Information processing device, information processing method, and information processing system

Abstract

The present disclosure relates to an information processing device, an information processing method, and an information processing system that make it possible to implement more suitable localization processing. A position acquisition unit acquires position information regarding positions on a travel path along which a mobile body has traveled. A reliability calculation unit calculates reliability information of a localization map that is used for localization processing of the mobile body. A map generation unit generates a reliability map that associates the position information with the reliability information. The technology according to the present disclosure is applicable to, for example, a vehicle capable of autonomous traveling.

Description

Information processing device, information processing method, and information processing system

[0001] The present disclosure relates to an information processing device, an information processing method, and an information processing system, and more particularly to an information processing device, an information processing method, and an information processing system that enable more suitable localization processing to be realized.

[0002] Patent document 1 discloses an error diagnosis device that determines that a positioning sensor has a positioning error if a first road section identified as the vehicle has traveled through and a second road section identified as the vehicle has traveled through after traveling the first road section are not continuous.

[0003] To achieve autonomous movement, a mobile object must accurately determine its own location. One method for accurately determining its own location is localization processing, which estimates its own location by matching feature points contained in a pre-generated map with feature points contained in camera images.

[0004] Japanese Patent Application Laid-Open No. 2022-38351

[0005] However, in the above-described localization process, there have been cases where erroneous matching occurs at completely different locations that have similar feature points, or where erroneous matching occurs due to changes in the external environment captured as a camera image.

[0006] The present disclosure has been made in light of such circumstances, and aims to enable more suitable localization processing to be realized.

[0007] The information processing device of the present disclosure is an information processing device that includes a position acquisition unit that acquires position information on a movement path traveled by a mobile body, a reliability calculation unit that calculates reliability information of a localization map used in localization processing of the mobile body, and a map generation unit that generates a reliability map that associates the position information with the reliability information.

[0008] The information processing method disclosed herein is an information processing method in which an information processing device acquires location information on a movement path traveled by a moving object, calculates reliability information of a localization map used in localization processing of the moving object, and generates a reliability map that associates the location information with the reliability information.

[0009] The information processing system of the present disclosure is an information processing system including a mobile body, a position acquisition unit that acquires position information on a movement path traveled by the mobile body, a reliability calculation unit that calculates reliability information of a localization map used in localization processing of the mobile body, and a map generation unit that generates a reliability map that associates the position information with the reliability information.

[0010] In the present disclosure, location information on a path traveled by a moving body is acquired, reliability information of a localization map used in localization processing of the moving body is calculated, and a reliability map that associates the location information with the reliability information is generated.

[0011] 1 is a diagram illustrating odometry estimation and its problems. It is a diagram illustrating self-localization estimation using a prior map. It is a block diagram illustrating a configuration example of a vehicle according to an embodiment of the present disclosure. It is a flowchart illustrating a flow of a reliability map generation process. It is a diagram illustrating a specific example of reliability map generation. It is a diagram illustrating a specific example of reliability map generation. It is a diagram illustrating a specific example of reliability map generation. It is a flowchart illustrating a flow of a reliability map utilization process. It is a block diagram illustrating a configuration example of a vehicle according to a first embodiment. It is a flowchart illustrating a reliability map utilization process. It is a diagram illustrating an example of a reliability map. It is a block diagram illustrating a configuration example of a vehicle according to a second embodiment. It is a flowchart illustrating a reliability map utilization process. It is a block diagram illustrating a configuration example of a vehicle according to a third embodiment. It is a flowchart illustrating a reliability map utilization process. It is a diagram illustrating an overview of a localization process according to a fourth embodiment. It is a block diagram illustrating a configuration example of a vehicle according to a fourth embodiment. It is a flowchart illustrating a reliability map utilization process. It is a block diagram illustrating a configuration example of a vehicle according to a fifth embodiment. It is a flowchart illustrating a reliability map utilization process. It is a block diagram illustrating a configuration example of an information processing system according to the present disclosure. It is a block diagram illustrating a configuration example of an information processing system according to a sixth embodiment. It is a block diagram illustrating a configuration example of an information processing system according to a seventh embodiment. It is a block diagram illustrating a configuration example of an information processing system according to an eighth embodiment. It is a diagram illustrating a hardware configuration example of a computer.

[0012] Modes for carrying out the present disclosure (hereinafter referred to as embodiments) will be described below in the following order.

[0013] 1. Conventional self-localization estimation methods and their issues 2. Vehicle configuration according to the present disclosure 3. Generation of reliability map 4. Use of reliability map 4-1. First embodiment (error correction of odometry estimation in highly reliable areas) 4-2. Second embodiment (recreating localization map based on geographical variations in reliability) 4-3. Third embodiment (configuring HD map based on temporal variations in reliability) 4-4. Fourth embodiment (localization using vehicle position information with higher reliability) 4-5. Fifth embodiment (notifying vehicles with lower reliability) 5. Application to information processing system 5-1. Sixth embodiment (integration of localization map based on reliability) 5-2. Seventh embodiment (localization using vehicle position information with higher reliability) 5-3. Eighth embodiment (notifying vehicles with lower reliability) 6. Other 7. Example of computer hardware configuration

[0014] <1. Conventional Self-Location Estimation Methods and Issues Thereof> To achieve autonomous movement, a mobile object needs to accurately determine its own location. Methods for accurately determining its own location can be broadly classified into two types. The first method is odometry estimation, which estimates the difference between the current position of the mobile object and the position up to the previous moment and accumulates this difference. The second method is localization processing, which directly estimates the absolute position of the mobile object using some kind of information provided from an external source.

[0015] Odometry estimation is a method for estimating a vehicle's position by calculating the amount of movement per unit time using the amount of wheel rotation of the vehicle and cameras and inertial sensors mounted on the vehicle as internal sensors. As shown in the left diagram of Figure 1, in odometry estimation, the current estimated position is calculated by accumulating the estimated positions from one second ago, two seconds ago, and three seconds ago. However, since errors accumulate with each position estimation, the further the vehicle moves, the greater the error in the estimated position from its actual position, as shown in the right diagram of Figure 1.

[0016] As described above, since the self-position cannot be accurately determined by odometry estimation alone, it is necessary to obtain the absolute position globally by localization processing.

[0017] There are several methods for this localization process, such as a method using a global positioning system (GPS) or a method using a pre-defined map.

[0018] The GPS method estimates the absolute position of the aircraft based on the distances from multiple satellites.

[0019] The method using a prior map is a method of estimating the vehicle's own position by matching feature points included in a prior map generated in advance with feature points included in a camera image. Specifically, as shown in Figure 2, the absolute position of the vehicle is estimated so that the position of a feature point Pa in the current observation is matched with the position of a feature point Pb in the environment generated in advance.

[0020] In this way, localization processing using a prior map is advantageous in terms of cost and accuracy in that it can be realized with a lightweight configuration that requires at least one camera, yet is capable of estimating self-position on the order of centimeters.

[0021] However, in localization processing using a prior map, there are cases where mismatches occur between completely different locations with similar feature points, or mismatches occur due to changes in the external environment captured in camera images. Specifically, if buildings with similar shapes exist in completely different locations, there is a possibility that the estimation of the self-location will be significantly incorrect. Furthermore, the localization processing will fail if the positions of the feature points of the buildings are observed incorrectly due to disturbances such as sunlight or other moving objects, or if the building to be observed does not exist in the prior map.

[0022] Therefore, the technology disclosed herein generates a reliability map by recording and mapping indices (reliability) for the success or accuracy of localization processing in chronological order. Furthermore, the generated reliability map can be used to determine the likelihood of success or failure of future localization processing (reliability of the next localization processing) and the need to update a preliminary map (localization map) used in the localization processing.

