Agent control system and agent control method

Abstract

To provide an agent control system in which an agent can perform a predetermined task as well while performing monitoring.SOLUTION: An agent control system comprises: a monitoring situation evaluation unit 305 that calculates a monitoring evaluation index that indicates whether a monitoring state in each location within a predetermined region is good or bad on the basis of monitoring information transmitted from an agent moving within the predetermined region; a global path generation unit 306 that generates a path plan for the agent on the basis of business management information containing a movement destination of the agent and a task type and the monitoring evaluation index; and a path plan transmission unit 309 that transmits data for the path plan to the agent.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] This invention relates to an agent control system, etc. [Background technology]

[0002] Automated transport systems (AGVs) are used in various fields to transport goods or people from a point within a designated area to a destination using agents (transport vehicles such as automobiles). In areas where controlled objects (e.g., autonomous vehicles) and uncontrolled objects (e.g., manually driven cars or people) coexist, such as in urban areas, it is desirable for AGVs to plan routes that minimize the risk of collisions between agents and uncontrolled objects.

[0003] Regarding such technology, for example, Patent Document 1 states that "In the mobile body distribution unit, the search degree and the tracking degree each satisfy predetermined levels, the risk potential to be monitored is determined, and multiple mobile bodies are assigned to the risk potential determined to be monitored." [Prior art documents] [Patent Documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2019-16306 [Overview of the project] [Problems that the invention aims to solve]

[0005] However, the technology described in Patent Document 1 only considers monitoring within a predetermined area and does not specifically consider other tasks (e.g., transporting goods or people). If the technology described in Patent Document 1 were to perform predetermined tasks other than monitoring, a dedicated agent for those tasks would be required, potentially necessitating a large number of agents.

[0006] Therefore, the object of the present invention is to provide an agent control system, etc., that enables an agent to perform predetermined tasks while simultaneously monitoring. [Means for solving the problem]

[0007] To solve these problems, the agent control system according to the present invention comprises: a monitoring status evaluation unit that calculates a monitoring evaluation index indicating the quality of monitoring at each location within a predetermined area based on monitoring information transmitted from an agent moving within a predetermined area; a route plan generation unit that generates a route plan for the agent based on business management information including the agent's destination and task type, and the monitoring evaluation index; and a route plan transmission unit that transmits the route plan data to the agent. The route planning generation unit sets a monitoring task ratio, which indicates the proportion of the importance of monitoring relative to the task, in association with the agent, based on the type of task included in the business management information. The higher the monitoring task ratio, the more the route plan is generated such that the agent travels along a route that includes sections with relatively high monitoring evaluation indicators. The higher the safety of the agent traveling through the section, the lower the monitoring evaluation indicator for that section is set. That's what we decided. Further details will be explained within the embodiments. [Effects of the Invention]

[0008] According to the present invention, it is possible to provide an agent control system, etc., in which an agent can perform predetermined tasks while simultaneously monitoring. [Brief explanation of the drawing]

[0009] [Figure 1] This is a functional block diagram of the agent control system according to the first embodiment. [Figure 2] This is a functional block diagram showing the system configuration of the agent in the agent control system according to the first embodiment. [Figure 3] This is an explanatory diagram relating to the dimensions and orientation of the agent in the agent control system according to the first embodiment. [Figure 4] This is a functional block diagram showing the system configuration of a base station in the agent control system according to the first embodiment. [Figure 5A] This figure shows an example of map information in the agent control system according to the first embodiment. [Figure 5B]This is a partially enlarged view of region K1 in the map information of Figure 5A used in the agent control system according to the first embodiment. [Figure 6A] This is an explanatory diagram of the coefficient αoj used to calculate the monitoring and evaluation index in the agent control system according to the first embodiment. [Figure 6B] This is an explanatory diagram of the coefficient αmj used to calculate the monitoring and evaluation index in the agent control system according to the first embodiment. [Figure 7A] This is an explanatory diagram showing the agent's path in the comparative example. [Figure 7B] This is an explanatory diagram showing the global path of an agent in the agent control system according to the first embodiment. [Figure 8] This is an explanatory diagram showing the relationship between the monitoring and evaluation index Cmj and the weight Wmj in the agent control system according to the first embodiment. [Figure 9A] This is an explanatory diagram showing the traffic conditions at time t=k in an area within a predetermined region in the agent control system according to the first embodiment. [Figure 9B] This is an explanatory diagram showing the traffic conditions at time t=k+1 in an area within a predetermined region in the agent control system according to the first embodiment. [Figure 10] This is an explanatory diagram showing the conditions for avoiding contact with obstacles in the agent control system according to the first embodiment. [Figure 11] This is a flowchart showing the operation flow of the agent control unit included in the agent control system according to the first embodiment. [Figure 12] This is a functional block diagram of the agent control system according to the second embodiment. [Figure 13] This is a functional block diagram showing the system configuration of a base station in the agent control system according to the second embodiment. [Figure 14] This is an explanatory diagram showing an example of the operation of the monitoring rate calculation unit in the agent control system according to the second embodiment. [Figure 15]This is an explanatory diagram of a theme park to which the agent control system according to the third embodiment is applied. [Figure 16A] This is an explanatory diagram showing the agent's path in the comparative example. [Figure 16B] This is an explanatory diagram showing the global path of an agent in the agent control system according to the third embodiment. [Figure 17] This is an explanatory diagram showing the travel path of an agent in the agent control system according to the third embodiment. [Modes for carrying out the invention]

[0010] ≪First Embodiment≫ Figure 1 is a functional block diagram of the agent control system W1 according to the first embodiment. The agent control system W1 calculates a path plan (time-series data such as coordinates, attitude, and velocity) for each agent 200-1 to 200-n (controllable mobile objects such as robots and vehicles) within a predetermined area (for example, a specific region or theme park), and moves agents 200-1 to 200-n based on this path plan.

[0011] In the first embodiment, as an example, a system in which an autonomous vehicle delivers people and goods within a predetermined area will be described. Note that the application of the first embodiment is not limited to autonomous vehicles within a predetermined area; as described later, it can also be applied to transport vehicles within areas such as ports and theme parks. Furthermore, agents 200-1 to 200-n are mobile entities that perform autonomous driving based on commands from the base station 100 (server). Note that if a predetermined agent assumes the role of the base station 100, the base station 100 can be omitted.

[0012] As shown in Figure 1, the agent control system W1 is configured to include a base station 100 that calculates the paths of agents 200-1 to 200-n within a predetermined area, and agents 200-1 to 200-n that move according to the paths calculated by the base station 100.

[0013] <Base station> The base station 100 calculates the travel routes of agents 200-1 to 200-n. The base station 100 includes a volatile memory element, RAM 101 (Random Access Memory), a non-volatile memory element, ROM 102 (Read Only Memory), and a CPU 103 (Central Processing Unit) which includes a processor. In addition to the above configuration, the base station 100 also includes a bus 104, an input / output interface 105, and a communication device 106. The program stored in ROM 102 is read and loaded into RAM 101, and the CPU 103 executes various processes.

[0014] Bus 104 is a signal line for interconnecting RAM 101, ROM 102, CPU 103, and input / output interface 105. The input / output interface 105 is used for data transmission via communication device 106. Communication device 106 performs predetermined wireless communication with agents 200-1 to 200-n. Communication device 106 is connected to bus 104 via input / output interface 105.

[0015] Note that Figure 1 shows an example where there is one base station 100, but the number of base stations 100 is not limited to this. For example, multiple base stations may perform the role of a single server. Alternatively, one or more of agents 200-1 to 200-n may perform the role of base station 100.

