Abstract: The present disclosure relates generally to aggregation of data associated with events related to automotive vehicles. Automotive vehicles may include a variety of sensing devices used in local sensing operations. However, these sensing devices may not be leveraged beyond the local sensing operations. When automotive vehicles are operated, sometimes events occur. As discussed herein, an event-based data aggregation service may aggregate sensing data from one or more sensing devices, such as sensing devices of the automotive vehicles, in response to receiving an event notification associated with one or more of the events and may use the sensing data when responding to the event notification.

Abstract: A system or a method for rendering building extrusion on an electronic map. The system receives geographic location information from a client device. Responsive to receiving the geographic location information, the system obtains a portion of two-dimensional electronic map data and a portion of three-dimensional electronic map data representing a building at a location indicated by the received geographic location information. The system also analyzes user data to obtain contextual information associated with the building, and renders the area of the electronic map with the contextual information associated with the building. The building on the electronic map is rendered in three dimensions as an extruded element, and rest of the area on the electronic map is rendered in two dimensions.

Abstract: A vehicle control device includes a first control unit that executes, when an abnormality of a driver of a vehicle is detected, stop control, a second control unit that executes, when the vehicle is determined to have a risk of collision, deceleration control, a determination unit that identifies an object around the vehicle as a target candidate of the collision and determines whether or not there is the risk of the collision with the identified target candidate, and a setting unit that sets, when the abnormality is detected, an operation mode of the deceleration control to a special mode from a normal mode, the normal mode provided for cases in which the abnormality is undetected. The determination unit expands a range for identifying the object around the vehicle as the target candidate of the collision in the special mode as compared with the range in the normal mode.

Abstract: The described aspects and implementations enable efficient identification of real and image signs in autonomous vehicle (AV) applications. In one implementation, disclosed is a method and a system to perform the method that includes obtaining, using a sensing system of the AV, a combined image that includes a camera image and a depth information for a region of an environment of the AV, classifying a first sign in the combined image as an image-true sign, performing a spatial validation of the first sign, which includes evaluation of a spatial relationship of the first sign and one or more objects in the region of the environment of the AV, and identifying, based on the performed spatial validation, the first sign as a real sign.

Abstract: A system for displaying information for a vehicle includes a plurality of vehicle sensors, a display, and a controller in electrical communication with the plurality of vehicle sensors and the display. The controller is programmed to detect a relevant traffic signal in an environment surrounding the vehicle using the plurality of vehicle sensors, receive information about the relevant traffic signal using the plurality of vehicle sensors, determine a status of the relevant traffic signal based on the received information, and display a graphic based on the status of the relevant traffic signal using the display.

Abstract: An autonomous vehicle vendor lot may include a plurality of vehicle selection indicators, a visual navigation system, and a control system. The indicators may be distributed in the lot, associated with a respective parking spot in the lot, and operable to generate a visual indication indicative of a selection of a vehicle in the respective parking spot. The navigation system may be operable to generate a visual indication of a route between various locations in the lot. The control system may be operatively connected to the indicators and the navigation system, and configured to: receive a vehicle search query; identify at least one vehicle in the lot corresponding to the query; operate each vehicle selection indicator corresponding to each identified vehicle; identify a respective location in the lot for each identified vehicle; and operate the visual navigation system to generate a visual indication of a route to at least one identified vehicle.

Abstract: An approach is provided for accurate travel time prediction. The approach involves, for example, determining probe data collected within a threshold proximity of a vehicle location and a pickup location. The probe data may be collected, for example, from a location sensor of at least one probe vehicle that has previously traversed the vehicle location and the pickup location. The approach also involves processing the probe data to identify a travel time of a route taken by the at least one probe vehicle from the vehicle location to the pickup location. The approach also involves providing the travel time as an output indicating a wait time for a vehicle at the vehicle location to reach the pickup location.

