Control device, system, vehicle, and control method

Abstract

A control device, system, vehicle, and control method are provided. The control device includes a control section configured to perform control to present a first path in a vehicle, the first path being a path for the vehicle to move to a parking space in a parking lot, predict a second path in which a pedestrian moves in the parking lot, and perform control to present a third path in the vehicle in place of the first path when the first path and the second path intersect.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to a control device, a system, a vehicle, and a control method. BACKGROUND

[0002] Japanese Patent Application Publication No. 2019-091279 discloses a device that sets a movement path so that a vehicle moves at a place where a risk of a pedestrian suddenly emerging is relatively small in a parking lot. SUMMARY

[0003] The above-described device does not set the movement path of the vehicle based on a path that the pedestrian actually moves. Therefore, it is possible that the vehicle stops for waiting for the pedestrian to cross, and the vehicle cannot move smoothly in the parking lot.

[0004] The present disclosure provides a control device, a system, a vehicle, and a control method that enable a vehicle to move smoothly in a parking lot.

[0005] A first aspect of the present disclosure relates to a control device including a control section. The control section is configured to perform control that prompts a first path in a vehicle, the first path being a path in which the vehicle moves to a parking space in a parking lot, predict a second path in which a pedestrian moves in the parking lot, and perform control that prompts a third path in the vehicle instead of the first path in a case where the first path and the second path intersect.

[0006] In the above-described first aspect, the control section can also predict the second path in a case where the pedestrian parked a vehicle in the parking lot, based on a position of a parking space in which the pedestrian parked.

[0007] In the above-described first aspect, the control section can also predict the second path by inputting position data indicating a position of a parking space in which the pedestrian parked to a prediction model for predicting a path, and acquiring a prediction result output from the prediction model.

[0008] In the above-described first aspect, the control section can also generate or update the prediction model by performing machine learning by associating data indicating a movement history of a plurality of pedestrians with data indicating positions of parking spaces in which the plurality of pedestrians parked.

[0009] In the above-described first aspect, the control section can also predict the second path in a case where the pedestrian moves to a destination outside the parking lot, based on a type of a transportation means used by the pedestrian in the movement to the destination.

[0010] In the above-described first technical solution, the parking lot can also have a plurality of locations respectively associated with one or more types of transportation means. The control unit can also predict, as the second path, a path of the pedestrian moving to a location of the plurality of locations corresponding to a type of transportation means used by the pedestrian in moving to the destination.

[0011] In the above-described first technical solution, the control unit can also predict the second path by inputting, to a prediction model for predicting a path, type data indicating a type of transportation means used by the pedestrian in moving to the destination, and obtaining a prediction result output from the prediction model.

[0012] In the above-described first technical solution, the control unit can also generate or update the prediction model by performing machine learning by associating data indicating a movement history of a plurality of pedestrians with data indicating types of transportation means used by the plurality of pedestrians.

[0013] In the above-described first technical solution, the control unit can also predict the second path by inputting, to a prediction model for predicting a path, distribution data indicating a distribution of vehicles parked in the parking lot, and obtaining a prediction result output from the prediction model.

[0014] In the above-described first technical solution, the control unit can also predict the second path further based on an attribute of the pedestrian.

[0015] In the above-described first technical solution, the control unit can also predict the second path further based on a movement tendency of the pedestrian.

[0016] In the above-described first technical solution, the control unit can also determine, as the third path, a path of the vehicle moving to the same parking space as the first path while bypassing the second path.

[0017] In the above-described first technical solution, the control unit can also determine, as the third path, a path of the vehicle moving to a different parking space from the first path.

[0018] In the above-described first technical solution, the control unit can also perform control to prompt the third path in the vehicle when the first path and the second path intersect and an increase in cost from the first path to the third path does not exceed a reference.

[0019] The second technical solution of the present disclosure relates to a system including the control device and a terminal device mounted on or connected to the vehicle and configured to prompt the first path to a user driving the vehicle.

[0020] The third technical solution disclosed herein relates to a vehicle that includes the aforementioned control device.

[0021] The fourth technical solution disclosed herein is a control method for guiding a vehicle to indicate a first path, wherein the first path is the path by which the vehicle moves towards a parking space in a parking lot. The control method includes: predicting a second path for a pedestrian to move within the parking lot via a control unit; and, if the first path intersects with the second path, guiding the vehicle to indicate a third path that replaces the first path via the control unit.

[0022] In the fourth technical solution described above, the prediction may also include: predicting the second path based on the location of the parking space where the pedestrian parked the car in the parking lot.

[0023] In the fourth technical solution described above, the prediction may also include: predicting the second path based on the type of transportation used by the pedestrian in moving to the destination outside the parking lot, when the pedestrian moves to the destination.

[0024] In the fourth technical solution above, the prediction may also include: predicting the second path by inputting distribution data into a prediction model for predicting a path and obtaining the prediction result output from the prediction model, wherein the distribution data represents the distribution of vehicles parked in the parking lot.

