Control device, control method, and program
Patent Information
- Application Number
- JP2024565563
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Filing Date
- 2025-06-20
- Publication Date
- 2025-08-27
AI Technical Summary
Conventional technologies fail to appropriately generate routes for moving objects, such as robots or micromobility devices, in dynamic environments like pedestrian areas, where the number and orientation of pedestrians and the speed of the target object influence the optimal path.
A control device and method that includes a recognition unit to detect pedestrians and set arrival positions based on predetermined conditions, using a route generation unit to create paths that consider the number of pedestrians, orientation, and speed of the target, adjusting the route generation criteria dynamically to ensure safe and effective navigation.
Enables the generation of optimal routes for moving objects in various scenarios, ensuring safety by adapting to changes in pedestrian density and target object movement, thereby improving navigation and reducing the risk of collisions or separation from the target.
Smart Images

Figure 2024134901000001 
Figure 2024134901000002
Abstract
Description
Control device, control method, and program
[0001] The present invention relates to a control device, a control method, and a program.
[0002] In recent years, moving objects (called robots, micromobility, etc.) that move autonomously following a user for purposes such as transporting the user's luggage have been put into practical use. An invention of a driving control device related to micromobility has been disclosed (Patent Document 1).
[0003] Japanese Patent Application Laid-Open No. 2022-134583
[0004] Conventional techniques sometimes fail to generate an appropriate route depending on the situation in which the moving object is placed.
[0005] The present invention has been made in consideration of these circumstances, and one of its objectives is to provide a control device, a control method, and a program that are capable of generating an appropriate route depending on the situation in which a moving body is placed.
[0006] The control device, control method, and program according to the present invention employ the following configuration: (1): A control device according to one aspect of the present invention controls a mobile body that autonomously moves in an area where a pedestrian walks, following a target to be followed, and includes: a recognition unit that recognizes objects including the pedestrian and the target to be followed; a setting unit that sets a position that has a predetermined positional relationship with the target to be followed as a destination position of the mobile body; a path generation unit that generates a path from the location of the mobile body to the destination position; and a drive control unit that controls a drive unit attached to the mobile body so that the mobile body moves along the path, wherein the setting unit sets a plurality of the destination positions and provides them to the path generation unit if a first condition is satisfied, and sets a single destination position and provides it to the path generation unit if the first condition is not satisfied, and when a plurality of the destination positions are provided from the setting unit, the path generation unit generates the paths for at least some of the destination positions and selects one path based on a predetermined evaluation criterion.
[0007] (2) In the above aspect (1), the first condition is that the recognition unit has recognized a predetermined number of pedestrians within a predetermined area.
[0008] (3): In the above aspect (1), the recognition unit further recognizes the orientation of the target to be followed, and when the first condition is satisfied, the setting unit sets the plurality of arrival positions behind the target to be followed, aligned in a direction intersecting the orientation of the target to be followed.
[0009] (4): In the above aspect (1), the recognition unit further recognizes the speed of the object to be followed, and the setting unit sets the position of the object to be followed to the arrival position when the speed of the object to be followed is less than a predetermined speed.
[0010] (5): In the aspect (1) above, the recognition unit further recognizes the orientation of the target to be followed, and if the first condition is not satisfied and a second condition including a condition regarding the angle between the orientation of the target to be followed and the orientation of the moving body is not satisfied, the setting unit sets the candidate closest to the moving body as the destination position among multiple destination position candidates lined up behind the target to be followed in a direction intersecting the orientation of the target to be followed.
[0011] (6) In the aspect (5) above, the second condition includes that the angle formed between the orientation of the target and the orientation of the moving body is equal to or smaller than a reference angle.
[0012] (7): In the above aspect (6), the second condition further includes that, when the orientation of the moving body is defined as a first coordinate axis and the orientation perpendicular to the first coordinate axis is defined as a second coordinate axis, the distance between the target to be tracked and the moving body with respect to the first coordinate axis is less than a first reference distance, and the distance between the target to be tracked and the moving body with respect to the second coordinate axis is less than a second reference distance.
