JP7296567B2 - TRAFFIC SIGNAL CONTROL DEVICE, TRAFFIC SIGNAL CONTROL SYSTEM AND TRAFFIC SIGNAL CONTROL METHOD - Google Patents

Description

TECHNICAL FIELD The present invention relates to a traffic signal control device, a traffic signal control system, and a traffic signal control method for controlling a traffic signal installed in a target area.

The traffic control system controls the traffic signals installed at intersections based on the traffic conditions of the target road network for the purpose of ensuring smooth traffic flow, ensuring traffic safety, and controlling traffic pollution. is being done. In this traffic signal control, the sub-area configuration is determined based on information collected by vehicle sensors installed on the road, and the signal control parameters (cycle length, offset, split) are generated. .

In such traffic signal control, pattern control and MODERATO (Management by Origin-Destination Related Adaptation for Traffic Optimization) control are adopted as signal control methods. There are also many intersections.

In order to apply pattern control, it is necessary for a skilled engineer to typify traffic conditions and design optimal control parameter values for each typified traffic condition. However, due to the decrease in the number of experienced engineers in recent years, review of control design (traffic situation typification, optimal control parameter design) in response to changes in traffic conditions over time has been delayed.

Therefore, a method that makes it possible to review the control design without a skilled engineer by using traffic condition estimation using machine learning and general-purpose control parameters is conceivable.

As a technology that applies such machine learning to traffic management, conventionally, a machine learning model (neural network) is used to extract future traffic volume and design information for traffic signals as output information from traffic volume as input information. Techniques for acquiring are known (see Patent Literatures 1 and 2).

JP-A-7-6292 JP-A-8-124085

Incorporated Association of Traffic Engineers, Ed., "Handbook of Traffic Signals", Incorporated Association of Traffic Engineers, July 1994, p. 78, 82-83

However, in the above-mentioned conventional technology, it is possible to predict changes in traffic demand and to have the device perform actual design that was previously done by experts based on their experience and skills. Therefore, there is a problem that the optimum signal control parameters corresponding to the current traffic conditions cannot be obtained.

Accordingly, the present invention provides a traffic signal control device, a traffic signal control system, and a traffic signal control method that can optimize signal control parameters in real time in response to changes in traffic conditions without a skilled engineer. The main purpose is to

A traffic signal control device of the present invention is a traffic signal control device that transmits signal control information to a signal controller to control a traffic signal installed in a target area, and collects the latest traffic condition information of the target area. , setting a candidate for signal control information for each intersection in the target area, executing a machine learning model using the candidate for signal control information and the latest traffic condition information as input information, and obtaining the above as output information Obtaining traffic information predicted when the traffic light is controlled by the candidates of signal control information, evaluating the candidates of the signal control information using the traffic information as an evaluation index, and selecting appropriate ones from the candidates of the signal control information. A control unit for selecting appropriate signal control information is provided.

Further, the traffic signal control system of the present invention is a traffic signal control system for controlling a traffic signal installed in a target area, and collects signal control information based on the latest traffic condition information of the target area collected by an information collecting device. The traffic signal control device sets candidate signal control information for each intersection in the target area, and uses the candidate signal control information and the latest traffic condition information as input information. , executing a machine learning model to obtain, as output information, traffic information predicted when the traffic light is controlled by the candidate for the signal control information, and using the traffic information as an evaluation index to obtain the candidate for the signal control information. The configuration is provided with a control unit that evaluates and selects appropriate signal control information from among the candidates for the signal control information.

Further, a traffic signal control method of the present invention is a traffic signal control method for controlling a traffic signal installed in a target area, wherein an information processing device sets candidates for signal control information for each intersection in the target area, A candidate for signal control information and the latest traffic condition information for a target area collected by an information collection device are used as input information to execute a machine learning model, and the signal control information candidate is used as output information to control the traffic light. traffic information predicted in the event of a traffic signal is acquired, candidates for the signal control information are evaluated using the traffic information as an evaluation index, and appropriate signal control information is selected from the candidates for the signal control information. .

