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

Abstract

Accurately estimate the destination of a moving target. [Solution] An information processing device for estimating the destination of a moving target includes: a selection unit that selects a plurality of geographic locations from around the dynamic target; a calculation unit that uses a likelihood function to calculate the likelihood that each of the plurality of geographic locations is the destination; a re-selection unit that re-selects the plurality of geographic locations based on the likelihood at each geographic location; and an estimation unit that estimates the destination based on the re-selected plurality of geographic locations. The likelihood function is based on at least one of the state of the dynamic target and the positions of obstacles around the dynamic target.

Description

[Technical Field]

[0001] The present invention relates to an information processing device, an information processing method, a mobile device, a program, and a system. [Background technology]

[0002] To assist users, autonomous mobile robots capable of following users are provided. In the technology described in Patent Document 1, a virtual target different from the actual target is set in order to make the autonomous mobile robot follow the user with more natural behavior. [Prior art documents] [Patent Documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2021-77088 [Overview of the project] [Problems that the invention aims to solve]

[0004] To control a moving object, the destination of a moving dynamic target around the object may be used. Some aspects of the present invention provide techniques for accurately estimating the destination of a moving dynamic target. [Means for solving the problem]

[0005] According to some embodiments, an information processing device is provided for estimating the destination of the movement of a dynamic target, comprising: selection means for selecting a plurality of geographic locations from around the dynamic target; calculation means for calculating the likelihood that each of the plurality of geographic locations is the destination using a likelihood function; reselection means for reselecting the plurality of geographic locations based on the likelihood at each geographic location; and estimation means for estimating the destination based on the reselected plurality of geographic locations, wherein the likelihood function is based on at least one of the state of the dynamic target and the positions of obstacles around the dynamic target. [Effects of the Invention]

[0006] According to some embodiments, the destination of the movement of the dynamic object target can be accurately estimated.

Brief Description of the Drawings

[0007] [Figure 1] Schematic diagram for explaining an example of the external configuration of a moving body according to some embodiments. [Figure 2] Block diagram for explaining an example of the functional configuration of a moving body according to some embodiments. [Figure 3] Flow chart for explaining a control method of a moving body according to some embodiments. [Figure 4] Schematic diagram for explaining a method for determining the target destination of a dynamic object target according to some embodiments. [Figure 5] Schematic diagram for explaining a method for determining a likelihood function according to some embodiments.

Modes for Carrying Out the Invention

[0008] Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. Note that the following embodiments do not limit the invention according to the claims, and not all combinations of the features described in the embodiments are essential for the invention. Two or more of the features described in the embodiments may be arbitrarily combined. Also, the same or similar configurations are given the same reference numerals, and duplicate explanations are omitted.

[0009] <Configuration of the Moving Body> Referring to Figure 1, an example of the external configuration of a mobile body 100 according to one embodiment will be described. In Figure 1, arrow X indicates the front-to-back direction of the mobile body 100. F indicates the front and R indicates the rear. Arrows Y and Z indicate the width direction (left-right direction) and the up-down direction of the mobile body 100, respectively. The mobile body 100 is capable of autonomous movement. For example, the mobile body 100 is equipped with a battery and moves mainly by motor power. The mobile body 100 may be used in the vicinity of amusement facilities, large commercial facilities, airports, parks, sidewalks, parking lots, etc. The mobile body 100 may be a vehicle that moves on the ground using wheels, an aircraft that moves in the air (e.g., a drone), or a robot that moves on the ground using two or more legs. Movement using wheels is also called driving. Movement in the air is also called flying. Movement using two or more legs is also called walking. The following description will focus on the case where the mobile body 100 is a vehicle, but similar descriptions apply to other forms of mobile bodies.

[0010] The mobile unit 100 is capable of moving in accordance with the user of the mobile unit 100 (hereinafter simply referred to as the user). "Moving in accordance with the user" means that the mobile unit 100 moves based on the user's proactive movements. The following example describes a configuration in which no person rides in the mobile unit 100, but the mobile unit 100 may carry a person other than the user. The mobile unit 100 comprises, for example, a pair of left and right front wheels 101 and rear wheels 102, which are included in the driving unit 204 (Figure 2). The driving unit 204 may take other forms, such as a four-wheeled or two-wheeled vehicle. The mobile unit 100 may be capable of autonomously moving to a pre-set destination, either in place of or in addition to accompanying its user.