[0013] (8): In the aspect (5) above, when the first condition is not satisfied and the second condition is satisfied, the setting unit sets one of the arrival positions diagonally behind the target to be followed.
[0014] (9): In the aspect (5) above, when the second condition is satisfied, the setting unit changes the threshold value of the second condition to a value that makes the second condition more likely to be met, and maintains the changed threshold value until it is determined that the second condition is not satisfied using the changed threshold value.
[0015] (10): Another aspect of the present invention is a control method in which a control device controls a mobile body that moves autonomously in an area where a pedestrian walks, following a target to be followed, recognizes objects including the pedestrian and the target to be followed, sets a position that is in a predetermined positional relationship with the target to be followed as a destination position of the mobile body, generates a path from the position of the mobile body to the destination position, controls a drive unit attached to the mobile body so that the mobile body moves along the path, and, when setting the destination positions, sets multiple destination positions if a first condition is satisfied, or sets one destination position if the first condition is not satisfied, and, when generating the path, if multiple destination positions are set, generates the path for at least some of the multiple destination positions and selects one path based on a predetermined evaluation criterion.
[0016] (11): Another aspect of the present invention provides a program that causes a processor of a control device that controls a mobile body that moves autonomously in an area where a pedestrian walks, following a target to recognize objects including pedestrians and the target to be followed, sets a position that is in a predetermined positional relationship with the target to be followed as a destination position of the mobile body, generates a path from the position of the mobile body to the destination position, controls a drive unit attached to the mobile body so that the mobile body moves along the path, and, when setting the destination positions, sets multiple destination positions if a first condition is satisfied, or sets one destination position if the first condition is not satisfied, and, when generating the path, if multiple destination positions are set, generates the path for at least some of the multiple destination positions, and selects one path based on predetermined evaluation criteria.
[0017] (12): A control device according to another aspect of the present invention is a control device that controls a moving body that moves autonomously in an area where pedestrians walk, following a target to be followed, and includes a recognition unit that recognizes objects including pedestrians and the target to be followed, a setting unit that sets a position that is in a predetermined positional relationship with the target to be followed as the arrival position of the moving body, a path generation unit that generates a path from the position of the moving body to the arrival position, and a drive control unit that controls a drive unit attached to the moving body so that the moving body moves along the path, wherein the recognition unit further recognizes the orientation of the target to be followed, and when predetermined conditions including a condition regarding the angle between the orientation of the target to be followed and the orientation of the moving body are not satisfied, the setting unit sets the candidate for the arrival position that is closest to the moving body among multiple candidates for the arrival position lined up behind the target to be followed in a direction intersecting the orientation of the target to be followed as the arrival position.
[0018] (13): Another aspect of the present invention is a control method in which a control device controls a moving body that moves autonomously in an area where a pedestrian walks, following a target to be followed, recognizes objects including the pedestrian and the target to be followed, sets a position that is in a predetermined positional relationship with the target to be followed as a destination position of the moving body, generates a path from the position of the moving body to the destination position, controls a drive unit attached to the moving body so that the moving body moves along the path, and, during the recognition, further recognizes the orientation of the target to be followed, and, if, during the setting, predetermined conditions including a condition regarding the angle between the orientation of the target to be followed and the orientation of the moving body are not satisfied, sets, as the destination position, the candidate closest to the moving body out of multiple candidates for the destination position lined up behind the target to be followed in a direction intersecting the orientation of the target to be followed.
[0019] (14) A program according to another aspect of the present invention is a program for causing a processor of a control device that controls a moving body that moves autonomously by following a target to move in an area where a pedestrian walks to recognize objects including pedestrians and the target to be followed, set a position that is in a predetermined positional relationship with the target to be followed as a destination position of the moving body, generate a path from the position of the moving body to the destination position, control a drive unit attached to the moving body so that the moving body moves along the path, further recognize the orientation of the target to be followed during the recognition, and if predetermined conditions including a condition regarding the angle between the orientation of the target to be followed and the orientation of the moving body are not satisfied during the setting, set the candidate for the destination position that is closest to the moving body out of multiple candidates for the destination position lined up behind the target to be followed in a direction intersecting the orientation of the target to be followed as the destination position.
