Information processing method, information processing device, and program

Abstract

The present disclosure pertains to an information processing method, an information processing device, and a program that make it possible to achieve a travel environment in which the self-position can be estimated more easily. The present disclosure presents an improvement proposal for: estimating, on the basis of detection data detected by an external sensor provided to an autonomous mobile body that autonomously moves in a travel environment, the self-position of the autonomous mobile body; calculating a score indicating the ease of estimating the self-position of the autonomous mobile body at a prescribed measurement point in the travel environment; and improving, on the basis of the score, the ease of estimating the self-position of the autonomous mobile body. The present technology can be applied to, for example, an autonomous mobile robot.

Description

Information processing method, information processing device, and program

[0001] The present disclosure relates to an information processing method, an information processing device, and a program, and more particularly to an information processing method, an information processing device, and a program that enable a driving environment in which it is easier to estimate a vehicle's own position.

[0002] In recent years, autonomous mobile objects such as transport robots have widely adopted a method for estimating their self-location using point clouds detected by LiDAR (Light Detection and Ranging), which measures the distance to surrounding objects by irradiating the surroundings with pulsed light and detecting the reflected light with an optical sensor. To ensure that autonomous mobile objects can reliably carry out their tasks, there is a demand for them to estimate their self-location with higher accuracy.

[0003] For example, Patent Document 1 discloses a mobile device that improves the accuracy of estimating its own position by utilizing the rate of change of a score that indicates the degree of agreement between map information and sensor information.

[0004] International Publication No. 2023 / 189721

[0005] The accuracy with which an autonomous mobile body estimates its own position varies depending on the driving environment in which the autonomous mobile body travels. Conventionally, whether a driving environment allows for more accurate estimation of the self-position has been determined based on the empirical rules of an expert, such as a developer of the autonomous mobile body. Therefore, for example, even if the driving environment needs to be changed because information necessary for highly accurate estimation of the self-position is lacking, only an expert could determine how to change the driving environment. Therefore, there is a need to realize a driving environment that facilitates self-position estimation without relying on the empirical rules of an expert.

[0006] The present disclosure has been made in consideration of such circumstances, and aims to realize a driving environment in which it is easier to estimate one's own position.

[0007] An information processing method according to one aspect of the present disclosure includes an information processing device estimating a self-position of an autonomous moving body based on detection data detected by an external sensor provided on the autonomous moving body that moves autonomously in a driving environment, calculating a score indicating the ease of estimating the self-position of the autonomous moving body at a predetermined measurement point within the driving environment, and presenting an improvement proposal for improving the ease of estimating the self-position of the autonomous moving body based on the score.

[0008] An information processing device according to one aspect of the present disclosure includes an estimation unit that estimates the self-position of an autonomous moving body based on detection data detected by an external sensor provided on the autonomous moving body that moves autonomously in a driving environment, a calculation unit that calculates a score indicating the ease of estimating the self-position of the autonomous moving body at a predetermined measurement point within the driving environment, and an improvement suggestion unit that presents improvement suggestions for improving the ease of estimating the self-position of the autonomous moving body based on the score.

[0009] A program according to one aspect of the present disclosure causes a computer of an information processing device to perform information processing including estimating the self-position of an autonomous moving body based on detection data detected by an external sensor provided on the autonomous moving body that moves autonomously in a driving environment, calculating a score indicating the ease of estimating the self-position of the autonomous moving body at a predetermined measurement point within the driving environment, and presenting improvement suggestions for improving the ease of estimating the self-position of the autonomous moving body based on the score.

[0010] In one aspect of the present disclosure, the self-position of an autonomous moving body is estimated based on detection data detected by an external sensor provided on the autonomous moving body that moves autonomously in a driving environment, a score indicating the ease of estimating the self-position of the autonomous moving body at a specified measurement point in the driving environment is calculated, and an improvement proposal for improving the ease of estimating the self-position of the autonomous moving body is presented based on the score.

[0011] FIG. 1 is a diagram illustrating a self-localization method to which the present technology is applied. FIG. 2 is a diagram illustrating an example of a score calculation method. FIG. 3 is a block diagram illustrating a configuration example of an embodiment of an autonomous mobile robot to which the present technology is applied. FIG. 4 is a flowchart illustrating a first driving control process. FIG. 5 is a diagram illustrating a first display example of a presentation screen. FIG. 6 is a diagram illustrating a second display example of a presentation screen. FIG. 7 is a flowchart illustrating a second driving control process. FIG. 8 is a diagram illustrating a display example of a presentation screen. FIG. 9 is a flowchart illustrating a third driving control process. FIG. 10 is a flowchart illustrating an improvement suggestion process. FIG. 11 is a diagram illustrating an example of improving the ease of self-localization estimation. FIG. 12 is a block diagram illustrating a configuration example of an embodiment of a computer to which the present technology is applied.

[0012] Hereinafter, specific embodiments to which the present technology is applied will be described in detail with reference to the drawings.

[0013] <Regarding Self-Location Estimation Method> A self-location estimation method to which the present technology is applied will be described with reference to FIGS. 1 and 2 .

[0014] FIG. 1 shows an example of a traveling environment in which the autonomous mobile robot 11 travels, with walls in the traveling environment indicated by hatching.

[0015] For example, at position A shown in Figure 1, the autonomous mobile robot 11 can estimate its own position with high accuracy by recognizing walls on three sides. On the other hand, at position B shown in the upper part of Figure 1, the autonomous mobile robot 11 can only recognize walls that are parallel to it, and it is difficult for it to recognize where its own position is along those walls, so it is not possible to estimate its own position with high accuracy.