[0011] The mobile unit 100 has a housing 110 capable of accommodating luggage. The front 111 of the housing is provided with a lid that can be opened and closed to accommodate luggage, and the lid is equipped with a locking mechanism. The locking mechanism is controlled by the mobile unit 100. For example, the mobile unit 100 releases the lock when user authentication is successful. Alternatively, the mobile unit 100 may accommodate luggage in other ways.

[0012] A touchscreen 120 is located on the top surface 112 of the housing, allowing the user to, for example, change the settings of the mobile unit 100 or check information about the facility. The sensor box 130 contains a detection unit 206 (Figure 2), such as a camera, inside. The detection unit 206 observes the user and other targets included in the environment surrounding the mobile unit 100 through the front 131, sides, and back of the sensor box 130.

[0013] <Example of a mobile device's functional configuration> Referring to Figure 2, an example of the functional configuration of the mobile body 100 will be described. The mobile body 100 includes the components shown in Figure 2. The mobile body 100 may also include components not shown in Figure 2, or may not include some of the components shown in Figure 2.

[0014] The mobile unit 100 is an electrically powered autonomous mobile unit equipped with a driving unit 204 and powered primarily by a battery 205. The battery 205 is a secondary battery such as a lithium-ion battery, and the driving unit 204 uses the power supplied from the battery 205 to propel the mobile unit 100.

[0015] The driving unit 204 accelerates and decelerates the mobile body 100 by changing the rotational speed of a pair of front wheels 101 using a motor as the drive source. The driving unit 204 may also include a braking mechanism for decelerating the mobile body 100. The driving unit 204 steers the mobile body 100 by making the rotational speeds of the pair of front wheels 101 different. The driving unit 204 can detect and output physical quantities representing the motion of the mobile body 100, such as the mobile body 100's speed, acceleration, steering angle, angular velocity of the mobile body 100's housing 110, and angular acceleration.

[0016] The mobile body 100 includes a detection unit 206 containing one or more sensors. The detection unit 206 generates data for recognizing targets (including objects and people in the environment surrounding the mobile body 100) contained in the environment surrounding the mobile body 100. The detection unit 206 includes sensors such as an imaging device (camera), radar device, lidar (Light Detection and Ranging), and ultrasonic sensor, with a detection range around the mobile body 100, and outputs sensor information. The imaging device may be configured using a fisheye lens or may be configured to perform stereo imaging. Furthermore, the detection unit 206 includes a GNSS (Global Navigation Satellite system) sensor and receives GNSS signals to detect the current position of the mobile body 100. The detection unit 206 may detect the current position using Wi-Fi (Local Area Network) or Bluetooth signals. The imaging device may be an RGB camera or may further have a depth measurement function. For example, the mobile unit 100 may have RGB cameras with depth measurement capabilities on the front and rear sides of the sensor box 130, and RGB cameras without depth measurement capabilities on the right and left sides of the sensor box 130.

[0017] The mobile unit 100 includes a control unit (ECU (Electronic Control Unit)) 201. The control unit 201 functions as a control device for the mobile unit 100. The control unit 201 includes one or more processors 202, such as a CPU (Central Processing Unit), and a memory 203, which is a storage device such as a semiconductor memory. Therefore, the control unit 201 can also be called an information processing device or a computer. The memory 203 stores programs executed by the processors 202 and data used by the processors 202 for processing. Multiple sets of processors 202 and memory 203 may be provided according to the function of the mobile unit 100 and configured to communicate with each other.

[0018] The control unit 201 acquires physical quantities representing the motion output by the travel unit 204, detection results from the detection unit 206, input information from the touchscreen 120, and audio information input from the audio input device 207, and executes corresponding processing. For example, the control unit 201 controls the motor of the travel unit 204, controls the display on the touchscreen 120, and provides audio notifications to the surrounding environment.

