ​​and reflection intensities obtained from the sensor 200.

[0017] The sensor 200 has a function of acquiring distance values ​​and reflection intensities corresponding to each region. The sensor 200 corresponds to a first sensor. The first sensor is a sensor that performs measurements using electromagnetic waves. A specific example of the sensor 200 is a 3D-LiDAR (Light Detection and Ranging).

[0018] The controller 300 has a function of controlling the direction of travel of the autonomous mobile vehicle 1 and the start and stop of travel of the autonomous mobile vehicle 1. As a specific example, the controller 300 is realized by a controller for a radio control or a TV game, or the like.

[0019] 2 is a block diagram showing an example of the configuration of a map generation system 90 that realizes the map creation phase. The purpose of the map creation phase is to create a new map using the data collected in the data collection phase.

[0020] The control device 101 includes a map creation unit 50 and a storage unit 41. The control device 101 may be realized by the same computer as the computer that realizes the control device 100.

[0021] The map creation unit 50 creates a map for the autonomous vehicle based on the measurement data stored in the storage unit 41. The map is created, for example, by SLAM (Simultaneous Localization and Mapping) technology.

[0022] The storage unit 41 has a function of storing various information and is realized by a storage device such as a hard disk. The storage unit 41 is mainly used to store measurement data that is the basis of maps and created maps. The storage unit 41 may be realized by the storage device that realizes the storage unit 40.

[0023] 3 is a block diagram showing an example configuration of a map generation system 90 that realizes the map update phase. In the map update phase, the autonomous vehicle 3 travels through the environment while estimating its own position based on the created map, and updates the map when it is determined that a map update is necessary.

[0024] The autonomous vehicle 3 includes a housing 4 equipped with drive wheels and power, a control device 102, and a sensor 201. The autonomous vehicle 3 corresponds to the second autonomous vehicle. The second autonomous vehicle may be the same as the first autonomous vehicle. The housing 4 may be realized by the same housing as the housing 2.

[0025] The sensor 201 has a function of acquiring a distance value and reflection intensity corresponding to each region. The sensor 201 corresponds to the second sensor. The second sensor is a sensor that performs measurements using electromagnetic waves. As a specific example, the sensor 201 is a 3D-LiDAR, and may be realized by the same sensor as the sensor 200.

[0026] The control device 102 includes a driving control unit 11, a task control unit 60, a self-position estimation unit 70, a map update unit 80, and a storage unit 42. The control device 102 may be realized by the same computer as the computer that realizes the control device 100.

[0027] The driving control unit 11 controls the driving of the autonomous vehicle 3 based on instructions from the task control unit 60 .

[0028] The task control unit 60 has a function of instructing how to move the autonomous mobile unit 3. In this embodiment, it is assumed that a task of autonomously traveling along a predefined route is defined.

[0029] The self-position estimation unit 70 has the function of comparing the information obtained from the sensor 201 with the map stored in the memory unit 42, and searching for where on the map the autonomous mobile unit 3 is located.