[0016] The stars on the wall in Figure 1 represent the positions of clusters (features extracted by compressing the point cloud information) obtained by performing normal estimation on a point cloud obtained from a sensor such as LiDAR and then performing clustering processing on the mapping as a normal vector. For example, the normal vector may be a unit vector, or the distance to the wall may be used as the length. The autonomous mobile robot 11 can then determine the ease of estimating its own location based on, for example, the direction and number of clusters at its current location.

[0017] 1, clusters are arranged above and below position B, but no clusters are arranged to the right or left of the drawing. Therefore, it can be determined that it is difficult for the autonomous mobile robot to estimate its own position along the left-right direction of the drawing at position B, and it is recognized that it is difficult to estimate its own position with high accuracy. Therefore, when performing a task that requires stopping at position B, it is expected that the stopping position of the autonomous mobile robot 11 will easily shift from position B to the right or left of the drawing.

[0018] Therefore, this technology calculates a score to determine the ease with which the autonomous mobile robot 11 can estimate its own position, and presents improvement suggestions that encourage improvements to the driving environment so that the score increases, thereby making it possible to create a driving environment that makes it easier to estimate its own position.

[0019] For example, as shown in the lower part of Figure 1, an improvement proposal is presented to install a landmark LM, such as a retroreflective material with a reflectivity that is clearly different from that of a wall, near position B. When the landmark LM is installed in accordance with the improvement proposal, a cluster is placed at the position of the landmark LM due to the light reflected by the landmark LM, which increases the score at position B and realizes a driving environment in which it is easier to estimate the vehicle's own position.

[0020] A method for calculating a score indicating the ease of self-location estimation will be described with reference to FIG.

[0021] For example, the unit normal vector C of each of the N clusters i The score s in the x direction obtained for (i = 0, ..., n) x is the direction x and the unit normal vector C k It can be calculated by the sum of the absolute values ​​of the inner products (k=0 to n), that is, according to the following formula (1).

[0022]

[0023] In a traveling environment in which clusters are arranged only at positions (0, 1) and (0, -1) for the autonomous mobile robot 11, as shown in FIG. 2A, the score s x is calculated as 0, and the score s in the direction (0.5, 0.9) x is calculated as 1, and the score s in the direction (0.9, 0.5) x is calculated as 1.7, and the score s x is calculated as 2. Therefore, the score s x It can be recognized that the driving environment is difficult to estimate the self-position along the direction (1, 0) where the calculated value is low.

[0024] In addition, the score s x can be calculated continuously for any x direction. In the example shown in FIG. 2, the score s x The score s x is calculated using the above-mentioned formula (1), or may be calculated using, for example, the sum of squares.

[0025] The score S at that point is calculated by multiplying the scores s obtained for all x directions. x For example, the score s of the four directions shown in FIG. 2B can be calculated by summing up the smaller values ​​of the comparison results of the four directions s x The score S can be calculated as 3.0.

[0026]

[0027] In this way, by determining the ease with which the autonomous mobile robot 11 estimates its own location according to the score S, in a traveling environment in which it is difficult to estimate its own location, an improvement proposal such as installing a landmark LM can be displayed and presented on the presentation screen as shown in C of Fig. 2. Then, by installing the landmark LM according to the improvement proposal, the ease of estimating its own location can be improved, and a traveling environment in which it is easier to estimate its own location can be realized. In addition, the score S (Score: 3.9 in the illustrated example) indicating the result of improving the ease of estimating its own location according to the improvement proposal may be displayed in real time on the presentation screen and presented to the user.

[0028] In the present embodiment, as shown in FIG. 2C, the score s x is smaller than a predetermined threshold value, the area within the measurement range of the LiDAR centered on the current position of the autonomous mobile robot 11 is represented by hatching with dots, and the score s x The hatching is shown thicker in the direction where the value of s is lower. That is, the area where the installation of landmarks LM such as retroreflective materials or partitions is instructed (hereinafter referred to as the instruction area) is represented by the area hatched with dots. Therefore, in FIG. 2C, the score s in the direction (1, 0) along the wall is x is the lowest score, and x An example is shown in which an improvement proposal is made to install a landmark LM within a designated area where the .times. ...

[0029] <Configuration Example of Autonomous Mobile Robot> FIG. 3 is a block diagram showing a configuration example of an embodiment of an autonomous mobile robot to which the present technology is applied.

[0030] 3 , the autonomous mobile robot 11 can be connected to a user terminal 12 via, for example, wireless communication, and is configured to include an external sensor 21, an internal sensor 22, a drive unit 23, and a driving control device 24. The driving control device 24 is configured to include an obstacle recognition unit 31, a normal vector mapping unit 32, a behavior planning unit 33, a map creation unit 34, and a self-location estimation processing unit 35, and the self-location estimation processing unit 35 has a score calculation unit 41, a determination unit 42, an improvement proposal unit 43, and a simulation unit 44.

[0031] The user terminal 12 is equipped with a touch panel and displays a presentation screen that presents improvement suggestions to make it easier for the autonomous mobile robot 11 to estimate its own position, and transmits input information entered in accordance with the user's operation on the presentation screen to the autonomous mobile robot 11.

[0032] The external sensor 21 is composed of various sensors that detect the external state of the autonomous mobile robot 11, such as a 2D LiDAR that scans light in a plane, a 3D LiDAR that scans light three-dimensionally, a camera that captures images, etc. The external sensor 21 supplies external sensor detection data including a point cloud obtained by the LiDAR, for example, to the obstacle recognition unit 31, the normal vector mapping unit 32, and the map creation unit 34.

