Information processing device and control method

Abstract

An information processing device (100) has: an acquisition unit (120) that acquires information indicating an acceptance level map, an ideal congestion map, and a plurality of routes that are route candidates for an AMR (200); a calculation unit (150) that calculates a movement cost for each route by using the distance of the route, a constant that is a region present on the route and corresponds to the acceptance level indicated by a region present on the acceptance level map, the distance of a route portion that passes through said region, a constant that is a region present on the route and corresponds to congestion indicated by a region present on the ideal congestion map, and the distance of a route portion that passes through said region; a determination unit (160) that determines a route for the AMR (200) on the basis of the movement costs of each of the plurality of routes; and a control unit (170) that controls the AMR (200) so that the AMR (200) moves along the determined route and outputs guidance information.

Description

Information processing device and control method

[0001] The present disclosure relates to an information processing device and a control method.

[0002] Mobile objects such as robots can provide services to many users. However, there are users who do not accept mobile objects such as robots. Therefore, a technology that takes into account user acceptance has been proposed (see Patent Literature 1). The information processing device in Patent Literature 1 plans the behavior of the mobile object based on the acceptance of the mobile object and behavior parameters set for each user.

[0003] International Publication No. 2023 / 153221

[0004] Meanwhile, an autonomous mobile object such as a robot moves within a facility. For example, the facility is a train station. In the above technology, the autonomous mobile object moves while taking into consideration the acceptance of the autonomous mobile object. However, in the above technology, the autonomous mobile object does not move while taking into consideration the wishes of the facility operator.

[0005] The objective of the present disclosure is to move autonomous vehicles taking into consideration the acceptability and wishes of facility operators.

[0006] According to one aspect of the present disclosure, there is provided an information processing device, the information processing device including: an acquisition unit that acquires an acceptance map that represents on a map an acceptance level indicating a degree of acceptance of each of a plurality of users present in a facility for an autonomous mobile body; an ideal congestion level map that represents on the map a congestion level desired by an operator of the facility; and information indicating a plurality of routes on the map that are route candidates for the autonomous mobile body; a calculation unit that calculates a travel cost for each route using a distance of the route, a constant that is an area on the route and corresponds to the acceptance level indicated by the area on the acceptance level map, a distance of a route portion passing through the area, a constant that is an area on the route and corresponds to the congestion level indicated by the area on the ideal congestion level map, and a distance of a route portion passing through the area; a determination unit that determines a route for the autonomous mobile body based on the travel costs of each of the plurality of routes; and a control unit that controls the autonomous mobile body to travel along the determined route and output guidance information that is information for guiding a user.

[0007] According to the present disclosure, it is possible to move an autonomous vehicle while taking into consideration the acceptability and the wishes of the facility operator.

[0008] 1 is a diagram showing a control system of embodiment 1. FIG. 2 is a diagram showing hardware possessed by an information processing device of embodiment 1. FIG. 3 is a block diagram showing functions of an information processing device of embodiment 1. FIG. 4 is a diagram showing an example of an acceptance degree map of embodiment 1. FIG. 5 is a diagram showing an example of an ideal congestion degree map of embodiment 1. FIG. 6 is a diagram showing a specific example of a method for calculating travel costs of embodiment 1. FIG. 7 is a flowchart showing an example of processing executed by an information processing device of embodiment 1. FIG. 8 is a diagram showing a specific example of calculation processing of variant 2 of embodiment 1. FIG. 9 is a block diagram showing functions of an information processing device of embodiment 2. FIG. 10 is a diagram showing a specific example (part 1) of cause analysis processing of embodiment 2. FIG. 11 is a diagram showing a specific example (part 2) of cause analysis processing of embodiment 2.

[0009] Hereinafter, an embodiment will be described with reference to the drawings.

[0010] 1 is a diagram showing a control system according to a first embodiment. The control system includes an information processing device 100 and an AMR (Autonomous Mobile Robot) 200. The information processing device 100 and the AMR 200 communicate with each other via a network.

[0011] The information processing device 100 is a device that executes the control method. For example, the information processing device 100 is a server. The information processing device 100 can control the AMR 200.

[0012] The AMR 200 is also referred to as an autonomous mobile unit. For example, the AMR 200 has a display, a speaker, a camera, a temperature sensor, and a microphone. The AMR 200 is present in a facility. For example, the facility may be a station, an airport, a theme park, or the like.

[0013] Next, the hardware of the information processing device 100 will be described. Fig. 2 is a diagram showing the hardware of the information processing device of embodiment 1. The information processing device 100 is also called a computer. The information processing device 100 has a processor 101, a volatile storage device 102, and a non-volatile storage device 103.

[0014] The processor 101 controls the entire information processing device 100. For example, the processor 101 is a central processing unit (CPU) or a field programmable gate array (FPGA). The processor 101 may be a multiprocessor. The information processing device 100 may also include a processing circuit.

[0015] The volatile storage device 102 is a main storage device of the information processing device 100. For example, the volatile storage device 102 is a random access memory (RAM). The nonvolatile storage device 103 is an auxiliary storage device of the information processing device 100. For example, the nonvolatile storage device 103 is a hard disk drive (HDD) or a solid state drive (SSD).