[0023] 2. Configuration of a Vehicle According to the Present Disclosure FIG. 3 is a block diagram showing an example configuration of a vehicle that is one embodiment of a moving body according to the present disclosure.

[0024] 3 is configured as a vehicle capable of autonomous driving. The vehicle 1 is configured to include a control unit 10 and a sensing unit 20 as a vehicle control system (information processing system) that realizes processing related to driving assistance and automatic driving of the vehicle 1.

[0025] The control unit 10 is an information processing device according to the present disclosure. The control unit 10 is a so-called ECU (Electronic Control Unit) and is configured by various processors such as a CPU (Central Processing Unit) and an MPU (Micro Processing Unit).

[0026] The sensing unit 20 is composed of a camera, radar, LiDAR (Light Detection and Ranging, Laser Imaging Detection and Ranging), as well as a speed sensor, an acceleration sensor, an angular velocity sensor (gyro sensor), an IMU (Inertial Measurement Unit) that integrates these, etc. Sensing information detected by the sensing unit 20 is supplied to the control unit 10 and used for various processes.

[0027] By executing a predetermined program, the control unit 10 realizes a localization map management unit 31, a localization processing unit 32, a position acquisition unit 33, a reliability calculation unit 34, a reliability map generation and management unit 35, a reliability map reference unit 36, and a utilization processing unit 37. Note that each functional block realized in the control unit 10 may be realized in a sensing unit including the sensing unit 20 or in other components that make up the vehicle control system.

[0028] The localization map management unit 31 stores and manages point cloud map information, in which characteristic points (point clouds) of the environment in which the vehicle 1 moves are mapped on a map, as a localization map to be used in the localization process.

[0029] The localization processing unit 32 executes localization processing (self-location estimation processing) based on the sensing information from the sensing unit 20 and the localization map (point cloud map information) stored in the localization map management unit 31. Specifically, the localization processing unit 32 estimates the self-location by matching feature points included in the localization map with feature points included in the sensing information. The result of the localization processing is supplied to the reliability calculation unit 34 and the utilization processing unit 37.

[0030] The position acquisition unit 33 acquires position information on the route traveled by the vehicle 1 and supplies it to the reliability map generation and management unit 35 .

[0031] The reliability calculation unit 34 calculates reliability information of the localization map used in the localization process of the vehicle 1 based on the localization process result from the localization processing unit 32, and supplies the reliability information to the reliability map generation and management unit 35 and the utilization processing unit 37. Here, reliability information at each position represented by the position information acquired by the position acquisition unit 33 is calculated.

[0032] The reliability map generation and management unit 35 generates a reliability map that associates the location information from the location acquisition unit 33 with the reliability information from the reliability calculation unit 34. The generated reliability map is managed (stored) in the reliability map generation and management unit 35, and is referred to by the reliability map reference unit 36 ​​as appropriate.

[0033] The reliability map reference unit 36 ​​refers to the reliability map managed by the reliability map generation and management unit 35 to obtain reliability information on the current position of the vehicle 1 and current (current time) reliability information, and supplies this to the localization processing unit 32 and the utilization processing unit 37 as necessary.

[0034] The utilization processing unit 37 executes utilization processing using the reliability information of the reliability map from the reliability map reference unit 36. For example, the utilization processing unit 37 executes processing based on the reliability information of the current frame calculated by the reliability calculation unit 34 and the reliability information acquired from the reliability map, as utilization processing. The utilization processing unit 37 also executes processing based on the comparison result of multiple pieces of reliability information in the reliability map, as utilization processing.

[0035] 3. Generation of Reliability Map (Flow of Reliability Map Generation Process) The flow of the reliability map generation process by the vehicle 1 (control unit 10) in Fig. 3 will be described with reference to the flowchart in Fig. 4. The process in Fig. 4 may be executed in parallel with the localization process executed by the localization processing unit 32 in the moving vehicle 1, for example.

[0036] In step S11, the position acquisition unit 33 acquires position information on the route along which the vehicle 1 has traveled.

[0037] For example, the position acquisition unit 33 can acquire, as position information, a GPS signal received on the route traveled by the vehicle 1. Position information may be acquired from a base station installed on the ground using a real-time kinematic (RTK) instead of a GPS signal. Furthermore, the position acquisition unit 33 can acquire position information by odometry estimation on the route traveled by the vehicle 1. The acquired position information is supplied to the reliability map generation and management unit 35.

[0038] In step S12, reliability information of the localization map is calculated based on the results of the localization processing executed by the localization processing unit 32.

[0039] For example, the reliability information may be binary information indicating the success or failure of the localization process at each position, or information indicating the matching distance (the sum of the distances between each observed point cloud and the point cloud on the point cloud map) between point cloud data acquired as sensing information and a localization map. Furthermore, the reliability information may be information indicating the percentage of point clouds that match between the point cloud data acquired at each position and the localization map, or information indicating the error in the direction of gravity between the point cloud data acquired at each position and the localization map. Furthermore, the reliability information may be information indicating the position and orientation error between the point cloud data acquired at each position and a reference object, such as a lane or sign, on the localization map.

[0040] In step S13, the reliability map generation and management unit 35 generates a reliability map that associates the location information acquired by the location acquisition unit 33 with the reliability information calculated by the reliability calculation unit 34. The reliability map can also be considered distribution information in which the success or failure of the localization process and an index of accuracy are recorded for each location.

[0041] The above process generates a reliability map that serves as an index for the success or failure and accuracy of the localization process, making it possible to determine the inaccuracy of the localization process based on past information, and to compare the past information with the success or failure of the current localization process to determine whether the localization map needs to be updated.As a result, it becomes possible to achieve more optimal localization.

[0042] (Correction of location information) The reliability map generation process described above may be performed in real time if accurate location information, such as location information from a GPS signal or RTK, can be obtained. However, if location information is obtained by odometry estimation, which accumulates errors, the location information may be corrected after the vehicle 1 has finished moving.

[0043] For example, the position acquisition unit 33 can correct the position information acquired by odometry estimation based on the position information of two known points on the movement route.

[0044] Specifically, as shown in the left diagram of Fig. 5, the self-position acquired by odometry estimation in real time while moving gradually deviates from the original moving route due to accumulated errors. On the other hand, since the start point and end point of the moving route of the autonomously traveling vehicle 1 are known, the position acquisition unit 33 collects position information while moving, and can correct the position information acquired by odometry estimation after the moving route ends based on the position information of the start point and end point, as shown in the right diagram of Fig. 5.

[0045] The two known points on the movement route are not limited to different positions such as the start point and end point in FIG. 5, but may be the same position.

[0046] Specifically, as shown in the left diagram of Fig. 6, the self-position acquired by odometry estimation in real time while moving gradually deviates from the original moving route due to accumulated errors. After the movement ends, if it is detected that the vehicle 1 has finally returned to the starting point, the position information acquired by odometry estimation can be corrected as shown in the right diagram of Fig. 6.

[0047] Furthermore, the position acquisition unit 33 can correct the position information acquired by odometry estimation by using position information associated with higher reliability information in an existing reliability map as the position information of two known points. In other words, when a reliability map for a certain area has already been generated, it is possible to expand the reliability map with high accuracy by treating points with high reliability in the reliability map as the above-mentioned start point and end point.

[0048] Furthermore, the position acquisition unit 33 may acquire an average value of position information acquired by odometry estimation on a travel route traveled multiple times.

[0049] Specifically, as shown in the left diagram of Fig. 7, the error that occurs in the odometry estimation varies depending on the travel conditions such as the time of day, weather, driving style, etc. By allowing for such deviations in the error in the odometry estimation, repeating the generation of the reliability map for a certain period of time and calculating the average value of the location information, it is possible to obtain highly accurate location information, as shown in the right diagram of Fig. 7.