[0030] The map update unit 80 has a function of updating the map stored in the memory unit 42. Specifically, when the second autonomous vehicle travels a second travel path within the classification target area based on the update target map, the map update unit 80 updates the reliability corresponding to the second unclassified area to a target update value. Here, in the update target map, each area within a portion of the classification target area is classified as either a drivable area or a travel-prohibited area based on the first travel path and the results of measurement of the periphery of the first autonomous vehicle by a first sensor provided in the first autonomous vehicle when the first autonomous vehicle travels the first travel path. Furthermore, a value indicating that the first unclassified area is neither a drivable area nor a travel-prohibited area is set as a reliability, which is an index corresponding to the possibility that the first unclassified area is a drivable area. A travel-prohibited area is an area in which travel by the autonomous vehicle is prohibited. Whether each area is a drivable area or a travel-prohibited area may be determined based on the corresponding reliability. The update target map is a map showing the classification target area. The target update value is a value corresponding to the distance between the second unclassified area and the target classified area, and is a value corresponding to whether the target classified area is a drivable area or a prohibited area. The second unclassified area is each area that exists between the target classified area and the target point, and is each area that is not classified as either a drivable area or a prohibited area in the map to be updated. The target classified area is each area that is discovered based on the results of a measurement of the surroundings of the second autonomous vehicle by a second sensor provided in the second autonomous vehicle when the second autonomous vehicle is traveling at the target point, and is each area that is classified as either a drivable area or a prohibited area in the map to be updated. The distance from the target point to the target classified area may be within the measured distance. The measured distance may be set in any manner. The target point is a point on the second traveling trajectory. The target point may be a point within the drivable area or may be a point within another area. The other area is an area that has not been determined to be either a drivable area or a prohibited area. The first traveling trajectory is the traveling trajectory when the first autonomous vehicle travels within the classified area.The first unclassified areas are areas within the classification target area that are not classified as either a drivable area or a prohibited area. The map update unit 80 may not update the reliability corresponding to the second unclassified area if the reliability value already set for the second unclassified area is higher than the target update value. When the map update unit 80 detects areas in the classification target area where an obstacle exists based on the measurement results of the second sensor, the map update unit 80 may classify the detected areas as prohibited areas in the update target map. In the update target map, areas for which the corresponding distance could not be measured by the first sensor may be classified as prohibited areas. When each area within the classification target area is set as a measurement target area, the measurement target area may be classified as a prohibited area in the update target map if the height of the measurement target area measured by the first sensor is equal to or greater than a height threshold. In the update target map, the measurement target area may be classified as a prohibited area if the reflection intensity corresponding to the measurement target area when the first sensor irradiates electromagnetic waves onto the measurement target area is different from a reference reflection intensity. The reference reflection intensity is the reflection intensity corresponding to the first travel track, that is, the reflection intensity corresponding to the electromagnetic wave irradiated by the first sensor.

[0031] The storage unit 42 has a function of storing various information and is realized by a storage device such as a hard disk. The storage unit 42 is mainly used to store maps used by the self-position estimation unit 70 and the map update unit 80. The maps are maps created by the map creation unit 50 or maps obtained by updating maps created by the map creation unit 50. The storage unit 42 may be realized by the same storage device as the storage device that realizes the storage unit 40.

[0032] 4 shows an example of the hardware configuration of the control device 100 according to this embodiment. The control device 100 is composed of a computer. The control device 100 may be composed of multiple computers.

[0033] As shown in the figure, the control device 100 is a computer that includes hardware such as a processor 91, a memory 92, an auxiliary storage device 93, an input / output IF (Interface) 94, and a communication device 95. These pieces of hardware are connected appropriately via signal lines 99.

[0034] The processor 91 is an integrated circuit (IC) that performs arithmetic processing and controls the hardware of the computer. Specific examples of the processor 91 include a central processing unit (CPU), a digital signal processor (DSP), or a graphics processing unit (GPU). The control device 100 may include multiple processors that replace the processor 91. The multiple processors share the role of the processor 91.

[0035] The memory 92 is typically a volatile storage device, and a specific example is RAM (Random Access Memory). The memory 92 is also called a primary storage device or a main memory. Data stored in the memory 92 is saved in the secondary storage device 93 as needed.

[0036] The auxiliary storage device 93 is typically a non-volatile storage device, and specific examples thereof include a ROM (Read Only Memory), an HDD (Hard Disk Drive), or a flash memory. Data stored in the auxiliary storage device 93 is loaded into the memory 92 as needed. The memory 92 and the auxiliary storage device 93 may be configured integrally.

[0037] The input / output IF 94 is a port to which an input device and an output device are connected. Specific examples of the input / output IF 94 include a USB (Universal Serial Bus) terminal. Specific examples of the input device include a keyboard and a mouse. Specific examples of the output device include a display.

[0038] The communication device 95 is a receiver and a transmitter, and is specifically a communication chip or a NIC (Network Interface Card).