[0020] According to the aspects (1) to (14), it is possible to generate an appropriate route depending on the situation in which the moving body is placed.
[0021] FIG. 1 is a configuration diagram of a moving body. FIG. 2 is a configuration diagram of a control device. FIG. 3 is a diagram showing an overview of risks set by a risk distribution prediction unit. FIG. 4 is a flowchart showing an example of the flow of processing executed by a destination position setting unit. FIG. 5 is a diagram for explaining a first condition. FIG. 6 is a diagram for explaining a second condition. FIG. 7 is a diagram showing an example of a specified position.
[0022] [Overview] Hereinafter, with reference to the drawings, embodiments of a control device, a control method, and a program of the present invention will be described. The control device of the present invention controls a driving device of a mobile object to move the mobile object. The control device may be mounted on the mobile object, or may be installed in a location separate from the mobile object and remotely control the mobile object via communication. In the present invention, a mobile object autonomously moves in an area where pedestrians walk, following a follow-up target. The area where pedestrians walk includes sidewalks, public open spaces, floors within buildings, and may also include roadways. In the following description, a mobile object is assumed to have no human on board, but a human may also occupy the mobile object. The follow-up target is, for example, a single pedestrian (hereinafter referred to as "master M"), but it may also be a robot or an animal. A mobile object is used for purposes such as accompanying a master M on shopping trips and carrying luggage. However, it may also be used for other purposes, such as carrying a patient in a hospital and following the master M, who is a nurse, or for a group of multiple mobile objects moving in a convoy following a master M, who is a master M.
[0023] 1 is a configuration diagram of a mobile object 1. The mobile object 1 is equipped with, for example, an HMI (Human Machine Interface) 10, an object detection device 20, a driving device 30, a sensor 40, and a control device 100. These components are supported or housed by a base 5. The base 5 may be provided with a luggage storage section or the like.
[0024] The HMI 10 presents various information to the master M and accepts input operations by the master M. The HMI 30 includes various display devices, a speaker, a buzzer, a touch panel, switches, keys, a short-range wireless communication device, and the like.
[0025] The object detection device 20 is a device that generates data for recognizing objects (including pedestrians) present around the moving body 1 and the master M. The object detection device 20 includes, for example, a camera whose imaging range covers the area around the moving body 1. The object detection device 20 may include sensors such as a radar device, a LIDAR (Light Detection and Ranging), and an ultrasonic sensor, as well as an object recognition device that identifies objects by performing sensor fusion processing based on the outputs of these sensors.
[0026] The drive device 30 is a mechanism for moving the mobile body 1 including the base body 5 in any direction. The drive device 30 includes, for example, a plurality of wheels, a drive motor attached to one or more wheels, and a steering device attached to one or more wheels. There are no particular restrictions on the configuration of the drive device 30, and the drive device 30 may have any configuration. In principle, the drive device 30 moves the mobile body 1 while keeping the front surface of the base body 5 facing the traveling direction of the mobile body 1.
[0027] The sensor 40 is a sensor for detecting the behavior of the mobile body 1. The sensor 40 includes, for example, a wheel speed sensor for detecting the wheel speed, an acceleration sensor for detecting the acceleration acting on the mobile body 1, a yaw rate sensor attached near the center of gravity of the base body 5 in the horizontal direction, a steering angle sensor for detecting the steering angle of the steered wheels (steered wheels), and an orientation sensor for detecting the orientation of the mobile body 1 in the horizontal direction.
[0028] FIG. 2 is a configuration diagram of the control device 100. The control device 100 includes, for example, a recognition unit 110, a destination position setting unit 120, a risk distribution prediction unit 130, a path generation unit 140, and a drive control unit 150. These components are realized by a hardware processor, such as a central processing unit (CPU), executing a program (software). Some or all of these components may be realized by hardware (including circuitry), such as a large-scale integration (LSI), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a graphics processing unit (GPU), or may be realized by a combination of software and hardware. The program may be stored in advance in a storage device (a storage device with a non-transitory storage medium) such as a hard disk drive (HDD) or flash memory, or may be stored in a removable storage medium (a non-transitory storage medium) such as a DVD or CD-ROM, and installed in the storage device by inserting the storage medium into a drive device.