[0033] The internal sensor 22 is composed of various sensors that detect the internal state of the autonomous mobile robot 11, such as an IMU (Inertial Measurement Unit) that detects three-axis angular velocity and acceleration accompanying the movement of the autonomous mobile robot 11, and an odometry detection unit that detects the traveling trajectory according to the movement of the wheels, steering, etc. of the autonomous mobile robot 11. The internal sensor 22 then supplies the self-position estimation processing unit 35 with internal sensor detection data including the angular velocity, acceleration, traveling trajectory, etc. of the autonomous mobile robot 11.

[0034] The driving unit 23 drives the wheels, steering, etc. of the autonomous mobile robot 11 in accordance with control commands supplied from the behavior planning unit 33 of the driving control device 24 to cause the autonomous mobile robot 11 to travel.

[0035] The driving control device 24 executes a driving control process that supplies control commands to the drive unit 23 based on the external sensor detection data supplied from the external sensor 21 and the internal sensor detection data supplied from the internal sensor 22, and controls the driving of the autonomous mobile robot 11. For example, the driving control device 24 can execute a first driving control process (see the flowchart in FIG. 4) in which the autonomous mobile robot 11 drives while proposing improvements to the ease of self-position estimation when creating a map of the driving environment while estimating its current position.

[0036] When the obstacle recognition unit 31 recognizes an obstacle in the driving environment in which the autonomous mobile robot 11 is traveling based on the external sensor detection data supplied from the external sensor 21, it supplies obstacle position information indicating the position of the obstacle to the behavior planning unit 33.

[0037] The normal vector mapping creation unit 32 performs normal estimation on the point cloud included in the external sensor detection data supplied from the external sensor 21, and supplies cluster position information indicating the position of the cluster obtained by applying a clustering process to the mapping as a normal vector to the score calculation unit 41 of the self-position estimation processing unit 35.

[0038] The behavior planning unit 33 refers to the map created by the map creation unit 34 and supplies control commands to the driving unit 23 so that the autonomous mobile robot 11 acts in accordance with the behavior plan created in accordance with the task instructed to the autonomous mobile robot 11, based on the self-position estimated by the self-position estimation processing unit 35. At this time, the behavior planning unit 33 creates a behavior plan based on the obstacle position information supplied from the obstacle recognition unit 31 so that the autonomous mobile robot 11 will travel while avoiding obstacles.

[0039] The map creation unit 34 creates a map of the driving environment using the self-position estimated by the self-position estimation processing unit 35 as the measurement point, so that walls, objects, etc. detected in the external sensor detection data supplied from the external sensor 21 are positioned.

[0040] The self-position estimation processing unit 35 estimates the self-position of the autonomous mobile robot 11 based on the external sensor detection data supplied from the external sensor 21 and the internal sensor detection data supplied from the internal sensor 22 .

[0041] The score calculation unit 41 calculates a score indicating the ease of estimating the self-position of the autonomous mobile robot 11 at each position in the traveling environment based on the direction and number of clusters supplied from the normal vector mapping unit 32. That is, the score calculation unit 41 calculates the score s for each x-direction at each position in the traveling environment in accordance with the above-mentioned formula (1). x and calculates the score S at each position in the driving environment according to the above-mentioned formula (2).

[0042] The determination unit 42 determines whether the score S calculated by the score calculation unit 41 is equal to or greater than a predetermined threshold value. The determination unit 42 also determines whether the autonomous mobile robot 11 has traveled the entire traveling environment in the traveling control process.

[0043] The improvement suggestion unit 43 calculates the score s of the current position calculated by the score calculation unit 41 at a position where the score S calculated by the score calculation unit 41 is less than a predetermined threshold. x Based on this, an improvement proposal is presented to the user terminal 12, which encourages the user to improve the ease of self-location estimation by placing a landmark in the designated area as shown in C of FIG. 2 above.

[0044] As will be described later with reference to Figures 11 and 12, the simulation unit 44 performs offline simulation (e.g., ray casting) on ​​a map created by a conventional creation method, and edits the map so that landmarks are placed in the simulation, thereby improving the ease of self-location estimation.

[0045] The autonomous mobile robot 11 is configured as described above, and when it detects a location where the estimation accuracy of its own position is low when creating a map of the driving environment while estimating its current position, or when it detects a location where the estimation accuracy of its own position has become low due to a change in the driving environment during autonomous driving, it calculates a score s xThe system can present an improvement proposal for arranging landmarks based on the proposed improvement. By placing landmarks in accordance with the proposed improvement, it is possible to realize a driving environment in which it is easier to estimate the autonomous mobile robot's position. This enables the autonomous mobile robot 11 to perform tasks such as stopping with high precision.

[0046] For example, the autonomous mobile robot 11 can present improvement proposals as a planar overhead view on the presentation screen displayed on the user terminal 12, or can use AR (Augmented Reality) technology to present the improvement proposals by superimposing them on an image of the real world, or can project the improvement proposals onto a wall or the like using a light source such as a laser mounted on the autonomous mobile robot 11. Furthermore, the autonomous mobile robot 11 may present the improvement proposals including height information, or may present the improvement proposals in 3D.

[0047] Furthermore, when presenting improvement suggestions, the autonomous mobile robot 11 can place landmarks in optimal positions by combining information specified by the user using the user terminal 12. For example, if the user has prior knowledge of areas where the driving environment changes significantly, the user can input information to the autonomous mobile robot 11 specifying whether or not to install landmarks, restrictions on the orientation of the landmarks, and the like.

[0048] Furthermore, by using landmarks such as retroreflective materials, the autonomous mobile robot 11 can treat the landmarks as virtual walls with a certain area, and can determine where the landmarks should be placed to ensure stable ease of self-position estimation.

[0049] It is preferable that the landmarks are not distinctive objects or obstacles, but rather markers that do not impede the movement of the autonomous mobile robot 11. For example, the landmarks are preferably objects whose positions are statically determined or markers that can be recognized by any sensor, and that can be attached to a wall, etc. Alternatively, patterns projected by an irradiation device can be used as landmarks.