[0039] Each part of the control device 100 may use the input / output IF 94 and the communication device 95 as appropriate when communicating with other devices.

[0040] The auxiliary storage device 93 stores a control program. The control program is a program that causes a computer to realize the functions of each unit included in the control device 100. The control program is loaded into the memory 92 and executed by the processor 91. The functions of each unit included in the control device 100 are realized by software.

[0041] Data used when executing the control program and data obtained by executing the control program are stored in the storage device as appropriate. Each part of the control device 100 uses the storage device as appropriate. Specific examples of the storage device include at least one of the memory 92, the auxiliary storage device 93, a register in the processor 91, and a cache memory in the processor 91. Note that the terms "data" and "information" may have the same meaning. The storage device may be independent of the computer. The functions of the memory 92 and the auxiliary storage device 93 may be realized by other storage devices.

[0042] The control program may be recorded on a computer-readable non-volatile recording medium. Specific examples of the non-volatile recording medium include an optical disk and a flash memory. The control program may be provided as a program product. The hardware configuration of the other control devices may be similar to the hardware configuration of the control device 100.

[0043] ***Explanation of Operation*** The operation procedure of each control device corresponds to a control method. Also, the program that realizes the operation of each control device corresponds to a control program.

[0044] The detailed operations in each phase will be explained below with specific examples.

[0045] <Data Collection Phase> Fig. 5 is a flowchart showing an example of processing performed in the data collection phase. This processing will be described with reference to Fig. 5.

[0046] (Step S1 ) The data acquisition unit 30 stores the data measured by the sensor 200 in the storage unit 40 .

[0047] (Step S2) In this step, it is determined whether the data collection phase should be terminated. As a specific example, a person determines whether the environment for which a map is to be created has been covered in the data collection process by the sensor 200, and the data collection phase is terminated if it is determined that the environment has been covered.

[0048] 6 shows a specific example of a range in which data is collected in the data collection phase. In this example, data is collected within the range while the autonomous vehicle 1 is moving along the arrow.

[0049] <Map Creation Phase> Fig. 7 is a flowchart showing an example of processing performed in the map creation phase. This processing will be described with reference to Fig. 7.

[0050] (Step S3) The map creation unit 50 creates a map using the measurement data stored in the memory unit 41. Specifically, the map creation unit 50 creates a map using SLAM technology with the distance values ​​stored in the memory unit 41 as input data. The map created in this step is called a base map. The entire area shown on the base map is the area to be classified. Figure 8 shows a specific example of the map created in this step. At the end of this step, the areas shown on the base map have not been classified as either drivable areas or no-drivable areas.

[0051] (Step S4) The map creation unit 50 performs a process of setting a drivable area in the base map. Fig. 9 is a flowchart showing an example of this process. This process will be described using Fig. 9.

[0052] (Step S4-1) The map creation unit 50 determines whether each area indicated by the base map is on the travel trajectory. The travel trajectory is the trajectory traveled by the autonomous vehicle 1 in the data collection phase. In other words, the processing of this step is processing for identifying areas on the base map that correspond to the movement path of the autonomous vehicle 1 in the data collection phase. At this time, the map creation unit 50 may divide the area indicated by the base map in any way to determine each area to be determined. As a specific example, the map creation unit 50 determines whether each area indicated by the base map is on the travel trajectory by estimating the self-position of the autonomous vehicle 1 at each time point when the autonomous vehicle 1 traveled through the classification target area, based on the distance value used when creating the base map.

[0053] (Step S4-2) The map creation unit 50 assigns a value indicating that each area of ​​the classification target area that is determined to be on the driving trajectory is a drivable area. A drivable area specifically refers to an area to which a reliability of 100 is assigned. The reliability is an index corresponding to the possibility that the area is actually a drivable area, and specifically takes a value ranging from 0 to 100. Through the processing of this step, each area is classified as a drivable area. Specifically, the map creation unit 50 assigns a reliability of 100 to each point of the classification target area that is on the driving trajectory. At this time, the map creation unit 50 may consider the entire area within a radius of X m from each point on the driving trajectory to be a drivable area. Specifically, the value of X is determined based on the size of the autonomous vehicle 1.