[0016] <Agent 200> Agents 200-1 to 200-n perform monitoring within a predetermined area and follow the route based on route information transmitted wirelessly from the base station 100. Hereafter, the term "agent 200" will be used to refer to individual vehicles of agents 200-1 to 200-n, as well as to the agents collectively. As shown in Figure 1, agent 200 includes a RAM 201, a ROM 202, a CPU 203, a bus 204, and an input / output interface 205. In addition to the above configuration, agent 200 also includes a communication device 206, an external environment recognition sensor 207, a position measurement device 208, an attitude measurement device 209, and a control device 210.

[0017] In the example shown in Figure 1, RAM 201, ROM 202, and CPU 203 are connected to the input / output interface 205 via bus 204. Additionally, a communication device 206, an external environment recognition sensor 207, a position measurement device 208, an attitude measurement device 209, and a control device 210 are also connected to the input / output interface 205. An agent 200 with this configuration moves based on route information transmitted wirelessly from the base station 100, and also monitors the driving environment using the external environment recognition sensor 207, transmitting the results to the base station 100.

[0018] The communication device 206 is a terminal that enables wireless communication such as Bluetooth, Wi-Fi, or a mobile phone network. The external environment recognition sensor 207 is a sensor that measures the surrounding environment of the agent 200. Examples of such external environment recognition sensors 207 include LiDAR (Light Detection And Ranging) and cameras.

[0019] The position measurement device 208 is a device that measures the position of agent 200 on a map. For example, GNSS (Global Navigation Satellite System) is used for processing by the position measurement device 208. Alternatively, instead of the position measurement device 208, the position and orientation of agent 200 on the map may be calculated based on SLAM (Simultaneous Localization and Mapping) technology using LiDAR or a camera. The attitude measurement device 209 is a device that measures the orientation and orientation of agent 200. For example, an IMU (Inertia Measurement Unit) or an encoder may be used as such an attitude measurement device 209. The control device 210 is a device that converts the speed command and orientation command of agent 200 into the actuator output of agent 200. For example, a control microcontroller may be used as such a control device 210.

[0020] <Description of Agent 200> Figure 2 is a functional block diagram showing the system configuration of agent 200. As shown in Figure 2, the CPU 203 of agent 200 has a functional configuration comprising a state detection unit 211, a follow control unit 212, and a risk monitoring unit 213. The state detection unit 211 calculates the state (position and orientation) of agent 200 based on the output values ​​of the position measurement device 208 as well as the output values ​​of the attitude measurement device 209.

[0021] Figure 3 is an explanatory diagram regarding the dimensions and orientation of Agent 200. In the example shown in Figure 3, agent 200 is configured as a vehicle and is equipped with front wheels 221, 221 and rear wheels 222, 222. The position and orientation of agent 200 are represented by state p(t) = [x(t), y(t), θ(t)] (where t is time). The orientation θ(t) shown in Figure 3 indicates the direction of agent 200 relative to a predetermined direction. The steering angle φ(t) is the angle indicating the turning direction of agent 200 relative to the orientation θ(t). The length L shown in Figure 3 is the longitudinal distance between the front wheels 221 and the rear wheels 222. The orientation θ(t), steering angle φ(t), and length L are used in the processing of the follow control unit 212, etc. (see Figure 2).

[0022] The tracking control unit 212, shown in Figure 2, performs feedback control to minimize the difference between the target path r(t) and the state p(t), based on the target path r(t)=[xr(t),yr(t),θr(t)] of the agent 200 acquired from the base station 100 (see Figure 1) via the communication device 206, and the state p(t)=[x(t),y(t),θ(t)] of the agent 200 acquired from the state detection unit 211. The tracking control unit 212 then outputs control values ​​such as steering amount and acceleration / deceleration (accelerator amount, brake amount) to the control device 210.

[0023] The control device 210 controls the agent 200's tires to rotate at a predetermined speed and the steering to rotate at a predetermined angle, based on the control values ​​calculated by the tracking control unit 212. The risk monitoring unit 213 detects other vehicles (vehicles not belonging to agent 200) and pedestrians around agent 200 based on sensor information acquired from the external environment recognition sensor 207, and transmits the detection results, along with the location information of agent 200, to the base station 100 (see Figure 1) via the communication device 206.

[0024] <Explanation of base station 100> Figure 4 is a functional block diagram showing the system configuration of base station 100. As shown in Figure 4, the base station 100 includes an agent information management unit 301, a monitoring information management unit 302, a map information management unit 303, a business management unit 304, and an agent control unit 300. The agent control unit 300 has the function of calculating the movement path of agent 200 (see Figure 1). As shown in Figure 4, the agent control unit 300 is connected to the agent information management unit 301, the monitoring information management unit 302, the map information management unit 303, and the business management unit 304. The processing of the agent control unit 300 is executed on the CPU 103 of the base station 100 (see Figure 1).

[0025] <Agent Information Management Department 301> The agent information management unit 301 manages individual agent information (referred to as agent individual information) of agents 200 traveling within a predetermined area. This agent individual information includes the dimensions of agent 200, numerical values ​​indicating the performance of the external environment recognition sensor 207 (see Figure 2), and the cruising range of agent 200. However, the agent individual information managed by the agent information management unit 301 is not limited to these; for example, it may also include the number of passengers agent 200 can carry and the maximum load capacity of luggage.

[0026] For example, the agent individual information may be information collected in advance and stored in the ROM 102 of the base station 100 (see Figure 1), or the base station 100 may periodically acquire and update agent individual information managed by a server building other than the base station 100 (not shown). The agent individual information is output from the agent information management unit 301 to the monitoring status evaluation unit 305, as well as to the route correction unit 308.

[0027] <Monitoring information management department 302> The monitoring information management unit 302 collects, in chronological order, the position information of vehicles and pedestrians other than the agent 200 (see FIG. 1) within a predetermined area, in addition to the position of the agent 200. Such monitoring information is collected, for example, by transmitting, via the communication device 206, the measured value of the position measuring device 208 (see FIG. 1) of the agent 200 and the position information of surrounding vehicles and pedestrians extracted from the sensor information of the external recognition sensor 207 (see FIG. 1) to the base station 100. The monitoring information collected in this way is output from the monitoring information management unit 302 to the monitoring state evaluation unit 305. Note that the method of collecting the monitoring information is not limited to this. For example, a fixed sensor (not shown) may be attached to an intersection or the like in the city, and information on surrounding pedestrians and vehicles obtained from the fixed sensor may be transmitted to the base station 100. As such a fixed sensor, for example, a camera or LiDAR is used.

[0028] <Map information management unit 303> The map information management unit 303 manages the map information of the predetermined area 500 (see FIG. 5A). The map information is output from the map information management unit 303 to the global route generation unit 306.

[0029] FIG. 5A is an explanatory diagram showing an example of map information. For example, the map information of the predetermined area 500 (the area indicated by dots) shown in FIG. 5A is stored in advance in the map information management unit 303 (see FIG. 4).

[0030] FIG. 5B is a partially enlarged view of the area K1 in the map information of FIG. 5A. The map information is represented, for example, by a graph G(V j (j = 0, 1, 2, ··· N) and nodes (nodes) V provided at the start and end points of each edge E j . j In the first embodiment, the E j -th edge at a point on the map and on the road corresponding to the map is defined as the section E j , and the V j -th node is defined as the node V j , and the V j -th node is defined as the node V jLet's assume that.

[0031] Map information may, for example, be stored in the ROM 102 of the base station 100 (see Figure 1) with a map of a predetermined area 500 created in advance, or the base station 100 may receive periodically updated maps via wireless communication from a predetermined map management server (not shown) outside the base station 100.

[0032] <Business Management Department 304> The business management unit 304 shown in Figure 4 manages the destination and main task set for each agent 200 (see Figure 1). The destination information for agent 200 is contained in the map information, specifically node V. j It is managed based on the following. The destination information may be location information based on a predetermined coordinate system, or it may be latitude and longitude information. The main task (task) is a task related to the service of transporting people or cargo by agent 200. Examples of such main tasks include, but are not limited to, transport, repositioning, vehicle dispatch, and power supply (refueling).