[0016] Next, a description will be given of functions of the information processing device 100. Fig. 3 is a block diagram showing functions of the information processing device of embodiment 1. The information processing device 100 has a storage unit 110, an acquisition unit 120, an estimation unit 130, a generation unit 140, a calculation unit 150, a determination unit 160, and a control unit 170.

[0017] The storage unit 110 may be realized as a storage area secured in the volatile storage device 102 or the non-volatile storage device 103. The storage unit 110 may also be called a memory. Some or all of the acquisition unit 120, estimation unit 130, generation unit 140, calculation unit 150, determination unit 160, and control unit 170 may be realized by a processing circuit. Furthermore, some or all of the acquisition unit 120, estimation unit 130, generation unit 140, calculation unit 150, determination unit 160, and control unit 170 may be realized as program modules executed by the processor 101.

[0018] The storage unit 110 stores various information.

[0019] The acquisition unit 120 acquires an image including a plurality of users present in the facility. For example, the acquisition unit 120 acquires the image from the storage unit 110. Alternatively, for example, the acquisition unit 120 acquires the image from an external device. Note that the external device is a device that exists outside the information processing device 100. For example, the external device is a cloud server, an external memory, or the like. The illustration of the external device is omitted. Alternatively, the acquisition unit 120 may acquire the image from a surveillance camera installed in the facility.

[0020] The estimation unit 130 estimates the emotion of each of the multiple users based on the image. The estimation unit 130 performs estimation using conventional technology. For example, the estimation unit 130 estimates the emotion based on the face of the user included in the image. Note that when the acquisition unit 120 acquires a video including multiple users, the estimation unit 130 estimates the emotion of each of the multiple users based on the images that make up the video.

[0021] The acquisition unit 120 may acquire biometric information of each of the multiple users. For example, the acquisition unit 120 may acquire biometric information from wearable devices owned by the multiple users. The estimation unit 130 may estimate the emotion of each of the multiple users based on the biometric information. For example, the estimation unit 130 performs the estimation using conventional technology.

[0022] The acquisition unit 120 acquires a trained model that estimates an acceptance level indicating the degree of acceptance of the AMR 200. For example, the acquisition unit 120 acquires the trained model from the storage unit 110 or an external device. The estimation unit 130 estimates the acceptance level of each of the multiple users using the emotions of each of the multiple users and the trained model. For example, when the estimation unit 130 inputs the emotion of a certain user into the trained model, the trained model outputs the acceptance level of the user.

[0023] The acquisition unit 120 may acquire information indicating whether each of the plurality of users is in a moving state. The estimation unit 130 may further use the information to estimate the acceptance level of each of the plurality of users. The acquisition unit 120 may acquire information indicating the schedule of each of the plurality of users. The estimation unit 130 may further use the information to estimate the acceptance level of each of the plurality of users.

[0024] The estimation unit 130 may estimate the age of each of the multiple users based on the images acquired by the acquisition unit 120. The estimation unit 130 detects users who are older than a predetermined age as elderly. The estimation unit 130 subtracts a predetermined value from the acceptance level of elderly people. As will be described later, the AMR 200 may approach the user. Many elderly people do not like robots such as the AMR 200. Therefore, the information processing device 100 lowers the acceptance level if the user is elderly. Therefore, the information processing device 100 can appropriately adjust the acceptance level.

[0025] The acquisition unit 120 may acquire video including the multiple users. For example, the acquisition unit 120 acquires video from an external device or a surveillance camera. The estimation unit 130 estimates whether each of the multiple users is a commuter based on the video. For example, if a user is wearing a suit, the estimation unit 130 estimates the user as a commuter. Also, for example, if a user is not wandering around, the estimation unit 130 estimates the user as a commuter. The estimation unit 130 subtracts a predetermined value from the acceptance level of a user who is a commuter. As will be described later, the AMR 200 may approach a user. Commuters are in a hurry. Having the AMR 200 approach a commuter is a nuisance to the commuter. Therefore, the information processing device 100 lowers the acceptance level when the user is a commuter. Thus, the information processing device 100 can appropriately adjust the acceptance level.

[0026] The acquisition unit 120 may acquire video including the multiple users. For example, the acquisition unit 120 acquires video from an external device or a surveillance camera. The estimation unit 130 estimates whether each of the multiple users is a tourist based on the video. For example, if a user is looking at a tourist poster, the estimation unit 130 estimates that the user is a tourist. Also, for example, if a user is wandering around, the estimation unit 130 estimates that the user is a tourist. The estimation unit 130 adds a predetermined value to the acceptance level of the user who is a tourist. As will be described later, the AMR 200 may approach the user. The display of the AMR 200 may display tourist information, event information, etc. Therefore, when the AMR 200 approaches a tourist, the tourist becomes interested in the AMR 200. Therefore, the information processing device 100 increases the acceptance level if the user is a tourist. Thus, the information processing device 100 can appropriately adjust the acceptance level.