[0050] For example, the autonomous mobile robot 11 can present improvement suggestions such as the location or area for a new landmark or a method for changing the location of an already installed landmark. The improvement suggestions can be displayed on the user terminal 12 as described above, or can be superimposed on a map or image of the traveling environment on a display device mounted on the autonomous mobile robot 11.

[0051] Referring to the flowchart shown in Figure 4, a first driving control process will be described in which the autonomous mobile robot 11 travels while proposing improvements to the ease of self-position estimation when creating a map of the driving environment while estimating its current position.

[0052] For example, the process starts when an instruction to create a map is input to the autonomous mobile robot 11. In step S11, the self-position estimation processing unit 35 estimates the current self-position of the autonomous mobile robot 11 based on the external sensor detection data supplied from the external sensor 21 and the internal sensor detection data supplied from the internal sensor 22. The normal vector mapping unit 32 estimates normals to the point cloud included in the external sensor detection data supplied from the external sensor 21, using the current position of the autonomous mobile robot 11 as a measurement point, and performs clustering processing on the mapping as normal vectors. The normal vector mapping unit 32 then supplies the clusters determined by the clustering processing to the score calculation unit 41, and the score calculation unit 41 calculates the score s at the current position in accordance with the above-mentioned equations (1) and (2). x and the score S is calculated.

[0053] In step S12, the determination unit 42 determines whether the score S of the current position calculated by the score calculation unit 41 in step S11 is equal to or greater than a predetermined threshold value.

[0054] If the determination unit 42 determines in step S12 that the score S of the current position is not equal to or greater than the predetermined threshold value (i.e., is less than the threshold value), the process proceeds to step S13.

[0055] In step S13, the improvement suggesting unit 43 calculates the score s of the current position calculated by the score calculation unit 41 in step S11.x Based on this, an improvement proposal is presented to the user terminal 12, which encourages the user to improve the ease of self-location estimation by placing a landmark in the designated area as shown in C of FIG. 2 above.

[0056] After the process of step S13, the process returns to step S11, and the same process is repeated. When a landmark is installed in accordance with the improvement proposal in step S13, the score S calculated in step S11 increases. If the determination unit 42 determines in step S12 that the score S of the current position is equal to or greater than a predetermined threshold, the process proceeds to step S14.

[0057] In step S14, the map creation unit 34 creates a map of the driving environment based on the external sensor detection data supplied from the external sensor 21 at the current position of the autonomous mobile robot 11 (i.e., the current self-position estimated by the self-position estimation processing unit 35).

[0058] In step S15, the behavior planning unit 33 determines whether or not the vehicle has traveled through the entire traveling environment for which a map is to be created.

[0059] If the behavior planning unit 33 determines in step S15 that the autonomous mobile robot 11 has not traveled through the entire traveling environment, the process proceeds to step S16, where the behavior planning unit 33 issues a control command to the driving unit 23 to travel to the next measurement point. In accordance with this control command, the driving unit 23 drives the wheels, steering, etc. to cause the autonomous mobile robot 11 to travel to the next measurement point, and then the process returns to step S11, and the same process is repeated thereafter.

[0060] On the other hand, if the behavior planning unit 33 determines in step S15 that the entire traveling environment has been traveled, the processing is terminated.

[0061] By executing the first driving control process as described above, the autonomous mobile robot 11 can make improvement suggestions such as encouraging the installation of new landmarks when creating a map that includes a driving environment in which the accuracy of estimating its own position is low, such as an open area or a long corridor. By responding to the improvement suggestions, a driving environment in which the autonomous mobile robot 11 can easily estimate its own position can be created, and the autonomous mobile robot 11 can more reliably perform tasks based on the created map.

[0062] FIG. 5 is a diagram showing a first display example of the presentation screen displayed on the user terminal 12 in step S13 of FIG.

[0063] As shown in the upper part of FIG. 5, the presentation screen displays a map in the process of being created (a local map being created in real time) with a score s based on the current position of the autonomous mobile robot 11. x The display also shows the current location's score S (in the example shown, Score: 21) and a message suggesting improvements to the driving environment: "Please install retroreflective material in the designated area."

[0064] Then, in accordance with this presentation screen, landmarks are placed in two locations within the designated area, and the light reflected from these two landmarks is detected by the LiDAR, resulting in the display of two landmarks (landmark_01, landmark_02) on the presentation screen, as shown in the lower part of Fig. 5. Furthermore, the presentation screen displays a score S (in the illustrated example, Score: 76) indicating that the ease of self-localization has improved as a result of the placement of the two landmarks, as well as a message urging the user to continue creating a map, saying, "Your score has improved. Please resume driving."

[0065] FIG. 6 is a diagram showing a second display example of the presentation screen displayed on the user terminal 12 in step S13 of FIG.

[0066] As shown in the upper part of FIG. 6, the presentation screen displays a score s based on the current position of the autonomous mobile robot 11 on a map that is currently being created. xThe display also shows the current location's score S (in the example shown, Score: 39) and a message suggesting improvements to the driving environment: "Install retroreflective material in the designated area and press the registration button."

[0067] Then, in accordance with this presentation screen, a landmark is placed at one location within the designated area, and light reflected from the landmark is detected by the LiDAR, resulting in the landmark (landmark_01) being displayed on the presentation screen as shown in the lower part of Fig. 6. Furthermore, the presentation screen displays a score S (in the illustrated example, Score: 88) indicating that the ease of self-localization estimation has improved as a result of the placement of the landmark, as well as a message urging the user to continue creating a map, "Your score has improved. Please resume driving."