[0025] According to the various technical solutions disclosed herein, vehicles can move smoothly within a parking lot. Attached Figure Description

[0026] The features, advantages, and technical and industrial significance of exemplary embodiments of the present invention will be described below with reference to the accompanying drawings, wherein like reference numerals denote like elements, and wherein:

[0027] Figure 1 This is a diagram illustrating the configuration of a system according to an embodiment of this disclosure.

[0028] Figure 2 This is a diagram representing an example of the first path.

[0029] Figure 3 This is a diagram representing an example of the second path.

[0030] Figure 4 This is a diagram representing an example of the third path.

[0031] Figure 5 This is a block diagram illustrating the configuration of the control device involved in the embodiments of this disclosure.

[0032] Figure 6This is a block diagram illustrating the configuration of a terminal device according to an embodiment of the present disclosure.

[0033] Figure 7 This is a flowchart illustrating the operation of the system involved in the embodiments of this disclosure.

[0034] Figure 8 This is a flowchart illustrating the operation of a system involved in a variation of an embodiment of this disclosure. Detailed Implementation

[0035] Hereinafter, several embodiments of the present disclosure will be described with reference to the accompanying drawings.

[0036] In each figure, the same or equivalent parts are assigned the same reference numeral. In the descriptions of each embodiment, descriptions of the same or equivalent parts are appropriately omitted or simplified.

[0037] One embodiment of this disclosure will be described.

[0038] Reference Figure 1 The configuration of system 10 according to this embodiment will be described.

[0039] The system 10 of this embodiment includes at least one control device 20 and at least one terminal device 30. The control device 20 is capable of communicating with the terminal device 30 via a network 40.

[0040] The control device 20 is installed in facilities such as data centers. The control device 20 is a computer such as a server belonging to a cloud computing system or other computing system.

[0041] The terminal device 30 is mounted on the vehicle 12 and used by the user 11 who drives the vehicle 12. The terminal device 30 is, for example, an in-vehicle device such as a vehicle navigation system. Alternatively, the terminal device 30 can also be connected to the vehicle 12 as an external device, or be held by the user 11. The terminal device 30 can also be, for example, a mobile device such as a mobile phone, smartphone, or tablet computer.

[0042] Vehicle 12 can be any type of automobile, such as a gasoline vehicle, diesel vehicle, hybrid vehicle (HV), plug-in hybrid vehicle (PHV), electric vehicle (EV), or fuel cell vehicle (FCV). In this embodiment, vehicle 12 is driven by a driver, but driving can also be automated at any level. The level of automation can be, for example, any level from Level 1 to Level 5 in the Society of Automotive Engineers (SAE) classification. Vehicle 12 can also be a dedicated Mobility as a Service (MaaS) vehicle.

[0043] Network 40 includes the Internet, at least one wide area network (WAN), at least one metropolitan area network (MAN), or any combination thereof. Network 40 may also include at least one wireless network, at least one optical network, or any combination thereof. Wireless networks are, for example, ad hoc networks, cellular networks, local area networks (LANs), satellite communication networks, or terrestrial microwave networks.

[0044] Reference Figures 1-4 A summary of this embodiment will be provided.

[0045] The control device 20 provides prompts in the vehicle 12, such as... Figure 2 The control of the first path 71 as shown. The first path 71 is the path by which the vehicle 12 moves to the parking space 56 in the parking lot 51. In this embodiment, the control of prompting the first path 71 in the vehicle 12 means that the terminal device 30 prompts the first path 71. That is, in this embodiment, the terminal device 30 prompts the user 11 with the first path 71.

[0046] Control device 20 predicts as follows Figure 3 The second path 72 is shown. The second path 72 is the path that pedestrian 13 moves within parking lot 51.

[0047] When the first path 71 and the second path 72 intersect, the control device 20 provides a prompt in the vehicle 12, such as... Figure 4The control of the third path 73 as shown. The third path 73 is the path that replaces the first path 71. In this embodiment, the control of prompting the third path 73 in the vehicle 12 means that the terminal device 30 prompts the third path 73. That is, in this embodiment, the terminal device 30 prompts the user 11 with the third path 73.

[0048] According to this embodiment, the movement path guided in the vehicle 12 can be adjusted according to the actual movement path of the pedestrian 13. Therefore, it is easy to avoid the vehicle stopping while waiting for the pedestrian 13 to cross. As a result, the vehicle 12 can move smoothly within the parking lot 51. The safety within the parking lot 51 is also improved.

[0049] Parking lot 51 can be located anywhere, but... Figures 2-4 In this example, the location is within the block area. User 11 and pedestrian 13 are a resident, commuter, or visitor of the block, respectively.