[0019] The voice input device 207 picks up sounds from the environment surrounding the mobile body 100. The control unit 201 can recognize the input sounds and execute corresponding processing. The storage device 208 is a non-volatile large-capacity storage device that stores map information including roads that the mobile body 100 can travel on, areas where entry is restricted, landmarks, stores, etc. The storage device 208 may also store programs executed by the processor 202 and data used by the processor 202 for processing. The communication device 209 is a communication device that can connect to an external network via wireless communication such as fifth-generation mobile communication or wireless LAN.

[0020] The display device 210 displays (presents) a user interface screen to the user on the touchscreen 120, or outputs (presents) spoken audio to the environment surrounding the mobile body 100 via the microphone. The input device 211 may include, for example, a touch panel and be configured as an integral part of the touchscreen 120. The input device 211 receives operation input from the user via the touch panel.

[0021] The processor 202 of the control unit 201 implements the functions of the information acquisition unit 221, target determination unit 222, driving control unit 223, and destination estimation unit 224 by executing a program stored in the memory 203 or storage device 208. The information acquisition unit 221 acquires various information used for processing by other components. The target determination unit 222 determines the target position of the mobile body 100 for the user based on the information acquired by the information acquisition unit 221. The target position is the target position to which the mobile body 100 will move. The driving control unit 223 supplies control signals to the driving unit 204 to move the mobile body 100. The driving control unit 223 moves the mobile body 100 toward the target position. The destination estimation unit 224 estimates the destination of the movement of the dynamic target. Details of the processing of the information acquisition unit 221, target determination unit 222, driving control unit 223, and destination estimation unit 224 will be described later.

[0022] <Control method for mobile unit 100> Referring to Figure 3, the method by which the control unit 201 controls the mobile body 100 will be described. As described above, the control unit 201 can control the mobile body 100 to accompany the user. Each step of the method in Figure 3 may be performed by the processor 202 executing a program stored in memory 203 or storage device 208. Alternatively, at least some of the steps of the method in Figure 3 may be performed by a dedicated integrated circuit such as an ASIC (Application Specific Integrated Circuit). The method in Figure 3 may be started in response to the user instructing the mobile body 100 to accompany the user. The control unit 201 repeatedly executes the processes S301 to S303 (for example, with a 100ms cycle).

[0023] The method shown in Figure 3 is performed on a user of the mobile device 100. The control unit 201 identifies the user at the start of the method in Figure 3 and controls the mobile device 100 to accompany this user. The control unit 201 may identify a person positioned in front of the mobile device 100 in an image captured by the detection unit 206 (e.g., an imaging device) or a person who has previously registered as a user as the user. During the execution of the method in Figure 3, the control unit 201 continuously determines whether it can detect the user. If the user cannot be detected for a predetermined period of time since the last detection, the control unit 201 determines that the user has been lost and interrupts the method in Figure 3. Subsequently, the control unit 201 may restart the method in Figure 3 depending on whether the user has been detected.

[0024] In S301, the control unit 201 (for example, the information acquisition unit 221) acquires information to be used in subsequent processing. This information may include user information, mobile device information, and environmental information. The control unit 201 may store at least a portion of the acquired information in the memory 203 or storage device 208 for use in subsequent processing.

[0025] User information refers to information about the user. User information may include the user's current geographical location and the user's current posture. The control unit 201 may acquire user information based on the detection results of the detection unit 206 (for example, images captured by the imaging device).

[0026] Mobile object information refers to information about the mobile object 100. Mobile object information may include the current speed of the mobile object 100, the current geographical location of the mobile object 100, and the current angular velocity of the mobile object 100. The control unit 201 may acquire mobile object information based on the output from the driving unit 204 or the detection results from the detection unit 206 (for example, GNSS positioning data or inertial sensor data).

[0027] Environmental information refers to information about the environment surrounding the mobile body 100. Environmental information may include the number, type, location, and size of targets included in the environment surrounding the mobile body 100. Targets may include static and dynamic targets. Static targets may include structures such as walls, guardrails, pillars, and steps. Static targets are targets that are fixed directly or indirectly to the ground and do not move. Static targets that may obstruct the movement of the mobile body 100 may be called static obstacles. Dynamic targets may include pedestrians, cyclists, autonomous mobile bodies, animals, etc. Dynamic targets are targets that can move relative to the ground. Dynamic targets that may obstruct the movement of the mobile body 100 may be called dynamic obstacles. The control unit 201 may acquire environmental information based on the detection results of the detection unit 206 (for example, images captured by the imaging device).