[0068] Referring to the flowchart shown in Figure 7, we will explain the second driving control process in which the autonomous mobile robot 11 drives while suggesting improvements to the ease of self-location estimation if the ease of self-location estimation decreases due to changes in the driving environment since the map was created when the autonomous mobile robot 11 drives in a driving environment using a created map.

[0069] For example, the process begins when a predetermined task is assigned to the autonomous mobile robot 11 and the autonomous mobile robot 11 starts moving in accordance with the task. Then, in steps S21 and S22, the same processes as in steps S11 and S12 in FIG. 4 are carried out.

[0070] If the determination unit 42 determines in step S22 that the score S of the current position is not equal to or greater than the predetermined threshold value (i.e., is less than the threshold value), the process proceeds to step S23.

[0071] In step S23, the improvement suggesting unit 43 calculates the score s of the current position calculated by the score calculation unit 41 in step S11. x Based on this, an improvement proposal is presented to the user terminal 12, which encourages the user to improve the ease of self-location estimation by placing a landmark in the designated area as shown in C of FIG. 2 above.

[0072] After the process of step S23, the process returns to step S21, and the same process is repeated thereafter. When a landmark is installed in accordance with the improvement proposal in step S23, the score S calculated in step S21 increases, and if the determination unit 42 determines in step S22 that the score S of the current position is equal to or greater than a predetermined threshold, the process returns to step S21, and the same process is repeated thereafter.

[0073] By executing the second driving control process as described above, the autonomous mobile robot 11 can propose improvements to make it easier to estimate its own position when it encounters a location where the accuracy of measuring its own position has decreased due to a change in the driving environment after the map was created (for example, a box or shelf that was placed there has moved). This makes it possible to create a driving environment in which the autonomous mobile robot 11 can easily estimate its own position.

[0074] FIG. 8 is a diagram showing an example of a presentation screen displayed on the user terminal 12 in step S23 of FIG.

[0075] As shown in the upper part of FIG. 8, the presentation screen displays a score s on the created map with the current position of the autonomous mobile robot 11 as the reference. x The display also shows the landmark (landmark_01) that was installed when the map was created, the score S for the current location (in the example shown, Score: 39), and a message suggesting improvements by relocating the landmark: "Move the retroreflective material to the designated area and press the register button."

[0076] When the landmark is moved within the designated area in accordance with this presentation screen, the landmark (landmark_01) is displayed on the presentation screen in accordance with the position of the landmark after the movement, as shown in the lower part of Fig. 8. Furthermore, the presentation screen displays a score S (in the illustrated example, Score: 88) indicating that the ease of self-location estimation has improved as a result of the landmark being installed, as well as a message urging the user to continue performing the task, "Your score has improved. Please resume driving."

[0077] With reference to the flowchart shown in FIG. 9, a third driving control process that proposes improving the ease of self-position estimation after creating a map of the driving environment while estimating the current position will be described.

[0078] For example, when an instruction to create a map is input to the autonomous mobile robot 11, the process starts, and in step S31, the same process as step S11 in FIG. 4 is carried out.

[0079] In step S32, the map creation unit 34 creates a map of the traveling environment based on the external sensor detection data supplied from the external sensor 21 at the current position of the autonomous mobile robot 11 (i.e., the current position estimated by the self-position estimation processing unit 35). At this time, the map creation unit 34 records on the map, of all the measurement points calculated by the score calculation unit 41, those whose scores S are determined to be less than a predetermined threshold value.

[0080] In steps S33 and S34, the same processing as in steps S15 and S16 in FIG. 4 is performed, and if the behavior planning unit 33 determines in step S33 that the entire traveling environment has been traveled, the processing proceeds to step S35.

[0081] In step S35, the improvement suggestion unit 43 identifies measurement points where the score S is determined to be less than a predetermined threshold in the map of the entire driving environment created by the map creation unit 34 as locations where the estimation accuracy of the self-location is low, and presents to the user terminal 12 an improvement suggestion that encourages improving the ease of self-location estimation at those locations. For example, by recording on the map measurement points where the score S is determined to be less than a predetermined threshold, the improvement suggestion unit 43 can find appropriate installation positions that will achieve a certain score over the entire space with a minimum number of landmarks and present an improvement suggestion. Then, the processing ends.

[0082] By executing the third driving control process as described above, the autonomous mobile robot 11 can create a map of the driving environment and then make improvement suggestions to make it easier to estimate its own position. Therefore, by installing landmarks in accordance with the improvement suggestions, a driving environment in which the autonomous mobile robot 11 can easily estimate its own position can be realized.

[0083] For example, it may be determined that the autonomous mobile robot 11 has been improved to make it easier to estimate its own position based on the virtual placement of landmarks on the presentation screen displayed on the user terminal 12. Alternatively, as will be described later, in combination with a simulation by the simulation unit 44, the autonomous mobile robot 11 may be caused to travel in a simulated traveling environment after the landmarks have been placed, thereby confirming that the autonomous mobile robot 11 has been improved to make it easier to estimate its own position.

[0084] FIG. 10 is a diagram showing an example of the presentation screen displayed on the user terminal 12 in step S35 of FIG.

[0085] As shown in the upper part of Figure 5, the presentation screen displays a circular designated area on the created map that includes the measurement point with the low score S. The presentation screen also displays that the stopping accuracy in the designated area is 0.3 m, and displays a message suggesting improvements to the driving environment: "Install retroreflective material in the designated area and press the registration button."

[0086] Then, when landmarks are placed in five locations within the designated area in accordance with this presentation screen and the registration button is pressed, five landmarks (landmark_01 to landmark_05) are displayed on the presentation screen, as shown in the lower part of Fig. 10. Furthermore, the presentation screen displays that the installation of the five landmarks has improved the ease of self-location estimation, resulting in a stopping accuracy of 0.05 m, and displays the message "Score improved."