[0050] Parking lot 51 includes surface parking lots, underground parking lots, multi-level parking garages, or any combination thereof. Movement from parking lot 51 to residential or office buildings within the block can utilize various last-mile mobility methods. Last-mile mobility includes automated guided vehicles (AGVs) or delivery robots for cargo handling, pedestrian-only vehicles such as electric scooters or electric pedals, shared or car-sharing vehicles, shuttle buses or on-demand buses for passenger transport, or any combination thereof. Figures 2-4 In this example, one can rent an AGV, delivery robot, or vehicle for use in the pedestrian area from the waiting area 52 within parking lot 51. One can ride a shared vehicle from the dedicated parking space 53 within parking lot 51. One can wait for a shuttle bus or call an on-demand bus from the adjacent stop 54 and ride the arriving shuttle bus or on-demand bus.

[0051] Parking lot 51 has more than one entrance and more than one exit. Figures 2-4In this example, there are a first entrance / exit 61, a second entrance / exit 62, a gate 63, and a third entrance / exit 64. The first entrance / exit 61 is used by people moving on foot from parking lot 51 to the building complex in the block or from the building complex in the block to parking lot 51. The second entrance / exit 62 is the entrance / exit closest to the waiting area 52 and is used by people moving from parking lot 51 to the building complex in the block or from the building complex in the block to parking lot 51 via mobility services in the pedestrian area. The second entrance / exit 62 can also be used by people who have rented AGVs or delivery robots. The gate 63 is an entrance / exit located in front of the dedicated parking space 53 and is used by people moving from parking lot 51 to the building complex in the block or from the building complex in the block to parking lot 51 via shared vehicles. The third entrance / exit 64 is the entrance / exit closest to the stop 54 and is used by people moving from parking lot 51 to the building complex in the block or from the building complex in the block to parking lot 51 via shuttle buses or on-demand buses.

[0052] Parking lot 51 has multiple locations, each associated with more than one mode of transportation. Figures 2-4 In the example, entrance / exit 61 is a location associated with "walking". Waiting area 52 is a location associated with "transportation for pedestrian areas". Waiting area 52 can also be further associated with "AGV" or "delivery robot". Alternatively, instead of waiting area 52, entrance / exit 62 can be associated with "AGV", "delivery robot", or "transportation for pedestrian areas". Dedicated parking space 53 is a location associated with "shared vehicles". Alternatively, instead of dedicated parking space 53, gate 63 can be associated with "shared vehicles". Entrance / exit 64 is a location associated with "tour bus" or "on-demand bus". Alternatively, instead of entrance / exit 64, stop 54 can be associated with "tour bus" or "on-demand bus".

[0053] Parking lot 51 is equipped with a sensor array for observing pedestrians 13. The sensor array includes one or more cameras, one or more LiDAR (light detection and ranging) sensors, or any combination thereof.

[0054] In this embodiment, when pedestrian 13 parks his car in parking lot 51, control device 20 predicts second path 72 based on the location of parking space 57 where pedestrian 13 parked.

[0055] As a first example, suppose resident X, living in residence B1 near parking lot 51, parks his car in parking space 57. The location of parking space 57 is registered in a database in association with resident X. For example, if resident X is temporarily using parking space 57, it is registered at the time of parking; if resident X has signed a monthly rental contract, it is registered at the time of signing the contract. Suppose resident X walks from residence B1 to parking lot 51 to go shopping outside the block, entering parking lot 51 through entrance 61. In this case, control device 20 analyzes images obtained from the sensor array within parking lot 51 and detects resident X as pedestrian 13. Control device 20 identifies resident X using any method such as facial recognition. Figure 3 As shown, the control device 20 predicts the path from resident X's current location to the location of parking space 57 registered in the database associated with resident X as the second path 72.

[0056] In this embodiment, when pedestrian 13 moves toward a destination outside parking lot 51, control device 20 predicts a second path 72 based on the type of transportation used by pedestrian 13 in moving toward the destination.

[0057] As a second example, suppose a commuter Y, who works in office B2 located far from parking lot 51, drives from his home outside the block to parking lot 51 and parks in parking space 57. Suppose the type of transportation used by commuter Y to move to office B2 is registered in a database associated with commuter Y. For example, if commuter Y temporarily uses parking space 57, it is registered at the time of parking; if commuter Y has signed a monthly lease, it is registered at the time of signing the lease. Suppose commuter Y gets out of the car and walks out of parking lot 51. In this case, control device 20 analyzes images obtained from the sensor array within parking lot 51 and detects commuter Y as pedestrian 13. Control device 20 identifies commuter Y using any method such as facial recognition. Control device 20 predicts a second path 72 from commuter Y's current location to the location corresponding to the type of transportation registered in the database associated with commuter Y. For example, if the mode of transportation registered in the database associated with commuter Y is "walking," then control device 20 predicts the path from commuter Y's current location to the location of the first entrance / exit 61 as the second path 72. Alternatively, if the mode of transportation registered in the database associated with commuter Y is "transportation for pedestrian areas," then control device 20 predicts the path from commuter Y's current location to the location of the waiting area 52 as the second path 72. Alternatively, if the mode of transportation registered in the database associated with commuter Y is "shared vehicle," then control device 20 predicts the path from commuter Y's current location to the location of the dedicated parking space 53 as the second path 72. Alternatively, if the mode of transportation registered in the database associated with commuter Y is "shuttle bus" or "on-demand bus," then control device 20 predicts the path from commuter Y's current location to the location of the third entrance / exit 64 as the second path 72.