[0033] For example, a server (not shown) that receives customer requests for vehicle dispatch, etc., may assign destination information and a main task to agent 200 and periodically transmit this information to base station 100 via wireless communication.

[0034] <Agent Control Unit 300> As shown in Figure 4, the agent control unit 300 includes a monitoring status evaluation unit 305, a global route generation unit 306 (route plan generation unit), a speed limit calculation unit 307, a route correction unit 308, and a route plan transmission unit 309. Based on individual agent information, monitoring information, map information, and business information (destination / main task), the agent control unit 300 calculates the route for each agent 200 and transmits the calculation result to each agent 200.

[0035] <Monitoring Status Evaluation Unit 305> The monitoring status evaluation unit 305 generates a risk map showing monitoring evaluation indicators for each location based on individual agent information obtained from the agent information management unit 301, monitoring information obtained from the monitoring information management unit 302, and information on the destination and main task of agent 200 obtained from the business management unit 304. The monitoring evaluation indicator is a numerical value that indicates the quality of the monitoring status for each location within a predetermined area 500 (see Figure 5A).

[0036] Furthermore, the aforementioned risk map is a map in which the values ​​of the monitoring and evaluation indicators are associated with each location within a predetermined area 500. Note that the risk map does not necessarily have to be a graph including edges Ej and nodes Vj (see Figure 5B); for example, it may be grid data obtained by dividing the predetermined area 500 (see Figure 5A) into a grid.

[0037] For example, the higher the value of the monitoring evaluation index, the higher the risk (risk of contact with other vehicles or people, etc.) of that location, and the more likely it is to require monitoring. On the other hand, the lower the value of the monitoring evaluation index, the more likely it is that the location is well monitored and the lower the risk. Note that within a predetermined time ΔT, section E j The more pedestrians and vehicles that pass through section E within a predetermined time ΔT, the higher the value of the monitoring evaluation index. j The more vehicles (i.e., agents 200) responsible for the monitoring task that pass through, the lower the value of the monitoring evaluation index becomes. The predetermined time ΔT is, for example, the period during which the calculation of the monitoring evaluation index is repeated.

[0038] In the first embodiment, the monitoring status evaluation unit 305 evaluates each section E linked to the map information. j The monitoring status is being evaluated. Edge E at time (T+ΔT) j Monitoring evaluation index C mj (T+ΔT) is given by a predetermined coefficient α, for example, as shown in equation (1) below. oj or coefficient α mj , coefficient α envj , coefficient α esp The product of these is the monitoring evaluation index C at time T. mjIt is calculated by multiplying by (T). Note that the coefficient α oj Section E j This value is determined by the number of vehicles and pedestrians that pass through within a predetermined time ΔT. Coefficient α mj Section E j This value is determined by the number of agents 200 responsible for monitoring tasks that pass through within a predetermined time ΔT. (Coefficient α) envj Section E j This value reflects factors such as road surface conditions and accident rates. (Coefficient α) esp This is a coefficient that reflects the passage of time (forgetting coefficient). Note that this is the monitoring and evaluation index C. mj (T) and coefficient α mj The subscript "m" indicates monitoring.

[0039]

number

[0040] <Explanation of monitoring and evaluation indicators> Figure 6A shows the coefficient α used in calculating the monitoring and evaluation index. oj This is an explanatory diagram. Note that the horizontal axis in Figure 6A represents the interval E within a predetermined time. j This represents the number of pedestrians and vehicles that passed through, with the vertical axis being the coefficient α. oj This is the value of the coefficient α, as shown in Figure 6A. oj For example, the intercept is 1 and the slope is a o This can be expressed as a positive linear function. That is, the interval E j The more pedestrians and vehicles that pass through, the higher the coefficient α. oj A large value is set for this.

[0041] Figure 6B shows the coefficient α used in calculating the monitoring and evaluation index. mj This is an explanatory diagram. Note that the horizontal axis in Figure 6B represents the interval E within a predetermined time. j This represents the number of surveillance vehicles (i.e., agents 200 responsible for the surveillance task) that passed through, and the vertical axis is the coefficient α. mj This is the value of the coefficient α, as shown in Figure 6B. mjFor example, the intercept is 1 and the slope is a m This can be expressed as a negative linear function. That is, the interval E j The more surveillance vehicles that pass through, the higher the coefficient α mj A small value is set for the coefficient α. oj (See Figure 6A) and coefficient α mj (See Figure 6B) These do not necessarily have to be linear functions; for example, they may be changed exponentially, or pre-created tabular data based on statistical data on traffic volume and accident rates may be used.

[0042] The coefficient α included in the above equation (1) envj This is determined by considering factors such as the accident rate and visibility based on prior surveys. For example, for locations with a high accident rate, such as intersections, a coefficient α is set. envj The coefficient α is set to a value greater than 1, and is configured so that the monitoring evaluation index increases over time. In addition, for safe sections such as roads with good visibility or sections where fences are installed at the boundary between sidewalks and roadways, the coefficient α is set. envj The value is set low (for example, to 1 or less), and furthermore, the monitoring evaluation index is set to decrease over time. A location-dependent coefficient α is applied to the monitoring evaluation index. envj By including this information, it becomes possible to reflect the need for monitoring not only in terms of pedestrian traffic and vehicle volume, but also in terms of the specific conditions at the site.

[0043] Furthermore, the coefficient α takes into account the passage of time. esp The monitoring and evaluation index is set using a positive constant so that it increases over time. By defining the monitoring and evaluation index in this way, a risk map can be created in which the monitoring and evaluation index is high in sections with high pedestrian and traffic volume, sections with a high number of accidents, and sections with little traffic from monitoring vehicles. Note that the values ​​of the monitoring and evaluation index for each section in the risk map change moment by moment.

[0044] <Global route generation unit 306> The global route generation unit 306 (route plan generation unit) shown in Figure 4 generates a global route (route plan) for agent 200 based on business management information including the destination and task type of agent 200, and monitoring and evaluation indicators. Specifically, the global route generation unit 306 generates a global route for each agent 200 (see Figure 1) based on graph-based search methods such as Dijkstra's algorithm. The term "global route" refers to the general path that agent 200 takes to reach a predetermined destination.

[0045] Figure 7A is an explanatory diagram showing the agent's path in the comparative example. Note that the symbols CAV1 and CAV2 shown in Figure 7A represent vehicles that are examples of agent 200 (see Figure 1). Hereafter, the term "agent" will also be used to refer to these symbols CAV1 and CAV2. Figure 7A shows a comparative example route plan that considers only the conventional route length. That is, the shortest route Gp1 is generated for agent CAV1 to travel to destination Tg2 after moving to destination Tg1 and picking up a passenger. In addition, the shortest route Gp2 is generated for another agent CAV2 to travel to destination Tg3.

[0046] <Explanation of operation of the global route generation unit 306> Figure 7B is an explanatory diagram showing the global path of an agent in the agent control system according to the first embodiment. For example, suppose agents CAV1 and CAV2, located within a predetermined area 500, patrol (i.e., monitor) while performing tasks such as transportation, repositioning, and charging. Specifically, "patrolling" means that, based on a route plan transmitted from the agent control unit 300 (see Figure 4), agents CAV1 and CAV2 move within the predetermined area 500, detecting people and other vehicles in their surroundings using the external recognition sensor 207 (see Figure 1), and transmitting the detection results as monitoring information to the monitoring information management unit 302 (see Figure 4). Agent CAV1 performs a dispatch task to destination Tg1, and then performs a transport task to destination Tg2 with passengers on board. At this time, suppose the monitoring evaluation index for section E1 shown in Figure 7B is relatively high. Agent CAV1, moving with passengers, performs a transport task, and if it selects the shortest route, a route Gp1 that passes through section E1 will be selected.