[0050] As described above, the correlation between the location information and the reliability information in the reliability map can be performed not only in real time while the vehicle 1 is moving, but also after the vehicle 1 has finished moving.

[0051] 4. Use of Reliability Map (Flow of Reliability Map Utilization Process) The flow of reliability map utilization process by the vehicle 1 (control unit 10) in Fig. 3 will be described with reference to the flowchart in Fig. 8. The process in Fig. 8 can be executed at least in a state where a reliability map generated in advance is managed by the reliability map generation and management unit 35.

[0052] In step S31, the reliability map reference unit 36 ​​refers to the reliability map managed by the reliability map generation and management unit 35.

[0053] In step S32, the reliability map reference unit 36 ​​acquires reliability information of the current position of the vehicle 1 in the reliability map being referenced, current (current time) reliability information, etc., and determines whether or not to execute utilization processing by the utilization processing unit 37. For example, the reliability map reference unit 36 ​​determines whether or not to execute utilization processing by the utilization processing unit 37 based on a comparison result of the acquired multiple pieces of reliability information.

[0054] If it is determined in step S32 that the utilization process is to be executed, the process proceeds to step S33, where the utilization processing unit 37 executes the utilization process using the reliability information acquired by the reliability map reference unit .

[0055] On the other hand, if it is determined in step S32 that the utilization process is not to be executed, step S33 is skipped and the utilization process using the reliability information acquired by the reliability map reference unit 36 ​​is not executed.

[0056] A specific example of the process of using the reliability map and an embodiment of the vehicle 1 that executes the process will be described below.

[0057] (4-1. First embodiment: Correction of odometry estimation error in highly reliable areas) Self-position estimation in the vehicle 1 is basically performed using lightweight and high-speed odometry estimation, but estimation errors accumulate over long periods of time. Such errors are corrected by localization processing, but if the localization processing fails, a significantly incorrect position will be estimated. Therefore, in this embodiment, localization processing can be executed to correct errors due to odometry estimation when the vehicle is in an area where reliability information is high in the reliability map.

[0058] FIG. 9 is a block diagram illustrating an example configuration of a vehicle according to the first embodiment of the present disclosure.

[0059] In the vehicle 101 shown in FIG. 9, the control unit 10 (FIG. 3) realizes a reliability map management unit 111, a current position reliability determination unit 112, a localization processing unit 113, a reliability calculation unit 114, and a self-position integration unit 115.

[0060] The reliability map management unit 111 corresponds to the reliability map generation and management unit 35 in FIG. 3, and manages a reliability map generated in advance.

[0061] The current position reliability determination unit 112 corresponds to the reliability map reference unit 36 ​​in Figure 3, and refers to the reliability map managed by the reliability map management unit 111 to determine whether the reliability information of the current position of the vehicle 101 is equal to or greater than a predetermined threshold.

[0062] 3, and executes localization processing using a localization map in accordance with the determination result of the current location reliability determination unit 112. When localization processing is executed, the result of the localization processing is supplied to the reliability calculation unit 114 and the self-location integration unit 115.

[0063] 3, calculates reliability information based on the localization processing result from the localization processing unit 113, and supplies the reliability information to the self-location integrating unit 115. The calculated reliability information may be fed back to the reliability map management unit 111, thereby updating the reliability information of the corresponding position in the reliability map.

[0064] The self-position integrating unit 115 corresponds to the utilization processing unit 37 in Fig. 3. The self-position integrating unit 115 executes a self-position integrating process that corrects an error in the self-position estimated by odometry estimation using the localization processing result from the localization processing unit 113 in accordance with the reliability information from the reliability calculation unit 114.

[0065] The reliability map utilization process in the vehicle 101 of Fig. 9 will be described with reference to the flowchart of Fig. 10. The process of Fig. 10 is executed in the vehicle 101 while it is moving.

[0066] In step S111 , the current position reliability determination unit 112 refers to the reliability map managed by the reliability map management unit 111 .

[0067] In step S112, the current position reliability determination unit 112 determines whether the reliability information of the current position in the reliability map being referenced is equal to or greater than a threshold value.

[0068] If it is determined in step S112 that the reliability information is equal to or greater than the threshold value, the process proceeds to step S113, where the localization processing unit 113 executes localization processing using the localization map.

[0069] In step S114 , the reliability calculation unit 114 calculates reliability information based on the localization processing result of the localization processing unit 113 .

[0070] In step S115, the self-location integrating unit 115 determines whether the reliability information of the current location calculated by the reliability calculating unit 114 is equal to or greater than a threshold. In other words, the self-location integrating unit 115 determines whether or not to perform localization processing using the localization map based on the reliability information of the reliability map. The threshold here may be the same as or different from the threshold used in the determination by the current location reliability determining unit 112.

[0071] If it is determined in step S115 that the reliability information is equal to or greater than the threshold value, the process proceeds to step S116, where the self-location integrating unit 115 executes the self-location integrating process using the localization process result of the localization processing unit 113.

[0072] On the other hand, if it is determined in step S112 that the reliability information is not above the threshold, or if it is determined in step S115 that the reliability information is not above the threshold, the reliability of the localization process at that position is deemed to be low, and the self-position integration process is not executed.

[0073] FIG. 11 is a diagram illustrating an example of a reliability map.

[0074] In the reliability map shown in Fig. 11, the level of reliability information is indicated by the density of hatching of dots on the map. Specifically, the higher the density of hatching, the higher the reliability information, and the lower the density of hatching, the lower the reliability information. In other words, in areas with high density of hatching, self-location estimation by localization processing using a localization map is trusted, and in areas with low density of hatching, self-location estimation (e.g., odometry estimation) that is not localization processing using a localization map is trusted.

[0075] (4-2. Second embodiment: Recreating a localization map based on geographical variations in reliability) When there is an area in the reliability map where there is no geographical continuity in the reliability information, such as when the reliability information of a surrounding area is high but the reliability information is locally low, it is highly likely that a specific object is interfering with accurate localization processing. Therefore, in this embodiment, as a result of comparing multiple pieces of reliability information in one reliability map, it is possible to analyze the cause of locally low reliability based on reliability information variation information (reliability information change information). More specifically, it is possible to analyze the cause of locally low reliability information based on the geographical continuity of reliability information, which is one type of reliability information variation information (reliability information change information).

[0076] For example, areas under overpasses and footbridges have similar feature points, so the localization processing results are likely to be completely different locations, resulting in low reliability information for the localization map. This embodiment achieves detection of such areas. Furthermore, if the cause of low reliability information becomes clear, it becomes possible to take measures such as using only the scenery visible under the footbridge as feature points.

[0077] FIG. 12 is a block diagram illustrating an example configuration of a vehicle according to the second embodiment of the present disclosure.

[0078] In the vehicle 201 shown in FIG. 12, the control unit 10 (FIG. 3) realizes a reliability map management unit 211, a current position reliability determination unit 212, a localization processing unit 213, a reliability calculation unit 214, a self-position integration unit 215, a surrounding reliability search unit 216, a surrounding environment analysis unit 217, and a localization map re-creation unit 218.

[0079] The reliability map management unit 211, current location reliability determination unit 212, localization processing unit 213, reliability calculation unit 214, and self-location integration unit 215 in vehicle 201 have the same functions as the reliability map management unit 111, current location reliability determination unit 112, localization processing unit 113, reliability calculation unit 114, and self-location integration unit 115 in vehicle 101 in Figure 9, respectively, so their description will be omitted.

[0080] The surrounding reliability search unit 216, the surrounding environment analysis unit 217, and the localization map re-creation unit 218, like the self-location integration unit 215, correspond to the utilization processing unit 37 in FIG.