[0058] Parking lot 51 can also accommodate both manually driven vehicles and autonomous vehicles (AVs).

[0059] Reference Figure 5 The configuration of the control device 20 according to this embodiment will be described.

[0060] The control device 20 includes a control unit 21, a storage unit 22, and a communication unit 23.

[0061] The control unit 21 includes at least one processor, at least one programmable circuit, at least one dedicated circuit, or any combination thereof. The processor is a general-purpose processor such as a central processing unit (CPU) or a graphics processing unit (GPU), or a dedicated processor for specific processing. The programmable circuit is, for example, a field-programmable gate array (FPGA). The dedicated circuit is, for example, an application-specific integrated circuit (ASIC). The control unit 21 controls each part of the control device 20 while performing processing related to the operation of the control device 20.

[0062] The storage unit 22 includes at least one semiconductor memory, at least one magnetic memory, at least one optical memory, or any combination thereof. The semiconductor memory is, for example, random access memory (RAM) or read-only memory (ROM). RAM is, for example, static random access memory (SRAM) or dynamic random access memory (DRAM). ROM is, for example, electrically erasable programmable read-only memory (EEPROM). The storage unit 22 functions as, for example, a main storage device, an auxiliary storage device, or a cache memory. The storage unit 22 stores data used in the operation of the control device 20 and data obtained through the operation of the control device 20.

[0063] The communication unit 23 includes at least one communication interface. The communication interface is, for example, a LAN interface. The communication unit 23 receives data used in the operation of the control device 20, and also transmits data obtained through the operation of the control device 20.

[0064] The functions of the control device 20 are implemented by the processor, which acts as the control unit 21, executing the control program according to this embodiment. That is, the functions of the control device 20 are implemented by software. The control program causes the computer to perform the actions of the control device 20, thereby enabling the computer to function as the control device 20. In other words, the computer functions as the control device 20 by executing the actions of the control device 20 according to the control program.

[0065] Programs can be stored on non-transitory computer-readable media. Examples of non-transitory computer-readable media include flash memory, magnetic recording devices, optical discs, optical-magnetic recording media, or ROM. Program distribution can be achieved, for example, by selling, transferring, or lending removable media such as Secure Digital (SD) cards, digital versatile discs (DVDs), or compact disc read-only memory (CD-ROMs) containing the program. Program distribution can also be achieved by storing the program in a server's storage and transferring it from the server to other computers. The program can also be provided as a program product.

[0066] Computers may temporarily store programs, such as those stored on removable media or transferred from servers, in main storage. The computer then reads the program stored in main storage using its processor and executes the processing according to the read program. Alternatively, the computer may directly read programs from removable media and execute the processing according to the program. The computer may also execute the processing according to the received program each time a program is transferred from a server. Alternatively, the transfer of programs from a server to the computer may be omitted, and processing may be performed through a service provided by an application service provider (ASP), which performs its functions solely by executing instructions and obtaining results. A program includes information considered as a program for processing implemented by a computer. For example, data that is not a direct instruction to the computer but has the nature of specifying the computer's processing is considered "information considered as a program."

[0067] Some or all of the functions of the control device 20 can also be implemented by a programmable circuit or a dedicated circuit that serves as the control unit 21. That is, some or all of the functions of the control device 20 can also be implemented by hardware.

[0068] Reference Figure 6 The configuration of the terminal device 30 according to this embodiment will be described.

[0069] The terminal device 30 includes a control unit 31, a storage unit 32, a communication unit 33, an input unit 34, an output unit 35, and a positioning unit 36.

[0070] The control unit 31 includes at least one processor, at least one programmable circuit, at least one dedicated circuit, or any combination thereof. The processor is a general-purpose processor such as a CPU or GPU, or a dedicated processor for specific processing. The programmable circuit is, for example, an FPGA. The dedicated circuit is, for example, an ASIC. The control unit 31 controls various parts of the terminal device 30 while performing processing related to the operation of the terminal device 30.

[0071] The storage unit 32 includes at least one semiconductor memory, at least one magnetic memory, at least one optical memory, or any combination thereof. The semiconductor memory is, for example, RAM or ROM. RAM is, for example, SRAM or DRAM. ROM is, for example, EEPROM. The storage unit 32 functions as, for example, a main storage device, an auxiliary storage device, or a cache memory. The storage unit 32 stores data used in the operation of the terminal device 30 and data obtained by the operation of the terminal device 30.