[0047] In contrast, in the first embodiment, agent CAV1 is configured to take a detour to reduce risk and select route Gp3 to the destination Tg2. This increases the reliability of agent CAV1 when performing the transport task. Incidentally, agent CAV1 monitors its own travel route while performing the transport task.

[0048] Furthermore, the agent CAV2 shown in Figure 7B is not carrying passengers and is traveling to destination Tg3 to supply power. Also, the monitoring evaluation index for section E2 is assumed to be relatively high. In this case, the first embodiment assigns a monitoring task to agent CAV2 to improve the monitoring status of sections with high monitoring evaluation indicators within a predetermined area 500. Specifically, agent CAV2 selects a route Gp4 that passes through section E2 different from the shortest route Gp2 shown in Figure 7A. Then, agent CAV2 uses the external environment recognition sensor 207 (see Figure 2) to recognize the surroundings of section E2, and after improving the monitoring evaluation index of section E2 based on the above equation (1), proceeds to destination Tg3.

[0049] Thus, in the first embodiment, agents CAV1 and CAV2 perform both monitoring and main tasks (transportation, dispatching, repositioning, power supply, etc.). This eliminates the need to install dedicated monitoring agents (not shown) or fixed sensors (not shown) in a predetermined area 500 (see Figure 5A), thereby increasing the overall efficiency of the system and reducing costs.

[0050] <Monitoring Task Ratio β> i > To realize the aforementioned path planning, in the first embodiment, the global path generation unit 306 (see Figure 4) assigns monitoring tasks to the agent 200 according to the type of main task and the capabilities (sensing range, resolution, environmental resistance, etc.) of the external recognition sensor 207 (see Figure 2) mounted on the agent 200. The ratio of the importance of monitoring to the main task (task) is called the monitoring task ratio β. i (i is the identification number of agent 200).

[0051] For example, the monitoring task ratio β i The higher the value, the more likely the agent 200 is to select a path that passes through a route with a relatively high monitoring and evaluation index of the surrounding environment. i The lower the value, the lower the monitoring evaluation index and the safer the selected route. As mentioned above, the monitoring evaluation index is for each section E of the predetermined area 500 (see Figure 5A). j (See Figure 5B) is calculated. On the other hand, the monitoring task ratio β i Each of the 200 agents is configured individually to provide a one-to-one correspondence.

[0052] <Monitoring Task Ratio β> i How to set it up > Monitoring task ratio β i This is determined based on the type of main task of agent 200 and the sensor capabilities (sensing range, resolution, environmental resistance, etc.) of the external environment recognition sensor 207 (see Figure 2) installed on agent 200. iThis may be determined based on factors other than those mentioned above. For example, the range of agent 200 may be considered, and environmental factors such as weather and time of day may also be added. To give a specific example, the longer the range of agent 200, the higher the monitoring task ratio β. i It may be set to be higher. Also, in the case of bad weather such as rain or snow, the monitoring task ratio β is higher compared to when it is sunny or cloudy. i It may be set to be higher. In addition, during nighttime hours, the monitoring task ratio β is higher compared to other times. i It may be set to be higher.

[0053] Data identifying the main task assigned to agent 200 is output from the business management unit 304 (see Figure 4) to the global route generation unit 306. Examples of the types of main tasks for agent 200 include transport, repositioning, dispatching, power supply, and warehousing. Of these, for tasks that do not involve carrying passengers or cargo (repositioning, dispatching, power supply, warehousing), the global route generation unit 306 monitors the task ratio β. i The ratio of monitoring tasks assigned to agent 200 is increased. In other words, the global route generation unit 306 (route planning generation unit) has a higher monitoring task ratio β when the main task is movement for repositioning, dispatching, or power supply than when the main task is the transport of people or luggage. i Set it to a high value.

[0054] On the other hand, for agent 200, which is assigned the transport task as its main task, the global route generation unit 306 monitors the task ratio β. i The monitoring task ratio β is reduced by lowering it and decreasing the proportion of monitoring tasks assigned to Agent 200. Note that Agent 200's main task may switch midway, such as from "vehicle dispatch" to "transportation." In addition to the timing of such main task switches, the monitoring task ratio β is adjusted in accordance with changes in Agent 200's remaining range, weather, and time of day. i It also fluctuates.

[0055] Monitoring task ratio β iFor example, this is set to a predetermined value for each main task. Also, if the external environment recognition sensor 207 (see Figure 2) installed on each agent 200 is different, the global path generation unit 306 (path planning generation unit) will set the monitoring task ratio β to be higher the higher the performance of the external environment recognition sensor 207 (sensing range, resolution, durability, etc.). i Set this to a high value. Specifically, the monitoring task ratio β takes into account the external environment recognition sensor 207 (see Figure 2). i The added value is pre-set for each of the 200 agents, and this added value is added to a predetermined monitoring task ratio based on the type of main task, thereby determining the monitoring task ratio β for each of the 200 agents. i It may be possible to calculate it in this way.

[0056] <Interval E in route calculation> j Weight calculation method > Section E used to calculate the path for agent 200 j The weight of w j For example, section E j Weights related to the path length w dj And, section E j Weights related to the magnitude of the monitoring evaluation indicator w mj Using and , it is calculated based on the following equation (2).

[0057]

number

[0058] The global route generation unit 306 (see Figure 4) generates, for example, weights w when agent 200 moves to a predetermined destination. j The global routes for agent 200 are set so that the sum of the factors is minimized. The weights w related to route length are included in equation (2). dj From the map information, section E j This is set by pre-measuring the route length. j The longer the distance, the heavier the weight. dj The value of also increases. Furthermore, the weight of the magnitude of the monitoring and evaluation indicator w mj For example, the monitoring task ratio β iand monitoring evaluation index C mj It is calculated based on

[0059] FIG. 8 shows the monitoring evaluation index C mj and the weight w mj It is an explanatory diagram showing the relationship with Note that the horizontal axis of FIG. 8 is the interval E j The monitoring evaluation index C in mj That is. Also, the vertical axis of FIG. 8 is the monitoring evaluation index C mj The weight w related to mj That is. For example, when the monitoring task ratio β i is equal to or greater than a predetermined value β th the greater the monitoring evaluation index C mj the smaller the weight w mj is set (see the solid line M1 in FIG. 8). That is, the global route generation unit 306 (the route planning generation unit is such that the higher the monitoring task ratio β i the higher the monitoring evaluation index C mj generates a route plan so that the agent 200 travels on a relatively high route. As a result, the agent 200 with a relatively high monitoring task ratio β i prioritizes monitoring of routes with a poor monitoring situation. Note that the predetermined value β th is a threshold value of the monitoring task ratio β mj used as a criterion for determining whether to use either of the straight lines M1 and M2 shown in FIG. 8 when the global route generation unit 306 sets the weight w i and is set in advance. i is a threshold value of the monitoring task ratio β

[0060] Also, when the monitoring task ratio β i is less than the predetermined value β th the greater the monitoring evaluation index C mj the greater the weight w mj is set (see the dashed line M2 in FIG. 8). That is, the global route generation unit 306 (see FIG. 4) increases the weight w mj of a route with a large monitoring evaluation index C and high risk mj This can suppress, for example, the agent 200 carrying people or goods from traveling on a route with a poor monitoring situation.

[0061] Note that weight mj The calculation method is not limited to the example in Figure 8. For example, monitoring evaluation index C mj And weight lol mj The slope of the line showing the monitoring task ratio β i It may also be made to be a function of w. mj is the monitoring evaluation index C mj The weight w may also change exponentially. j The calculation formula is not limited to formula (2), but for example, the monitoring task ratio β i To increase the influence, the global route generation unit 306 may use the following equation (3). Note that the range of the monitoring task ratio βi included in equation (3) is 0 ≤ β i The result is ≤ 1.

[0062]

number

[0063] The global route generation unit 306 (see Figure 4) calculates the interval E using the following procedure. j The weight of w j Using this method, the global paths for each of the 200 agents are calculated using graph-based search techniques such as Dijkstra's algorithm.