[0028] In S302, the control unit 201 (for example, the target determination unit 222) determines the target position of the moving object 100. For example, the control unit 201 may first predict the direction of movement in which the user is trying to move, based on various information acquired in S301. The direction of movement of the user may be predicted based on, for example, the orientation of the user's body or the user's past movement path. The control unit 201 may then determine the target position as a position that forms a predetermined angle with respect to the predicted movement path and is at a predetermined distance from the user. The control unit 201 may determine the target position so as not to overlap with obstacles (for example, static obstacles).

[0029] In S303, the control unit 201 (for example, the travel control unit 223) moves the mobile body 100 toward the target position determined in S302. Specifically, the control unit 201 generates a trajectory from the current position of the mobile body 100 toward the target position and moves the mobile body 100 along this trajectory. Depending on the current attitude and speed of the mobile body 100, this trajectory may or may not pass through the target position. After that, the control unit 201 transitions to processing S301 and repeats the above processing.

[0030] While executing the method shown in Figure 3, the control unit 201 may monitor the distance between the moving body 100 and any dynamic obstacles around it, and if this distance falls within a threshold (e.g., 1.5 m), it may take action (e.g., make an audio announcement) to ask the dynamic obstacles to yield the path. Furthermore, while executing the method shown in Figure 3, the control unit 201 may stop the moving body 100 if the distance between the moving body 100 and any dynamic obstacles around it falls within another threshold (e.g., 1 m). In addition, in S303, the control unit 201 may generate a trajectory that avoids the dynamic obstacles.

[0031] <Method for obtaining the position of a dynamic target> Referring to Figure 4, a method for estimating the destination of a moving target will be described. The moving target may be the user of the moving object 100, or it may be another moving target included in the environment surrounding the moving object 100. The destination of the moving target is the geographical location to which the moving target is about to move. The process of estimating the destination of the moving target may be included in the process of acquiring user information and environment information in S301 of Figure 3. That is, the method in Figure 4 may be executed as part of S301 in Figure 3. As described above, S301 is executed repeatedly. The method in Figure 4 may be executed each time S301 is executed, or it may be executed at a predetermined frequency relative to the execution of S301. Alternatively, the method in Figure 4 may be executed at a different trigger than the execution of S301.

[0032] Each step in Figure 4 may be performed by a control unit 201 (e.g., a destination estimation unit 224). If there are multiple dynamic targets around the mobile body 100, the control unit 201 may perform the method in Figure 4 for each dynamic target, or it may perform the method in Figure 4 for a specific dynamic target (e.g., the user of the mobile body 100, pedestrians around the mobile body 100, or an autonomous mobile robot around the mobile body 100). In the following description of Figure 4, the dynamic target whose destination is estimated will be referred to as the target target. In the method in Figure 4, the destination is estimated by performing processing similar to that of a particle filter.

[0033] In S401, the control unit 201 acquires information about the target object and information about the environment surrounding the target object. The information about the target object may include, for example, the geographical location of the target object and the direction of movement of the target object. The geographical location may be represented by two-dimensional coordinate values ​​in the horizontal plane. The geographical location may be defined by the relative position of the moving object 100 to the geographical location at the time the method of Figure 4 is started, or by latitude and longitude. The direction of movement of the target object is the direction in which the target object is moving. The direction of movement of the target object may be determined, for example, based on the orientation of the target object's body or the target object's past movement path. For example, if the target object is a person, the orientation of their waist may be used as the orientation of the target object's body (i.e., the direction of movement of the target object). The orientation of the target object's body may be determined by analyzing data observed by the detection unit 206 (e.g., images taken by a camera). Information about the environment surrounding the target object may include information about static obstacles present around the target object. Information about static obstacles may include the area occupied by the static obstacles.