[0072] The communication unit 33 includes at least one communication interface. This communication interface may be, for example, an interface supporting mobile communication standards such as LTE, 4G, or 5G; an interface supporting short-range wireless communication standards such as Bluetooth; or a LAN interface. "LTE" is short for Long Term Evolution. "4G" is short for 4th generation. "5G" is short for 5th generation. The communication unit 33 receives data used in the operation of the terminal device 30 and also transmits data obtained from the operation of the terminal device 30.

[0073] The input unit 34 includes at least one input interface. The input interface may be, for example, a physical button, an electrostatic capacitive button, a pointing device, a touchscreen integrated with the display, a camera, a LiDAR, or a microphone. The input unit 34 accepts operations for inputting data used in the operation of the terminal device 30. Alternatively, the input unit 34 may be connected to the terminal device 30 as an external input device, instead of being installed on the terminal device 30. As a connection interface, for example, interfaces supporting standards such as USB, HDMI, or Bluetooth may be used. "USB" is short for Universal Serial Bus. "HDMI" is short for High-Definition Multimedia Interface.

[0074] The output unit 35 includes at least one output interface. The output interface may be, for example, a display or a speaker. The display may be, for example, a liquid crystal display (LCD) or an organic electroluminescence (EL) display. The output unit 35 outputs data obtained through the operation of the terminal device 30. Alternatively, the output unit 35 may be connected to the terminal device 30 as an external output device, instead of being installed on the terminal device 30. As a connection interface, for example, an interface supporting standards such as USB, HDMI, or Bluetooth may be used.

[0075] The positioning unit 36 ​​includes at least one Global Navigation Satellite System (GNSS) receiver. GNSS receivers may include, for example, the Global Positioning System (GPS), Quasi-Zenith Satellite System (QZSS), BeiDou Navigation Satellite System (BDS), GLONASS, or Galileo. QZSS satellites are referred to as Quasi-Zenith satellites. The positioning unit 36 ​​determines the position of the terminal device 30.

[0076] The functions of the terminal device 30 are implemented by the processor, which serves as the control unit 31, executing the terminal program according to this embodiment. That is, the functions of the terminal device 30 are implemented by software. The terminal program causes the computer to perform the actions of the terminal device 30, thereby enabling the computer to function as the terminal device 30. In other words, the computer functions as the terminal device 30 by executing the actions of the terminal device 30 according to the terminal program.

[0077] Some or all of the functions of the terminal device 30 can also be implemented by a programmable circuit or a dedicated circuit that serves as the control unit 31. That is, some or all of the functions of the terminal device 30 can also be implemented by hardware.

[0078] Reference Figure 7 The operation of the system 10 according to this embodiment will be described. The operation of the control device 20 included in this operation is equivalent to the control method according to this embodiment.

[0079] In step S101, the control unit 21 of the control device 20 calculates the first path 71. The first path 71 is the path by which the vehicle 12 moves to the parking space 56 in the parking lot 51. The processing of step S101 can be performed according to any procedure, but in this embodiment, the processing is performed according to the following procedure.

[0080] The positioning unit 36 ​​of the terminal device 30 determines the position of the terminal device 30. The control unit 31 of the terminal device 30 causes the communication unit 33 to send position data D1. The position data D1 is data that represents the position measured by the positioning unit 36 ​​as the position of the vehicle 12. The communication unit 33 sends the position data D1 to the control device 20. The communication unit 23 of the control device 20 receives the position data D1 from the terminal device 30. The control unit 21 of the control device 20 determines the position of the vehicle 12 by acquiring the position data D1 received by the communication unit 23.

[0081] The control unit 21 of the control device 20 analyzes the parking tendency of the user 11. Parking tendency can be analyzed by any method, but in this embodiment, data on the user 11's past parking locations in the parking lot 51, whether parking instructions were followed, the number of passengers, whether charging equipment was used, and parking methods such as whether the car was facing forward or backward are input into a learned model. Analysis results are obtained from the learned model to analyze the parking tendency. Parking locations include, for example, near the entrance, near the exit, near stairs, near the elevator, or on a floor. Parking methods include, for example, facing forward or backward. Based on the user 11's parking tendency, the control unit 21 selects a parking space 56 from the multiple parking spaces in the parking lot 51. Figures 2-4 In the example, among the empty parking spaces 55 in parking lot 51, based on user 11's parking preferences, artificial intelligence (AI) determines that parking space 56 is the most satisfying for user 11, and therefore, parking space 56 is selected.

[0082] The control unit 21 of the control device 20 calculates the path from the determined position of the vehicle 12 to the selected parking space 56 as the first path 71. Known methods can be used to calculate the path. Machine learning methods such as deep learning can also be used.

[0083] Parking space 56 can also be selected manually by user 11 instead of automatically by control device 20.

[0084] In step S102, the control unit 21 of the control device 20 detects pedestrian 13. In the first example described above, the control unit 21 detects resident X as pedestrian 13. In the second example, the control unit 21 detects commuter Y as pedestrian 13. Then, the processing in step S103 is executed. Alternatively, if pedestrian 13 is not detected, the processing in step S107 is executed.