[0064] <Speed ​​limit calculation unit 307> The speed limit calculation unit 307 shown in Figure 4 calculates the monitoring evaluation index C calculated by the monitoring status evaluation unit 305 (see Figure 4). mj The monitoring task ratio β calculated by the global route generation unit 306 (see Figure 4) is as follows: i Based on this, the speed limit for Agent 200 is calculated. The method for calculating the speed limit will be described later.

[0065] <Route correction unit 308> The path correction unit 308 shown in Figure 4 corrects the path of agent 200. Specifically, the path correction unit 308 refers to the global path calculated by the global path generation unit 306 (see Figure 4), and further generates a target path for agent 200 to follow, using the speed limit calculated by the speed limit calculation unit 307 as a constraint. Note that for path correction, it is possible to explicitly incorporate speed constraints by using, for example, a model predictive control framework.

[0066] Figure 9A is an explanatory diagram showing the traffic conditions at time t=k in an area within a predetermined region. In the example in Figure 9A, it is assumed that agent CAV4 is equipped with an external environment recognition sensor 207 with a wide sensing range (see Figure 2) (see the triangle with a dot). Also in Figure 9A, the time-series positions of agents CAV3 and CAV4 at each calculation step are indicated by black triangles.

[0067] At time t=k (where k is the calculation step), as shown in Figure 9A, agent CAV3 is performing the transport task, while agent CAV4 is performing the return task. Both agents CAV3 and CAV4 are assumed to be moving towards node V5, passing through intersection CR13. Note that section E within intersection CR13... j As a monitoring evaluation metric, it is assumed that the same value is shared between agents CAV3 and CAV4.

[0068] <Explanation of the operation of the route correction unit 308> As shown in Figure 9A, if the monitoring evaluation index for intersection CR13 is relatively large, it is risky for agent CAV3 carrying people or cargo to pass through. Therefore, in the first embodiment, a speed constraint is imposed on agent CAV3 to delay the time it takes to reach intersection CR13 or to lower its speed when passing through intersection CR13, thereby reducing the risk. On the other hand, when agent CAV4, which is equipped with an external recognition sensor 207 with high sensing capabilities and is being transported, passes through intersection CR13, the risk is lower compared to agent CAV3 because there is no concern about damage to cargo, etc. Therefore, there is no particular need for the speed limit calculation unit 307 (see Figure 4) to impose a speed constraint.

[0069] Figure 9B is an explanatory diagram showing the traffic conditions in a predetermined area at time t=k+1. For example, in the situation shown in Figure 9A (time t=k), if the external environment recognition sensor 207 of agent CAV4 senses the situation at intersection CR13, the monitoring evaluation index C of intersection CR13 is... m13 If this improves, the risk of intersection CR13 will be reduced. Thus, monitoring evaluation index C m13 If the value improves, the risk for agent CAV3 when passing through intersection CR13 is reduced, and the speed limit calculation unit 307 (see Figure 4) releases the speed constraint imposed on agent CAV3.

[0070] Furthermore, if there are pedestrians or other vehicles (vehicles not belonging to agent 200) at intersection CR13, the speed limit calculation unit 307 (see Figure 4) may impose constraints on agent CAV4 to avoid collisions with obstacles. This allows agent CAV4 to generate a route that avoids pedestrians or vehicles, or a route that slows down or stops immediately before encountering pedestrians or vehicles.

[0071] <Formulation of a system using model predictive control> The vector containing the position and orientation of the i-th agent 200 is p iThe node on the global route Gpi of the i-th agent 200, calculated by the global route generation unit 306 (see Figure 4), is V i Furthermore, the virtual target position is set to r i Then, it can be expressed as shown in equations (4a) and (4b) below. Also, vector p i and virtual target position r i The deviation between e i Let it be defined as shown in equation (4c) below. Note that k represents the calculation step (time).

[0072]

number

[0073]

number

[0074]

number

[0075] The motion model of agent 200 can be formulated, for example, as shown in equation (5). Note that the velocity v included in equation (5) i and steering angle φ i This corresponds to the control command of agent 200. Also, L is the longitudinal distance between the front wheel 221 and the rear wheel 222 of agent 200 (see Figure 3).

[0076]

number

[0077] Also, the velocity v of the i-th agent 200 i and steering angle φ i A control command vector u that combines these elements. i We define it by equation (6).

[0078]

number

[0079] Furthermore, by discretizing equation (5) with a predetermined sampling period Δt, we obtain the following equation (7).

[0080]

number

[0081] The route correction unit 308 (see Figure 4) determines the position p of agent 200 at each time k. i (k) and the virtual target location r on the global route Gpi. i The deviation e between (k) and i (k) becomes small, the command vector u i Calculate (k).

[0082] Furthermore, through a formulation using model predictive control, Q i ,R i With the weight matrix and Np as the prediction step, the following equation (8) for the evaluation function J is obtained. Equation (8) is used to optimize the path from a given time k0 to time (Np+k0-1).

[0083]

number

[0084] In model predictive control, the optimal control input u is determined to minimize the evaluation function J, expressed by equation (8), at each time step k. i (k) is calculated. The optimal control input u obtained in this way i By substituting (k) into equation (7), the position (x(k), y(k)) and orientation θ(k) of agent 200 at each time k are calculated. Then, time-series data (data from time k0 to Np steps ahead) identified by the position (x(k), y(k)) and orientation θ(k) is generated.

[0085] <Monitoring Task Ratio β> i Speed ​​constraints depending on the conditions > The speed limit calculation unit 307 shown in Figure 4 has a monitoring task ratio β i In addition, section E j Monitoring and evaluation index C mj Based on this, for example, the velocity constraint expressed by equation (9) below is calculated. This imposes a constraint on the predetermined evaluation function J, and a predetermined constraint is imposed on the velocity of agent 200.

[0086]

number

[0087] In other words, monitoring evaluation index C mj a predetermined threshold C th Higher than, and monitoring task ratio β i is a predetermined value β th If less than, the speed of agent 200 v i The predetermined speed limit v slow It can be kept below the following. Also, in other cases, the speed of agent 200 v i The predetermined speed upper limit v max It can be kept below. Note that the speed limit v slow The value of is the speed limit v max It shall be lower than this. Thus, the speed limit calculation unit 307 (see Figure 4) monitors the task ratio β i is a predetermined value β th If it is less than the monitoring evaluation index C mj Speed ​​limit v when driving agent 200 in an area where the relative speed is high slow The monitoring task ratio β i is a predetermined value β th In the above cases, the speed limit (speed limit v max ) should be lower than ). Using the above equation (9), the monitoring task ratio β i Agent 200, which has a low rating, is subject to the monitoring evaluation index C. mj It can be set to travel at a low speed in areas with high humidity.

[0088] Then, the route correction unit 308 corrects the travel path of the agent 200 so as to keep the agent 200's travel speed below the speed limit and avoid contact between the agent 200 and surrounding objects, based on a predetermined speed limit and monitoring information.

[0089] Furthermore, the methods for imposing speed constraints are not limited to the conditions described above. For example, if agent 200 is performing a transport task, the monitoring evaluation index C mj To impose speed constraints before entering high-speed areas, the monitoring evaluation index C for the next section that agent 200 will travel is used. mj Based on this, the speed limit calculation unit 307 (see Figure 4) may impose speed constraints on each agent 200. The speed limit v at this time slow The speed should ideally be sufficient to adequately react to sudden movements such as vehicles stepping out into the road. Also, the speed limit v max For example, the lower of the agent 200's maximum speed or the legal speed limit is used.

[0090] <Constraints regarding obstacle avoidance> Figure 10 is an explanatory diagram showing the conditions for avoiding contact with obstacles. Agent 200 may, for example, impose constraints on the evaluation function J described above regarding the relative distance between Agent 200 and other objects in order to avoid contact with vehicles (including other Agent 200) or pedestrians. As shown in Figure 10, the width of the i-th Agent 200 is w i Let the length be L. i Therefore, Agent 200 is given the radius ra in equation (10) i It can be enclosed in a circle.