According to the present invention, a machine learning model is used to acquire traffic information corresponding to candidates for signal control information, and appropriate signal control information is selected using the traffic information as an evaluation index. As a result, it is possible to optimize signal control parameters in real time in response to changes in traffic conditions without a skilled engineer.

Overall configuration diagram of the traffic signal control system according to the present embodiment Block diagram showing a schematic configuration of the traffic management device 3 Explanatory diagram showing an outline of processing performed by the signal control parameter candidate setting unit 24, the simulation unit 25, the signal control parameter selection unit 26, and the signal control unit 27. FIG. 2 is a flow diagram showing the procedure of processing performed by the learning information collection unit 21, the learning processing unit 22, and the machine learning model construction unit 23; Explanatory diagram showing parameter candidate configuration patterns used in the control method of pattern control and an outline of pattern selection Explanatory diagram showing parameter candidate configuration patterns used in the control method of pattern control and an outline of pattern selection Explanatory diagram showing an example of the road network in the target area FIG. 2 is a flowchart showing the procedure of processing performed by the signal control parameter candidate setting unit 24, the simulation unit 25, the signal control parameter selection unit 26, and the signal control unit 27;

A first invention made to solve the above problems is a traffic signal control device that transmits signal control information to a traffic signal controller to control a traffic signal installed in a target area, Collect traffic condition information, set candidates for signal control information for each intersection in the target area, and execute a machine learning model using the candidates for signal control information and the latest traffic condition information as input information. obtains, as output information, traffic information predicted when the traffic light is controlled by the candidate of the signal control information, evaluates the candidate of the signal control information using the traffic information as an evaluation index, and obtains the signal control information The configuration is provided with a control unit that selects appropriate signal control information from among the candidates.

According to this, a machine learning model is used to acquire traffic information corresponding to a candidate for signal control information, and the traffic information is used as an evaluation index to select appropriate signal control information. As a result, it is possible to optimize signal control parameters in real time in response to changes in traffic conditions without a skilled engineer.

In a second aspect of the invention, the control unit operates based on general-purpose setting information in which general-purpose setting values for signal control information are registered in advance, the current configuration of each intersection in the target area, and the distance between the intersections. , to set candidates for the signal control information.

According to this, it is possible to appropriately and easily set candidates for signal control information for each intersection in the target area.

In a third aspect of the invention, the control unit selects appropriate signal control information based on at least one of traffic congestion length and travel time as the traffic information.

According to this, appropriate signal control information can be selected.

A fourth aspect of the invention is a traffic signal control system for controlling a traffic signal installed in a target area, the traffic signal control system generating signal control information based on the latest traffic condition information of the target area collected by an information collecting device. A signal control device is provided, and the traffic signal control device sets candidates for signal control information for each intersection in a target area, and uses the candidates for the signal control information and the latest traffic condition information as input information for machine learning. The model is executed to obtain, as output information, traffic information predicted when the traffic light is controlled by the candidate for the signal control information, and the candidate for the signal control information is evaluated using the traffic information as an evaluation index. and a control unit for selecting appropriate signal control information from among the candidates for the signal control information.

According to this, similarly to the first invention, optimization of signal control parameters corresponding to changes in traffic conditions can be performed in real time without a skilled engineer.

A fifth aspect of the invention is a traffic signal control method for controlling a traffic signal installed in a target area, wherein an information processing device sets candidates for signal control information for each intersection in the target area, and the signal control information and the latest traffic condition information of the target area collected by the information collection device as input information, a machine learning model is executed, and as output information, when the traffic light is controlled with the candidate of the signal control information Predicted traffic information is acquired, candidates for the signal control information are evaluated using the traffic information as an evaluation index, and appropriate signal control information is selected from the candidates for the signal control information.

According to this, similarly to the first invention, optimization of signal control parameters corresponding to changes in traffic conditions can be performed in real time without a skilled engineer.

BEST MODE FOR CARRYING OUT THE INVENTION Hereinafter, embodiments of the present invention will be described with reference to the drawings.