[0034] In S402, the control unit 201 selects multiple geographic locations from around the dynamic target. The control unit 201 may select the multiple geographic locations randomly or regularly (e.g., in a grid). The multiple geographic locations may be selected from a specific range on the map (e.g., a range within a predetermined distance from the moving object 100 or the target object). In the following description, let's assume that N geographic locations are selected, where N could be, for example, 100 or 1000. Each of the multiple geographic locations corresponds to a particle in a particle filter.

[0035] In S403, the control unit 201 uses a likelihood function to calculate the likelihood that each of the multiple geographic locations selected in S402 (or re-selected in S404) is a destination. The likelihood function is a function that outputs the likelihood that a particular geographic location is a destination. A specific example of the likelihood function will be described later.

[0036] In S404, the control unit 201 re-selects multiple geographic locations based on the likelihood of each geographic location. Re-selecting multiple geographic locations is equivalent to resampling in a particle filter. For example, the control unit 201 selects new N geographic locations by repeating the process of selecting one of the existing N geographic locations based on the likelihood of each geographic location N times. As a result, geographic locations with low likelihood among the existing geographic locations are discarded with a high probability (i.e., not selected as new geographic locations). On the other hand, geographic locations with high likelihood among the existing geographic locations are selected with a high probability, and in some cases the same geographic location is selected multiple times. Thus, some of the new N geographic locations may be the same location.

[0037] In S405, the control unit 201 determines whether the condition for terminating the iteration (termination condition) is met. If the termination condition is met (YES in S405), the control unit 201 transitions the process to S406; otherwise (NO in S405), it transitions the process to S403. In this way, steps S403 to S405 are repeated until the termination condition is met. The termination condition may be that steps S403 to S405 are repeated a predetermined number of times (for example, 5 times). Alternatively, or in addition to this, the termination condition may be based on the convergence status of re-selection. For example, the control unit 201 may determine that re-selection has converged (i.e., the termination condition has been met) if the amount of change in the centroids of multiple geographical locations before and after S404 is less than a threshold.

[0038] In S406, the control unit 201 estimates the destination based on multiple geographical locations at this point in time (i.e., multiple geographical locations that were re-selected immediately before). For example, the control unit 201 estimates the centroid of multiple geographical locations as the destination. As described above, many geographical locations that have been determined to have a high likelihood by the likelihood function are re-selected. Therefore, the destination is determined to be a location with a high likelihood of being the destination.

[0039] The control unit 201 may store the destination estimated in S406 in the memory 203 or the storage device 208 for use in subsequent processing. In S303 of FIG. 3 described above, the control unit 201 may control the movement of the moving body 100 based on the destination of the dynamic target. For example, when the dynamic target is the user of the moving body 100, the control unit 201 may control the moving body 100 to move along the predicted trajectory to the user's destination. When the dynamic target is a dynamic obstacle, the control unit 201 may control the movement of the moving body 100 so as not to intersect the predicted trajectory to the destination of the dynamic obstacle.

[0040] <Example of likelihood function> The likelihood function used in S403 of FIG. 4 may be based on at least one of the state of the target and the positions of the obstacles around the target. Specifically, the likelihood function may be based on at least one of the moving direction of the target, whether each geographical position overlaps with a static obstacle, and the predicted trajectory along which the target is predicted to move toward each geographical position, or may be based on all of these.

[0041] For example, the likelihood function p(i) may be given by JPEG2026062057000002.jpg1558. In this equation, i represents a number assigned to a plurality of geographical positions and is an integer from 1 to N. The numerator is the sum of three terms W (i) (i) , W o (i) and W t (i) . The term W d (i) is a value calculated based on the moving direction of the target for the i-th geographical position. The term W o <00​​​This value is calculated based on the predicted trajectory that the target object will travel to reach each geographical location, for the i-th geographical location. The larger the value of each term in the numerator, the larger the value output by the likelihood function p(i). The denominator on the right side is the term used to normalize the likelihood. In the following explanation, the superscript (i) will be omitted for each term.

[0042] Refer to Figure 5, term W d , W o and W t An example of the calculation method is described below. Map 500 shows the environment surrounding the target object 501. Static obstacles 502 exist around the target object 501. There are three static obstacles 502 in map 500, and only one of them is assigned a reference number. Multiple geographic locations 503 are selected in map 500. In the example of map 500, six geographic locations 503 are selected, and only one of them is assigned a reference number. The multiple geographic locations 503 may be geographic locations selected in S402, or geographic locations re-selected in S404.