[0091]

number

[0092] Furthermore, the distance between the i-th agent 200, the obstacle Q1 that may come into contact with the agent 200, and the agent 200 itself is expressed by the following equation (11).

[0093]

number

[0094] Therefore, if the constraint condition in equation (12) below is met, contact between the i-th agent 200 and the obstacle Q1 can be avoided. Here, r obj This represents the size of obstacles Q1, such as pedestrians and other vehicles. obj The value may be, for example, a value calculated by the external environment recognition sensor 207 (see Figure 2), or it may be a value that is not related to the type of obstacle Q1 and is set in advance.

[0095]

number

[0096] The path correction unit 308 (see Figure 4) calculates a control input sequence U(k) = [U1(k)···UN(k)] that minimizes the evaluation function J in equation (8) under the constraints of equation (12). This allows each agent 200 to calculate an efficient travel path while avoiding collisions with other vehicles or pedestrians.

[0097] <Route planning and transmission unit 309> The route planning transmission unit 309 shown in Figure 4 transmits route planning data to each agent 200. Specifically, the route planning transmission unit 309 transmits the route calculated by the route correction unit 308 (see Figure 4) to each agent 200 via wireless communication. Each agent 200 performs predetermined follow-up control based on the route transmitted by the route planning transmission unit 309.

[0098] <Flowchart of Agent Control Unit> Figure 11 is a flowchart showing the operation flow of the agent control unit (see also Figure 4 as appropriate). First, in step S601, the agent control unit 300 obtains individual agent information (agent individual information) of the agent 200 to be controlled from the agent information management unit 301. Next, in step S602, the agent control unit 300 obtains destination information and task information for agent 200 from the business management unit 304. In step S603, the agent control unit 300 acquires monitoring information from the monitoring status evaluation unit 305, including the position of the agent 200 and the current positions of pedestrians and vehicles within the predetermined area 500.

[0099] In step S604, the agent control unit 300 calculates monitoring and evaluation indices for each section within the predetermined area 500 using the monitoring and evaluation unit 305 (monitoring and evaluation processing). Specifically, the agent control unit 300 calculates monitoring and evaluation indices for each section based on the position of the agent 200 and the current positions of pedestrians and vehicles within the predetermined area 500, obtained from the monitoring and evaluation unit 305.

[0100] In step S605, the agent control unit 300 calculates the global route of agent 200 using the global route generation unit 306, and the monitoring task ratio β i The agent control unit 300 calculates the global route Gpi and monitoring task ratio β for each agent 200 based on the monitoring and evaluation index for each section calculated in step S604, the map information acquired by the map information management unit 303, and the destination information and main task information of the agent 200 acquired by the business management unit 304. i The result is calculated. For agent 200, for which the global route has already been calculated, the previous global route calculation result may be used to reduce the calculation time.

[0101] Next, in step S606, the agent control unit 300 calculates the speed limit for agent 200 using the speed limit calculation unit 307. Specifically, the agent control unit 300 uses a risk map showing the monitoring and evaluation indicators for each point calculated by the monitoring status evaluation unit 305 and the monitoring task ratio β calculated by the global route generation unit 306. i Based on this, the speed limit for agent 200 is calculated.

[0102] In step S607, the agent control unit 300 corrects the path of agent 200 using the path correction unit 308. Specifically, the agent control unit 300 calculates the path between nodes based on the speed limit of agent 200 calculated by the speed limit calculation unit 307 and the obstacle information around agent 200. In step S608, the agent control unit 300 transmits the route information calculated in step S607 to each agent 200 via wireless communication using the route planning transmission unit 309 (route planning transmission process). Upon receiving the route information from the base station 100 (see Figure 1), each agent 200 performs tracking control within a predetermined area 500 based on the route information. By repeating the above process, the agent control unit 300 controls each agent 200 within the predetermined area 500.

[0103] <Effects> According to the first embodiment, agents 200 within a predetermined area 500 are assigned monitoring tasks according to their respective capabilities and the type of main task they are performing. This eliminates the need for agents (not shown) that only perform monitoring or fixed sensors (not shown), allowing monitoring and transport to be performed with a smaller number of agents 200 overall. As a result, the overall efficiency of the system is increased, and operating costs can be reduced. Furthermore, the agent control unit 300 calculates the paths of the agents 200 based on monitoring evaluation indicators, enabling efficient path planning while maintaining the reliability of each agent 200. Thus, according to the first embodiment, an agent control system W1 is provided in which agents 200 can perform both monitoring and predetermined tasks.

[0104] ≪Second Embodiment≫ The second embodiment differs from the first embodiment in that the agent control unit 300A (see Figure 12) includes a monitoring rate calculation unit 310 (see Figure 12), and sets a predetermined monitoring rate in accordance with a monitoring evaluation index based on the detection results of the fixed sensor 400, etc. (see Figure 12). Other aspects are the same as the first embodiment. Therefore, the parts that differ from the first embodiment will be described, and the overlapping parts will be omitted from the explanation.

[0105] Figure 12 is a functional block diagram of the agent control system W2 according to the second embodiment. As shown in Figure 12, the agent control system W2 consists of a base station 100A, agents 200-1 to 200-n, and fixed sensors 400-1 to 400-m. The fixed sensors 400-1 to 400-m are, for example, cameras and are installed at intersections within a predetermined area 500 (see Figure 5A). The moment-by-moment detection results from the fixed sensors 400-1 to 400-m are transmitted to the base station 100A. The fixed sensors 400-1 to 400-m are collectively referred to as fixed sensors 400.

[0106] In the second embodiment, an example is described in which monitoring is performed within a predetermined area 500 (see Figure 5A) by fixed sensors 400 installed in places with high traffic volume of people and vehicles, such as intersections, and agents 200 that are responsible for monitoring tasks. By installing multiple fixed sensors 400, the sensing capability of the entire system is improved, but at the same time, the communication volume of the entire system also increases. Therefore, in the second embodiment, based on the respective monitoring evaluation indicators for each location, the monitoring rate of agents 200 and fixed sensors 400 is set higher in places with poor monitoring conditions or high traffic volume, and lower in places with low traffic volume or low pedestrian and vehicle traffic volume. This makes it possible to reduce the amount of communication while appropriately monitoring within the predetermined area 500.

[0107] <Monitoring rate control when fixed sensors are present> Figure 13 is a functional block diagram showing the system configuration of base station 100A. As shown in Figure 13, the agent control unit 300A includes a monitoring state evaluation unit 305, a global route generation unit 306, a speed limit calculation unit 307, a route correction unit 308, and a route plan transmission unit 309, as well as a monitoring rate calculation unit 310. The unit calculates the movement path of agent 200 (see Figure 12), as well as the monitoring rates of agent 200 and fixed sensors 400, and transmits the calculation results to agent 200 and fixed sensors 400.

[0108] <Agent Information Management Department 301> The agent information management unit 301 shown in Figure 13 holds individual information for the fixed sensor 400 (see Figure 12) in addition to the individual information for the agent 200 (see Figure 12). The individual information for the fixed sensor 400 includes the installation location of the fixed sensor 400 and sensor information (sensing range, resolution, environmental resistance, etc.).

[0109] <Monitoring rate calculation unit 310> Figure 14 is an explanatory diagram showing an example of the operation of the monitoring rate calculation unit (see also Figure 13 as appropriate). In Figure 14, "Sensor Acquisition" refers to the operation in which the fixed sensor 400 (see Figure 12) and the external environment recognition sensor 207 of the agent 200 (see Figure 12) generate monitoring information. Furthermore, "Monitoring Processing" in Figure 14 refers to the process in which the fixed sensor 400 and the agent 200 transmit monitoring information to the base station 100A (see Figure 12). Also, in the graph on the left side of Figure 14, the horizontal axis represents time, and the vertical axis represents the monitoring evaluation index C. mj The solid line graph in Figure 14 represents the monitoring and evaluation index C at a given location. mj The graph shows the trend, and the dashed line represents the monitoring evaluation index C in a different location. mj This shows the trend.