[0027] The acceptance level may be expressed as a numerical value or a degree. For example, when the acceptance level is expressed as a degree, the acceptance level is expressed as high, medium, or low. In the following description, the acceptance level is expressed as a degree.

[0028] The acquisition unit 120 acquires location information of each of the multiple users. The location information of each of the multiple users may be information obtained from an image or video including the multiple users. Furthermore, the location information may be information obtained from a terminal owned by each of the multiple users.

[0029] The generation unit 140 generates an acceptance map in which the acceptance of each of the plurality of users is represented on a map based on the acceptance of each of the plurality of users and the location information of each of the plurality of users. The generation unit 140 may generate the acceptance map based on the acceptance of each of the plurality of users, the location information of each of the plurality of users, and a map showing the facility. An example of the acceptance map is shown below.

[0030] FIG. 4 is a diagram showing an example of an acceptance map according to the first embodiment. FIG. 4 shows an acceptance map 300. FIG. 4 also shows a case where acceptance is expressed as a degree. The acceptance region is represented by a rectangle with the user at the center. FIG. 4 shows that user 1 has a high acceptance. FIG. 4 shows that users 2 to 4 have a medium acceptance. FIG. 4 shows that user 5 has a low acceptance. For ease of explanation, FIG. 4 shows users. An acceptance map is a map that shows regions that indicate acceptance. Therefore, users are not actually included in an acceptance map.

[0031] The acquisition unit 120 acquires the acceptability map from the generation unit 140 .

[0032] The acquisition unit 120 acquires an ideal congestion level map, which represents the congestion level desired by the facility operator on a map, from the storage unit 110 or an external device. The congestion level may be expressed numerically or as a degree. In the following description, the congestion level is expressed as a degree. The congestion level is also referred to as an ideal congestion level. An example of the ideal congestion level map is shown below.

[0033] FIG. 5 is a diagram showing an example of an ideal congestion level map according to the first embodiment. FIG. 5 shows an ideal congestion level map 400. Area 410 is an area where the operator desires a low level of congestion. Areas 420 and 430 are areas where the operator desires a high level of congestion. For example, the ideal congestion level map 400 is created by the operator of a facility. For example, the facility may be a train station. If an event is being held at the station, the operator sets the congestion levels of areas 420 and 430, which are areas of the event venue, to "high." The ideal congestion level map 400 may be changed depending on the time of day.

[0034] The acquisition unit 120 acquires map information of the facility from the storage unit 110 or an external device. The calculation unit 150 calculates multiple routes using the map information. For example, the calculation unit 150 calculates multiple routes using an A-star search algorithm. The multiple routes are route candidates for the AMR 200 on the map. The acquisition unit 120 acquires information indicating the multiple routes from the calculation unit 150.

[0035] The calculation unit 150 calculates the travel cost for each route using the distance of the route, a constant corresponding to the acceptability of an area on the route that exists on the acceptability map, the distance of the route portion that passes through the area, a constant corresponding to the congestion level of an area on the route that exists on the ideal congestion level map, and the distance of the route portion that passes through the area. Note that the distance of the route is calculated by the calculation unit 150 using a map.

[0036] A method for calculating travel costs will be described using a specific example. FIG. 6 is a diagram showing a specific example of a method for calculating travel costs in embodiment 1. FIG. 6 shows an acceptability map and an ideal congestion map superimposed on each other. Point X is the starting point of AMR 200. Point Y is the end point of AMR 200. It is assumed that two routes have been calculated. The first route is the route indicated by a solid line. The second route is the route indicated by a dashed line.

[0037] The constants corresponding to the acceptance level are explained below. The lower the acceptance level, the larger the value set for the constant. Constant C corresponding to "low" acceptance level １is set to 2. The constant C corresponding to the "medium" acceptance level ２ is set to -1. The constant C corresponding to "high" acceptance ３ is set to -3.

[0038] The constants corresponding to the congestion levels indicated by the areas on the ideal congestion level map will be explained. The lower the ideal congestion level, the smaller the value set for the constant. Constant D corresponding to "low" ideal congestion level １ is set to -2. The constant D corresponding to the ideal congestion level "high" ２ is set to 2.

[0039] A method for calculating the travel cost of the solid line route will now be described. The calculation unit 150 calculates the travel cost of the solid line route using equation (1).

[0040]

[0041] Specifically, the distance of the solid line from point X to point Y is set to 150. The distance ab is set to 15. The distances cd, ef, and gh are set to 10. The distance AB is set to 30. The calculation unit 150 calculates the travel cost to be "15".

[0042] For example, the distance of the route is the distance of the solid line from point X to point Y. The constant corresponding to the acceptance level of an area on the route and on the acceptance level map is constant C ２ and constant C ３ The distances of the route portions passing through the area are the distance ab, the distance cd, the distance ef, and the distance gh. The constant corresponding to the congestion level indicated by the area on the route and on the ideal congestion level map is the constant D １ The distance of the path portion passing through the region is the distance AB.

[0043] A method for calculating the travel cost of the broken line route will now be described. The calculation unit 150 calculates the travel cost of the broken line route using equation (2).