[0043] Refer to map 510, term W based on the direction of movement 511 of the target object 501. d The method for calculating this will be explained. Generally, the target object 501 is likely to be moving towards its destination. Therefore, term W d This is the angle θ between the direction of movement 511 of the target object 501 and the direction 512 from the target object 501 toward each geographical location 503. d The calculation is performed such that the smaller the (0 degrees or more, 180 degrees or less) range, the larger the value.

[0044] For example, term W d teeth, It may also be calculated according to JPEG2026062057000003.jpg1038. A is a predetermined positive constant, determined before performing the method in Figure 5 and stored in memory 203 or storage device 208. Region 513 is term W for each geographic location 503. d This visually represents the size of the region 513. The larger the region 513, the greater the term W dIt's big.

[0045] Refer to map 520, term W is based on whether each geographic location 503 overlaps with a static obstacle 502. o The method for calculating this will be explained. The target object 501 may be moving towards one of the static obstacles 502 (for example, a store or meeting spot). Therefore, term W o The values ​​are calculated such that when each geographical location 503 overlaps with a static obstacle 502, the values ​​are greater than when each geographical location 503 does not overlap with a static obstacle 502.

[0046] For example, term W o teeth, It may also be calculated according to JPEG2026062057000004.jpg3373. B is a predetermined positive constant, determined before performing the method in Figure 5 and stored in memory 203 or storage device 208. Region 521 is term W for each geographic location 503. o The size is visually represented. The larger the region 521, the greater the term W o It's big.

[0047] Referencing map 530, term W is based on the predicted trajectory 531 by which the object target 501 will move toward each geographical location 503. t The method for calculating this will be explained. The target object 501 may be moving in a direction different from the direction in which the destination is located in order to avoid the static obstacle 502. Therefore, term W t This is the angle θ between the track 531 and the direction of movement 511 of the target object 501. t The angle θ is calculated to be larger the smaller the angle (0 degrees or more, 180 degrees or less). The trajectory 531 is determined based on the current position of the target object 501, each geographical location 503, and the position of the static obstacle 502. t This may be the angle between the tangential direction of the track 531 and the direction of movement 511 at the current position of the target object 501.

[0048] For example, term W t teeth, It may also be calculated according to JPEG2026062057000005.jpg1037. C is a predetermined positive constant, which is determined before performing the method in Figure 5 and stored in memory 203 or storage device 208. Term W is calculated when the geographic location 503 overlaps with a static obstacle 502. t This becomes zero. The region 532 is the term W for each geographical location 503. t The size is visually represented. The larger the region 532, the greater the term W t It's big.

[0049] Map 540 shows the likelihood calculated for each geographical location 503 using the likelihood function p(i). Region 541 visually shows the likelihood for each geographical location 503. The larger Region 541, the greater the likelihood.

[0050] As described above, since the likelihood function p(i) is based on at least one of the state of the target object and the positions of obstacles around the target object, the destination of the movement of the target object 501 can be accurately estimated by the method in Figure 4. In the example above, the likelihood function p(i) has three terms W d (i) , W o (i) and W t (i) It is expressed as the normalized sum of these terms. Alternatively, the likelihood function p(i) may be given by other operations on these three terms. Furthermore, the likelihood function p(i) may contain only one or two of these three terms.

[0051] In the above-described embodiment, the method shown in Figure 4 is performed by the control unit 201. Alternatively, at least one step of the method shown in Figure 4 may be performed by an external server connected to the mobile body 100 via a network. In other words, the method shown in Figure 4 may be performed by the cooperation of the external server and the control unit 201. In this case, the server and the control unit 201 constitute an information processing system for controlling the mobile body 100. Furthermore, when all steps of the method shown in Figure 4 are performed by the external server, the external server functions as an information processing device for performing the method shown in Figure 4.