[0110] The monitoring rate calculation unit 310 calculates the communication rate (i.e., monitoring rate) of the monitoring information of the agent 200 and the fixed sensor 400 based on the individual information of the agent 200 and the fixed sensor 400 obtained from the agent information management unit 301, as well as the monitoring information obtained from the monitoring status evaluation unit 305. The monitoring rate calculated in this way is transmitted to the agent 200 and the fixed sensor 400 via the route planning and transmission unit 309.

[0111] The monitoring rate is the number of times (i.e., frequency) per unit time that the agent 200 or fixed sensor 400 provides monitoring information to the base station 100A (monitoring status evaluation unit 305, etc.), and is set for each location within a predetermined area 500.

[0112] The monitoring rate calculation unit 310 calculates the monitoring evaluation index C mj Based on this, the monitoring rate is calculated. That is, the monitoring rate calculation unit 310 calculates the monitoring evaluation index C mj and a predetermined threshold C th The monitoring rate is calculated by comparing the magnitudes of the following: mj Traffic volume and pedestrian traffic have increased, and monitoring evaluation index C mj Threshold C th If the above occurs, the monitoring rate calculation unit 310 increases the monitoring rate of the agent 200 and fixed sensor 400 in that area. In other words, the monitoring rate calculation unit 310 increases the monitoring evaluation index C mj The higher this monitoring evaluation index C is, the higher the value of this index. mj Increase the monitoring rate for the corresponding locations.

[0113] On the other hand, traffic volume decreases at night, etc., and monitoring evaluation index C mj Threshold C th If the value falls below a certain level, the monitoring rate calculation unit 310 lowers the monitoring rate of the agent 200 and the fixed sensor 400. Note that the method for calculating the monitoring rate is not limited to this; for example, the monitoring evaluation index C may be used. mj The monitoring rate may be varied in inverse proportion to the value of .

[0114] <Effects> According to the second embodiment, the monitoring rate calculation unit 310 changes the monitoring rates of the agent 200 and the fixed sensor 400 based on the monitoring information. As a result, the amount of communication is adjusted according to the monitoring status within a predetermined area 500, thereby suppressing an increase in the overall amount of communication of the system. In addition, by installing the fixed sensor 400 in places with a lot of pedestrian traffic, such as intersections, the sensing capability of the entire system can be improved.

[0115] ≪Third Embodiment≫ The third embodiment differs from the first embodiment in that the transport and monitoring of people and other objects in the theme park 700 (see Figure 15) are performed using the agent control system W1 (see Figure 1). Other aspects (such as the configuration of the agent control system W1: see Figures 1, 2, and 4) are the same as in the first embodiment. Therefore, we will explain the parts that differ from the first embodiment, and omit explanations of overlapping parts.

[0116] <Example of application to vehicles within a theme park> Figure 15 is an explanatory diagram of a theme park 700 to which the agent control system according to the third embodiment is applied. In the example shown in Figure 15, theme park 700 has an entrance area and a central area, as well as areas A to D surrounding the central area. Within theme park 700, agents CAV5, CAV6, CAV7, and CAV8 are each responsible for transporting passengers from a certain location to a designated destination. The following describes the case where agent CAV5, as shown in Figure 15, picks up a passenger in area A and transports them to destination Tg5 in area C.

[0117] Figure 16A is an explanatory diagram showing the agent's path in the comparative example. Furthermore, as part of the Theme Park 700 map, Node V is set in front of the main attractions. j And each node V j Section E connecting j And, a graph G(E) containing j ,Vj The map information of ) will be used. Now, suppose that section E10, which is a passage from the central area to area C, is crowded with pedestrians, and the monitoring evaluation index for section E10 is relatively high (i.e., high risk). If agent CAV5 takes the shortest route with passengers, a predetermined route Gp5 that passes through section E10, as shown in the comparative example in Figure 16A, will be calculated.

[0118] Figure 16B is an explanatory diagram showing the global path of an agent in the agent control system according to the third embodiment. In the third embodiment, a route is set such that agent CAV5, which transports people, passes through areas with low monitoring and evaluation indicators. For example, a route Gp6 is calculated that passes through section E11, which has a lower risk than section E10. Incidentally, if agent CAV6 is being moved around in the central area, a route Gp5 is calculated that causes agent CAV6 to patrol section E10, which has a relatively high monitoring and evaluation indicator.

[0119] Figure 17 is an explanatory diagram showing the travel path of an agent in the agent control system according to the third embodiment. Based on the calculation results described above, agents CAV5 and CAV6 will ultimately travel along the route (trajectory) shown in Figure 17. In this way, the agent control system W1 (see Figure 1) creates a route plan that assigns monitoring tasks to agents CAV5 and CAV6 according to the content of their main tasks. This ensures safety by allowing agents CAV5 and others to travel along low-risk routes while transporting passengers. Furthermore, by having agent CAV6 monitor high-risk areas while it is in transit, the monitoring situation of theme park 700 can be improved.

[0120] ≪Variations≫ Although the agent control systems W1, W2, etc. according to the present invention have been described in each embodiment above, the present invention is not limited to these descriptions and can be modified in various ways. For example, in each embodiment, a case has been described in which the monitoring evaluation index is calculated based on individual agent information, monitoring information, and destination / main task information of agent 200, but it is not limited to this. That is, when calculating the monitoring evaluation index, some of the above information (for example, individual agent information or destination / main task information) may be omitted. In other words, the monitoring state evaluation unit 305 may calculate a monitoring evaluation index that indicates the quality of the monitoring state for each location within a predetermined area based on monitoring information transmitted from agent 200 moving within a predetermined area. The same effects as in each embodiment can be achieved with such a configuration.

[0121] Furthermore, while the first embodiment described a case where the agent control unit 300 (see Figure 4) includes a speed limit calculation unit 307 and a route correction unit 308, it is not limited to this. In other words, one or both of the speed limit calculation unit 307 and the route correction unit 308 may be omitted from the configuration of the agent control unit 300. The same applies to the second and third embodiments. Furthermore, in the first embodiment, as shown in Figure 4, the case in which the agent information management unit 301, the monitoring information management unit 302, the map information management unit 303, the business management unit 304, and the agent control unit 300 are provided in one base station 100 was described, but the system is not limited to this. That is, some of the above-described components may be provided in other servers or predetermined agents 200.

[0122] Furthermore, in the first embodiment, section E within a predetermined time ΔT j The number of vehicles and pedestrians that passed through, the number of agents (200) responsible for monitoring tasks, and section E j Based on road surface conditions, accident rates, etc., monitoring and evaluation index C mj The cases in which the monitoring evaluation index C is calculated have been explained, but it is not limited to these cases. That is, the monitoring condition evaluation unit 305 calculates the monitoring evaluation index C based on at least one of the following: the traffic volume of pedestrians and general vehicles (vehicles other than agent 200 that are not specifically monitored), the traffic volume of monitoring vehicles including agent 200, and road conditions. mj You may also calculate it in this way.

[0123] Furthermore, in the first embodiment, the monitoring task ratio β is determined based on the type of main task (task) of agent 200 and the performance of the external environment recognition sensor 207. i The above describes the cases in which this is set, but it is not limited to these cases. That is, the global route generation unit 306 (route plan generation unit) monitors the task ratio β based on the type of main task (task) included in the business management information. i You can also configure it to correspond to agent 200. Furthermore, while the second embodiment described a case in which the agent control system W2 (see Figure 12) is equipped with a plurality of fixed sensors 400, the invention is not limited to this. That is, in a configuration in which the fixed sensors 400 are omitted, the monitoring rate calculation unit 310 (see Figure 13) may calculate the monitoring rate based on the monitoring evaluation index and transmit this monitoring rate to the agent 200. The same effects as in the second embodiment can be achieved with such a configuration as well.