[0087] With reference to the flowchart shown in FIG. 11, an improvement suggestion process for suggesting an improvement to the ease of self-location estimation for a map created by a conventional creation method will be described.

[0088] For example, the process starts when a map created using a conventional creation method is supplied to the driving control device 24 via the user terminal 12. In step S41, the simulation unit 44 performs an offline simulation on the map created using the conventional creation method, and supplies cluster position information indicating the positions of clusters to be placed on the map to the score calculation unit 41. The score calculation unit 41 then calculates a score S for each position on the map based on the direction and number of clusters supplied from the simulation unit 44, and the simulation unit 44 visualizes the score S calculated by the score calculation unit 41, for example, using a heat map.

[0089] In step S42, the simulation unit 44 determines whether or not the score S calculated in step S41 is equal to or greater than a predetermined threshold value over the entire area on the map.

[0090] In step S42, if the simulation unit 44 determines that the score S calculated in step S41 is not greater than or equal to a predetermined threshold value across the entire map, i.e., if there is a location where the score S is less than the predetermined threshold value, the processing proceeds to step S43.

[0091] In step S43, the simulation unit 44 edits the map so that landmarks are placed at locations where the score S is less than a predetermined threshold.

[0092] After step S43, the process returns to step S41, and the same process is repeated for the map on which the landmarks were placed in step S43. If the score S is increased by the offline simulation for the map on which the landmarks were placed, and if it is determined in step S42 that the score S calculated in step S41 is equal to or greater than a predetermined threshold value over the entire map, the process proceeds to step S44.

[0093] In step S44, the improvement suggestion unit 43 presents the map finally created in step S43 with the landmarks arranged thereon, i.e., the map in which the score S is equal to or greater than the predetermined threshold value over the entire area of ​​the map, to the user terminal 12 as an improvement suggestion for encouraging improvement of the ease of self-location estimation. Then, the process ends.

[0094] By executing the above-described improvement proposal process, it is possible to make improvement proposals that make it easier to estimate the autonomous mobile robot's own position in a simulation using a map created by a conventional method, thereby realizing a driving environment in which the autonomous mobile robot 11 can easily estimate its own position.

[0095] FIG. 12 is a diagram illustrating an example in which the ease of self-location estimation is improved by editing the map in step S43 of FIG.

[0096] 12 shows a heat map of the score S obtained by the simulation on the map before editing. For example, this map shows that the stopping accuracy is 0.3 m in the area with thick hatching and 0.05 m in the area with light hatching.

[0097] 12 shows a map in which the score S obtained by the simulation after editing the map to include two landmarks (landmark_01, landmark_02) is visualized as a heat map. As shown in the figure, the ease of self-localization is improved by the changes in the vicinity of the two landmarks.

[0098] As described above, in this embodiment, a traveling environment can be realized in which the autonomous mobile robot 11 can easily estimate its own position.

[0099] The autonomous mobile robot 11 can navigate using a map that improves the ease of estimating its own position.

[0100] For example, the autonomous mobile robot 11 can perform navigation such as changing the expansion amount of the prohibited area according to the difficulty of estimating its own position, or adaptively changing the avoidance width of the prohibited area, traveling speed, etc. In this case, the autonomous mobile robot 11 may also perform evaluation taking time series data into account.

[0101] For example, since the ease of estimating the autonomous mobile robot's position varies depending on the robot's motion model, the direction of movement, the stability of the previous step, etc., the autonomous mobile robot 11 can perform calculations to improve the ease of estimating the autonomous mobile robot's position by taking into account the direction and history in which the ease of estimating the autonomous mobile robot's position is likely to be improved. x Depending on the direction in which x The autonomous mobile robot 11 may create an action plan to move in a direction where the value of the external sensor 21 is higher. Furthermore, the autonomous mobile robot 11 may use external sensor detection data that is integrated by weighting the detection data of each of the multiple sensors included in the external sensor 21 based on the ease of estimating the autonomous mobile robot's position for each sensor.

[0102] Furthermore, the autonomous mobile robot 11 can provide user applications that use maps with improved ease of self-position estimation.

[0103] For example, the autonomous mobile robot 11 can use the user application to notify the user of places where the ease of self-localization estimation is low, to notify the user when there are consecutive places where the ease of self-localization estimation is low during map creation, and to notify the user to recreate the map.Furthermore, the autonomous mobile robot 11 can use the user application to notify the user to install distinctive features such as partitions, to notify candidates for where installing distinctive features will improve the score, and to visualize changes in the map resulting from installing distinctive features.

[0104] Furthermore, the autonomous mobile robot 11 can indicate whether or not a location is available where stopping accuracy can be set, present a value by which stopping accuracy can be set, start, reset, present better locations as map switching points, etc. For example, the autonomous mobile robot 11 may display clusters such as those indicated by stars in FIG.

[0105] <Example of Computer Configuration> Next, the above-described series of processes (information processing method) can be performed by hardware or software. When the series of processes is performed by software, a program constituting the software is installed in a general-purpose computer or the like.

[0106] FIG. 13 is a block diagram showing an example of the configuration of an embodiment of a computer in which a program for executing the above-described series of processes is installed.

[0107] The program can be recorded in advance on the hard disk 105 or ROM 103 as a recording medium built into the computer.

[0108] Alternatively, the program can be stored (recorded) on a removable recording medium 111 driven by the drive 109. Such a removable recording medium 111 can be provided as a so-called package software. Here, examples of the removable recording medium 111 include a flexible disk, a CD-ROM (Compact Disc Read Only Memory), an MO (Magneto Optical) disk, a DVD (Digital Versatile Disc), a magnetic disk, and a semiconductor memory.