[0052] <Summary of Embodiments> (Item 1) An information processing device (201) for estimating the destination of the movement of a dynamic target (501), Selection means for selecting multiple geographical locations (503) from around the aforementioned dynamic target, A calculation means that uses a likelihood function (p(i)) to calculate the likelihood that each of the multiple geographic locations is the destination, A reselection means for reselecting the plurality of geographic locations based on the likelihood at each geographic location, The system comprises estimation means for estimating the destination based on the re-selected plurality of geographic locations, The likelihood function is based on at least one of the state of the dynamic target and the position of obstacles (502) around the dynamic target, according to the information processing device. According to this section, the destination of a moving target can be estimated with high accuracy. (Item 2) The likelihood function is based on the direction of movement (511) of the dynamic target, as described in item 1 of the information processing device. According to this section, the intention of a dynamic target can be understood based on its direction of movement, allowing for accurate estimation of the target's destination. (Item 3) The information processing device according to item 2, wherein the direction of movement of the dynamic target is determined based on the orientation of the body of the dynamic target. According to this section, the direction of movement of a dynamic target can be determined with high accuracy. (Item 4) The likelihood function is the angle (θ) between the direction of movement of the dynamic target (511) and the direction from the dynamic target toward each geographical location (512). d An information processing device as described in item 2 or 3, which outputs a larger value the smaller the value of ). According to this section, the intention of a dynamic target can be understood based on its direction of movement, allowing for accurate estimation of the target's destination. (Item 5) The likelihood function is based on whether each geographic location overlaps with a static obstacle (502), as described in any one of items 1 to 4. According to this section, it is possible to understand the intention of a dynamic target moving towards a static obstacle, thereby accurately estimating the destination of the dynamic target's movement. (Item 6) The information processing device described in item 5 outputs a likelihood function that is larger when each geographic location overlaps with a static obstacle than when each geographic location does not overlap with a static obstacle. According to this section, it is possible to understand the intention of a dynamic target moving towards a static obstacle, thereby accurately estimating the destination of the dynamic target's movement. (Item 7) The likelihood function is based on the predicted trajectory (531) of the dynamic target moving toward each geographical location, as described in any one of items 1 to 6 of the information processing device. According to this section, it is possible to understand the intention of dynamic targets as they move to avoid static obstacles, thereby accurately estimating the destination of the dynamic targets. (Item 8) The likelihood function is the angle (θ) between the trajectory and the direction of movement (511) of the moving target. d The information processing device described in item 7 outputs a larger value the smaller the value of ). According to this section, it is possible to understand the intention of dynamic targets as they move to avoid static obstacles, thereby accurately estimating the destination of the dynamic targets. (Item 9) The aforementioned likelihood function is, The direction of movement of the aforementioned dynamic target and Whether each geographical location overlaps with a static obstacle, The predicted trajectory of the dynamic target as it moves toward each geographical location, An information processing device described in any one of items 1 through 8, based on the above. According to this section, the likelihood of each geographical location is calculated from various perspectives, allowing for accurate estimation of the destination of moving objects. (Item 10) The information processing device according to any one of items 1 to 9, further comprising control means for controlling the movement of a moving body (100) equipped with a sensor (206) for observing the dynamic target, based on the estimated geographical location. According to this item, the moving object can be controlled appropriately. (Item 11) An information processing device (201) described in any one of items 1 to 10, A mobile body (100) equipped with a sensor (206) for observing a moving target. According to this section, a mobile object is provided that can accurately estimate the destination of a moving target. (Item 12) A program to cause a computer (201) to function as one of the means of an information processing device described in any one of items 1 through 10. This section provides a program that can accurately estimate the destination of a moving target. (Item 13) An information processing method performed by a computer (201) to estimate the destination of the movement of a dynamic target (501), A selection step (S402) to select a plurality of geographical locations (503) from around the aforementioned dynamic target, A calculation step (S403) is performed to calculate the likelihood that each of the multiple geographical locations is the destination, using the likelihood function (p(i)), A reselection step (S404) in which the plurality of geographic locations are reselected based on the likelihood at each geographic location, The process includes an estimation step (S406) for estimating the destination based on the re-selected plurality of geographic locations, An information processing method wherein the likelihood function is based on at least one of the state of the dynamic target and the position of obstacles (502) around the dynamic target. According to this section, the destination of a moving target can be estimated with high accuracy. (Item 14) A system for estimating the destination of a moving target (501), Selection means for selecting multiple geographical locations (503) from around the aforementioned dynamic target, A calculation means that uses a likelihood function (p(i)) to calculate the likelihood that each of the multiple geographic locations is the destination, A reselection means for reselecting the plurality of geographic locations based on the likelihood at each geographic location, The system comprises estimation means for estimating the destination based on the re-selected plurality of geographic locations, The likelihood function is based on at least one of the state of the dynamic target and the position of obstacles (502) around the dynamic target in the system. According to this section, the destination of a moving target can be estimated with high accuracy.