[0044]

[0045] Specifically, the distance of the dashed line from point X to point Y is set to 130. The distance ij is set to 15. The distance CD is set to 10. The calculation unit 150 calculates the travel cost to be "180".

[0046] The determination unit 160 determines a route for the AMR 200 based on the travel costs of each of the multiple routes. Specifically, the determination unit 160 determines the route with the smallest travel cost among the multiple travel costs as the route for the AMR 200. The determination unit 160 may also determine the route with the second smallest travel cost among the multiple travel costs as the route for the AMR 200. For example, in the case of FIG. 6 , the determination unit 160 determines the route indicated by the solid line as the route for the AMR 200.

[0047] The control unit 170 controls the AMR 200 so that the AMR 200 moves along the determined route and outputs guidance information. Specifically, the control unit 170 transmits to the AMR 200 information indicating the determined route and an instruction for the AMR 200 to move along the route. The control unit 170 also transmits an instruction to output guidance information to the AMR 200. As a result, the AMR 200 moves along the determined route and outputs the guidance information. The guidance information may be displayed on a display of the AMR 200. The guidance information may also be output as audio from a speaker of the AMR 200. The guidance information is information for guiding a user. The guidance information may also be expressed as information for guiding a user to a location desired by a facility operator. For example, the guidance information is information for guiding a user to an event venue. For example, the guidance information is information for guiding a user to another location to alleviate a highly crowded location. For example, the guidance information is advertisements.

[0048] Next, the processing executed by the information processing device 100 will be described using a flowchart. FIG. 7 is a flowchart showing an example of the processing executed by the information processing device of embodiment 1. (Step S11) The acquisition unit 120 acquires an image including multiple users present in a facility. (Step S12) The estimation unit 130 estimates the emotions of each of the multiple users based on the image. (Step S13) The estimation unit 130 estimates the acceptance level of each of the multiple users using the emotions of each of the multiple users and the trained model. (Step S14) The generation unit 140 generates an acceptance level map based on the acceptance level of each of the multiple users and the location information of each of the multiple users. (Step S15) The acquisition unit 120 acquires an ideal congestion level map.

[0049] (Step S16) The acquisition unit 120 acquires map information of the facility. (Step S17) The calculation unit 150 calculates multiple routes using the map information. (Step S18) The calculation unit 150 calculates the travel cost for each of the multiple routes. (Step S19) The determination unit 160 determines a route for the AMR 200 based on the travel cost for each of the multiple routes. (Step S20) The control unit 170 controls the AMR 200 so that the AMR 200 moves along the determined route and outputs guidance information.

[0050] According to the first embodiment, the information processing device 100 calculates the travel cost using the acceptance map and the ideal congestion map. As described above, the ideal congestion map reflects the wishes of the facility operator. Therefore, the calculated travel cost takes into account the acceptance and the wishes of the facility operator. The information processing device 100 then controls the AMR 200 based on the travel cost. Therefore, the information processing device 100 can move the AMR 200 (i.e., the autonomous vehicle) taking into account the acceptance and the wishes of the facility operator.

[0051] In the above, the case where the information processing device 100 generates the acceptance map has been described. The acceptance map may be generated by an external device. In the case where the external device generates the acceptance map, the acquisition unit 120 acquires the acceptance map from the external device.

[0052] In the above description, the information processing device 100 calculates multiple routes. The multiple routes may be calculated by an external device. When the external device calculates multiple routes, the acquisition unit 120 acquires information indicating the multiple routes from the external device.

[0053] The information processing device 100 may perform the following processes. The generation unit 140 generates a future congestion map, which is a future congestion map. For example, the generation unit 140 generates the future congestion map based on the current congestion map and the current pedestrian flow. The generation unit 140 may generate the future congestion map using a trained model. The generation unit 140 may generate the future congestion map by taking into account the weather, temperature, humidity, event information, time, day of the week, and the like. The acquisition unit 120 acquires the future congestion map from the generation unit 140. Here, the future congestion map may be generated by an external device. When the external device generates the future congestion map, the acquisition unit 120 acquires the future congestion map from the external device. The calculation unit 150 compares the future congestion map with the ideal congestion map, and calculates a travel cost if the future congestion map and the ideal congestion map differ. If the future congestion map and the ideal congestion map are the same, the calculation unit 150 does not calculate a travel cost. For example, it may be considered that the information processing device 100 does not execute the processes from step S17 onwards. Therefore, by adding the process of comparing the future congestion degree map with the ideal congestion degree map, the load on the information processing device 100 may be reduced.

[0054] Variation 1 of Embodiment 1 In the first embodiment, the case where the acceptability and the ideal congestion degree are treated equally is described. In Variation 1 of the first embodiment, a case where weights are added to the acceptability and the ideal congestion degree will be described.