[0081] The surrounding reliability search unit 216 determines whether the gradient of the reliability information around the current position in the reliability map is equal to or greater than a threshold value, according to the determination result of the current position reliability determination unit 212. In other words, the surrounding reliability search unit 216 determines whether the geographical fluctuation (change) of the reliability information, which is one piece of fluctuation information of the reliability information (change information of the reliability information), exceeds a certain standard, as a result of comparing the reliability information between multiple positions in the reliability map.

[0082] The surrounding environment analysis unit 217 determines whether or not there is an object in the vicinity that interferes with the localization process by analyzing the surrounding environment of the current location in accordance with the determination result of the surrounding reliability search unit 216. The analysis of the surrounding environment may be performed using, for example, sensing information (camera images, point cloud data, etc.) detected by the sensing unit 20.

[0083] The localization map re-creation unit 218 re-creates a localization map based on feature points observed from the current position, in accordance with the analysis result (determination result) of the surrounding environment analysis unit 217. The feature points observed from the current position may be acquired as sensing information detected by the sensing unit 20.

[0084] The reliability map utilization process in the vehicle 201 of Fig. 12 will be described with reference to the flowchart of Fig. 13. The process of Fig. 13 is executed in the vehicle 201 while it is moving.

[0085] The processes in steps S211 to S216 in the flowchart of FIG. 13 are the same as the processes in steps S111 to S116 in the flowchart of FIG. 10, and therefore a description thereof will be omitted.

[0086] That is, if it is determined in step S212 that the reliability information is not greater than or equal to the threshold, the process proceeds to step S217, where the surrounding reliability search unit 216 determines whether the gradient of the reliability information around the current position in the reliability map is greater than or equal to the threshold.

[0087] If it is determined in step S217 that the gradient of the surrounding reliability information is greater than or equal to the threshold, the process proceeds to step S218, where the surrounding environment analysis unit 217 analyzes the surrounding environment of the current location to determine whether there are any objects in the vicinity that may interfere with the localization process.

[0088] If it is determined in step S218 that there is an object in the vicinity that interferes with the localization process, the process proceeds to step S219, where the localization map re-creation unit 218 determines whether or not it is possible to deal with the object. For example, the localization map re-creation unit 218 determines, from feature points observed from the current position, whether or not it is possible to perform localization processing using only useful subjects other than the object in question.

[0089] If it is determined in step S219 that the object can be dealt with, the process proceeds to step S220, where the localization map re-creation unit 218 re-creates the localization map based on feature points observed from the current position.

[0090] On the other hand, if it is determined in step S217 that the gradient of the reliability information of the surrounding area is not equal to or greater than the threshold, and if it is determined in step S218 that there is no object in the surrounding area that would interfere with the localization process, it is assumed that there is no factor in the surrounding area that would lower the reliability information of the localization map, and the process ends. Also, if it is determined in step S219 that the object cannot be dealt with, it is assumed that localization process using only useful subjects other than the object cannot be performed, and the process ends.

[0091] According to the above process, it is possible to use the geographical continuity of the reliability information in the reliability map to analyze the cause of locally low reliability information and take measures against that cause.

[0092] (4-3. Third embodiment: Construction of HD map based on temporal fluctuation of reliability) When newly calculated reliability information is low in an area where reliability information of a reliability map generated in the past is high, it is considered that some kind of change has occurred in the environment (feature points) of that area. Therefore, in this embodiment, as a result of comparing reliability information in multiple reliability maps generated at different times, linkage with external map information is made possible based on information on fluctuations in reliability information (information on changes in reliability information). More specifically, linkage with external map information is made possible based on the temporal continuity of reliability information, which is one type of information on fluctuations in reliability information (information on changes in reliability information).

[0093] FIG. 14 is a block diagram illustrating an example configuration of a vehicle according to the third embodiment of the present disclosure.

[0094] In the vehicle 301 shown in FIG. 14, the control unit 10 (FIG. 3) realizes a reliability map management unit 311, a localization processing unit 312, a reliability calculation unit 313, a current reliability determination unit 314, a past reliability search unit 315, and an HD map update unit 316.

[0095] The reliability map management unit 311 corresponds to the reliability map generation and management unit 35 in Fig. 3 and manages reliability maps generated in advance. Note that the reliability map management unit 311 manages not only the most recently generated reliability map but also reliability maps generated before that.

[0096] The localization processing unit 312 corresponds to the localization processing unit 32 in FIG. 3, executes localization processing using a localization map, and supplies the results of the localization processing to the reliability calculation unit 313 .

[0097] 3, calculates reliability information based on the localization processing result from the localization processing unit 312, and supplies the calculated reliability information to the current reliability determination unit 314. The calculated reliability information may be fed back to the reliability map management unit 311, thereby updating the reliability information of the corresponding position in the reliability map.

[0098] The current reliability determination unit 314 and the past reliability search unit 315 correspond to the reliability map reference unit 36 ​​in FIG.

[0099] The current reliability determination unit 314 refers to the reliability map managed by the reliability map management unit 311 and determines whether the difference with the reliability information from the reliability calculation unit 313 is equal to or greater than a predetermined threshold.

[0100] The past reliability search unit 315 searches for reliability information of the current location by referring to a reliability map generated in the past and managed by the reliability map management unit 311, depending on the determination result of the current reliability determination unit 314. Then, the past reliability search unit 315 acquires a temporal fluctuation (change) in the reliability information as one piece of fluctuation information of the reliability information (information on changes in the reliability information) as a result of comparing the reliability information in a plurality of reliability maps generated at different times.

[0101] The HD (High Definition) map update unit 316 corresponds to the utilization processing unit 37 in Fig. 3. The HD map update unit 316 updates an external HD map 317 in accordance with temporal fluctuations in the reliability information acquired by the past reliability search unit 315. The HD map 317 may be placed on a server on a cloud that can communicate with the vehicle 301.

[0102] The reliability map use process in the vehicle 301 of Fig. 14 will be described with reference to the flowchart of Fig. 15. The process of Fig. 15 is executed in the vehicle 301 while it is moving.

[0103] In step S311, the localization processing unit 312 executes localization processing using a localization map.

[0104] In step S312 , the reliability calculation unit 313 calculates reliability information based on the localization processing result of the localization processing unit 312 .

[0105] In step S313 , the current reliability determination unit 314 refers to the reliability map managed by the reliability map management unit 311 .

[0106] In step S314, the current reliability determination unit 314 determines whether the difference between the reliability information in the reliability map being referenced and the current reliability information calculated by the reliability calculation unit 313 is equal to or greater than a predetermined threshold.

[0107] If it is determined in step S314 that the difference between the reliability information in the reliability map and the current reliability information is equal to or greater than the predetermined threshold, the process proceeds to step S315, where the past reliability search unit 315 searches for reliability information for the current location from a reliability map generated in the past.The past reliability search unit 315 then obtains temporal fluctuations (changes) in the reliability information.

[0108] In step S315, the HD map update unit 316 updates the external HD map 317 for areas where the temporal fluctuation of the reliability information acquired by the past reliability search unit 315 exceeds a certain standard.

[0109] On the other hand, if it is determined in step S314 that the difference between the reliability information in the reliability map and the current reliability information is not equal to or greater than the predetermined threshold, it is assumed that there is no temporal variation in the reliability information, and the process ends.

[0110] According to the above process, it is possible to link with external map information such as an HD map by using the temporal continuity of the reliability information in the reliability map.