FIG. 1 is an overall configuration diagram of a traffic signal control system according to this embodiment.

This traffic signal control system (traffic control system) controls the traffic lights installed in the target area. device, information processing device) 3;

The vehicle detector 1 is, for example, an ultrasonic vehicle detector or an optical vehicle detector (optical beacon). status information). This vehicle detector information is transmitted from the vehicle detector 1 to the traffic management device 3 .

The signal controller 2 controls the operation of the traffic signal (signal lamp) based on signal control parameters (signal control information) transmitted from the traffic management device 3 .

The traffic management device 3 is a central device of the traffic control center, generates signal control parameters (signal control information) based on vehicle detector information transmitted from the vehicle detector 1, and transmits the signal control parameters as signals. Send to controller 2.

In this embodiment, the traffic management device 3 is configured to perform signal control using vehicle sensor information. Signal control may be performed using probe information (traffic condition information) collected from an on-vehicle device mounted on a running vehicle.

Next, a schematic configuration of the traffic management device 3 will be described. FIG. 2 is a block diagram showing a schematic configuration of the traffic management device 3. As shown in FIG. FIG. 3 is an explanatory diagram showing an outline of processing performed by the signal control parameter candidate setting unit 24, the simulation unit 25, the signal control parameter selection unit 26, and the signal control unit 27. As shown in FIG.

As shown in FIG. 2 , the traffic management device 3 includes a communication section 11 , a control section 12 and a storage section 13 .

The communication unit 11 communicates with the vehicle detector 1 and the signal controller 2, receives vehicle detector information transmitted from the vehicle detector 1, and transmits signal control parameters (signal control information) to the signal controller 2. Send to

The storage unit 13 stores signal control setting information, road network configuration information, vehicle sensor information, event regulation information, weather information, signal control parameters (signal control information), traffic information, general-purpose setting information for signal control parameters, and the like. Remember. The storage unit 13 also stores programs executed by the processors that constitute the control unit 12 .

Here, the signal control setting information is setting information related to signal control such as the current configuration of each intersection in the target area.

The road network configuration information is information about the connection form of nodes (intersections) and links (roads) that configure the road network, the link length of each link (distance between intersections), and the like.

The vehicle detector information is information representing the traffic conditions collected by the vehicle detector 1. Specifically, the traffic volume, that is, the number of vehicles passing the position of the vehicle detector 1 every unit time (for example, 5 minutes). It is the number of vehicles, the occupancy rate (time occupancy rate), that is, the ratio of the time that the vehicle exists at the position of the vehicle sensor 1 within a unit time.

Event restriction information is information about lane restrictions, traffic closures, and the like on the road network in the target area. The weather information is information about the weather (such as rainfall) of the target area. This weather information may be obtained from the weather information providing server, but the administrator may input the weather of the day.

A signal control parameter (signal control information) is information that is an element that determines the display timing of a traffic signal at a traffic signal, and specifically includes cycle length, split, and offset.

The traffic information is information about travel time, congestion length, etc. in each link of the road network of the target area.

The general-purpose setting information of signal control parameters is registered with general-purpose setting values of signal control parameters.

Vehicle detector information, event regulation information, weather information, and signal control parameters include past information and latest information. Past information serves as learning information for constructing a machine learning model, and The information in is related to current signal control.

The control unit 12 includes a learning information collection unit 21, a learning processing unit 22, a machine learning model construction unit 23, a signal control parameter candidate setting unit 24, a simulation unit 25, a signal control parameter selection unit 26, a signal control a portion 27; The control unit 12 is configured by a processor, and each unit of the control unit 12 is realized by executing a program stored in the storage unit 13 by the processor.

The learning information collecting unit 21 collects information for a predetermined period regarding the road network of the target area from the storage unit 13 as learning information. This learning information is a combination of input information and corresponding output information. The input information includes signal control parameters (signal control information), vehicle detector information, event restriction information (lane restrictions, etc.), and Weather information (rainfall, etc.) is output, and traffic information (travel time, length of traffic congestion, etc.) is output. Various types of information used as learning information are acquired in past signal control and stored in the storage unit 13 .