[0054] (Step S4-3) The map creation unit 50 determines whether or not area determination has been completed for each area on the travel path. If area determination has not been completed, the map creation unit 50 returns to step S4-1. Otherwise, the map creation unit 50 ends the processing of step S4.

[0055] (Step S5) The map creation unit 50 performs a process of setting a no-travel area on the map created by performing the process of step S4. Fig. 10 shows a flowchart illustrating an example of this process. This process will be described using Fig. 10.

[0056] (Step S5-1) The map creation unit 50 determines whether or not there is an unmeasurable area within the classification target area. An unmeasurable area is an area for which a corresponding distance value could not be calculated due to the characteristics of the sensor 200. As a specific example, when a 3D LiDAR is used as the sensor 200, it is not possible to measure the distance to an area where an object with low reflectivity exists. Therefore, there is a high probability that this area will become an unmeasurable area. If an unmeasurable area exists within the classification target area, the map creation unit 50 performs the process of step S5-4.

[0057] (Step S5-2) The map creation unit 50 determines whether or not an obstacle candidate area exists within the classification target area. An obstacle candidate area is an area whose corresponding height is equal to or greater than a threshold. The threshold may be set in any manner. An area whose corresponding height is equal to or greater than a certain height is likely to be an area corresponding to an obstacle. Therefore, the processing of this step is performed to make the obstacle candidate area a no-travel area. If an obstacle candidate area exists within the classification target area, the map creation unit 50 performs the processing of step S5-4.

[0058] (Step S5-3) The map creation unit 50 determines whether a reflection-difference area exists within the classification target area. A reflection-difference area is an area having a reflection intensity different from the reflection intensity corresponding to the drivable area. Reflection intensity is an index that indicates the proportion of electromagnetic waves reflected back from an object when the electromagnetic waves are irradiated onto the object. Therefore, the higher the reflectivity of an object present in an area, the higher the corresponding reflection intensity value. The reflection intensity corresponding to the drivable area corresponds to the reference reflection intensity. In this embodiment, it is determined that there is a high possibility that the autonomous moving body cannot travel through an area having a reflection intensity different from the reflection intensity corresponding to the drivable area. Note that the reflection intensity corresponding to the drivable area may refer to the entire reflection intensity within a range determined according to the minimum and maximum values ​​of the reflection intensity corresponding to each area within the drivable area. The minimum value of the range may be lower than the minimum value of the reflection intensity corresponding to each area within the drivable area. The maximum value of the range may be higher than the maximum value of the reflection intensity corresponding to each area within the drivable area. When the reflection intensity corresponding to the drivable area is the entire reflection intensity within a certain range, if the reflection intensity of a certain area is not included in the certain range, the certain area is determined to have a reflection intensity different from the reflection intensity corresponding to the drivable area. Furthermore, the map creation unit 50 may determine that a certain area is a reflection-different area if the difference between the reflection intensity corresponding to the certain area and the reflection intensity corresponding to the drivable area is equal to or greater than a certain level. If a reflection-different area exists within the classification target area, the map creation unit 50 performs the process of step S5-4.

[0059] (Step S5-4) The map creation unit 50 sets each area within the classification target area that corresponds to either an unmeasurable area, an obstacle candidate area, or a reflection different area as a no-travel area. At this time, the map creation unit 50 assigns a value indicating a no-travel area to each area as a specific example. As a specific example, a no-travel area is an area to which a reliability of 0 is assigned. Through the processing of this step, each area is classified as a no-travel area. As a specific example, the map creation unit 50 assigns a reliability of 0 to parts of the classification target area that correspond to either an unmeasurable area, an obstacle candidate area, or a reflection different area.

[0060] (Step S5-5) The map creation unit 50 determines whether or not the determination of the no-travel area has been completed. If the determination of the no-travel area has not been completed, the map creation unit 50 returns to step S5-1. Otherwise, the map creation unit 50 ends the processing of step S5.

