Control device, control method, and storage medium

Abstract

The present invention provides a control device, a control method, and a storage medium capable of appropriately generating a path of a moving body on the basis of the characteristic of what kind of movement a pedestrian has in the future. A control device that at least temporarily controls a moving body that autonomously moves in a region where a pedestrian walks, the control device being provided with: a recognition unit that time-series recognizes the position of the pedestrian; a calculation unit that calculates an index value indicating the degree of coordination for each pedestrian on the basis of the recognition result of the recognition unit; a setting unit that sets a risk area around the pedestrian, and sets the risk area to be larger as the index value is smaller; and a generation unit that generates a path through which the moving body should advance in the future so as to avoid the risk region.

Description

Technical Field

[0001] The invention relates to a control device, a control method and a storage medium. Background Art

[0002] In recent years, research and practical application have been advanced on mobile bodies that can move in the same space as pedestrians. Such mobile bodies move autonomously by creating a path so as not to get too close to obstacles such as pedestrians. In connection with this, an invention of a device for detecting pedestrians' reactions caused by the approach of a mobile body and expanding or reducing a no-entry area (personal space) according to the detected pedestrians' reactions has been disclosed (Japanese Patent Application Publication No. 2009-157735). Summary of the invention

[0003] Problems to be solved by the invention

[0004] In the conventional technology, the personal space is expanded when the pedestrian performs a predetermined reaction that is quantified in advance, such as stopping or moving the upper body violently. However, in such processing, there is a case where the path of the moving body cannot be appropriately generated based on the characteristics of the pedestrian's future movement.

[0005] The present invention has been made in consideration of such circumstances, and one of its objects is to provide a control device, a control method, and a storage medium that can appropriately generate a path for a moving object based on the characteristics of how a pedestrian will move in the future.

[0006] Solutions to Solve Problems

[0007] The control device, control method, and storage medium of the present invention adopt the following structures.

[0008] (1): A control device according to one embodiment of the present invention at least temporarily controls a moving body that moves autonomously in an area where pedestrians walk, wherein the control device comprises: an identification unit that identifies the positions of pedestrians in a time series; a calculation unit that calculates an index value representing the degree of coordination of each of the pedestrians based on the identification result of the identification unit; a setting unit that sets a risk area around the pedestrian, and the smaller the index value, the larger the risk area is set; and a generation unit that generates a path that the moving body should move along in the future in a manner that avoids the risk area.

[0009] (2): Based on the scheme of (1) above, the calculation unit repeatedly performs the process of predicting the position of the pedestrian at a second time point later than the first time point at a first time point in a time series and calculating the difference between the identified position of the pedestrian and the predicted position of the pedestrian at the second time point, and the larger the value obtained by summing up the differences, the larger the index value.

[0010] (3): A control device according to another embodiment of the present invention at least temporarily controls a moving body that moves autonomously in an area where pedestrians are walking, wherein the control device comprises: an identification unit that identifies the positions of pedestrians in a time series; a calculation unit that calculates an index value for each of the pedestrians based on the identification result of the identification unit; a setting unit that sets a risk area around the pedestrian, and the risk area is set to be larger as the index value is lower; and a generation unit that generates a path that the moving body should move along in the future in a manner that avoids the risk area, wherein the calculation unit repeatedly performs a process of predicting the position of the pedestrian at a second time point later than the first time point at a first time point and calculating the difference between the position of the identified pedestrian and the predicted position of the pedestrian at the second time point in a time series, and the larger the value obtained by summing up the differences, the larger the index value is calculated.

[0011] (4): In any one of the above (1) to (3), the calculation unit calculates the index value by focusing on a pedestrian who is in a crossing relationship with the moving object or another pedestrian.

[0012] (5): In the above aspect (4), the setting unit sets the risk area using a value near an upper limit of a range that the index value can take, instead of the index value, for pedestrians for whom the index value is not calculated.