[0055] The acquisition unit 120 acquires a weight (hereinafter, "acceptance weight") to be assigned to the acceptance indicated by an area on the acceptance map and a weight (hereinafter, "congestion weight") to be assigned to the congestion indicated by an area on the ideal congestion map from the storage unit 110 or an external device. The acceptance weight and the congestion weight may be expressed as a percentage. For example, the acceptance weight and the congestion weight are set so that the sum of the acceptance weight and the congestion weight is 100%. For example, the acceptance weight is set to 70%. The congestion weight is set to 30%. In this example, the travel cost is calculated with greater consideration given to the acceptance. Also, for example, the acceptance weight is set to 30%. The congestion weight is set to 70%. In this example, the travel cost is calculated with greater consideration given to the ideal congestion.

[0056] The calculation unit 150 calculates, for each route, the distance of the route, a constant corresponding to the acceptability of an area that is on the route and exists on the acceptability map, the distance of the route portion that passes through the area, a constant corresponding to the congestion degree of an area that is on the route and exists on the ideal congestion degree map, the distance of the route portion that passes through the area, and an acceptability weight W １ and the congestion weight W ２ The travel cost is calculated using

[0057] A specific example of the travel cost will be described with reference to Fig. 6. First, a method for calculating the travel cost of the solid line route will be described. The calculation unit 150 calculates the travel cost of the solid line route using equation (3).

[0058]

[0059] Specifically, the distance of the solid line from point X to point Y is set to 150. The distance ab is set to 15. The distances cd, ef, and gh are set to 10. The distance AB is set to 30. The acceptability weight W １ is set to 0.7. ２ The calculation unit 150 calculates the movement cost as "79.8".

[0060] Next, a method for calculating the travel cost of the broken line route will be described. The calculation unit 150 calculates the travel cost of the broken line route using equation (4).

[0061]

[0062] Specifically, the distance of the dashed line from point X to point Y is set to 130. The distance ij is set to 15. The distance CD is set to 10. The calculation unit 150 calculates the travel cost to be "157".

[0063] According to the first modification of the first embodiment, the information processing device 100 can change the importance of the acceptability and the ideal congestion degree by using weights.

[0064] Variation 2 of Embodiment 1 When AMR 200 moves, the density of people on the route (hereinafter referred to as "people density") affects the travel cost. Furthermore, when AMR 200 moves, the movement of people on the route affects the travel cost. Therefore, in Variation 2 of Embodiment 1, a case will be described in which the people density and people flow are allowed to affect the route distance, thereby optimizing the travel cost.

[0065] The acquisition unit 120 acquires the person density on each of the multiple routes. The person density may be estimated by the estimation unit 130. When the estimation unit 130 estimates the person density, the person density is estimated based on an image including multiple users. Then, the acquisition unit 120 acquires the person density from the estimation unit 130. The person density may also be estimated by an external device. When the external device estimates the person density, the acquisition unit 120 acquires the person density from the external device.

[0066] The acquisition unit 120 acquires information indicating the flow of people on each of the multiple routes. The flow of people may be estimated by the estimation unit 130. When the estimation unit 130 estimates the flow of people, the flow of people is estimated based on video including multiple users. The acquisition unit 120 then acquires the information indicating the flow of people from the estimation unit 130. The flow of people may also be estimated by an external device. When the external device estimates the flow of people, the acquisition unit 120 acquires the information indicating the flow of people from the external device.

[0067] The calculation unit 150 calculates the distance of each of a plurality of routes affected by the person density and the person flow. The calculation process will be described using a specific example.

[0068] FIG. 8 is a diagram showing a specific example of the calculation process of the second modification of the first embodiment. FIG. 8 shows a route from point X to point Y. The human density from point X1 to point X2 is medium. The human density from point X3 to point X4 is low. A weight is associated with each human density. The higher the human density, the larger the value set for the weight. For example, for a low human density Cr １ is set to -2. ２ is set to -1. ３ is set to 2. In the above, the case where the human density is expressed as a degree has been shown. The human density may be expressed as a numerical value. When the human density is expressed as a numerical value, a weight is associated with the numerical human density.

[0069] The direction of the people flow from point X1 to point X2 is the same as the planned movement route of AMR200. The direction of the people flow from point X3 to point X4 is opposite to the planned movement route of AMR200. The calculation unit 150 adds a weight when the direction of the people flow and the planned movement route of AMR200 is the same. For example, the calculation unit 150 adds 0.5. The calculation unit 150 adds a weight when the direction of the people flow and the planned movement route of AMR200 is opposite. For example, the calculation unit 150 adds 2. In this way, when the direction of the people flow and the planned movement route of AMR200 is opposite, the weight is larger than the weight when the direction of the people flow and the planned movement route of AMR200 is the same.

[0070] In the specific example of FIG. 8, the calculation unit 150 calculates the distance of the route using equation (5).

[0071]

[0072] For example, the calculated distance is used as one of the distances in equations (1) to (4) (that is, the XY distance).

[0073] According to the second modification of the first embodiment, the information processing device 100 can optimize the travel cost.

[0074] Furthermore, the information processing device 100 may add a weight to the calculated distance as in Modification 1 of Embodiment 1. A case where a weight is added to the calculated distance will be described.