[0029] Without this definition, it is expected that it will be difficult to obtain a patent in the United States. At least the destination position setting unit 120 and the path generation unit 140 are functions that are realized by, for example, separate hardware processors. For example, a first processor functions as the recognition unit 110, the destination position setting unit 120, and the risk distribution prediction unit 130, a second processor functions as the path generation unit 140, and a third processor functions as the drive control unit 150.
[0030] The recognition unit 110 recognizes objects, including pedestrians and the master M, based on data output by the object detection device 20. When the object detection device 20 is a camera, the recognition unit 110 recognizes pedestrians by inputting camera images into a trained model for identifying pedestrians. The same applies to objects other than pedestrians. To distinguish between pedestrians and the master M, the recognition unit 110 may store multiple images of the master M captured by a camera in advance as templates in a storage unit (not shown) and identify the master M by comparing the templates with the camera images. Alternatively, the recognition unit 110 may recognize the position of the master M by utilizing communication directionality and having the HMI 10 perform short-range wireless communication with a terminal device held by the master M. As described below, the recognition unit 110 also recognizes the orientation of the master M.
[0031] The arrival position setting unit 120 sets a position that has a predetermined positional relationship with the master M as the arrival position AP of the moving object 1. Details will be described later.
[0032] The risk distribution prediction unit 130 sets risk, which is an index value indicating the degree to which the moving body 1 should not enter or approach, on an imaginary plane S, which represents the area around the moving body 1 as a two-dimensional plane viewed from above. The higher the risk value, the more likely the moving body 1 should not enter or approach, and the closer the value is to zero, the more favorable it is for the moving body 1 to pass through. However, this relationship may be reversed. The risk distribution prediction unit 130 sets risk on the imaginary plane S not only for the current time, such as the current time t, after Δt (time t + Δt), after 2Δt (time t + 2Δt), etc., but also for future time points specified at regular time intervals. The risk distribution prediction unit 130 predicts risk at each future time point based on changes in pedestrians continuously recognized by the recognition unit 110.
[0033] 3 is a diagram showing an outline of the risk set by the risk distribution prediction unit 130. The risk distribution prediction unit 130 sets risks for objects (including the master M and pedestrians Pk) other than the moving body 1, with contour lines of ellipses or circles based on the direction and speed of travel on the imaginary plane S, and sets a fixed value of risk for the immovable area BD such as a wall. 1is the direction of the moving object 1 (details will be described later). R(P1) is the risk of stationary pedestrian P1, R(P2) is the risk of moving pedestrian P2, R(P3) is the risk of moving pedestrian P3, and R(P4) is the risk of moving pedestrian P4. Since pedestrians P2 to P4 continue to move, the risk is set at a position different from the current time for each future point in time. R(P2)_t is the risk of pedestrian P2 in a certain control cycle, R(P2)_t + Δt is the risk of pedestrian P2 in the next control cycle, and R(P2)_t + Δ2t is the risk of pedestrian P2 in the control cycle after that. R(BD) is the risk of the unmovable area BD. In the figure, the density of the hatching indicates the risk value, with the darker the hatching, the greater the risk.
[0034] The path generation unit 140 generates a path for the mobile object 1 to reach the destination position AP at each future point in time while avoiding passing through any positions with a risk value equal to or greater than a predetermined value. P in FIG. 3 represents the generated path. The path generation unit 140, for example, comprehensively searches for points that the path R can pass through at each sampling distance (e.g., approximately 1 m), and generates, as the path R, a path candidate that connects these points and has a good score (a score based on predetermined evaluation criteria) evaluating the degree of curvature of the path. Furthermore, the path generation unit 140 may modify the generated path R to make it smoother, for example, by fitting it to a spline curve. The path R may be generated assuming that the mobile object 1 moves at a constant speed, but the path R may also be assigned a speed profile, such as deceleration, stopping, or acceleration.