[0085] In step S103, the control unit 21 of the control device 20 predicts the second path 72. The second path 72 is the path that the pedestrian 13 will take within the parking lot 51. The processing in step S103 can be performed in any procedure, but in this embodiment, the processing is performed according to the following procedure.

[0086] When pedestrian 13 parks his car in parking lot 51, control unit 21 of control device 20 predicts a second path 72 based on the location of parking space 57 where pedestrian 13 parked. In the first example described above, control unit 21 predicts the path from resident X's current location to the location of parking space 57 registered in the database associated with resident X as the second path 72.

[0087] Specifically, the control unit 21 of the control device 20 predicts the second path 72 by inputting the location data D2 into a prediction model for predicting the path and obtaining the prediction result output from the prediction model. The location data D2 represents the location of the parking space 57. Alternatively, data representing the location of the pedestrian 13 may be input into the prediction model along with the location data D2. The location of the pedestrian 13 can be determined by any method, but for example, by analyzing images obtained from a group of sensors within the parking lot 51. Known methods can be used as image analysis methods. Machine learning methods such as deep learning can also be used.

[0088] The control unit 21 of the control device 20 generates or updates a predictive model by performing machine learning on data representing the movement history of multiple pedestrians and data representing the locations of parking spaces where the multiple pedestrians have parked. The movement history of multiple pedestrians includes the paths that each pedestrian has moved through in the parking lot 51 in the past. For example, by associating the locations of the parking spaces where each pedestrian has parked with the paths that each pedestrian has moved through in the parking lot 51 in the past as labels, teacher data for machine learning can be created. Furthermore, by using this teacher data to perform machine learning based on known algorithms, a learned model as a predictive model can be generated.

[0089] When pedestrian 13 moves to a destination outside parking lot 51, control unit 21 of control device 20 predicts a second path 72, which is the path that pedestrian 13 will take to one of several locations in parking lot 51 corresponding to the type of transportation used in the movement of pedestrian 13 to the destination. In the second example described above, if the type of transportation registered in the database associated with commuter Y is "walking", then control unit 21 predicts a path from commuter Y's current location to the location of the first entrance / exit 61 as the second path 72. Alternatively, if the type of transportation registered in the database associated with commuter Y is "transportation for pedestrian areas", then control unit 21 predicts a path from commuter Y's current location to the location of the waiting area 52 as the second path 72. Alternatively, if the type of transportation registered in the database associated with commuter Y is "shared vehicle", then control unit 21 predicts a path from commuter Y's current location to the location of the dedicated parking space 53 as the second path 72. Alternatively, if the type of transportation registered in the database associated with commuter Y is "circuit bus" or "on-demand bus", then control unit 21 predicts the path from commuter Y's current location to the location of the third entrance / exit 64 as the second path 72.

[0090] Specifically, the control unit 21 of the control device 20 predicts the second path 72 by inputting the category data D3 into a prediction model for predicting the path and obtaining the prediction result output from the prediction model. Category data D3 represents the type of transportation used by pedestrian 13 in its movement towards its destination. Alternatively, data representing the location of pedestrian 13 may be input into the prediction model along with the category data D3. The location of pedestrian 13 can be determined by any method, but for example, by analyzing images obtained from a group of sensors within parking lot 51. Known methods can be used as image analysis methods. Machine learning methods such as deep learning can also be used.

[0091] The control unit 21 of the control device 20 generates or updates a predictive model by performing machine learning on data representing the movement history of multiple pedestrians and data representing the types of transportation used by the multiple pedestrians. The movement history of multiple pedestrians includes the paths that each pedestrian has taken in the parking lot 51 in the past. For example, by associating the paths that each pedestrian has taken in the parking lot 51 with the types of transportation used by each pedestrian as labels, teacher data for machine learning can be created. Furthermore, by performing machine learning based on known algorithms using this teacher data, a learned model as a predictive model can be generated.

[0092] The control unit 21 of the control device 20 can predict the second path 72 based on the distribution of vehicles parked in the parking lot 51, regardless of whether the pedestrian 13 has parked the car in the parking lot 51 or whether the pedestrian 13 has moved to a destination outside the parking lot 51.

[0093] Specifically, the control unit 21 of the control device 20 can also predict the second path 72 by inputting the distribution data D4 into the prediction model for predicting the path and obtaining the prediction result output from the prediction model. The distribution data D4 is data representing the distribution of vehicles parked in the parking lot 51. The distribution data D4 can also be obtained using images obtained from the sensor group in the parking lot 51, or data obtained by processing the images into an easily analyzable form such as a heat map.

[0094] The control unit 21 of the control device 20 can further predict the second path 72 based on the attributes of pedestrian 13. Attributes may include, for example, classification, place of residence, family composition, age, gender, type of vehicle owned, interests, hobbies, presence or absence of physical disabilities, or any combination thereof. Classifications may include, for example, resident, commuter, or visitor. The attributes of pedestrian 13 can be determined by any method, but for example, by presenting pedestrian 13 with a questionnaire for attribute determination and analyzing the responses to the questionnaire. Known methods can be used as methods for response analysis. Machine learning methods such as deep learning can also be used.