[0013] (6): The control method of another scheme of the present invention causes the control device of the mobile body that at least temporarily controls the mobile body that moves autonomously in the pedestrian walking area to perform the following processing: identifying the positions of pedestrians in a time series; calculating an index value representing the degree of coordination of each of the pedestrians based on the result of the identification; setting a risk area around the pedestrian, and the smaller the index value, the larger the risk area is set; and generating a path that the mobile body should move in the future in a manner that avoids the risk area.

[0014] (7): The control method of another scheme of the present invention causes a control device for a mobile body that at least temporarily controls a mobile body that moves autonomously in an area where pedestrians are walking to perform the following processing: identifying the positions of pedestrians in a time series; calculating an index value for each of the pedestrians based on the results of the identification; setting a risk area around the pedestrian, and the risk area is set larger as the index value is lower; and generating a path that the mobile body should move forward in the future in a manner that avoids the risk area, the calculated processing including the following processing: repeatedly performing, in a time series, a process of predicting the position of the pedestrian at a second time point that is later than the first time point at a first time point and calculating the difference between the position of the identified pedestrian and the predicted position of the pedestrian at the second time point, and the larger the value obtained by summing up the differences, the larger the index value is calculated.

[0015] (8): In a storage medium storing a program in another embodiment of the present invention, the program causes a processor of a control device for controlling a moving body that moves autonomously in an area where pedestrians walk, at least temporarily, to perform the following processing: identifying the positions of pedestrians in a time series; calculating an index value representing the degree of coordination of each of the pedestrians based on the results of the identification; setting a risk area around the pedestrians, and setting the risk area larger as the index value is smaller; and generating a path that the moving body should move forward in the future in a manner that avoids the risk area.

[0016] (9): In a storage medium storing a program according to another embodiment of the present invention, the program causes a processor of a control device for controlling a mobile body that autonomously moves in an area where pedestrians are walking to perform the following processing: identifying the positions of pedestrians in a time series; calculating an index value for each of the pedestrians based on the results of the identification; setting a risk area around the pedestrian, and setting the risk area larger as the index value is lower; and generating a path that the mobile body should move in the future in a manner that avoids the risk area. The calculation processing includes the following processing: repeatedly performing, in a time series, a process of predicting the position of the pedestrian at a second time point later than the first time point at a first time point and calculating a difference between the position of the identified pedestrian and the predicted position of the pedestrian at the second time point, and the larger the value obtained by summing up the differences, the larger the index value is calculated.

[0017] Effects of the Invention

[0018] According to the above-mentioned aspects (1) to (9), it is possible to appropriately generate a path of a moving object based on the characteristics of how a pedestrian will move in the future. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 1 is a diagram showing a configuration of a moving object 1 on which a control device 100 is mounted.

[0020] Figure 2 1 is a diagram showing an example of the configuration of the control device 100 .

[0021] Figure 3 This is a diagram showing an overview of the risks set by the setting unit 130 .

[0022] Figure 4 This is a diagram showing an example of the distribution of risks set in consideration of deviation from the ideal path IP.

[0023] Figure 5The diagram compares the behavior assumed for a pedestrian P1 with high coordination in a passing traffic scene with a moving object 1 and the behavior assumed for a pedestrian P2 with low coordination in a passing traffic scene with a moving object 1 .

[0024] Figure 6 This is a diagram for explaining the content of the processing performed by the calculation unit 120.

[0025] Figure 7 It shows Figure 5 The diagram shown is an example of a case where the risk area set based on the above-mentioned principle is applied to pedestrians P1 and P2.

[0026] Figure 8 This is a diagram for explaining pedestrians in a crossing relationship with the moving object 1. DETAILED DESCRIPTION

[0027] Hereinafter, embodiments of the control device, control method, and storage medium of the present invention will be described with reference to the accompanying drawings. The control device of the present invention is a control device that controls a driving device of a moving body to move the moving body. The moving body in the present invention refers to a moving body that moves autonomously in an area where pedestrians walk. An area where pedestrians walk refers to sidewalks, open spaces, floors in buildings, etc., and may also include driveways. In the following description, it is assumed that there are no passengers on the moving body, but it is also possible for passengers to be on the moving body.