[0109] The program can be installed into the computer from the removable recording medium 111 as described above, or can be downloaded to the computer via a communication network or a broadcasting network and installed on the built-in hard disk 105. That is, the program can be transferred to the computer wirelessly from a download site via an artificial satellite for digital satellite broadcasting, or transferred to the computer by wire via a network such as a LAN (Local Area Network) or the Internet.

[0110] The computer includes a CPU (Central Processing Unit) 102 , to which an input / output interface 110 is connected via a bus 101 .

[0111] When a user inputs a command via the input / output interface 110 by operating the input unit 107, the CPU 102 executes a program stored in a read-only memory (ROM) 103 in accordance with the command. Alternatively, the CPU 102 loads a program stored on a hard disk 105 into a random access memory (RAM) 104 and executes the program.

[0112] As a result, the CPU 102 performs processing according to the flowchart described above or processing performed by the configuration of the block diagram described above. Then, the CPU 102 outputs the processing results from the output unit 106 via the input / output interface 110, transmits them from the communication unit 108, or records them on the hard disk 105, as necessary.

[0113] The input unit 107 is made up of a keyboard, a mouse, a microphone, etc. The output unit 106 is made up of an LCD (Liquid Crystal Display), a speaker, etc.

[0114] In this specification, the processing performed by a computer according to a program does not necessarily have to be performed in chronological order according to the order described in the flowchart. In other words, the processing performed by a computer according to a program also includes processing that is executed in parallel or individually (for example, parallel processing or object-based processing).

[0115] The program may be processed by a single computer (processor), or may be distributed among multiple computers. Furthermore, the program may be transferred to and executed on a remote computer.

[0116] Furthermore, 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.

[0117] Also, for example, a configuration described as one device (or processing unit) may be divided and configured as multiple devices (or processing units). Conversely, configurations described above as multiple devices (or processing units) may be combined and configured as one device (or processing unit). Of course, configurations other than those described above may be added to the configuration of each device (or each processing unit). Furthermore, as long as the configuration and operation of the entire system are substantially the same, part of the configuration of one device (or processing unit) may be included in the configuration of another device (or other processing unit).

[0118] Furthermore, for example, the present technology can be configured as a cloud computing system in which a single function is shared and processed collaboratively by a plurality of devices via a network.

[0119] Furthermore, for example, the above-described program can be executed in any device, as long as the device has the necessary functions (functional blocks, etc.) and can obtain the necessary information.

[0120] Also, for example, each step described in the above flowchart can be executed by one device or can be shared and executed by multiple devices. Furthermore, if 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. In other words, multiple processes included in one step can be executed as multiple step processes. Conversely, processes described as multiple steps can be executed collectively as a single step.

[0121] In addition, the processing of the steps of a program executed by a computer may be executed in chronological order according to the order described in this specification, or may be executed in parallel or individually at the required timing, such as when a call is made. In other words, as long as no contradiction occurs, the processing of each step may be executed in an order different from the order described above. Furthermore, the processing of the steps of this program may be executed in parallel with the processing of another program, or may be executed in combination with the processing of another program.

[0122] It should be noted that the present technologies described in this specification can be implemented independently and singly, unless a contradiction arises. Of course, any two or more of the present technologies can also be implemented in combination. For example, part or all of the present technologies described in any embodiment can be implemented in combination with part or all of the present technologies described in other embodiments. Furthermore, part or all of any of the present technologies described above can also be implemented in combination with other technologies not described above.

[0123] <Examples of Combinations of Configurations> The present technology can also be configured as follows. (1) An information processing method including: an information processing device estimating a self-position of an autonomous mobile body that moves autonomously in a traveling environment based on detection data detected by an external sensor provided on the autonomous mobile body; calculating a score indicating the ease of estimating the self-position of the autonomous mobile body at a predetermined measurement point in the traveling environment; and presenting an improvement proposal to improve the ease of estimating the self-position of the autonomous mobile body based on the score. (2) The information processing method described in (1) above, in which the detection data includes a point cloud detected by a sensor that measures distances from the measurement point to surrounding objects, and the score is calculated based on the direction and number of clusters obtained by performing normal estimation on the point cloud and performing clustering processing on a mapping as a normal vector. (3) The information processing method described in (2) above, in which, at the measurement point where the score is less than a threshold, the improvement proposal is presented to install a predetermined landmark within an area within a measurement range of the sensor in a direction from the measurement point where a directional score obtained for each predetermined direction is less than a threshold. (4) The information processing method according to (3) above, wherein the landmark is a retroreflective material having a reflectivity different from that of objects in the traveling environment. (5) The information processing method according to (3) above, wherein the landmark is a marker recognized by any sensor. (6) The information processing method according to (3) above, wherein the landmark is a pattern projected by an illumination device. (7) The information processing method according to any of (3) to (6) above, wherein the improvement proposal is presented by being displayed on a display unit of a user terminal. (8) The information processing method according to any of (3) to (6) above, wherein the improvement proposal is presented by being superimposed on an image of the real world using AR (Augmented Reality) technology. (9) The information processing method according to any of (3) to (6) above, wherein the improvement proposal is projected using a light source mounted on the autonomous moving body.(10) The information processing method according to any one of (3) to (9) above, wherein the improvement proposal is presented to encourage the installation of a new landmark when the autonomous mobile body creates a map of the traveling environment while estimating its current position. (11) The information processing method according to (10) above, wherein the map of the traveling environment is created based on detection data detected by the external sensor, with the self-position of the autonomous mobile body set as a measurement point. (12) The information processing method according to (11) above, wherein the improvement proposal is presented on a local map being created in real time. (13) The information processing method according to any one of (3) to (12) above, wherein the improvement proposal is presented to encourage the movement of the landmark when the score has decreased due to changes in the traveling environment since the map was created when the autonomous mobile body travels in the traveling environment using a created map. (14) The information processing method according to any one of (2) to (13) above, wherein an improvement to the score is proposed after the autonomous mobile body creates a map of the traveling environment while estimating its current position. (15) The information processing method according to any of (2) to (14) above, which proposes an improvement to the score by performing a simulation on a map created by a conventional creation method. (16) The information processing method according to any of (2) to (15) above, which recognizes obstacles in the traveling environment based on detection data detected by the external sensor, and creates an action plan for traveling while avoiding the obstacle. (17) An information processing device comprising: an estimation unit that estimates a self-position of an autonomous mobile body that moves autonomously in a traveling environment based on detection data detected by an external sensor provided on the autonomous mobile body, a calculation unit that calculates a score indicating ease of estimating the self-position of the autonomous mobile body at a predetermined measurement point in the traveling environment, and an improvement suggestion unit that presents an improvement suggestion for improving the ease of estimating the self-position of the autonomous mobile body based on the score.(18) A program for causing a computer of an information processing device to execute information processing including: estimating the self-position of an autonomous mobile body based on detection data detected by an external sensor provided on the autonomous mobile body that moves autonomously in a driving environment; calculating a score indicating the ease of estimating the self-position of the autonomous mobile body at a predetermined measurement point in the driving environment; and presenting an improvement proposal for improving the ease of estimating the self-position of the autonomous mobile body based on the score.