[0095] The control unit 21 of the control device 20 can further predict the second path 72 based on the movement tendency of the pedestrian 13. The movement tendency of the pedestrian 13 includes, for example, the walking speed of the pedestrian 13 or whether the pedestrian 13 crosses the road at an angle. The movement tendency of the pedestrian 13 can be analyzed by any method, but for example, by inputting data representing the movement history of the pedestrian 13 into a learned model and obtaining the analysis results from the learned model, thereby analyzing the movement tendency of the pedestrian 13. The movement history of the pedestrian 13 includes the paths that the pedestrian 13 has previously moved within the parking lot 51.

[0096] In step S104, the control unit 21 of the control device 20 determines whether the first path 71 calculated in step S101 intersects with the second path 72 predicted in step S103. For example... Figure 3 As shown, if path 71 and path 72 intersect, step S105 is executed. If path 71 and path 72 do not intersect, step S107 is executed.

[0097] In step S105, the control unit 21 of the control device 20 calculates the third path 73. The third path 73 is a path that replaces the first path 71. The processing in step S105 can be performed in any procedure, but in this embodiment, the processing is performed according to the following procedure.

[0098] The control unit 21 of the control device 20 determines the path for the vehicle 12 to move around the second path 72 to the parking space 56, which is the same as the first path 71, as the third path 73. That is, as Figure 4 As shown, the control unit 21 calculates a third path 73, which is the path from the position of the vehicle 12 determined in step S101 to the position of the parking space 56 selected in step S101 without crossing the second path 72. Known methods can be used to calculate the path. Machine learning methods such as deep learning can also be used.

[0099] Parking space 56 can also be changed to another parking space. In such a variation, the control unit 21 of the control device 20 determines the path for the vehicle 12 to move to a parking space different from the first path 71 as the third path 73. That is, the control unit 21 calculates the path from the position of the vehicle 12 determined in step S101 to the position of a parking space different from the parking space 56 selected in step S101 as the third path 73. For example, the AI ​​determines the parking space in the parking lot 51 that is an empty parking space and can be reached from the position of the vehicle 12 without crossing the second path 72, and selects the parking space that is most satisfactory to the user 11 based on the user 11's parking preference as "a parking space different from parking space 56".

[0100] In step S106, the control unit 21 of the control device 20 controls the vehicle 12 to display the third path 73 calculated in step S105. This process can be performed in any procedure, but in this embodiment, it is performed in the following procedure.

[0101] The control unit 21 of the control device 20 generates guidance data D5. Guidance data D5 is data guiding the user 11 along the third path 73 calculated in step S105. The control unit 21 causes the communication unit 23 to send the generated guidance data D5. The communication unit 23 sends the guidance data D5 to the terminal device 30. The communication unit 33 of the terminal device 30 receives the guidance data D5 from the control device 20. The control unit 31 of the terminal device 30 obtains the guidance data D5 received by the communication unit 33. The control unit 31 prompts the user 11 with the obtained guidance data D5. Any method can be used to prompt the user 11 with the guidance data D5, but in this embodiment, the method of displaying the content of the guidance data D5 on a display that serves as the output unit 35 is used.

[0102] In step S107, the control unit 21 of the control device 20 controls the vehicle 12 to display the first path 71 calculated in step S101. This process can be performed in any procedure, but in this embodiment, it is performed in the following procedure.

[0103] The control unit 21 of the control device 20 generates guidance data D6. Guidance data D6 is data guiding the user 11 along the first path 71 calculated in step S101. The control unit 21 causes the communication unit 23 to send the generated guidance data D6. The communication unit 23 sends guidance data D6 to the terminal device 30. The communication unit 33 of the terminal device 30 receives guidance data D6 from the control device 20. The control unit 31 of the terminal device 30 obtains the guidance data D6 received by the communication unit 33. The control unit 31 prompts the user 11 with the obtained guidance data D6. Any method can be used to prompt the user 11 with guidance data D6, but in this embodiment, the method of displaying the content of guidance data D6 on a display that serves as an output unit 35 is used.

[0104] As described above, in this embodiment, the control unit 21 of the control device 20 controls the vehicle 12 to move along a first path 71 towards the parking space 56 in the parking lot 51. The control unit 21 predicts a second path 72 for the pedestrian 13 to move within the parking lot 51. If the first path 71 and the second path 72 intersect, the control unit 21 controls the vehicle 12 to be guided along a third path 73 that replaces the first path 71.

[0105] According to this embodiment, an alternative path is suggested when the predicted path for vehicle 12 to move to parking space 56 intersects with the path for pedestrian 13. Therefore, it is easier to avoid vehicles stopping while waiting for pedestrian 13 to cross. As a result, vehicle 12 can move smoothly within parking lot 51. Safety within parking lot 51 is also improved.