[0111] In this embodiment, in addition to updating the HD map as described above, if the reliability information gradually decreases over a long period of time, the localization map may be updated, assuming that this is due to seasonal changes over time caused by fallen leaves or snow. Furthermore, if the reliability information significantly decreases over a short period of time, the localization map may be updated, assuming that a new building has been built or has been demolished. In this case, the localization process may avoid using feature points in the area where construction is underway, or may use a newly generated localization map until the construction is completed.

[0112] While the above describes an embodiment in which a usage process is completed within a single vehicle, the following describes an embodiment in which a usage process is performed in cooperation with other vehicles, in which the usage process is performed based on the results of a comparison of reliability information in multiple reliability maps generated for different vehicles.

[0113] (4-4. Fourth embodiment: Localization using location information of a vehicle with higher reliability) When vehicles with completely different sensor configurations are present in the same area, localization processing of the other vehicles may be performed based on the localization processing results of the vehicle with higher reliability information in the reliability map that each vehicle has.

[0114] For example, assume that vehicles V10, V20, and V30 with different sensor configurations are present in the same area as shown in Fig. 16. In the example of Fig. 16, the reliability information for the area in the reliability map of vehicle V10 is high, and the reliability information for the area in the reliability maps of vehicles V20 and V30 is low.

[0115] In this case, the vehicle V10 can accurately estimate its own location by performing localization processing using a localization map with high reliability information. Meanwhile, the vehicles V20 and V30 perform localization processing indirectly using the own location of the vehicle V10 based on the relative position with respect to the vehicle V10. This allows the vehicles V20 and V30 to also more accurately estimate their own locations.

[0116] FIG. 17 is a block diagram illustrating an example configuration of a vehicle according to the fourth embodiment of the present disclosure.

[0117] In the two vehicles 401-1 and 401-2 shown in FIG. 17, the control unit 10 (FIG. 3) respectively realizes a reliability map management unit 411, a reliability map reference unit 412, a vehicle search unit 413, a reliability information comparison unit 414, a localization processing unit 415, a self-location information transmission unit 416, a self-location information reception unit 417, and a relative position calculation unit 418.

[0118] In the following description, when there is no need to distinguish between the vehicles 401-1 and 401-2, they will simply be referred to as vehicle 401.

[0119] The reliability map management unit 411 corresponds to the reliability map generation and management unit 35 in Fig. 3 and manages the reliability maps generated in advance. Here, it is assumed that the reliability information of the reliability map possessed by the vehicle 401-1 is higher than the reliability information of the reliability map possessed by the vehicle 401-2.

[0120] The reliability map reference unit 412 corresponds to the reliability map reference unit 36 ​​in FIG. 3, and refers to the reliability map managed by the reliability map management unit 411 to supply the vehicle search unit 413 with reliability information on the current position.

[0121] The vehicle search unit 413 searches for vehicles 401 present in the vicinity of the vehicle itself, and if a vehicle 401 is present in the vicinity, supplies specific information identifying the vehicle to the reliability information comparison unit 414 together with the reliability information from the reliability map reference unit 412.

[0122] The reliability information comparison unit 414 transmits and receives reliability information to and from the surrounding vehicles 401 identified by the identification information from the vehicle search unit 413, and compares the reliability information between the vehicles. The result of the comparison of the reliability information (level of the reliability information) is supplied to the localization processing unit 415 or the self-location information receiving unit 417.

[0123] When the localization processing unit 415 receives the comparison result of the reliability information from the reliability information comparison unit 414, it performs localization processing using a localization map and supplies self-location information representing the estimated self-location to the self-location information transmission unit 416.

[0124] The self-location information transmission unit 416 corresponds to the utilization processing unit 37 in Fig. 3. The self-location information transmission unit 416 transmits the self-location information from the localization processing unit 415 to a nearby vehicle 401 (here, vehicle 401-2).

[0125] In other words, the self-location information transmitter 416 executes the utilization process based on the comparison result of the reliability information in the plurality of reliability maps generated for different vehicles. The comparison result here indicates the reliability of the reliability information, and the utilization process is to provide utilization information usable by at least one of the vehicles (specifically, self-location information usable by other vehicles).

[0126] When the self-location information receiving unit 417 receives the comparison result of the reliability information from the reliability information comparing unit 414, it receives the self-location information transmitted from the surrounding vehicle 401 (here, vehicle 401-1) and supplies it to the relative position calculating unit 418.

[0127] The relative position calculation unit 418 also corresponds to the utilization processing unit 37 in Fig. 3. The relative position calculation unit 418 calculates the relative position (attitude) with respect to the surrounding vehicles 401, and determines the self-position by indirectly performing localization processing using the self-position information of the surrounding vehicles 401 based on the calculated relative position.

[0128] In other words, the relative position calculation unit 418 performs the utilization process based on the comparison result of the reliability information in the multiple reliability maps generated for different vehicles. The comparison result here indicates the reliability of the reliability information, and the utilization process is to estimate the vehicle position using the reliability information with the higher reliability.

[0129] The reliability map use process in the vehicle 401 of Fig. 17 will be described with reference to the flowchart of Fig. 18. The process of Fig. 17 is executed in each of the plurality of vehicles 401.

[0130] In step S411, the reliability map reference unit 412 refers to the reliability map managed by the reliability map management unit 411 to obtain reliability information of the current position.

[0131] In step S412, the vehicle search unit 413 searches for vehicles 401 present in the vicinity of the subject vehicle.

[0132] In step S413, the vehicle search unit 413 determines whether or not the vehicle 401 is present in the vicinity based on the search result.

[0133] If it is determined in step S413 that no vehicle 401 is present in the vicinity, the subsequent steps are skipped and the process ends.

[0134] On the other hand, if it is determined in step S413 that a vehicle 401 is present in the vicinity, the process proceeds to step S414, where the reliability information comparison unit 414 receives the reliability information of the surrounding vehicles 401 and compares the reliability information with each other.

[0135] In step S415, the reliability information comparison unit 414 determines whether the reliability information of the subject vehicle is the highest as a result of the comparison.

[0136] If it is determined in step S415 that the reliability information of the own vehicle is the highest (that is, if the own vehicle is the vehicle 401-1), the process proceeds to step S416, where the localization processing unit 415 executes localization processing using the localization map.

[0137] Then, in step S416, the self-position information transmitting unit 416 transmits self-position information indicating the self-position estimated by the localization process to the surrounding vehicle 401 (vehicle 401-2).

[0138] On the other hand, if it is determined in step S415 that the reliability information of the vehicle itself is not the highest (i.e., if the vehicle itself is vehicle 401-2), the process proceeds to step S418, and the self-position information receiving unit 417 receives self-position information from a nearby vehicle 401 (vehicle 401-1).

[0139] Then, in step S419, the relative position calculation unit 418 calculates the relative position with respect to the surrounding vehicles 401. In this case, the vehicle 401 can determine its own position by indirectly performing a localization process using the self-position information of the surrounding vehicles 401 based on the calculated relative position.

[0140] According to the above processing, even if the reliability information in the reliability map of the vehicle itself is low, the accuracy of the localization processing can be improved by referring to the self-position of a surrounding vehicle that has a reliability map with higher reliability information.

[0141] (4-5. Fifth embodiment: Notification to a vehicle with lower reliability) When reliability maps generated by multiple vehicles with the same sensor configuration repeatedly driving in the same area are compared, if only the reliability information of the reliability map of a specific vehicle is low, there is a possibility that some kind of defect has occurred in that vehicle. In this case, the vehicle may be notified that there is a possibility that some kind of defect has occurred.

[0142] FIG. 19 is a block diagram illustrating an example configuration of a vehicle according to the fifth embodiment of the present disclosure.

[0143] In the vehicle 501 shown in FIG. 19, the control unit 10 (FIG. 3) realizes a reliability map management unit 511, a reliability map reference unit 512, a vehicle search unit 513, a reliability map comparison unit 514, and a notification information transmission unit 515.