The learning processing unit 22 uses the learning information acquired by the learning information collecting unit 21 to execute learning processing for the machine learning model, and acquires model parameters related to the machine learning model as a learning result.

The machine learning model construction unit 23 applies the model parameters acquired by the learning processing unit 22 to the machine learning model to construct a machine learning model in which the learning result is reflected. This machine learning model reflects the characteristics of the road network in the target area, and the machine learning model can reproduce the behavior of the road network in the target area.

Although the machine learning model is not particularly limited, for example, a neural network, an RBF (Radial Basis Function) network, a support vector machine, etc. can be adopted.

As shown in FIG. 3, the signal control parameter candidate setting unit 24 sets the signal for each intersection in the target area based on the general-purpose setting information of the signal control parameter, the current configuration of each intersection in the target area, and the inter-intersection distance. Set candidate control parameters. The current configuration of each intersection can be obtained from the signal control setting information in the storage unit 13, and the distance between intersections can be obtained from the road network configuration information.

The simulation unit 25 uses as input information the latest vehicle sensor information, event control information, weather information, and combinations (control patterns) of signal control parameter candidates set by the signal control parameter candidate setting unit 24, and learns. The machine learning model is executed to generate, as output information, traffic information (congestion length, travel time) predicted when the traffic light is controlled with the set signal control parameter candidates. The generation of traffic information by this machine learning model is repeated by changing combinations (control patterns) of signal control parameter candidates as input information.

It is preferable to simulate all traffic conditions without narrowing down the traffic conditions to be simulated (off-peak, normal, and congested) based on vehicle sensor information.

The signal control parameter selection unit 26 selects an optimum combination of signal control parameters (control pattern) based on the traffic information acquired by the simulation unit 25 . Traffic information as output information of the machine learning model serves as an evaluation index for control patterns of signal control parameters as input information, and the control patterns are evaluated based on the traffic information to select the optimum control pattern.

Specifically, a control pattern that minimizes the congestion length is selected. In addition, the control pattern with the shortest travel time is selected. In addition, the optimal control pattern is selected by considering both the traffic jam length and the travel time. Since the congestion length and travel time are obtained for each link, the required statistical processing is performed and the evaluation is performed for the entire target area.

For all control patterns of signal control parameters, traffic information may be generated by a machine learning model and the control pattern may be evaluated. The generation of traffic information by the machine learning model and the search for the control pattern may be repeated until the pattern is found.

The signal control unit 27 transmits the combination (control pattern) of the signal control parameters selected by the signal control parameter selection unit 26 from the communication unit 11 to the signal controller 2 as the latest signal control parameters for each intersection in the target area. .

In this embodiment, the traffic management device 3 includes a learning information collection unit 21, a learning processing unit 22, a machine learning model construction unit 23, a signal control parameter candidate setting unit 24, a simulation unit 25, a signal control Although the parameter selection unit 26 and the signal control unit 27 are provided, only the simulation unit 25, the signal control parameter selection unit 26, and the signal control unit 27 are operated during signal control operation. Further, the learning information collecting unit 21, the learning processing unit 22, and the machine learning model construction unit 23 are configured by separate information processing devices, and the traffic management device 3 includes a signal control parameter candidate setting unit 24, a simulation unit 25, a signal control A parameter selection unit 26 and a signal control unit 27 may be provided to introduce a machine learning model generated by another information processing device into the traffic management device 3 .

Next, processing performed by the learning information collection unit 21, the learning processing unit 22, and the machine learning model construction unit 23 will be described. FIG. 4 is a flowchart showing the procedure of processing performed by each unit.

As shown in FIG. 4A, first, the learning information collection unit 21 collects learning information for a predetermined period regarding the road network of the target area from the storage unit 13 (ST101). This learning information is a combination of input information and corresponding output information. The input information includes signal control parameters (signal control information), vehicle detector information, event restriction information (lane restrictions, etc.), and It is weather information (rainfall, etc.), and the output information is traffic information (travel time, congestion length, etc.).