[0028] The mobile body leads the way for a leading person, or follows a following person, or moves toward a destination alone. The leading person and the following person may be, for example, a pedestrian, but may also be a robot or an animal. In the case of following a following person, for example, the location around the following person is treated as the destination. The following description also includes the movement of the mobile body toward the destination including the following person. It should be noted that such an action may not be performed all the time, but may be performed temporarily. For example, when the mobile body is in a specified state, the control device of the mobile body may temporarily perform an action by executing the algorithm of the present invention.

[0029] Figure 1 1 is a diagram showing a structure of a mobile body 1 equipped with a control device 100. The mobile body 1 includes, for example, a main body 5 equipped with an HMI 10, a detection device 20, a position determination device 30, and the control device 100, a moving mechanism 40 mounted on the main body 5, and a sensor 50 mounted on the moving mechanism 40.

[0030] HMI 10 presents various information to pedestrians and accepts input operations from users. HMI 10 includes various display devices, speakers, buzzers, touch panels, switches, buttons, etc. For example, HMI 10 accepts input of a destination (a predetermined place, oneself, etc.) from a user.

[0031] The detection device 20 is a device that generates data for identifying objects and pedestrians that exist around the moving body 1. The detection device 20 includes, for example, sensors such as cameras, radar devices, LIDAR (Light Detection and Ranging), and ultrasonic sensors that use the surroundings of the moving body 1 as a detection range, and an object recognition device that performs sensor fusion processing based on the outputs of these sensors to identify objects.

[0032] The position determination device 30 is a device for determining the position of the mobile body 1. The position determination device 30 includes, for example, a GNSS (Global Navigation Satellite System) receiver for determining the position of the vehicle M based on signals received from GNSS satellites. The position determination device 30 may also determine or supplement the position of the mobile body 1 by using an INS (Inertial Navigation System) output of a sensor 50 described later. In addition, the position determination device 30 may also have an electromagnetic wave receiving function, and determine or supplement the position of the mobile body 1 based on the intensity of electromagnetic waves coming from a surrounding electromagnetic wave transmission source (whose position is known).

[0033] The moving mechanism 40 is a mechanism for moving the moving body 1 including the main body 5 in any direction. The moving mechanism 40 includes, for example, a plurality of wheels, a drive motor mounted on one or more wheels, and a steering device mounted on one or more wheels. There are no particular restrictions on the structure of the moving mechanism 40, and the moving mechanism 40 may also include a foot for simulating bipedal walking.

[0034] The sensor 50 is a sensor for detecting the behavior of the mobile body 1. The sensor 50 includes, for example, a wheel speed sensor for detecting the speed of a wheel, an acceleration sensor for detecting the acceleration acting on the mobile body 1, a yaw rate sensor installed near the center of gravity in the horizontal direction of the main body 5, a steering angle sensor for detecting the steering angle of a steering wheel (steering wheel), and an azimuth sensor for detecting the orientation of the mobile body 1 in the horizontal direction.

[0035] Figure 21 is a diagram showing an example of the structure of the control device 100. The control device 100, for example, includes a recognition unit 110, a calculation unit 120, a setting unit 130, a generation unit 140, and a movement control unit 150. These components are implemented by executing a program (software) by a hardware processor such as a CPU (Central Processing Unit). Some or all of these components can be implemented by hardware (including circuitry) such as LSI (Large Scale Integration), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array), GPU (Graphics Processing Unit), etc., or can be implemented by the cooperation of software and hardware. The program can be pre-stored in a storage device such as an HDD (Hard Disk Drive) or a flash memory (a storage device having a non-temporary storage medium), or can be stored in a removable storage medium such as a DVD or CD-ROM (a non-temporary storage medium), and installed in the storage device by assembling the storage medium in a drive device. It should be noted that the control device 100 may store map information including at least a local map of a location where the moving body 1 is operating in the storage unit.