[0061] (Step S6) The map creation unit 50 assigns a reliability to each area within the classification target area that has not been assigned a reliability. At this time, the map creation unit 50 assigns a reliability value that does not correspond to either a drivable area or a prohibited area to each area. In other words, the map creation unit 50 assigns a provisional reliability corresponding to other areas to each area. As a specific example, the map creation unit 50 assigns a reliability of 50 to each area. Figure 11 shows a specific example of a map created by executing the processing of the map creation phase.

[0062] <Map Update Phase> When the autonomous vehicle 3 uses the map created in the map creation phase, it can only travel in an extremely limited area known as the drivable area. Here, the prohibited area is an area in which the autonomous vehicle 3 cannot travel with certainty. The other area is an area in which the autonomous vehicle 3 may be able to travel. Therefore, in the phase in which the map is actually used, the autonomous vehicle 3 expands the drivable area within the classification target area by performing a process to update the map while traveling in the other area. Specifically, the autonomous vehicle 3 reduces its speed while traveling in the other area and updates the map by performing the process shown in FIG. 12.

[0063] FIG. 12 is a flowchart showing an example of processing in the map update phase. In the map update phase, it is assumed that the autonomous vehicle 3 updates the map to be updated while performing an actual task. A specific example of the actual task is the task of transporting an object. The map to be updated is a general term for the map created in the map creation phase and the map updated in the map update phase. By performing processing in the map update phase each time the autonomous vehicle 3 travels in accordance with instructions from the task control unit 60, it becomes clear whether each area classified as other area is a drivable area. The processing in the map update phase will be described using FIG. 12.

[0064] (Step S7) The map update unit 80 determines each area to be updated from within the classification target area. FIGS. 13 and 14 show a specific example of the determination process. According to these figures, each time the autonomous vehicle 3 passes through an area with a corresponding reliability of 100, the map update unit 80 searches for an area with a corresponding reliability of 0 and an area other than the area in which the autonomous vehicle 3 is traveling that has a corresponding reliability of 100. If the map update unit 80 finds an area with a corresponding reliability of 0 or 100, it proceeds to step S8. Each of the found areas corresponds to a target classified area. Note that each searched area may be limited to areas located within a radius of X m from the target point. The value of X may be set to any value.

[0065] (Step S8) The self-position estimation unit 70 estimates the position of the autonomous vehicle 3 based on the map to be updated and the measurement results of the sensor 201. The map update unit 80 updates the reliability corresponding to each area classified as an "other" area based on the estimated position of the autonomous vehicle 3 and each discovered area. The estimated position of the autonomous vehicle 3 corresponds to the target point. As a specific example, as shown in FIG. 13 , for each area that exists between the position of the autonomous vehicle 3 and an area whose corresponding reliability is 0 and corresponds to an "other" area, the map update unit 80 assigns a higher value to each area whose corresponding reliability is closer to an area whose corresponding reliability is 100, and a lower value to each area whose corresponding reliability is closer to an area whose corresponding reliability is 0. At this time, as shown in FIG. 14 , if the reliability already assigned to a certain area is higher than the reliability to be assigned to the certain area, the map update unit 80 does not update the reliability of the certain area. Each area whose corresponding reliability is to be updated corresponds to a second unclassified area. Furthermore, as shown in Figures 15 and 16, when an obstacle appears in an area classified as other area, the map update unit 80 appropriately sets each area classified as other area as a no-travel area depending on the location where the obstacle appears.

[0066] (Step S9) The map update unit 80 determines whether to end the processing of the map update phase. As a specific example, the map update unit 80 ends the processing of the map update phase when the autonomous mobile body 3 has finished traveling.