[0035] The drive control unit 150 controls the drive device 30 attached to the moving body 1 so that the moving body 1 moves along the route R.
[0036] [Setting of Arrival Point] The following describes the process of setting the arrival position AP by the arrival position setting unit 120. The arrival position setting unit 120 varies the method of setting the arrival position AP based on the situation of the moving object 1 and the master M.
[0037] 4 is a flowchart showing an example of the flow of processing executed by the arrival position setting unit 120. First, the arrival position setting unit 120 determines whether or not a first condition is satisfied (step S200).
[0038] The first condition is, for example, that the recognition unit 110 has recognized a predetermined number of pedestrians or more within a predetermined area. FIG. 5 is a diagram for explaining the first condition. In the figure, WA is the predetermined area. The recognition unit 110 sets the predetermined area WA in the space between the moving body 1 and the master M based on some criteria, and counts the pedestrians P present within the predetermined area WA. The method for setting the predetermined area WA can be determined appropriately, and for example, it may be set to an area of a predetermined radius in the direction of travel of the moving body 1.
[0039] When the first condition is satisfied, the arrival position setting unit 120 sets the arrival position behind the master M in the direction D of the master M. M A plurality of destination positions AP-1 to AP-k (k is a natural number equal to or greater than 1) are set in a direction intersecting (e.g., perpendicular to) the direction of arrival, and provided to the path generation unit 140 (step S202). In this case, the path generation unit 140 generates paths from the mobile object 1 to at least some of the destination positions AP-1 to AP-k and selects the path with the best score among them. The path generation unit 140 may generate and evaluate paths to each of the destination positions AP-1 to AP-k, or may generate and evaluate paths in parallel and select one path, omitting the generation of paths for subsequent destination positions. Furthermore, before generating and evaluating the paths, the path generation unit 140 may perform a primary evaluation of the destination positions based on some criteria and cut off paths (removing paths with poor results from the primary evaluation), and then generate paths for the remaining destination positions and evaluate the paths. Note that "providing" may mean transmitting data via inter-processor communication or writing data to a shared memory area.
[0040] Master M's direction D M The recognition unit 110 recognizes the master M's movement vector, face direction, body direction, or a combination thereof as the master M's direction D MAt this time, the recognition unit 110 may perform a moving average process to prevent fluctuations in the recognition result.
[0041] If the first condition is not satisfied, as will be explained below, the arrival position setting unit 120 sets one arrival position AP and provides it to the path generation unit 140. First, the arrival position setting unit 120 determines whether the speed of the master M is less than a predetermined speed (step S204). The speed of the master M can be calculated, for example, by subtracting the speed vector of the moving body 1 from the relative speed vector of the master M, which is calculated from the change in the relative position of the master M with respect to the moving body 1, which is continuously recognized. If the speed of the master M is less than the predetermined speed, the arrival position setting unit 120 calculates the representative position R of the master M. M is set as the arrival position AP and provided to the route generation unit 140 (step S206). In this case, since the risk is set with the master M at the center, a situation in which the mobile unit 1 collides with the master M is avoided. M is the position of the master M's feet, which is obtained as a result of image processing, for example, and is determined based on an arbitrary criterion.
[0042] If the speed of the master M is equal to or greater than a predetermined speed, the arrival position setting unit 120 determines whether a flag described below is set to 1 (step S208). This flag determines whether a second condition described below is set to a condition that is more likely to be met (flag 1) or less likely to be met (flag 0). If the flag is set to 1, the arrival position setting unit 120 sets the threshold set for the second condition to a threshold set that is more likely to be met (step S210).