[0124] It should be noted that the present embodiment is not limited to the above-described embodiment, and various modifications are possible within the scope of the gist of the present disclosure. Furthermore, the effects described in this specification are merely examples and are not intended to be limiting, and other effects may also be obtained.

[0125] DESCRIPTION OF SYMBOLS 11 Autonomous mobile robot, 12 User terminal, 21 External sensor, 22 Internal sensor, 23 Driving unit, 24 Travel control device, 31 Obstacle recognition unit, 32 Normal vector mapping unit, 33 Action planning unit, 34 Map creation unit, 35 Self-position estimation processing unit, 41 Score calculation unit, 42 Determination unit, 43 Improvement proposal unit, 44 Simulation unit

Claims

1. An information processing method including: an information processing device estimating the self-position of an autonomous mobile body that moves autonomously in a driving environment based on detection data detected by an external sensor provided on the autonomous mobile body; calculating a score indicating the ease of estimating the self-position of the autonomous mobile body at a predetermined measurement point in the driving environment; and presenting an improvement proposal to improve the ease of estimating the self-position of the autonomous mobile body based on the score.

2. The information processing method according to claim 1, wherein the detection data includes a point cloud detected by a sensor that measures the distance from the measurement point to surrounding objects, and the score is calculated based on the direction and number of clusters obtained by performing normal estimation on the point cloud and performing clustering processing on the mapping as a normal vector.

3. The information processing method of claim 2, wherein the improvement proposal is to install a specified landmark within an area within the measurement range of the sensor, in a direction from the measurement point where the directional score obtained for each specified direction is less than the threshold, at the measurement point where the score is less than the threshold.

4. The information processing method according to claim 3, wherein the landmark is a retroreflective material having a reflectance different from that of objects in the driving environment.

5. The information processing method according to claim 3, wherein the landmark is a marker that can be recognized by any sensor.

6. The information processing method according to claim 3, wherein the landmark is a pattern projected by an illumination device.

7. The information processing method according to claim 3, wherein the improvement proposal is presented by displaying it on a display unit of a user terminal.

8. The information processing method according to claim 3, wherein the improvement proposal is presented by superimposing it on an image of the real world using AR (Augmented Reality) technology.

9. The information processing method according to claim 3, wherein the improvement proposal is projected using a light source mounted on the autonomous moving body.

10. The information processing method according to claim 3, wherein the autonomous moving body presents the improvement proposal that encourages the installation of a new landmark when creating a map of the driving environment while estimating its current position.

11. The information processing method according to claim 10, wherein a map of the traveling environment is created based on detection data detected by the external sensor, with the self-position of the autonomous moving body being used as a measurement point.

12. The information processing method according to claim 11, wherein the improvement proposal is presented on a local map that is being created in real time.

13. The information processing method according to claim 3, wherein when the autonomous mobile body travels in the driving environment using a created map, if the score has decreased due to changes in the driving environment since the map was created, the improvement suggestion that encourages moving the landmark is presented.

14. The information processing method according to claim 2, wherein the autonomous moving body creates a map of the driving environment while estimating its current position, and then proposes improvements to the score.

15. The information processing method according to claim 2, wherein improvements to the score are suggested by performing a simulation on a map created using a conventional creation method.

16. The information processing method according to claim 2, further comprising: recognizing obstacles in the driving environment based on detection data detected by the external sensor; and creating an action plan for driving while avoiding the obstacles.

17. An information processing device comprising: an estimation unit that estimates the self-position of an autonomous mobile body that moves autonomously in a driving environment based on detection data detected by an external sensor provided on the autonomous mobile body; a calculation unit that calculates a score indicating the ease of estimating the self-position of the autonomous mobile body at a predetermined measurement point in the driving environment; and an improvement suggestion unit that presents improvement suggestions for improving the ease of estimating the self-position of the autonomous mobile body based on the score.

18. A program for causing a computer of an information processing device to execute information processing including: estimating the self-position of an autonomous mobile body based on detection data detected by an external sensor attached to the autonomous mobile body that moves autonomously in a driving environment; calculating a score indicating the ease of estimating the self-position of the autonomous mobile body at a predetermined measurement point in the driving environment; and presenting improvement suggestions for improving the ease of estimating the self-position of the autonomous mobile body based on the score.

Images