[0075] The acquisition unit 120 calculates a weight (hereinafter referred to as distance weight W ３ ) is acquired from the storage unit 110 or an external device. １ and congestion weight W ２ and distance weight W ３ may be expressed as a percentage. For example, the acceptability weight W １ and congestion weight W ２ and distance weight W ３ The acceptance weight W １ and congestion weight W ２ and distance weight W ３ For example, the acceptability weight W １ is set to 50%. ２ is set to 25%. ３ is set to 25%. In this example, the travel cost is calculated with greater consideration given to acceptability.

[0076] The calculation unit 150 calculates, for each route, the distance of the route, a constant corresponding to the acceptability of an area that is on the route and exists on the acceptability map, the distance of the route portion that passes through the area, a constant corresponding to the congestion degree of an area that is on the route and exists on the ideal congestion degree map, the distance of the route portion that passes through the area, and an acceptability weight W １ and the congestion weight W ２ and the distance weight W ３ For example, equation (3) can be transformed into equation (6).

[0077]

[0078] Furthermore, for example, equation (4) is transformed into equation (7).

[0079]

[0080] In this way, the information processing device 100 can change the importance of the acceptability, the ideal congestion degree, and the travel distance by using the weights.

[0081] The above describes a case where both information indicating the pedestrian density and the pedestrian flow are acquired. Then, the description also describes a case where both information indicating the pedestrian density and the pedestrian flow are used. The acquisition unit 120 may acquire information indicating the pedestrian density or the pedestrian flow. The calculation unit 150 may perform calculations using information indicating the pedestrian density or the pedestrian flow. Therefore, the acquisition unit 120 may acquire at least one of the pedestrian density on each of the multiple routes and information indicating the pedestrian flow on each of the multiple routes. The calculation unit 150 may calculate the distance of each of the multiple routes affected by at least one of the pedestrian density and the pedestrian flow.

[0082] Modification 3 of First Embodiment The information processing device 100 may reflect the wishes of the facility manager in the travel cost. The process will be described in detail.

[0083] The acquisition unit 120 acquires a designated weight W ４ The calculation unit 150 obtains, for each route, the distance of the route, a constant corresponding to the acceptability of an area on the route and present on the acceptability map, the distance of the route portion passing through the area, a constant corresponding to the congestion degree of an area on the route and present on the ideal congestion degree map, the distance of the route portion passing through the area, and the acceptability weight W １ and the congestion weight W ２ and the distance weight W ３ and the specified weight W ４ The travel cost is calculated using the number of users on the route (hereinafter referred to as the number of users). For example, equation (6) is transformed into equation (8). In the case of FIG. 6, the number of users is 4.

[0084]

[0085] Furthermore, for example, equation (7) can be transformed into equation (9): In the case of FIG.

[0086]

[0087] According to the third modification of the first embodiment, the information processing device 100 can reflect the wishes of the facility manager in the travel cost.

[0088] Second Embodiment Next, a second embodiment will be described. In the second embodiment, differences from the first embodiment will be mainly described. Furthermore, in the second embodiment, descriptions of the commonalities between the first embodiment and the second embodiment will be omitted.

[0089] 9 is a block diagram showing the functions of the information processing device of embodiment 2. The information processing device 100 further includes an analysis unit 180. Part or all of the analysis unit 180 may be realized by a processing circuit. Alternatively, part or all of the analysis unit 180 may be realized as a program module executed by the processor 101. The functions of the analysis unit 180 will be described later.

[0090] The generator 140 generates a current congestion map, which is a current congestion map. For example, the generator 140 generates the current congestion map based on an image including a plurality of users.

[0091] The acquisition unit 120 acquires the current congestion level map from the generation unit 140. Here, the current congestion level map may be generated by an external device. When the external device generates the current congestion level map, the acquisition unit 120 acquires the current congestion level map from the external device.

[0092] Using the acceptance map and the current congestion map, if an area where a user with an acceptance level below a predetermined threshold exists overlaps with an area where the congestion level is above a predetermined threshold, the analysis unit 180 analyzes that the user's acceptance level is low because the user is located in a highly congested area. In other words, if an area where a user with a low acceptance level exists overlaps with an area with a high congestion level, the analysis unit 180 analyzes that the user's acceptance level is low because the user is located in a highly congested area. A specific example is shown.

[0093] FIG. 10 is a diagram showing a specific example (part 1) of the cause analysis process according to the second embodiment. FIG. 10 illustrates a state in which an area where a user with low acceptance exists overlaps with an area with high congestion. The analysis unit 180 analyzes that the user's acceptance is low because the user exists in a highly congested area. For example, the analysis unit 180 may analyze that the user is in a bad mood or feeling bad because the user exists in a highly congested area. Therefore, the analysis unit 180 may analyze that the user's acceptance is low. In this way, the information processing device 100 can analyze the cause of the user's low acceptance.