Next, in the learning processing section 22, learning processing relating to the machine learning model is performed according to a predetermined learning algorithm using the learning information collected by the learning information collection section 21 (ST102). Then, the model parameters acquired in the learning process are stored in the storage unit 13 (ST103).

As shown in FIG. 4B, the machine learning model construction unit 23 first acquires the model parameters acquired by the learning processing unit 22 from the storage unit 13 (ST201). Then, the model parameters are applied to the unlearned deep learning model to build a deep learning model reflecting the learning result (ST202).

Next, processing performed by the signal control parameter candidate setting unit 24 will be described. 5 and 6 illustrate parameter candidate configuration patterns and an outline of pattern selection used in a control method called pattern control. In the present invention, parameter candidates may be created using the idea of typifying parameter candidate configuration patterns in this figure. FIG. 7 is an explanatory diagram showing an example of the road network of the target area.

The signal control parameter candidate setting unit 24 selects signal control parameter candidates for each intersection in the target area based on the general-purpose setting information (template) of the signal control parameter, the current configuration of each intersection in the target area, and the inter-intersection distance. set.

FIG. 5A is a diagram for explaining cycle length selection in pattern control. In the cycle length pattern selection, cycle length patterns C1 to C5 are defined according to the intersection load factor ρ, a cycle length pattern is selected from the intersection load factor ρ, and the cycle length defined by the cycle length pattern is get. The intersection load factor ρ is the ratio of traffic volume to saturated traffic volume. In the present invention, parameter candidates can be created by referring to the concept of parameter categorization in this figure.

FIG. 5B is a diagram for explaining split selection in pattern control. In the pattern selection regarding the split, split patterns S1 to S6 are defined according to the main road traffic state quantity and the secondary road traffic state quantity. Get the split specified by the split pattern. The traffic state quantity is the weighted sum of the traffic volume collected by the vehicle detector 1 and the occupancy rate. In the present invention, parameter candidates can be created by referring to the concept of parameter categorization in this figure.

FIG. 6 is a diagram for explaining offset selection in pattern control. In the pattern selection regarding offset, offset patterns O1 to O10 are defined according to the inbound traffic volume and the inbound traffic volume. to get Also, the offset pattern is associated with the cycle length pattern, and by selecting the offset pattern, the corresponding cycle length pattern is determined. In the present invention, parameter candidates can be created by referring to the concept of parameter categorization in this figure.

In this way, general-purpose setting information (template) for signal control parameters is generated based on the pattern selection for signal control parameters (cycle length, offset, split). General set values for signal control parameters are registered according to the display configuration and the distance between intersections.

Specifically, the split general-purpose setting values are classified by presentation configuration (for example, 2 presentations, 3 presentations (independent), 3 presentations (right turn), 4 presentations (mutual right turn), etc.). to register. Also, general-purpose setting values for offset are classified and registered according to whether the distance between intersections is equal to or greater than a predetermined distance (for example, 200 m), that is, whether the intersection is a short link or a long link.

FIG. 7 shows an example of the road network of the target area. Here, as shown in FIG. 7A, the subarea S1 has intersections I1 and I2. The present configuration is 4 presents (mutual right turn) at the intersection I1 and 2 presents at the intersection I2. The distance between the intersections I1 and I2 is less than the predetermined distance (short link). Also, as shown in FIG. 7B, the sub-area S2 has intersections I3, I4, and I5. The present configuration is 3 presents (right turn) at intersections I3 and I4, and 3 presents (independent) at intersection I5. Also, the distance between intersections I3 and I4 is less than the predetermined distance (short link), and the distance between intersections I4 and I5 is greater than or equal to the predetermined distance (long link).

In addition, the 2nd presentation gives the right of way alternately to each road. 3-present (independent) means that the three directions of going straight, turning right and turning left are independent. The 3-present (right turn) is a separate right turn on the main road. A 4-present (mutual right turn) is a separate right turn on both the main road and the minor road.