[0036] The processing of the recognition unit 110, the calculation unit 120, the setting unit 130, the generation unit 140, and the movement control unit 150 described below is repeatedly executed in each control cycle that arrives at a predetermined period (executed in a time series). Therefore, before the moving body 1 reaches the destination, it does not move along the path generated at a certain point in time, but updates the path to a new path according to changes in the surrounding environment, so the control content of the moving body 1 is updated based on the updated latest path.

[0037] The recognition unit 110 recognizes objects existing around the moving body 1 based on information input from the detection device 20. The objects include pedestrians including the leading person and the following person when there are leading persons and the following person, and also include static obstacles. The recognition unit 110 recognizes the state of the object, such as the position, speed, and acceleration. The position of the object is recognized as a relative position observed from the moving body 1, for example, and is converted into a position on an imaginary plane S represented by a two-dimensional plane obtained by observing the space around the moving body 1 from above, and is used for subsequent processing. In the following description, a position refers to a point.

[0038] The calculation unit 120 calculates the index value α for each pedestrian based on the recognition result of the recognition unit 110. The index value α indicates the degree of coordination of the pedestrian. This will be described later.

[0039] The setting unit 130 sets the risk as an index value indicating the degree to which the mobile body 1 should not enter or approach in the aforementioned assumed plane S. For the risk, the larger the value, the less the mobile body 1 should enter or approach, and the closer the value is to zero, the more preferred it is for the mobile body 1 to pass. However, the relationship may be reversed. In the case where the mobile body 1 is able to fly by riding on a flying object, the setting unit 130 may perform the same processing in a three-dimensional space instead of in the assumed plane S. An area in which the risk associated with an object is summarized as one and is not zero is an example of a "risk area".

[0040] The setting unit 130 sets the risk in the hypothetical plane S not only for the current time point but also for each future time point specified at a constant time interval in the manner of current time point t, Δt later (time t+Δt), 2Δt later (time t+2Δt), ... The setting unit 130 predicts the risk at each future time point based on the change in the position of the mobile object target continuously recognized by the recognition unit 110.

[0041] Figure 3 : is a diagram showing an overview of the risks set by the setting unit 130. The setting unit 130 sets the risks based on the travel direction and speed of objects other than the moving body 1 on the imaginary plane S with ellipses or circles as contour lines, and sets the risks of a constant value for the immovable area BD such as a wall. In the figure, DM is the travel direction of the moving body 1. R(OB1) is the risk of the stationary object (a person standing still) OB1, R(OB2) is the risk of the moving object (pedestrian) OB2, R(OB3) is the risk of the moving object (pedestrian) OB3, and R(OB4) is the risk of the moving object (pedestrian) OB4. Pedestrians continue to move, so the risks are set at different positions from the current time for each future time point. R(OB2)_t is the risk of the object OB2 in a certain control cycle, R(OB2)_t+Δt is the risk of the object OB2 in the next control cycle, and R(OB2)_t+Δ2t is the risk of the object OB2 in the next control cycle. R(BD) is the risk of the immovable area BD. In the figure, the density of the hatching indicates the value of the risk, and the darker the hatching, the greater the risk.

[0042] The setting unit 130 may set an ideal path connecting the moving body 1 to the destination of the moving body 1 , and may add a greater risk as the distance from the ideal path increases. Figure 4 is a diagram showing an example of the distribution of risks set in consideration of deviations from the ideal path IP. In the figure, R(K) is the risk based on the deviation from the ideal path IP. Figure 4In the example of FIG. 1 , the ideal path IP is set to a straight line, but depending on the structure of the place where the moving body 1 moves, the ideal path IP may be set to a broken line or a curved line at a corner where the moving body 1 turns. In this case, the setting unit 130 (or other components) generates the ideal path IP by, for example, dividing the moving range into sections and determining a detailed position for each section.