[0067] ***Explanation of Effects of First Embodiment*** As described above, according to this embodiment, by utilizing the acquired distance values ​​and reflection intensities, and the fact that the autonomous vehicle traveled only in areas where it was permitted at the time the measurement data was acquired, it is possible to distinguish between drivable areas and prohibited areas with a relatively high degree of accuracy. Therefore, according to this embodiment, it is possible to reduce the number of excessively set prohibited areas. Furthermore, according to this embodiment, the reliability of each area on the map is updated appropriately each time the autonomous vehicle travels, making it possible to respond to changes in the environment.

[0068] ***Other Configurations*** <Modification 1> Fig. 17 shows an example of the hardware configuration of the control device 100 according to this modification. The control device 100 includes a processing circuit 98 instead of the processor 91, the processor 91 and memory 92, the processor 91 and auxiliary storage device 93, or the processor 91, memory 92, and auxiliary storage device 93. The processing circuit 98 is hardware that realizes at least a portion of the components included in the control device 100. The processing circuit 98 may be dedicated hardware, or may be a processor that executes a program stored in the memory 92.

[0069] When the processing circuitry 98 is dedicated hardware, the processing circuitry 98 may be, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a combination thereof. The control device 100 may include multiple processing circuits that replace the processing circuitry 98. The multiple processing circuits share the role of the processing circuitry 98.

[0070] In the control device 100, some of the functions may be realized by dedicated hardware, and the remaining functions may be realized by software or firmware.

[0071] The processing circuitry 98 is realized by, for example, hardware, software, firmware, or a combination of these. The processor 91, memory 92, auxiliary storage device 93, and processing circuitry 98 are collectively referred to as "processing circuitry." In other words, the functions of the functional components of the control device 100 are realized by the processing circuitry. The hardware configuration of other control devices may be the same as that of this modified example.

[0072] ***Other Embodiments*** Although the first embodiment has been described, it is possible to combine multiple parts of this embodiment and implement it. Alternatively, it is possible to implement this embodiment in part. In addition, various modifications may be made to this embodiment as necessary, and it is possible to implement it in any combination, either as a whole or in part. Note that the above-described embodiments are essentially preferred examples and are not intended to limit the scope of the present disclosure, its applications, and uses. The procedures described using flowcharts, etc. may be modified as appropriate.

[0073] 1, 3 Autonomous vehicle, 2, 4 Housing, 10, 11 Travel control unit, 20 Manual control unit, 30 Data acquisition unit, 40, 41, 42 Memory unit, 50 Map creation unit, 60 Task control unit, 70 Self-position estimation unit, 80 Map update unit, 90 Map generation system, 91 Processor, 92 Memory, 93 Auxiliary storage device, 94 Input / output IF, 95 Communication device, 98 Processing circuit, 99 Signal line, 100, 101, 102 Control device, 200, 201 Sensor, 300 Controller.

Claims

1. In a map to be updated that shows a classification target area, each area within a portion of the classification target area is classified as either a drivable area or a prohibited area based on a first driving trajectory, which is the driving trajectory when a first autonomous vehicle drives within the classification target area, and a result of measurement of the surroundings of the first autonomous vehicle by a first sensor equipped on the first autonomous vehicle when the first autonomous vehicle drives along the first driving trajectory, and each area within the classification target area that is not classified as either a drivable area or a prohibited area is designated as a first unclassified area, when a value indicating that the first unclassified area is neither a drivable area nor a prohibited area is set for the first unclassified area as a reliability that is an index corresponding to the possibility that the first unclassified area is the drivable area, a control device comprising: a map update unit that, when a second autonomous vehicle travels on a second travel path within the classification target area based on the update target map, updates the reliability corresponding to target classified areas, which are areas that are discovered based on the results of a second sensor equipped on the second autonomous vehicle measuring the periphery of the second autonomous vehicle when the second autonomous vehicle is traveling at a target point on the second travel path, and which are areas that are classified as either the drivable area or the travel-prohibited area in the update target map and which exist between the target point, to a target update value that is a value corresponding to the distance between the second unclassified area and the target classified area and that is a value corresponding to whether the target classified area is the drivable area or the travel-prohibited area.