[0144] The reliability map management unit 511 corresponds to the reliability map generation and management unit 35 in FIG. 3, and manages a reliability map generated in advance.

[0145] The reliability map reference unit 512 corresponds to the reliability map reference unit 36 ​​in FIG. 3, and refers to and acquires the reliability map managed by the reliability map management unit 511 and supplies it to the vehicle search unit 513 .

[0146] The vehicle search unit 513, for example, searches for a vehicle having the same sensor configuration as the vehicle itself, and if a vehicle with the same sensor configuration exists, supplies specific information identifying the vehicle to the reliability map comparison unit 514 together with the reliability map from the reliability map reference unit 512.

[0147] The reliability map comparison unit 514 requests and receives the reliability map of the vehicle identified by the identification information from the vehicle search unit 513 through communication with the vehicle, and compares the reliability maps of the vehicles. The result of the comparison of the reliability maps (whether or not there is extremely low reliability information in the specific area) is supplied to the notification information transmission unit 515.

[0148] The notification information transmitting unit 515 corresponds to the utilization processing unit 37 in Fig. 3. Based on the comparison result from the reliability map comparing unit 514, the notification information transmitting unit 515 generates notification information for a vehicle having a reliability map that includes extremely low reliability information in a specific area, and transmits the notification information to the vehicle.

[0149] In other words, the notification information transmitter 515 performs a utilization process based on a comparison result of reliability information in a plurality of reliability maps generated for different vehicles. The comparison result indicates the reliability of the reliability information, and the utilization process is to provide utilization information (specifically, notification information for other vehicles) that can be used by at least one of the vehicles.

[0150] The reliability map utilization process in the vehicle 501 of Fig. 19 will be described with reference to the flowchart of Fig. 20. The process of Fig. 20 may be executed in any one of the plurality of vehicles 501.

[0151] In step S511 , the reliability map reference unit 512 refers to and acquires the reliability map managed by the reliability map management unit 511 .

[0152] In step S512, the vehicle search unit 513 searches for vehicles with the same sensor configuration that are present around the vehicle.

[0153] In step S513, the vehicle search unit 513 determines, based on the search result, whether or not a vehicle with the same sensor configuration exists.

[0154] If it is determined in step S513 that a vehicle with the same sensor configuration exists, the process proceeds to step S514, where the reliability map comparison unit 514 receives the reliability maps of vehicles with the same sensor configuration and compares the reliability maps with each other.

[0155] In step S515, the reliability map comparison unit 514 determines whether or not there is a reliability map among the compared reliability maps whose reliability information is lower than a predetermined threshold in a specific area.

[0156] If it is determined in step S515 that there is a reliability map in the specific area whose reliability information is lower than the threshold, the process proceeds to step S516, and the notification information sending unit 515 sends notification information to the vehicle in the specific area that has a reliability map whose reliability information is lower than the threshold.

[0157] On the other hand, if it is determined in step S513 that there is no vehicle with the same sensor configuration, or if it is determined in step S515 that there is no reliability map in the specific area whose reliability information is lower than the threshold value, the subsequent steps are skipped and the processing ends.

[0158] According to the above process, for example, if the reliability information of a specific vehicle in the reliability map is low among vehicles with the same sensor configuration, it is possible to notify the vehicle that some kind of defect may be occurring. In addition, since it is known that the defect is occurring in a specific area, it is also possible to investigate the cause.

[0159] Furthermore, by comparing reliability maps generated by multiple vehicles with different sensor configurations repeatedly driving the same area, and if the reliability information of each reliability map differs, it is possible to understand which sensor configuration is suitable for which environment, which can also be useful in considering sensor configurations.

[0160] 5. Application to Information Processing System The reliability map generated in the vehicle according to the present disclosure may be used in each vehicle or in other linked vehicles, or may be collectively managed and used by a server on the cloud or the like.

[0161] FIG. 21 is a block diagram illustrating a configuration example of an information processing system according to the present disclosure.

[0162] The information processing system 600 shown in FIG. 21 is composed of a plurality of vehicles 601 and an information processing device 610 .

[0163] Each of the plurality of vehicles 601 corresponds to vehicle 1 in FIG. 3 and is configured as a vehicle capable of autonomous driving.

[0164] The information processing device 610 may be configured as a cloud server, or as a computer such as a user-owned personal computer (PC), smartphone, or tablet terminal. The information processing device 610 transmits and receives various information to and from each of the multiple vehicles 601 via wireless communication lines. The information processing device 610 is configured to include an information processing unit 611.

[0165] The information processing unit 611 is composed of a CPU (Central Processing Unit), RAM (Random Access Memory), etc., and realizes various functions by executing various programs. For example, the information processing unit 611 receives a reliability map that associates location information with reliability information of a localization map used in localization processing of the vehicle 601, which is possessed by each of the multiple vehicles 601. Furthermore, the information processing unit 611 generates usage information that can be used by at least one of the vehicles 601 based on the received multiple reliability maps. The generated usage information is appropriately transmitted to at least one of the multiple vehicles 601 and used.

[0166] In the following, an embodiment of an information processing system 600 that generates usage information based on a reliability map will be described.

[0167] (5-1. Sixth Embodiment: Integration of Localization Maps Based on Reliability) When multiple vehicles of the same type travel in the same area, ideally, all of the vehicles would perform the localization process in the same way, generating equivalent localization maps and reliability maps. However, in reality, differences arise in the generated localization maps depending on the driving style, weather, vehicle condition, and the like. For example, if it is raining when a vehicle travels in a specific area, the localization map may not be generated appropriately, or if the camera lens of a vehicle is fogged up when it generates a localization map for a specific area, the resulting localization map may look unnatural.

[0168] Therefore, in this embodiment, by integrating localization maps of areas with high reliability information from among the reliability maps generated for multiple vehicles, it is possible to generate a single high-quality, wide-area localization map.

[0169] FIG. 22 is a block diagram illustrating an example of the configuration of an information processing system according to the sixth embodiment.

[0170] In the information processing system shown in FIG. 22, in N vehicles 601-1 to 601-N, a reliability map management unit 621 and a localization map extraction unit 622 are realized by the control unit 10 (FIG. 3).

[0171] The reliability map management unit 621 corresponds to the reliability map generation and management unit 35 in FIG. 3, and manages a reliability map generated in advance.

[0172] The localization map extraction unit 622 extracts localization maps of areas where reliability information is equal to or greater than a predetermined threshold from the reliability maps managed by the reliability map management unit 621. The localization maps extracted for each of the vehicles 601-1 to 601-N are transmitted to the integrated localization map generation unit 631.

[0173] The integrated localized map generation unit 631 is realized by the information processing unit 611 of the information processing device 610 executing a predetermined program. The integrated localized map generation unit 631 generates an integrated localized map that integrates the localized maps of the vehicles 601-1 to 601-N as usage information that can be used by at least any of the vehicles 601-1 to 601-N.

[0174] The localization maps transmitted from the vehicles 601-1 to 601-N are extracted from areas with reliability information higher than a certain level, so that an overall high-quality, wide-area localization map can be generated as an integrated localization map. The generated integrated localization map can also be distributed to the vehicles 601-1 to 601-N as needed.

[0175] (5-2. Seventh embodiment: Localization using position information of a vehicle with higher reliability) In the fourth embodiment described with reference to Fig. 16 to Fig. 18, the reliability information in the reliability map is compared between vehicles. In this embodiment, the reliability information in the reliability maps of multiple vehicles can be compared collectively.

[0176] FIG. 23 is a block diagram illustrating a configuration example of an information processing system according to the seventh embodiment of the present disclosure.