[0043] The generation unit 140 generates a path that the mobile body 1 should travel in the future, based on the risk based on the recognition result of the recognition unit 110, by passing through a part with a lower risk (in other words, by avoiding the risk area). For example, the generation unit 140 generates a path by sequentially connecting the positions corresponding to each time point in the future where the risk is not above a threshold. There is not necessarily one path that satisfies this condition, and there may be a situation where multiple path candidates are generated. The generation unit 140 may also calculate scores for each of the multiple path candidates and select the path candidate with the highest score as the path. For example, the generation unit 140 calculates the score in such a way that the smaller the degree of rotation (e.g., evaluated by the angle between the vector from the past track point to the object track point and the vector from the object track point to the future track point) and the smaller the total risk of each passed point, the higher the score.

[0044] The movement control unit 150 controls the movement mechanism 40 so that the moving body 1 moves along the path. The movement control unit 150 controls the drive motor and the steering device so that the position and behavior of the moving body 1 obtained by the output of the sensor 50 approach the path.

[0045] [Indicator value and setting of risk area based on the indicator value]

[0046] The relationship between the index value α and the risk area is described below. The calculation unit 120 repeatedly performs the process of predicting the position of the pedestrian at a second time point later than the first time point in a time series and calculating the difference between the position of the identified pedestrian at the second time point and the position of the pedestrian predicted at the first time point, and the greater the value obtained by summing up the differences, the greater the index value α is calculated. The index value α indicates the degree and frequency of the pedestrian changing the route, and therefore indicates the degree of change of the route by observing the moving body 1 or other pedestrians, that is, the coordination. Figure 5 This is a diagram comparing the behavior (route R1) assumed for a pedestrian P1 with high coordination (large index value α) in a cross-traffic scenario with a moving object 1 and the behavior (route R2) assumed for a pedestrian P2 with low coordination (small index value α) in a cross-traffic scenario with a moving object 1. As shown in the figure, it is assumed that a pedestrian with high coordination changes the route early and avoids approaching the moving object 1, while a pedestrian with low coordination changes the route after extremely approaching the moving object 1.

[0047] In addition, the index value α is not limited to the case where the pedestrian changes the route by observing the moving body 1, and can also be calculated in the same manner for the case where the pedestrian changes the route by observing other pedestrians. Even when the pedestrian is far away from the moving body 1, the index value α can be calculated based on the degree to which the pedestrian changes the route by observing other pedestrians. In this way, the index value α can be calculated for a wider range of pedestrians.

[0048] Figure 6 This is a diagram for explaining the content of the processing performed by the calculation unit 120. In the figure, t, t-1, t-2, ... represent control timings (hereinafter referred to as moments) that arrive at predetermined time intervals, Lp(t) represents the position of the pedestrian at moment t, and #Lp(t) represents the position of the pedestrian at moment t predicted at time t-1. The calculation unit 120 predicts the position of the pedestrian at a subsequent control timing (or after a predetermined moment) at each control timing that arrives at a predetermined time interval. The calculation unit 120, for example, assumes that the state is a constant speed or a constant acceleration, and predicts the position of the pedestrian by extending the movement vector between a previous moment and the current moment. Furthermore, the calculation unit 120 calculates the index value α, for example, based on formula (1). In the formula, q is the number of steps back when the differences are totaled.

[0049]

[0050] The setting unit 130 sets the risk area by reflecting the index value α. In the following, the setting unit 130 sets the risk area to be a circle, but the risk area is also set based on the same principle when it is set to be an ellipse or other shapes. For example, the setting unit 130 determines the radius r of the risk area based on formula (2). In the formula, D is the distance between the moving object and the pedestrian, V is the speed of the pedestrian, and α is the index value. The function f is a function that returns a smaller value as D increases, a larger value as V increases, and a smaller value as α increases.