[0094] When the analysis is performed, the control unit 170 controls the AMR 200 to move to the vicinity of the user and to output information for moving people in the vicinity to another location. The process will be described in detail. For example, the control unit 170 transmits an instruction for the AMR 200 to move to the vicinity of the user. As a result, the AMR 200 moves to the vicinity of the user. The control unit 170 transmits an instruction for the AMR 200 to output information for moving people in the vicinity to another location. As a result, for example, the AMR 200 displays an image on the display stating, "Please move to the event venue." The AMR 200 may also output a voice message stating, "Please move to the event venue." from a speaker. Under the control of the control unit 170, people in the vicinity move to another location. Therefore, the degree of congestion around the user decreases. Therefore, the information processing device 100 can improve user acceptance.

[0095] Next, a case where an area where users with low acceptance levels exist does not overlap with an area where congestion levels are high will be described. A specific example is shown. Fig. 11 is a diagram showing a specific example (part 2) of the cause analysis process of the second embodiment. Fig. 11 shows a state where an area where users with low acceptance levels exist does not overlap with an area where congestion levels are high.

[0096] Using the acceptance map and the current congestion map, when an area where a user whose acceptance level is below a predetermined threshold exists does not overlap with an area where a congestion level is above a predetermined threshold, the acquisition unit 120 acquires at least one of a video showing the user's surroundings, a temperature around the user, and sound data showing sounds around the user. For example, the control unit 170 instructs the AMR 200 to capture an image of the user's surroundings. The AMR 200 captures an image of the user's surroundings. The AMR 200 transmits the image of the user's surroundings to the information processing device 100. This allows the acquisition unit 120 to acquire the image. Alternatively, the acquisition unit 120 may acquire the image from a surveillance camera installed in a facility. Alternatively, for example, the control unit 170 instructs the AMR 200 to measure the temperature around the user. The AMR 200 measures the temperature around the user. The AMR 200 transmits the temperature to the information processing device 100. This allows the acquisition unit 120 to acquire the temperature. For example, the control unit 170 instructs the AMR 200 to record sounds around the user. The AMR 200 records the sounds around the user. The AMR 200 transmits sound data indicating the sounds to the information processing device 100. This allows the acquisition unit 120 to acquire the sound data.

[0097] The analysis unit 180 analyzes the cause of low user acceptance using at least one of the video, the temperature, and the sound data. For example, if the video contains dust, the analysis unit 180 analyzes that dust is the cause. For example, if the temperature is equal to or higher than a threshold, the analysis unit 180 analyzes that high temperature is the cause. For example, if the sound pressure of the sound indicated by the sound data is equal to or higher than a threshold, the analysis unit 180 analyzes that noise is the cause. In this way, the information processing device 100 can analyze the cause of low user acceptance.

[0098] When the analysis is completed, the control unit 170 transmits information indicating the cause to a terminal used by the facility manager, thereby enabling the manager to recognize the cause and take measures to improve the situation.

[0099] The embodiments are merely examples, and various modifications are possible within the scope of the present disclosure. Furthermore, the features of the embodiments can be combined with each other as appropriate.

[0100] 100 Information processing device, 101 Processor, 102 Volatile storage device, 103 Non-volatile storage device, 110 Storage unit, 120 Acquisition unit, 130 Estimation unit, 140 Generation unit, 150 Calculation unit, 160 Determination unit, 170 Control unit, 180 Analysis unit, 200 AMR, 300 Acceptance map, 400 Ideal congestion map, 410, 420, 430 Area.

Claims

1. An information processing device having: an acquisition unit that acquires an acceptance map that shows on a map the acceptance levels of each of multiple users present in a facility, indicating the degree to which they will accept an autonomous mobile unit; an ideal congestion map that shows on the map the congestion level desired by an operator of the facility; and information indicating multiple routes on the map that are candidate routes for the autonomous mobile unit; a calculation unit that calculates a travel cost for each route using the route distance, a constant that is an area on the route and corresponds to the acceptance level indicated by the area on the acceptance map, the distance of a route portion that passes through the area, a constant that is an area on the route and corresponds to the congestion level indicated by the area on the ideal congestion map, and the distance of a route portion that passes through the area; a determination unit that determines a route for the autonomous mobile unit based on the travel costs of each of the multiple routes; and a control unit that controls the autonomous mobile unit to move along the determined route and output guidance information that is information for guiding a user.

2. An information processing device as described in claim 1, further comprising: an estimation unit; and a generation unit; wherein the acquisition unit acquires an image including the plurality of users, a trained model, and location information of each of the plurality of users; the estimation unit estimates the emotions of each of the plurality of users based on the image, estimates the acceptance level of each of the plurality of users using the emotions of each of the plurality of users and the trained model, estimates the ages of each of the plurality of users based on the image, detects users older than a predetermined age as elderly, and subtracts a predetermined value from the acceptance level of the elderly; and the generation unit generates the acceptance level map based on the acceptance level of each of the plurality of users and the location information of each of the plurality of users.

3. An information processing device as described in claim 1, further comprising: an estimation unit; and a generation unit; wherein the acquisition unit acquires a video including the plurality of users, a trained model, and location information of each of the plurality of users; the estimation unit estimates the emotions of each of the plurality of users based on images constituting the video, estimates the acceptance level of each of the plurality of users using the emotions of each of the plurality of users and the trained model, estimates whether each of the plurality of users is a commuter based on the video, and subtracts a predetermined value from the acceptance level of users who are commuters; and the generation unit generates the acceptance level map based on the acceptance level of each of the plurality of users and the location information of each of the plurality of users.