[0043] Next, the arrival position setting unit 120 determines whether or not the second condition is satisfied (the second condition is that at least the direction D of the master M is M and the direction of the moving object 1 D 1 6 is a diagram for explaining the second condition. More specifically, the second condition includes, for example, (1) the angle θ is less than the reference angle θref, and (2) the distance from the representative position R1 of the mobile object 1 to the representative position R2 of the master M is M The direction D of the moving body 1 1is the first coordinate axis, the distance X M1 is less than the first reference distance Xref, and (3) the distance from the representative position R1 of the moving body 1 to the representative position R M The direction D of the moving body 1 1 When the direction perpendicular to the second coordinate axis is set as the second coordinate axis, the distance Y M1 is less than the second reference distance Yref.
[0044] Here, when the flag is 1, the reference angle θref, the first reference distance Xref, and the second reference distance Yref are set as follows. These are threshold sets that make it easy for the second condition to be met. θref: large (for example, 30 degrees) Xref: large (for example, 10 m) Yref: large (for example, 3 m)
[0045] On the other hand, when the flag is 0, the reference angle θref, the first reference distance Xref, and the second reference distance Yref are set as follows. These are threshold sets that make it difficult for the second condition to be met: θref: small (for example, 20 degrees), Xref: small (for example, 7 m), Yref: small (for example, 2 m).
[0046] Orientation D of moving body 1 1 For example, the direction may be a direction from the center of gravity of the moving body 1 toward an arbitrarily determined forward direction (i.e., forward of the base body 5), or a direction along the movement vector of the moving body 1, or a direction obtained by combining these.
[0047] If the second condition is not satisfied, the arrival position setting unit 120 determines whether the direction D of the master M is behind the master M. M Among multiple candidate arrival positions APc-1 to APc-m (m is a natural number of 2 or greater) aligned in a direction intersecting with the target position, the candidate arrival position closest to the moving object 1 is set as the arrival position AP and provided to the path generating unit 140 (step S214). In the example of FIG. 6, the candidate arrival position APc-m is set as the arrival position AP. For example, n>m. The arrival position setting unit 120 then sets the flag to 1 (step S216).
[0048] If the second condition is satisfied, the arrival position setting unit 120 sets one arrival position AP at a specified position diagonally behind the master M and provides it to the path generating unit 140 (step S218). Then, the arrival position setting unit 120 sets the flag to 0 (step S220). Fig. 7 is a diagram showing an example of the specified position APdef. In the example shown, the specified position APdef is set to the right rear of the master M.
[0049] By performing processing in this manner, the control device 100 can generate an appropriate route depending on the situation of the moving object 1. When there are few pedestrians around the moving object 1 and the master M, and the master M is moving in one direction at a relatively slow speed (when the first condition is not met and the second condition is met), the moving object 1 moves to follow the defined position APdef shown in Fig. 7, so that the moving object 1 always appears to be in the same position from the master M's perspective. This gives the master M a sense of security.
[0050] On the other hand, if the number of pedestrians increases around the moving body 1 and the master M, the route R that the moving body 1 can take becomes limited, making it unable to adequately follow the master M, and there is a concern that the moving body 1 may eventually lose track of the master M. In response to this, when the first condition is satisfied, the control device 100 provides multiple arrival positions AP to the route generation unit 140, and generates the route R so as to follow a position that is most suitable for the route generation unit 140 among the multiple arrival positions AP. As a result, the above-mentioned concern can be alleviated.
[0051] Furthermore, if the master M makes a sharp turn, accelerates, or the like, the moving body 1 may not be able to sufficiently follow the master M depending on its maneuverability, and may become separated from the master M. In particular, if the master M makes a sharp left turn, since the specified position APdef is to the rear right, the moving body 1 will have to make a wide turn to follow the master M's trajectory, which could further separate the moving body 1 from the master M, or could become a nuisance to nearby pedestrians. In response to this, when the second condition is not met, the control device 100 sets the position closest to the moving body 1 as the arrival position AP among multiple candidate arrival positions APc, thereby enabling the moving body 1 to quickly follow the master M. The second condition is set to be met when the master M makes a sharp turn or accelerates vertically or horizontally, and therefore the control device 100 can perform the above processing suitably.