[0051]

[0052] Figure 7 It shows Figure 5The figure shows an example of the situation where the risk area set by the above-mentioned principle is applied to pedestrians P1 and P2. In this figure, it is assumed that the speeds of pedestrians P1 and P2 are the same. In the figure, Path1 (1) and Path1 (2) are the paths of the moving body 1 generated in their respective cases. As shown in the figure, the risk area Rp1 corresponding to pedestrian P1 and the risk area Rp2 corresponding to pedestrian P2 both become larger as the moving body 1 approaches, but the risk area Rp2 is set larger than the risk area Rp1 from an early stage and is stably set larger thereafter. According to the processing characteristics of the aforementioned generation unit 140, the path of the moving body 1 is set in a manner to largely avoid the pedestrian P2, so that the avoidance trajectory can be obtained earlier for the pedestrian with a small index value α with a relatively high contact possibility.

[0053] As described above, according to the embodiment, it is possible to appropriately generate a path of a moving object based on the characteristics of how a pedestrian will move in the future.

[0054] It should be noted that the calculation unit 120 may perform the above-described process of calculating the index value α only for pedestrians who are in a crossing relationship with the moving object 1 or other pedestrians. Figure 8 This is a diagram for explaining pedestrians in a staggered traffic relationship with the moving body 1. As shown in the figure, the calculation unit 120 may set the monitoring area WA with the traveling direction DM of the moving body 1 as the center, lock the pedestrians in the monitoring area and the angle θ formed by the moving vector P of the pedestrian relative to the straight line connecting the pedestrian and the moving body 1 is within a specified range, and calculate the index value α, and do not calculate the index value α for other pedestrians. In this case, the pedestrians excluded from the lock are pedestrians with low importance in the path generation of the moving body 1, so the radius r of the risk area can be determined by using a value near the upper limit of the range that the index value α can take instead of the index value α. Pedestrians in a staggered traffic relationship with other pedestrians can also be extracted by the same method.

[0055] The above-described embodiment can be expressed as follows.

[0056] A control device for at least temporarily controlling a moving body that moves autonomously in an area where pedestrians walk, wherein:

[0057] The control device comprises:

[0058] one or more storage media storing computer-readable instructions; and

[0059] a processor connected to the one or more storage media,

[0060] The processor executes the computer-readable instructions to perform the following processing:

[0061] Identify the location of pedestrians according to the time series,

[0062] Calculating an index value indicating the degree of coordination of each of the pedestrians based on the recognition result;

[0063] A risk area is set around the pedestrian so that the risk area is larger as the index value is smaller.

[0064] A path that the moving object should travel in the future is generated in a manner that avoids the risk area.

[0065] Furthermore, the above-described embodiment can also be expressed as follows.

[0066] A control device for at least temporarily controlling a moving body that moves autonomously in an area where pedestrians walk, wherein:

[0067] The control device comprises:

[0068] one or more storage media storing computer-readable instructions; and

[0069] a processor connected to the one or more storage media,

[0070] The processor executes the computer-readable instructions to perform the following processing:

[0071] Identify the location of pedestrians according to the time series,

[0072] Calculate the index value of each pedestrian based on the recognition result,

[0073] The risk area is set larger around the pedestrian so that the risk area is larger as the index value is lower.

[0074] Generate a path that the moving body should travel in the future in a way that avoids the risk area,

[0075] The calculated processing includes the following processing: repeatedly executing the processing of predicting the position of the pedestrian at a second time point later than the first time point at a first time point in a time series and calculating the difference between the identified position of the pedestrian and the predicted position of the pedestrian at the second time point, and the larger the value obtained by summing up the differences, the larger the calculated index value will be.

[0076] Although specific embodiments of the present invention have been described above using the embodiments, the present invention is not limited to such embodiments at all, and various modifications and substitutions can be made without departing from the gist of the present invention.

Claims

1. A control device for at least temporarily controlling a moving body that moves autonomously in an area where pedestrians walk, wherein: The control device comprises: an identification unit for identifying the position of a pedestrian in a time series; a calculation unit that calculates an index value indicating a coordination degree of each of the pedestrians based on the recognition result of the recognition unit; a setting unit configured to set a risk area around the pedestrian, and to set the risk area larger as the index value is smaller; as well as A generating unit generates a path that the moving body should travel in the future so as to avoid the risk area.