[0177] In the two vehicles 601-1 and 601-2 shown in FIG. 23, the control unit 10 (FIG. 3) each realizes a reliability map management unit 411, a reliability map reference unit 412, a vehicle search unit 413, a reliability information communication unit 641, a localization processing unit 415, a self-location information transmission unit 416, a self-location information reception unit 417, and a relative position calculation unit 418.

[0178] 23 differ from the vehicles 401-1 and 401-2 shown in FIG. 17 in that a reliability information communication unit 641 is provided instead of the reliability information comparison unit 414.

[0179] In the following description, when there is no need to distinguish between the vehicles 601-1 and 601-2, they will simply be referred to as vehicle 601.

[0180] The reliability information communication unit 641 transmits the specific information from the vehicle search unit 413 together with the reliability information from the reliability map reference unit 412 to the reliability information comparison unit 651 .

[0181] The reliability information comparison unit 651 is realized by the information processing unit 611 of the information processing device 610 executing a predetermined program. The reliability information comparison unit 651 compares the reliability information transmitted from each vehicle 601, and transmits comparison information indicating the comparison result (level of reliability information) to the reliability information communication unit 641 of each vehicle 601 based on identification information that identifies each vehicle 601.

[0182] Even with the above configuration, even if the reliability information in the reliability map held by the vehicle itself is low, the accuracy of the localization process can be improved by referring to the self-position of a surrounding vehicle that has a reliability map with higher reliability information.

[0183] (5-3. Eighth embodiment: Notification to a vehicle with lower reliability) In the fifth embodiment described with reference to Figures 19 and 20, the reliability maps are compared between vehicles. In this embodiment, the reliability maps of multiple vehicles can be compared collectively.

[0184] FIG. 24 is a block diagram illustrating a configuration example of an information processing system according to the eighth embodiment of the present disclosure.

[0185] In the information processing system shown in FIG. 24, in N vehicles 601-1 to 601-N, a reliability map management section 661 and a reliability map transmission section 662 are realized by the control unit 10 (FIG. 3).

[0186] The reliability map management unit 661 corresponds to the reliability map generation and management unit 35 in FIG. 3, and manages a reliability map generated in advance.

[0187] The reliability map transmitting unit 662 transmits the reliability map managed by the reliability map managing unit 661 to the reliability map comparing unit 671 together with the identification information for identifying the subject vehicle.

[0188] The reliability map comparison unit 671 and the notification information generation unit 672 are realized by the information processing unit 611 of the information processing device 610 executing a predetermined program.

[0189] The reliability map comparison unit 671 compares the reliability maps transmitted from the vehicles 601-1 to 601-N, and supplies the comparison results (presence or absence of extremely low reliability information in a specific area) to the notification information generation unit 672, together with specific information identifying each of the vehicles 601-1 to 601-N.

[0190] Based on the comparison result from the reliability map comparison unit 671, the notification information generation unit 672 generates notification information for a vehicle having a reliability map that includes extremely low reliability information in a specific area, and transmits the notification information to the vehicle.

[0191] Even with the above configuration, for example, if the reliability information of the reliability map of a specific vehicle among vehicles with the same sensor configuration is low, it is possible to notify the vehicle that some kind of malfunction may have occurred.

[0192] 6. Others The reliability map according to the present disclosure may be generated not only by a mobile object but also by a device such as a smartphone or tablet terminal that stores a localization map. In other words, the reliability map may be generated when a user moves around while carrying such a device.

[0193] In this case, as the user moves around repeatedly, it becomes possible to determine what kind of reliability map is generated when using which localization map, and it is also possible to quantitatively evaluate the localization maps on each device spatially and temporally.

[0194] Furthermore, by comparing reliability maps generated by different devices, localization maps with high reliability information can be integrated and used for vehicle localization processing. In this case, it is expected that a more accurate localization map can be obtained in areas where many people move, such as intersections with landmarks.

[0195] The configuration and operation of an autonomous vehicle have been described above as one embodiment of a moving body according to the present disclosure. However, the technology according to the present disclosure is not limited to this, and can also be applied to other moving bodies such as autonomously moving transport robots, food delivery robots, and drones that fly autonomously within a space.

[0196] 7. Example of Computer Hardware Configuration The above-described series of processes can be executed by hardware or software. When the series of processes is executed by software, the program constituting the software is installed from a program recording medium into a computer incorporated in dedicated hardware, a general-purpose personal computer, or the like.

[0197] 25 is a block diagram showing an example of the hardware configuration of a computer that executes the above-described series of processes using a program. The above-described control unit 10 and information processing device 610 can be configured, for example, by a computer having a configuration similar to that shown in FIG.

[0198] The CPU 901 , ROM (Read Only Memory) 902 , and RAM 903 are interconnected by a bus 904 .

[0199] An input / output interface 905 is also connected to the bus 904. An input unit 906 including a keyboard, a mouse, etc., and an output unit 907 including a display, a speaker, etc. are connected to the input / output interface 905. Also connected to the input / output interface 905 are a storage unit 908 including a hard disk, a nonvolatile memory, etc., a communication unit 909 including a network interface, etc., and a drive 910 that drives removable media 911.

[0200] In a computer configured as described above, the CPU 901 performs the above-described series of processes by, for example, loading a program stored in the memory unit 908 into the RAM 903 via the input / output interface 905 and the bus 904 and executing it.

[0201] The program executed by the CPU 901 is installed in the storage unit 908, for example, by being recorded on removable media 911, or provided via a wired or wireless transmission medium such as a local area network, the Internet, or digital broadcasting.

[0202] The program executed by the computer may be a program that processes in chronological order according to the order described in this specification, or may be a program that processes in parallel or at the required timing, such as when called.

[0203] In this specification, a system refers to a collection of multiple components (devices, modules (components), etc.), regardless of whether all of the components are contained in the same housing. Therefore, multiple devices housed in separate housings and connected via a network, and a single device housed in a single housing with multiple modules, are both systems.

[0204] The effects described in this specification are merely examples and are not limiting, and other effects may also be present.

[0205] The embodiments of the present disclosure are not limited to the above-described embodiments, and various modifications are possible within the scope of the gist of the present disclosure.

[0206] For example, the embodiment of the present disclosure can be configured as a cloud computing system in which a single function is shared and processed collaboratively by multiple devices via a network.

[0207] Furthermore, each step described in the above flowchart can be executed by one device, or can be shared and executed by a plurality of devices.

[0208] Furthermore, when one step includes multiple processes, the multiple processes included in that one step can be executed by one device or can be shared and executed by multiple devices.

[0209] The effects described in this specification are merely examples and are not limiting, and other effects may also be present.