[0124] Furthermore, a real-time risk map showing the monitoring and evaluation indicators for each location, as described in the first embodiment, may be displayed on the administrator's display (display device). Also, the real-time monitoring rate, as described in the second embodiment, may be linked to the identification numbers of the fixed sensors 400 and agents 200 and displayed on the administrator's display (display device). This makes it easier for administrators to grasp the monitoring and evaluation indicators and monitoring rates in the predetermined area 500.

[0125] Furthermore, while each embodiment describes an automated transport system in a predetermined area 500 (see Figure 5A) and a mobile system in a theme park 700 (see Figure 15), the applications of the present invention are not limited to these. For example, it can be applied to factories, ports, and logistics warehouses where people and mobile objects coexist, and it can also be applied to other areas such as agriculture (farms) and tourism.

[0126] Furthermore, each embodiment can be combined as appropriate. For example, the second embodiment and the third embodiment can be combined, and the system configuration of the second embodiment (see Figures 12 and 13) can be applied to the theme park 700 described in the third embodiment (see Figure 15). Furthermore, the processing in the agent control system W1, etc., may be executed as a predetermined program on a computer. The aforementioned program can be provided via a communication line, or it can be written to a recording medium such as a CD-ROM and distributed.

[0127] Furthermore, each embodiment is described in detail to clearly explain the present invention and is not necessarily limited to having all the configurations described. Also, it is possible to add, delete, or replace some of the configurations in the embodiments with other configurations. In addition, the mechanisms and configurations described above are those that are considered necessary for explanation and do not necessarily represent all the mechanisms and configurations in the product. [Explanation of Symbols]

[0128] 100,100A base station 200, 200-1, 200-2, ..., 200n Agent 207 External environment recognition sensor 300, 300A Agent Control Unit 301 Agent Information Management Department 302 Monitoring Information Management Department 303 Map Information Management Department 304 Business Management Department 305 Monitoring Status Evaluation Unit 306 Global Route Generation Unit (Route Planning Generation Unit) 307 Speed ​​Limit Calculation Unit 308 Route Correction Unit 309 Route Planning and Communication Unit 310 Monitoring Rate Calculation Unit 400, 400-1, 400-2, ..., 400-m Fixed Sensor 500 predetermined area 700 Theme parks (designated area) CAV1, CAV2, CAV3, CAV4, CAV5, CAV6, CAV7, CAV8 Agents W1, W2 Agent Control System S604 Step (Monitoring Status Evaluation Process) S605 Step (Route Planning Generation Process) S606 Step (Speed ​​Limit Calculation Process) S608 Step (Route Planning Transmission Process)

Claims

1. A monitoring status evaluation unit calculates a monitoring evaluation index that indicates the quality of monitoring at each location within a predetermined area based on monitoring information transmitted from an agent moving within the predetermined area. A route planning generation unit generates a route plan for the agent based on business management information including the agent's destination and task type, and the monitoring and evaluation indicators. The system includes a route planning transmission unit that transmits the route planning data to the agent, The route planning generation unit sets a monitoring task ratio, which indicates the proportion of the importance of monitoring relative to the task, based on the type of task included in the business management information, and generates the route plan such that the agent travels along a route that includes sections where the monitoring evaluation index is relatively high, the higher the monitoring task ratio. An agent control system in which the monitoring and evaluation index for the section is set to a lower value the greater the safety of the agent traveling through that section.

2. A monitoring status evaluation unit calculates a monitoring evaluation index that indicates the quality of monitoring at each location within a predetermined area based on monitoring information transmitted from an agent moving within the predetermined area. A route planning generation unit generates a route plan for the agent based on business management information including the agent's destination and task type, and the monitoring and evaluation indicators. The system includes a route planning transmission unit that transmits the route planning data to the agent, The route planning generation unit sets a monitoring task ratio, which indicates the proportion of the task importance relative to the task, based on the type of task included in the business management information, and generates a route plan such that the agent travels along a route where the monitoring evaluation index is relatively higher, the higher the monitoring task ratio. The system further includes a speed limit calculation unit that calculates the agent's speed limit based on the aforementioned monitoring evaluation index and the aforementioned monitoring task ratio. The speed limit calculation unit is an agent control system that, when the monitoring task ratio is less than a predetermined value, sets a speed limit for the agent to travel through an area where the monitoring evaluation index is relatively high, which is lower than the speed limit when the monitoring task ratio is equal to or greater than the predetermined value.

3. The route planning generation unit sets the monitoring task ratio to a higher value when the task is for repositioning, dispatching, or power supply, compared to when the task is for transporting people or goods. An agent control system according to claim 1 or claim 2, characterized by the above.

4. The route planning generation unit sets the monitoring task ratio to a higher value the higher the performance of the external environment recognition sensor mounted on the agent. An agent control system according to claim 1 or claim 2, characterized by the above.

5. The system includes a route correction unit for correcting the agent's route, The route correction unit modifies the agent's travel path based on the speed limit and the monitoring information, so as to keep the agent's travel speed below the speed limit and avoid contact between the agent and surrounding objects. The agent control system according to claim 2, characterized by the following:

6. The monitoring status evaluation unit calculates the monitoring evaluation index based on at least one of the following: the volume of pedestrian and general vehicle traffic, the volume of monitoring vehicles including the agent, and road conditions. An agent control system according to claim 1 or claim 2, characterized by the above.

7. The system includes a monitoring rate calculation unit that sets a monitoring rate for each location within a predetermined area, which is the number of times the agent provides monitoring information to the monitoring state evaluation unit per unit time, based on the monitoring evaluation index. The monitoring rate calculation unit increases the monitoring rate at the location corresponding to the monitoring evaluation index as the monitoring evaluation index is higher. An agent control system according to claim 1 or claim 2, characterized by the above.

8. A monitoring state evaluation process in which a computer calculates a monitoring evaluation index that indicates the quality of monitoring for each location within a predetermined area, based on monitoring information transmitted from an agent moving within the predetermined area, A route plan generation process in which the computer generates a route plan for the agent based on business management information including the agent's destination and task type, and the monitoring and evaluation indicators. A route plan transmission process in which the computer transmits the route plan data to the agent, including, In the route planning generation process, a monitoring task ratio, which indicates the proportion of the importance of monitoring relative to the task, is set in association with the agent based on the type of task included in the business management information, and the higher the monitoring task ratio, the more the route plan is generated such that the agent travels along a route that includes sections where the monitoring evaluation index is relatively high. An agent control method wherein the higher the safety level when the agent travels through the aforementioned section, the lower the monitoring and evaluation index for that section is set to.

9. A monitoring state evaluation process in which a computer calculates a monitoring evaluation index that indicates the quality of monitoring for each location within a predetermined area, based on monitoring information transmitted from an agent moving within the predetermined area, A route plan generation process in which the computer generates a route plan for the agent based on business management information including the agent's destination and task type, and the monitoring and evaluation indicators. A route plan transmission process in which the computer transmits the route plan data to the agent, including, In the route planning generation process, based on the type of task included in the business management information, a monitoring task ratio indicating the proportion of monitoring importance relative to the task is set in association with the agent, and the higher the monitoring task ratio, the more the route plan is generated such that the agent travels along a route with a relatively higher monitoring evaluation index. The system further includes a speed limit calculation process in which the computer calculates the speed limit of the agent based on the monitoring evaluation index and the monitoring task ratio. An agent control method in which, in the speed limit calculation process, when the monitoring task ratio is less than a predetermined value, the speed limit when the agent drives through an area where the monitoring evaluation index is relatively high is lower than the speed limit when the monitoring task ratio is equal to or greater than the predetermined value.

Images