4. An information processing device as described in claim 1, further comprising: an estimation unit; and a generation unit; wherein the acquisition unit acquires a video including the plurality of users, a trained model, and location information of each of the plurality of users; the estimation unit estimates the emotions of each of the plurality of users based on images constituting the video, estimates the acceptance level of each of the plurality of users using the emotions of each of the plurality of users and the trained model, estimates whether each of the plurality of users is a tourist based on the video, and adds up the acceptance level of users who are tourists by a predetermined value; and the generation unit generates the acceptance level map based on the acceptance level of each of the plurality of users and the location information of each of the plurality of users.

5. An information processing device according to any one of claims 1 to 4, wherein the acquisition unit acquires a future congestion map, which is a future congestion map; and the calculation unit calculates the travel cost when the future congestion map and the ideal congestion map are different, and does not calculate the travel cost when the future congestion map and the ideal congestion map are the same.

6. An information processing device according to any one of claims 1 to 5, wherein the acquisition unit acquires at least one of a people density, which is the density of people present on each of the plurality of routes, and information indicating the flow of people on each of the plurality of routes, and the calculation unit calculates the distance of each of the plurality of routes affected by at least one of the people density and the flow of people.

7. An information processing device as described in any one of claims 1 to 6, wherein the acquisition unit acquires an acceptance weight which is a weight to be added to the acceptance indicated by the area present on the acceptance map and a congestion weight which is a weight to be added to the congestion indicated by the area present on the ideal congestion map, and the calculation unit calculates, for each route, a travel cost using the route distance, a constant corresponding to the acceptance indicated by the area that is on the route and present on the acceptance map, the distance of the route portion passing through the area, a constant corresponding to the congestion indicated by the area that is on the route and present on the ideal congestion map, the distance of the route portion passing through the area, the acceptance weight, and the congestion weight.

8. The information processing device described in claim 7, wherein the acquisition unit acquires a distance weight which is a weight to be added to the distance of the route, and the calculation unit calculates the travel cost for each route using the distance of the route, a constant corresponding to the acceptability indicated by the area that is on the route and exists on the acceptability map, the distance of the route portion passing through the area, a constant corresponding to the congestion indicated by the area that is on the route and exists on the ideal congestion map, the distance of the route portion passing through the area, the acceptability weight, the congestion weight, and the distance weight.

9. The information processing device described in claim 8, wherein the acquisition unit acquires a designated weight that is a weight designated by an operator of the facility, and the calculation unit calculates the travel cost for each route using the route distance, a constant corresponding to the acceptance indicated by an area that is on the route and exists on the acceptance map, the distance of the route portion that passes through the area, a constant corresponding to the congestion indicated by an area that is on the route and exists on the ideal congestion map, the distance of the route portion that passes through the area, the acceptance weight, the congestion weight, the distance weight, the designated weight, and the number of users present on the route.

10. An information processing device as described in claim 1, further comprising an analysis unit, wherein the acquisition unit acquires a current congestion map, which is a map of the current congestion level, and the analysis unit uses the acceptance map and the current congestion level map to analyze that, if an area where a user whose acceptance level is below a predetermined threshold exists overlaps with an area where the congestion level is above a predetermined threshold, the user is located in a location where the congestion level is high, and therefore the acceptance level of the user is low.

11. The information processing device described in claim 10, wherein the control unit controls the automatic moving body to move to the vicinity of the user when the analysis is performed, and outputs information for the automatic moving body to move people present in the vicinity to another location.

12. An information processing device as described in claim 1, further comprising an analysis unit, wherein the acquisition unit acquires a current congestion map that is a current congestion map, and, using the acceptance map and the current congestion map, when an area where there are users whose acceptance level is below a predetermined threshold does not overlap with an area where the congestion level is above a predetermined threshold, acquires at least one of video showing the user's surroundings, temperature around the user, and sound data showing sounds around the user, and the analysis unit analyzes the cause of the user's low acceptance level using at least one of the video, temperature, and sound data, and when the analysis is performed, the control unit transmits information showing the cause to a terminal used by an operator of the facility.

13. A control method in which an information processing device acquires an acceptance map on a map showing the acceptance levels of each of a plurality of users present in a facility, which indicate the degree to which each of the users will accept an autonomous mobile unit, an ideal congestion map on the map showing the congestion level desired by the operator of the facility, and information showing a plurality of routes on the map that are candidate routes for the autonomous mobile unit; calculates a travel cost for each route using the route distance, a constant that is an area on the route and corresponds to the acceptance level indicated by the area on the acceptance map, the distance of a route portion that passes through the area, a constant that is an area on the route and corresponds to the congestion level indicated by the area on the ideal congestion map, and the distance of a route portion that passes through the area; determines a route for the autonomous mobile unit based on the travel costs of each of the plurality of routes; and controls the autonomous mobile unit to travel along the determined route and output guidance information that is information for guiding the user.

Images