2. The control device according to claim 1, wherein: The calculation unit repeatedly performs the process of predicting the position of the pedestrian at a second time point later than the first time point at a first time point and calculating the difference between the identified position of the pedestrian and the predicted position of the pedestrian at the second time point in a time series, and the larger the value obtained by summing up the differences, the larger the index value.

3. A control device for at least temporarily controlling a moving body that moves autonomously in an area where pedestrians walk, wherein: The control device comprises: an identification unit for identifying the position of a pedestrian in a time series; a calculation unit that calculates an index value for each of the pedestrians based on the recognition result of the recognition unit; a setting unit configured to set a risk area around the pedestrian, and to set the risk area larger as the index value is lower; as well as a generating unit for generating a path that the moving body should travel in the future in a manner that avoids the risk area, The calculation unit repeatedly performs the process of predicting the position of the pedestrian at a second time point later than the first time point at a first time point and calculating the difference between the identified position of the pedestrian and the predicted position of the pedestrian at the second time point in a time series, and the larger the value obtained by summing up the differences, the larger the calculated index value will be.

4. The control device according to any one of claims 1 to 3, wherein: The calculation unit calculates the index value by focusing on a pedestrian who is in a crossing relationship with the moving object or other pedestrians.

5. The control device according to claim 4, wherein: The setting unit sets the risk area using a value near an upper limit value of a range that the index value can take, instead of the index value, for a pedestrian for whom the index value is not calculated.

6. A control method, wherein: The control method causes a control device that at least temporarily controls a moving body that moves autonomously in an area where pedestrians are walking to perform the following processing: Identify the location of pedestrians in time series; Calculating an index value representing the degree of coordination of each of the pedestrians based on the recognition result; Setting a risk area around the pedestrian, and setting the risk area larger as the index value is smaller; as well as A path that the moving object should travel in the future is generated in a manner that avoids the risk area.

7. A control method, wherein: The control method causes a control device that at least temporarily controls a moving body that moves autonomously in an area where pedestrians are walking to perform the following processing: Identify the location of pedestrians in time series; Calculating an index value of each of the pedestrians based on the recognition result; Setting a risk area around the pedestrian, and setting the risk area larger as the index value is lower; as well as Generate a path that the moving body should travel in the future in a way that avoids the risk area, The calculated processing includes the following processing: repeatedly executing the processing of predicting the position of the pedestrian at a second time point later than the first time point at a first time point in a time series and calculating the difference between the identified position of the pedestrian and the predicted position of the pedestrian at the second time point, and the larger the value obtained by summing up the differences, the larger the calculated index value will be.

8. A storage medium storing a program, wherein: The program is for causing a processor of a control device for controlling a moving body that autonomously moves in an area where pedestrians walk, at least temporarily, to execute the following processing: Identify the location of pedestrians in time series; Calculating an index value representing the degree of coordination of each of the pedestrians based on the recognition result; Setting a risk area around the pedestrian, and setting the risk area larger as the index value is smaller; as well as A path that the moving object should travel in the future is generated in a manner that avoids the risk area.

9. A storage medium storing a program, wherein: The program is for causing a processor of a control device for controlling a moving body that autonomously moves in an area where pedestrians walk, at least temporarily, to execute the following processing: Identify the location of pedestrians in time series; Calculating an index value of each of the pedestrians based on the recognition result; Setting a risk area around the pedestrian, and setting the risk area larger as the index value is lower; as well as Generate a path that the moving body should travel in the future in a way that avoids the risk area, The calculated processing includes the following processing: repeatedly executing the processing of predicting the position of the pedestrian at a second time point later than the first time point at a first time point in a time series and calculating the difference between the identified position of the pedestrian and the predicted position of the pedestrian at the second time point, and the larger the value obtained by summing up the differences, the larger the calculated index value will be.

Images