[0053] The invention is not limited to the embodiments described above, and various modifications and changes are possible within the scope of the gist of the invention. [Explanation of Symbols]

[0054] 100 Mobile object, 201 Control unit, 501 Target object, 502 Static obstacle, 503 Geographic location

Claims

1. An information processing device for estimating the destination of a moving dynamic target, Selection means for selecting multiple geographical locations from around the aforementioned dynamic target, A calculation means that uses a likelihood function to calculate the likelihood that each of the multiple geographic locations is the destination, A reselection means for reselecting the plurality of geographic locations based on the likelihood at each geographic location, The system comprises estimation means for estimating the destination based on the re-selected plurality of geographic locations, An information processing device wherein the likelihood function is based on at least one of the state of the dynamic target and the positions of obstacles around the dynamic target.

2. The information processing apparatus according to claim 1, wherein the likelihood function is based on the direction of movement of the dynamic target.

3. The information processing apparatus according to claim 2, wherein the direction of movement of the dynamic target is determined based on the orientation of the body of the dynamic target.

4. The information processing apparatus according to claim 2, wherein the likelihood function outputs a larger value the smaller the angle between the direction of movement of the dynamic target and the direction from the dynamic target to each geographical location.

5. The information processing apparatus according to claim 1, wherein the likelihood function is based on whether each geographical location overlaps with a static obstacle.

6. The information processing apparatus according to claim 5, wherein the likelihood function outputs a larger value when each geographic location overlaps with a static obstacle than when each geographic location does not overlap with a static obstacle.

7. The information processing apparatus according to claim 1, wherein the likelihood function is based on the predicted trajectory of the dynamic target as it moves toward each geographical location.

8. The information processing apparatus according to claim 7, wherein the likelihood function outputs a larger value as the angle between the trajectory and the direction of movement of the dynamic target decreases.

9. The aforementioned likelihood function is, The direction of movement of the aforementioned dynamic target and Whether each geographical location overlaps with a static obstacle, The predicted trajectory of the dynamic target as it moves toward each geographical location, An information processing apparatus according to claim 1, based on the present invention.

10. The information processing apparatus according to claim 1, further comprising control means for controlling the movement of a moving body equipped with a sensor for observing the dynamic target, based on the estimated geographical location.

11. An information processing device according to any one of claims 1 to 10, A mobile body equipped with sensors for observing dynamic targets.

12. A program for causing a computer to function as one of the means of an information processing device according to any one of claims 1 to 10.

13. An information processing method performed by a computer to estimate the destination of a moving dynamic target, A selection step of selecting multiple geographic locations from around the aforementioned dynamic target, A calculation step of using a likelihood function to calculate the likelihood that each of the multiple geographical locations is the destination, A reselection step of re-selecting the plurality of geographic locations based on the likelihood at each geographic location, The process includes an estimation step of estimating the destination based on the re-selected plurality of geographic locations, An information processing method wherein the likelihood function is based on at least one of the state of the dynamic target and the positions of obstacles around the dynamic target.

14. A system for estimating the destination of a moving dynamic target, Selection means for selecting multiple geographical locations from around the aforementioned dynamic target, A calculation means that uses a likelihood function to calculate the likelihood that each of the multiple geographic locations is the destination, A reselection means for reselecting the plurality of geographic locations based on the likelihood at each geographic location, The system comprises estimation means for estimating the destination based on the re-selected plurality of geographic locations, The likelihood function is based on at least one of the state of the dynamic target and the positions of obstacles around the dynamic target.

Images