[0052] In addition, in the above process, once the second condition is satisfied, the threshold set for the second condition is set to a value that makes it easier for the second condition to be satisfied, thereby preventing the behavior of the moving object 1 from becoming unstable due to frequent repetition of the second condition being satisfied and not being satisfied.
[0053] In the above description, the control device 100 is described as being mounted on the mobile body 1, but this is not limited to this. The control device 100 may be installed at a location away from the mobile body 1, acquire output data from the object detection device 20 via communication, and transmit a drive instruction signal to the drive unit 30, i.e., remotely control the mobile body 1.
[0054] According to the embodiment described above, it is possible to generate an appropriate route depending on the situation in which the moving body 1 is placed.
[0055] The above-described embodiment can be expressed as follows. a first processor connected to the one or more storage media; and a second processor connected to the one or more storage media, wherein the first processor recognizes objects including pedestrians and the target to be followed by setting a position that has a predetermined positional relationship with the target to be followed as a target position of the moving body by executing the computer-readable instructions; the second processor generates a path from the position of the moving body to the target position by executing the computer-readable instructions; the first processor sets a plurality of target positions and provides them to the path generation unit if a first condition is satisfied, and sets a single target position and provides it to the path generation unit if the first condition is not satisfied by executing the computer-readable instructions; and when a plurality of target positions are provided, the second processor generates the paths for at least some of the plurality of target positions and selects one path based on a predetermined evaluation criterion by executing the computer-readable instructions.
[0056] The above describes the form for carrying out the present invention using an embodiment, but the present invention is not limited to such an embodiment, and various modifications and substitutions can be made within the scope that does not deviate from the gist of the present invention.
[0057] REFERENCE SIGNS LIST 1 Mobile object 20 Object detection device 30 Drive unit 100 Control unit 110 Recognition unit 120 Arrival position setting unit 130 Risk distribution prediction unit 140 Path generation unit 150 Drive control unit
Claims
1. A control device that controls a mobile body that moves autonomously by following a target to be followed in an area where a pedestrian walks, comprising: a recognition unit that recognizes objects including pedestrians and the target to be followed; a setting unit that sets a position that is in a predetermined positional relationship with the target to be followed as a destination position of the mobile body; a path generation unit that generates a path from the position of the mobile body to the destination position; and a drive control unit that controls a drive unit attached to the mobile body so that the mobile body moves along the path, wherein the setting unit sets multiple destination positions and provides them to the path generation unit if a first condition is satisfied, and sets one destination position and provides it to the path generation unit if the first condition is not satisfied, and when multiple destination positions are provided by the setting unit, the path generation unit generates the paths for at least some of the multiple destination positions and selects one path based on a predetermined evaluation criterion.
2. The control device according to claim 1, wherein the first condition is that the recognition unit has recognized a predetermined number of pedestrians within a predetermined area.
3. The control device according to claim 1, wherein the recognition unit further recognizes the orientation of the target to be followed, and the setting unit, when the first condition is satisfied, sets a plurality of the arrival positions behind the target to be followed, aligned in a direction intersecting the orientation of the target to be followed.
4. The control device according to claim 1, wherein the recognition unit further recognizes the speed of the target to be followed, and the setting unit sets the position of the target to the arrival position when the speed of the target to be followed is less than a predetermined speed.
5. The control device described in claim 1, wherein the recognition unit further recognizes the orientation of the target to be followed, and the setting unit, if the first condition is not satisfied and a second condition including a condition regarding the angle between the orientation of the target to be followed and the orientation of the moving body is not satisfied, sets the candidate closest to the moving body as the destination position among multiple destination position candidates lined up behind the target to be followed in a direction intersecting the orientation of the target to be followed.
6. The control device according to claim 5, wherein the second condition includes that the angle between the orientation of the target and the orientation of the moving body is equal to or smaller than a reference angle.
7. The control device according to claim 6, wherein the second condition further includes the following: when the orientation of the moving body is defined as a first coordinate axis and the orientation perpendicular to the first coordinate axis is defined as a second coordinate axis, the distance between the target to be tracked and the moving body with respect to the first coordinate axis is less than a first reference distance, and the distance between the target to be tracked and the moving body with respect to the second coordinate axis is less than a second reference distance.