In general setting information for signal control parameters, general-purpose setting information for signal control parameters (cycle length, offset, split) is provided for each traffic situation (for example, off-peak hours, normal hours, congested hours, etc.) according to the degree of traffic demand. setting values may be registered.

In this way, in the signal control parameter general-purpose setting information, general-purpose setting values of signal control parameters are registered according to the current configuration of intersections and the distance between intersections. Therefore, by applying the control parameter general setting information to the target area based on the current configuration of each intersection in the target area and the inter-intersection distance, candidate signal control parameters for each intersection are set.

Specifically, the cycle length candidates are set based on the general set value of the cycle length registered in the general set information. Further, split candidates corresponding to the current configuration of each intersection in the target area are set based on the general set values of the split for each current configuration registered in the general-purpose setting information. Also, offset candidates corresponding to the distances between intersections in the target area are set based on the general-purpose set value of the offset for each distance between intersections registered in the general-purpose setting information.

Next, processing performed by the signal control parameter candidate setting unit 24, the simulation unit 25, the signal control parameter selection unit 26, and the signal control unit 27 will be described. FIG. 8 is a flowchart showing the procedure of processing performed by each unit.

First, the signal control parameter candidate setting unit 24 selects signal control parameter candidates for each intersection in the target area based on the general-purpose setting information for the signal control parameter, the current configuration of each intersection in the target area, and the inter-intersection distance. Set (ST301).

Next, simulation section 25 acquires the latest vehicle sensor information, event control information, and weather information from storage section 13 (ST302). Then, with the latest vehicle sensor information, event regulation information, weather information, and a combination of signal control parameter candidates (control pattern) as input information, a learned machine learning model is executed, and output information is: Traffic information (length of congestion, travel time) predicted when a traffic light is controlled by the set signal control parameter candidate is acquired (ST303).

Next, in the signal control parameter selection unit 26, the traffic information output from the machine learning model is used as an evaluation index to evaluate a combination of signal control parameter candidates (control pattern), and an optimum signal control parameter candidate combination is obtained. (control pattern) is selected (ST304). In other words, a control pattern that minimizes congestion length and a control pattern that minimizes travel time are selected from the traffic information (congestion length, travel time) output from the machine learning model.

Next, in the signal control section 27, the selected combination of signal control parameters (control pattern) is transmitted from the communication section 11 to the signal controller 2 as the latest signal control parameter for each intersection (ST305).

As described above, the embodiments have been described as examples of the technology disclosed in the present application. However, the technology in the present disclosure is not limited to this, and can also be applied to embodiments with modifications, replacements, additions, omissions, and the like. Further, it is also possible to combine the constituent elements described in the above embodiments to form new embodiments.

INDUSTRIAL APPLICABILITY The traffic signal control device, traffic signal control system, and traffic signal control method according to the present invention have the effect of optimizing signal control parameters in real time in response to changes in traffic conditions without a skilled engineer. It is useful as a traffic signal control device, a traffic signal control system, a traffic signal control method, etc. for controlling a traffic signal installed in a target area.

1 Vehicle detector (information collection device)
2 Signal controller 3 Traffic management device (traffic signal control device, information processing device)
11 communication unit 12 control unit 13 storage unit 21 learning information collection unit 22 learning processing unit 23 machine learning model construction unit 24 signal control parameter candidate setting unit 25 simulation unit 26 signal control parameter selection unit 27 signal control unit

Claims (6)