[0210] Furthermore, the technology according to the present disclosure may have the following configuration. (1) An information processing device including: a position acquisition unit that acquires position information on a movement path traveled by a moving object; a reliability calculation unit that calculates reliability information of a localization map used in localization processing of the moving object; and a map generation unit that generates a reliability map that associates the position information with the reliability information. (2) The information processing device according to (1), in which the position acquisition unit acquires, as the position information, a GPS signal received on the movement path. (3) The information processing device according to (1), in which the position acquisition unit acquires the position information by odometry estimation on the movement path. (4) The information processing device according to (3), in which the position acquisition unit corrects the position information acquired by odometry estimation based on the position information of two known points on the movement path. (4-1) The information processing device according to (4), in which the two known points are a start point and an end point on the movement path. (5) The information processing device according to (4), in which the two known points are different positions. (6) The information processing device according to (4), in which the two known locations are the same location. (7) The information processing device according to any one of (4) to (6), in which the position acquisition unit corrects the position information acquired by the odometry estimation by using the position information associated with reliability information higher than a reference value in the existing reliability map as the position information of the two known locations. (8) The information processing device according to (3), in which the position acquisition unit acquires an average value of the position information acquired by the odometry estimation along the movement route traveled a plurality of times. (9) The information processing device according to any one of (1) to (8), further comprising a utilization processing unit that executes utilization processing using the reliability information of the reliability map. (10) The information processing device according to (9), in which the utilization processing unit executes the utilization processing based on a comparison result of the plurality of pieces of reliability information in the reliability map. (10-1) The information processing device according to (10), in which the utilization processing unit determines whether or not to execute the localization processing using the localization map based on the reliability information of the reliability map.(11) The information processing device according to (10), wherein the utilization processing unit executes the utilization process based on the comparison result of the plurality of pieces of reliability information in one of the reliability maps. (12) The information processing device according to (11), wherein the comparison result represents geographical variation of the reliability information, and the utilization processing includes re-creating the localization map. (13) The information processing device according to (10), wherein the utilization processing unit executes the utilization process based on the comparison result of the reliability information in the plurality of reliability maps generated at different times. (14) The information processing device according to (13), wherein the comparison result represents temporal variation of the reliability information, and the utilization processing includes updating an external HD (High Definition) map. (15) The information processing device according to (10), wherein the utilization processing unit executes the utilization process based on the comparison result of the reliability information in the plurality of reliability maps generated for different moving objects. (15-1) The information processing device according to (15), wherein the comparison result indicates a level of reliability of the reliability information, and the usage process includes estimating a self-location using the reliability information with a higher reliability. (16) The information processing device according to (15), wherein the comparison result indicates a level of reliability of the reliability information, and the usage process includes providing usage information usable by at least one of the mobile bodies. (17) The information processing device according to (16), wherein the usage information is self-location information usable by other of the mobile bodies. (18) The information processing device according to (16), wherein the usage information is notification information for the other of the mobile bodies. (19) An information processing method, wherein an information processing device acquires position information on a movement route traveled by a mobile body, calculates reliability information of a localization map used in localization processing of the mobile body, and generates a reliability map that associates the position information with the reliability information. (20) An information processing system comprising: a moving body; a position acquisition unit that acquires position information on a movement path traveled by the moving body; a reliability calculation unit that calculates reliability information of a localization map used in localization processing of the moving body; and a map generation unit that generates a reliability map that associates the position information with the reliability information.(21) An information processing device comprising: an information processing unit that generates usage information usable by at least any of a plurality of mobile bodies based on a reliability map that associates location information with reliability information of a localization map that each of the mobile bodies has and that is used in localization processing of the mobile body. (22) The information processing device described in (21), wherein the information processing unit generates, as the usage information, an integrated localization map that integrates the localization maps of the plurality of mobile bodies. (23) The information processing device described in (21), wherein the information processing unit generates, as the usage information, comparison information that represents a comparison result of reliability information of the reliability maps that each of the plurality of mobile bodies has. (24) The information processing device described in (21), wherein the information processing unit generates, as the usage information, notification information for a mobile body that has a reliability map that includes lower reliability information than other mobile bodies.

[0211] REFERENCE SIGNS LIST 1 Vehicle, 10 Control unit, 20 Sensing unit, 31 Localization map management unit, 32 Localization processing unit, 33 Position acquisition unit, 34 Reliability calculation unit, 35 Reliability map generation and management unit, 36 Reliability map reference unit, 37 Usage processing unit, 101 Vehicle, 111 Reliability map management unit, 112 Current position reliability determination unit, 113 Localization processing unit, 114 Reliability calculation unit, 115 Self-position integration unit, 201 Vehicle, 211 Reliability map management unit, 212 Current position reliability determination unit, 213 Localization processing unit, 214 Reliability calculation unit, 215 Self-position integration unit, 216 Surrounding reliability search unit, 217 Surrounding environment analysis unit, 218 Localization map re-creation unit, 301 Vehicle, 311 Reliability map management unit, 312 localization processing unit, 313 reliability calculation unit, 314 current reliability determination unit, 315 past reliability search unit, 316 HD map update unit, 317 HD map, 401-1, 401-2 vehicle, 411 reliability map management unit, 412 reliability map reference unit, 413 vehicle search unit, 414 reliability information comparison unit, 415 localization processing unit, 416 self-position information transmission unit, 417 self-position information reception unit, 418 relative position calculation unit, 501 vehicle, 511 reliability map management unit, 512 reliability map reference unit, 513 vehicle search unit, 514 reliability map comparison unit, 515 notification information transmission unit, 600 information processing system, 601, 601-1, 601-2, ..., 601-N: vehicle; 610: information processing device; 611: information processing unit; 631: integrated localization map generating unit; 651: reliability information comparing unit; 671: reliability map comparing unit; 672: notification information generating unit

Claims

1. An information processing device comprising: a position acquisition unit that acquires position information on a route traveled by a moving object; a reliability calculation unit that calculates reliability information of a localization map used in localization processing of the moving object; and a map generation unit that generates a reliability map that associates the position information with the reliability information.

2. The information processing device according to claim 1, wherein the position acquisition unit acquires, as the position information, a GPS signal received along the movement route.

3. The information processing device according to claim 1, wherein the position acquisition unit acquires the position information by odometry estimation on the moving route.

4. The information processing device according to claim 3, wherein the position acquisition unit corrects the position information acquired by the odometry estimation based on the position information of two known points on the movement route.

5. The information processing device according to claim 4, wherein the two known points are different positions.

6. The information processing device according to claim 4, wherein the two known points are the same location.

7. The information processing device according to claim 4, wherein the position acquisition unit corrects the position information acquired by the odometry estimation by using the position information associated with reliability information higher than a standard in the existing reliability map as the position information of the two known points.

8. The information processing device according to claim 3, wherein the position acquisition unit acquires an average value of the position information acquired by the odometry estimation on the movement route traveled a plurality of times.

9. The information processing device according to claim 1, further comprising a utilization processing unit that executes utilization processing using the reliability information of the reliability map.

10. The information processing device according to claim 9, wherein the utilization processing unit executes the utilization process based on a comparison result of a plurality of pieces of reliability information in the reliability map.

11. The information processing device according to claim 10, wherein the utilization processing unit executes the utilization process based on the comparison result of a plurality of pieces of reliability information in one of the reliability maps.

12. The information processing apparatus according to claim 11, wherein the comparison result represents a geographic variation of the reliability information, and the utilization process includes recreating the localization map.

13. The information processing device according to claim 10, wherein the utilization processing unit executes the utilization process based on the comparison result of the reliability information in a plurality of the reliability maps generated at different times.

14. The information processing device according to claim 13, wherein the comparison result represents a temporal variation of the reliability information, and the utilization process includes updating an external HD (High Definition) map.

15. The information processing device according to claim 10, wherein the utilization processing unit executes the utilization processing based on the comparison result of the reliability information in a plurality of the reliability maps generated for different said moving bodies.

16. The information processing device according to claim 15, wherein the comparison result indicates a degree of reliability of the reliability information, and the utilization process includes providing utilization information usable by at least any of the mobile objects.

17. The information processing device according to claim 16, wherein the usage information is self-location information that can be used by other mobile bodies.

18. The information processing device according to claim 16, wherein the usage information is notification information for other mobile bodies.

19. An information processing method, in which an information processing device acquires position information on a route traveled by a moving object, calculates reliability information of a localization map used in localization processing of the moving object, and generates a reliability map that associates the position information with the reliability information.

20. An information processing system comprising: a moving body; a position acquisition unit that acquires position information on a path traveled by the moving body; a reliability calculation unit that calculates reliability information of a localization map used in localization processing of the moving body; and a map generation unit that generates a reliability map that associates the position information with the reliability information.

Images