8. The control device according to claim 5, wherein the setting unit sets one of the arrival positions diagonally behind the target when the first condition is not satisfied and the second condition is satisfied.
9. The control device according to claim 5, wherein, when the second condition is satisfied, the setting unit changes the threshold value of the second condition to a value that makes the second condition more likely to be met, and maintains the changed threshold value until it is determined that the second condition is not satisfied using the changed threshold value.
10. A control method in which a control device controls a mobile body that moves autonomously in an area where a pedestrian walks, following a target to be followed, the control device recognizes objects including pedestrians and the target to be followed, sets a position that has a predetermined positional relationship with the target to be followed as a destination position of the mobile body, generates a path from the position of the mobile body to the destination position, controls a drive unit attached to the mobile body so that the mobile body moves along the path, sets multiple destination positions if a first condition is met when setting the destination positions, and sets one destination position if the first condition is not met when generating the path, and if multiple destination positions are set when generating the path, generates the path for at least some of the multiple destination positions and selects one path based on predetermined evaluation criteria.
11. A program for causing a processor of a control device that controls a mobile body that moves autonomously in an area where a pedestrian walks, following a target to recognize objects including pedestrians and the target to be followed, setting a position that has a predetermined positional relationship with the target to be followed as the destination position of the mobile body, generating a path from the position of the mobile body to the destination position, controlling a drive unit attached to the mobile body so that the mobile body moves along the path, setting multiple destination positions if a first condition is met when setting, and setting one destination position if the first condition is not met, and generating the path for at least some of the multiple destination positions when multiple destination positions are set, and selecting one path based on predetermined evaluation criteria.
12. A control device for controlling a mobile body that moves autonomously by following a target to be followed in an area where pedestrians walk, comprising: a recognition unit that recognizes objects including pedestrians and the target to be followed; a setting unit that sets a position that is in a predetermined positional relationship with the target to be followed as the arrival position of the mobile body; a path generation unit that generates a path from the position of the mobile body to the arrival position; and a drive control unit that controls a drive unit attached to the mobile body so that the mobile body moves along the path, wherein the recognition unit further recognizes the orientation of the target to be followed; and when predetermined conditions including a condition regarding the angle between the orientation of the target to be followed and the orientation of the mobile body are not satisfied, the setting unit sets the candidate for the arrival position that is closest to the mobile body among multiple candidates for the arrival position lined up behind the target to be followed in a direction intersecting the orientation of the target to be followed as the arrival position.
13. A control method in which a control device controls a mobile body that moves autonomously by following a target to be followed in an area where pedestrians walk, recognizing objects including pedestrians and the target to be followed, setting a position that has a predetermined positional relationship with the target to be followed as a destination position of the mobile body, generating a path from the position of the mobile body to the destination position, controlling a drive unit attached to the mobile body so that the mobile body moves along the path, further recognizing the orientation of the target to be followed during the recognition, and if predetermined conditions including a condition regarding the angle between the orientation of the target to be followed and the orientation of the mobile body are not satisfied during the setting, setting the candidate for the destination position that is closest to the mobile body out of multiple candidates for the destination position lined up behind the target to be followed in a direction intersecting the orientation of the target to be followed as the destination position.
14. A program for causing a processor of a control device that controls a mobile body that moves autonomously by following a target to move in an area where a pedestrian walks, to recognize objects including pedestrians and the target to be followed, to set a position that is in a predetermined positional relationship with the target to be followed as the arrival position of the mobile body, to generate a path from the position of the mobile body to the arrival position, to control a drive unit attached to the mobile body so that the mobile body moves along the path, to further recognize the orientation of the target to be followed during the recognition, and if predetermined conditions including a condition regarding the angle between the orientation of the target to be followed and the orientation of the mobile body are not met during the setting, to set the candidate for the arrival position that is closest to the mobile body out of multiple candidates for the arrival position lined up behind the target to be followed in a direction intersecting the orientation of the target to be followed as the arrival position.