2. The control device according to claim 1, wherein the map update unit does not update the reliability corresponding to the second unclassified area when the reliability value already set for the second unclassified area is higher than the target update value.

3. A control device as described in claim 1 or 2, wherein when the map update unit detects areas in which obstacles exist within the classification target area based on the measurement results of the second sensor, it classifies the detected areas as no-travel areas in the update target map.

4. A control device according to any one of claims 1 to 3, wherein each area in the map to be updated for which the corresponding distance could not be measured by the first sensor is classified as a no-travel area.

5. A control device described in any one of claims 1 to 4, wherein when each area within the classification target area is a measurement target area, if the height of the measurement target area measured by the first sensor is equal to or greater than a height threshold, the measurement target area is classified as a no-travel area in the update target map.

6. A control device as described in any one of claims 1 to 5, wherein each of the first sensor and the second sensor is a sensor that performs measurements using electromagnetic waves, and when each area within the classification target area is set as a measurement target area, if the reflection intensity corresponding to the measurement target area when the first sensor irradiates the measurement target area with electromagnetic waves is different from a reference reflection intensity, which is the reflection intensity corresponding to the first driving track and corresponds to the electromagnetic waves irradiated by the first sensor, the measurement target area is classified as a no-travel area in the map to be updated.

7. The control device according to claim 6, wherein each of the first sensor and the second sensor is a 3D-LiDAR (Light Detection and Ranging) sensor.

8. A control device according to any one of claims 1 to 7, wherein the distance from the target point to the target classified area is within a measurement distance.

9. In a map to be updated that shows a classification target area, when each area within a portion of the classification target area is classified as either a drivable area or a prohibited area based on a first driving trajectory, which is the driving trajectory when a first autonomous vehicle drives within the classification target area, and a result of measurement of the periphery of the first autonomous vehicle by a first sensor equipped on the first autonomous vehicle when the first autonomous vehicle drives along the first driving trajectory, and when each area within the classification target area that is not classified as either a drivable area or a prohibited area is designated as a first unclassified area, a value indicating that the first unclassified area is neither a drivable area nor a prohibited area is set as a reliability, which is an index corresponding to the possibility that the first unclassified area is the drivable area, A control method in which a computer updates the reliability corresponding to target classified areas, which are areas that are discovered based on the results of measurements of the surroundings of a second autonomous vehicle by a second sensor equipped on the second autonomous vehicle when the second autonomous vehicle is traveling at a target point on the second traveling path based on the update target map, and which are areas that are classified as either the drivable area or the prohibited traveling area in the update target map and which exist between the target point and second unclassified areas, to a target update value that is a value corresponding to the distance between the second unclassified area and the target classified area and is a value corresponding to whether the target classified area is the drivable area or the prohibited traveling area.

10. In a map to be updated that shows a classification target area, when each area within a portion of the classification target area is classified as either a drivable area or a prohibited area based on a first driving trajectory, which is the driving trajectory when a first autonomous vehicle drives within the classification target area, and the results of measurements of the periphery of the first autonomous vehicle by a first sensor equipped on the first autonomous vehicle when the first autonomous vehicle drives along the first driving trajectory, and when each area within the classification target area that is not classified as either a drivable area or a prohibited area is designated as a first unclassified area, a value indicating that the first unclassified area is neither a drivable area nor a prohibited area is set as a reliability, which is an index corresponding to the possibility that the first unclassified area is the drivable area, a control program that causes a control device that is a computer to execute a map update process that updates the reliability corresponding to target classified areas, which are areas that are discovered based on the results of measurements of the surroundings of the second autonomous vehicle by a second sensor equipped on the second autonomous vehicle when the second autonomous vehicle is traveling at a target point on the second traveling path, and second unclassified areas, which are areas that exist between the target point and are not classified as either the drivable area or the drivable area in the update target map, to a target update value that is a value corresponding to the distance between the second unclassified area and the target classified area and that is a value corresponding to whether the target classified area is the drivable area or the drivable area.

Images