[0106] As a variation of this embodiment, the control unit 21 of the control device 20 may also control the prompting of the third path 73 in the vehicle 12 when the first path 71 intersects with the second path 72 and the cost increase from the first path 71 to the third path 73 does not exceed the baseline.

[0107] Reference Figure 8 The operation of system 10 in this modified example will be described. The operation of the control device 20 included in this operation is equivalent to the control method in this modified example.

[0108] Regarding the processing of steps S201 to S205, respectively, with... Figure 7 The processes in steps S101 to S105 are the same, therefore, the explanation is omitted.

[0109] Following step S205, in step S206, the control unit 21 of the control device 20 calculates the cost of the first path 71 calculated in step S201 as the first cost. The control unit 21 also calculates the cost of the third path 73 calculated in step S205 as the third cost. Furthermore, the control unit 21 calculates the difference between the calculated first cost and the calculated third cost as a cost increase. Known methods can be used as the cost calculation method.

[0110] In step S207, the control unit 21 of the control device 20 determines whether the cost increase calculated in step S206 exceeds the benchmark. If the cost increase does not exceed the benchmark, the process in step S208 is executed. If the cost increase exceeds the benchmark, the process in step S209 is executed.

[0111] Regarding the processing of steps S208 and S209, and... Figure 7 The processes in steps S106 and S107 are the same, therefore, the explanation is omitted.

[0112] This disclosure is not limited to the embodiments described above. For example, two or more functional blocks shown in the block diagram may be merged, or a single functional block may be divided. Alternatively, instead of executing two or more steps shown in the flowchart in chronological order as described, the steps may be executed in parallel or in different sequences depending on the processing capacity of the device executing each step or as needed. Furthermore, modifications may be made without departing from the spirit of this disclosure.

[0113] For example, control device 20 may also be located in vehicle 12. In this case, part of the operation of terminal device 30 may also be performed by control device 20. Alternatively, instead of terminal device 30, control device 20 may prompt user 11 with the first path 71. That is, the control of prompting the first path 71 in vehicle 12 may also be to directly prompt user 11 with the first path 71. Similarly, instead of terminal device 30, control device 20 may prompt user 11 with the third path 73. That is, the control of prompting the third path 73 in vehicle 12 may also be to directly prompt user 11 with the third path 73. Terminal device 30 may also be incorporated into control device 20.

Claims

1. A control device characterized by comprising: including a control section, the control section is configured to: perform control to prompt, in the vehicle, a first path that is a path for the vehicle to move to a parking space in a parking lot; predict a second path in which a pedestrian moves in the parking lot; and in a case where the first path and the second path intersect, perform control to prompt, in the vehicle, a third path that is a substitute for the first path, the parking lot has a plurality of locations respectively associated with one or more types of transportation means, the control section is configured to: in a case where the pedestrian moves to a destination outside the parking lot, predict, as the second path, a path in which the pedestrian moves to a location in the plurality of locations that corresponds to a type of transportation means used by the pedestrian in moving to the destination, predict the second path by inputting, to a prediction model for predicting a path, type data that indicates a type of transportation means used by the pedestrian in moving to the destination, and obtaining a prediction result output from the prediction model, generate or update the prediction model by performing machine learning by associating data indicating movement history of a plurality of pedestrians with data indicating types of transportation means used by the plurality of pedestrians.

2. The control device according to claim 1, wherein the control section is configured to determine, as the third path, a path in which the vehicle moves to the same parking space as the first path while bypassing the second path.

3. The control device according to claim 1, wherein the control section is configured to determine, as the third path, a path in which the vehicle moves to a different parking space from the first path.

4. The control device according to claim 1, wherein the control section is configured to perform control to prompt, in the vehicle, the third path in a case where the first path and the second path intersect and an increase in cost from the first path to the third path does not exceed a reference.

5. A control system characterized by, including: the control device according to any one of claims 1 to 4; and a terminal device mounted on or connected to the vehicle and configured to prompt the first path to a user who drives the vehicle.

6. A vehicle characterized by comprising: including: the control device according to any one of claims 1 to 4.

7. A control method of performing control to prompt, in a vehicle, a first path that is a path for the vehicle to move to a parking space in a parking lot, the parking lot has a plurality of locations respectively associated with one or more types of transportation means, the control method includes: predicting, by a control section, a second path in which a pedestrian moves in the parking lot; in a case where the first path and the second path intersect, performing, by the control section, control to prompt, in the vehicle, a third path that is a substitute for the first path; In a case where the pedestrian moves toward a destination outside the parking lot, the control section inputs category data to a prediction model for predicting a route, acquires a prediction result output from the prediction model, and thereby predicts a route of the pedestrian moving toward a place among the plurality of places corresponding to a category of a traffic means used by the pedestrian in moving toward the destination as the second route. And The control section performs machine learning by associating data indicating a movement history record of a plurality of pedestrians with data indicating categories of traffic means used by the plurality of pedestrians, and thereby generates or updates the prediction model.

Images