A traffic signal control device that transmits signal control information to a signal controller to control a traffic signal installed in a target area,
collecting up-to-date traffic information for the target area;
collecting weather information for the target area;
Signal control at each intersection in the target area based on the general-purpose setting information of the signal control information set for each traffic condition according to the degree of traffic demand, the current configuration of each intersection in the target area, and the inter-intersection distance. set information suggestions,
A case in which a machine learning model is executed using the candidates for the signal control information, the latest traffic condition information, and the weather information as input information, and the traffic lights are controlled using the candidates for the signal control information as output information. Get traffic information predicted for
A traffic signal control apparatus, comprising: a control unit that evaluates candidates for the signal control information using the traffic information as an evaluation index, and selects appropriate signal control information from the candidates for the signal control information. A traffic signal control device that transmits signal control information to a signal controller to control a traffic signal installed in a target area,
collecting up-to-date traffic information for the target area;
collecting event control information for the target area;
Signal control at each intersection in the target area based on the general-purpose setting information of the signal control information set for each traffic condition according to the degree of traffic demand, the current configuration of each intersection in the target area, and the inter-intersection distance. set information suggestions,
A machine learning model is executed using the signal control information candidate, the latest traffic condition information, and the event regulation information as input information, and the signal control information candidate is used as output information to control the traffic light. Get the traffic information predicted when
A traffic signal control apparatus, comprising: a control unit that evaluates candidates for the signal control information using the traffic information as an evaluation index, and selects appropriate signal control information from the candidates for the signal control information. A traffic signal control system that controls a traffic signal installed in a target area,
Equipped with a traffic signal control device that generates signal control information based on the latest traffic situation information in the target area collected by the information collection device,
This traffic signal controller
Signal control information for each intersection in the target area based on the general-purpose setting information for signal control information set for each traffic condition according to the degree of traffic demand, and the current configuration of each intersection in the target area and the distance between the intersections. set the candidates for
A machine learning model is executed using the signal control information candidate, the latest traffic condition information, and the target area weather information as input information, and the signal control information candidate is used as output information to control the traffic light. Acquisition of traffic information predicted when controlling,
A traffic signal control system, comprising: a control unit that evaluates candidates for the signal control information using the traffic information as an evaluation index, and selects appropriate signal control information from the candidates for the signal control information. A traffic signal control system that controls a traffic signal installed in a target area,
Equipped with a traffic signal control device that generates signal control information based on the latest traffic situation information in the target area collected by the information collection device,
This traffic signal controller
Signal control information for each intersection in the target area based on the general-purpose setting information for signal control information set for each traffic condition according to the degree of traffic demand, and the current configuration of each intersection in the target area and the distance between the intersections. set the candidates for
A machine learning model is executed using the signal control information candidate, the latest traffic condition information, and the event regulation information of the target area as input information, and the signal control information candidate is used as output information. Get the traffic information predicted when you control the
A traffic signal control system, comprising: a control unit that evaluates candidates for the signal control information using the traffic information as an evaluation index, and selects appropriate signal control information from the candidates for the signal control information. A traffic signal control method for controlling a traffic signal installed in a target area,
In the information processing device,
Signal control information for each intersection in the target area based on the general-purpose setting information for signal control information set for each traffic condition according to the degree of traffic demand, and the current configuration of each intersection in the target area and the distance between the intersections. set the candidates for
A candidate for the signal control information, the latest traffic condition information of the target area collected by the information collection device, and the weather information of the target area are used as input information to execute a machine learning model, and as output information, the signal Acquiring traffic information predicted when the traffic light is controlled by the control information candidate,
A traffic signal control method, comprising evaluating candidates for the signal control information using the traffic information as an evaluation index, and selecting appropriate signal control information from the candidates for the signal control information. A traffic signal control method for controlling a traffic signal installed in a target area,
In the information processing device,
Signal control information for each intersection in the target area based on the general-purpose setting information for signal control information set for each traffic condition according to the degree of traffic demand, and the current configuration of each intersection in the target area and the distance between the intersections. set the candidates for
A machine learning model is executed using the signal control information candidate, the latest traffic condition information of the target area collected by the information collection device, and the event regulation information of the target area as input information, and the output information is the Acquiring traffic information predicted when the traffic light is controlled by the candidate for signal control information,
A traffic signal control method, comprising evaluating candidates for the signal control information using the traffic information as an evaluation index, and selecting appropriate signal control information from the candidates for the signal control information.

Images