Abstract: A system and method for recognizing traffic signs during autonomous driving comprises a camera module obtaining a first recognition, a sensor obtains behavior information of the host vehicle and of nearby vehicles and a connected training module generates parameters for traffic sign recognition according to information as to the behavior of the host vehicle and the nearby vehicles. A recurrent neural network module is connected with the training module and the camera module, and outputs a second traffic sign recognition according to the parameters and the first recognition. Training parameters of the second recognition comprise the traffic sign recognition parameters and the first recognition, the accuracy of the training result being improved by combining other sensors to perform traffic sign recognition training.

Abstract: A system comprises a computer including a processor and a memory. The memory includes instructions such that the processor is programmed to receive geoindexed detected vehicle event data from at least one vehicle occurring within a predefined time period, normalize the geoindexed detected vehicle event data according to Global Position System (GPS) data corresponding to a geoindex map, and generate an infrastructure recommendation based on the normalized and aggregated geoindexed detected vehicle event data.

Abstract: A method, apparatus and computer program product are provided for controlling a functional road object. For example, at least one processor receives road sign attribute data indicating at least one attribute of a road sign and receives weather forecast data indicating a weather forecast of a location in which the road sign is disposed. The road sign includes at least one machinery for mitigating exposure to one or more weather conditions. The at least one processor identifies a state of visibility for the road sign using the road sign attribute data and the weather forecast data and generates a control signal for controlling the at least one machinery using the state of visibility.

Abstract: Devices, systems, and methods for remote deicing/anti-icing of an aircraft are described herein. One remote operator deicing/anti-icing station located in a remote location from a deicing/anti-icing rig includes a number of remote rig control components for actuation by a remote operator, wherein the remote rig control components include a remote operator user interface, located outside of a rig being at least partially controlled by the remote operator deicing/anti-icing station, the rig including a truck and a deicing/anti-icing control cabin that controls disbursement of substances to deice/anti-ice an aircraft, and a communication device that communicates instructions from the remote operator user interface and the number of remote rig control components to the rig to control at least one of the truck and the deicing/anti-icing control cabin.

Abstract: A method for reducing parking violations includes: receiving, by a controller of a vehicle, sign information of one or more traffic signs in an area surrounding the vehicle, wherein the sign information is a time series of data acquired by a set of cameras as the vehicle moves, using the vehicle as a frame of reference; identifying, by the controller, a potential parking spot in an area surrounding the vehicle; determining, by the controller, using the sign information, whether the potential parking spot is valid or invalid for the vehicle; and generating, by the controller, a notification if the potential parking spot is invalid.

Abstract: Disclosed is a method for a network to communicate with a vehicle in a wireless communication system. The method may comprise: receiving a location message from a vehicle stopped in a predetermined area; receiving a message about a traffic light system from a traffic light in the predetermined area; and acquiring the vehicle registration number of the stopped vehicle on the basis of a predetermined condition being satisfied. In particular, the predetermined condition may be satisfied when the stopped vehicle is determined to have committed a parking violation on the basis of the location message of the stopped vehicle and the message about the traffic light system.

Abstract: A traffic obstruction early warning system installed in roadway locations with limited visibility or restricted line of sight to warn drivers approaching a hazardous road condition well in advance so that precautionary measures may be taken and thereby reduce the risk of the multiple vehicle involvement. Selected roadway locations for the system installations can be the location of past vehicle pile-ups, or at-risk locations. The system timely and cohesively integrates inputs from a plurality of roadway sensors and human reporting to deploy a variety of visible and audible alerts to approaching drivers, law enforcement, emergency responders, local hospitals, utility companies, vehicle apps, and others using a variety of communication modalities.

Abstract: A system and method are disclosed for overheight vehicle impact avoidance and incident detection. A detection subsystem of the system determines whether an incoming vehicle is clear to pass, depending at least on its height. The detection subsystem relies on distance sensors located along the freeway to detect the highest point of the vehicle and outputs an indication of whether the vehicle can pass. A warning subsystem receives the indication that a vehicle is overheight and provides a warning indication to the driver about the vehicle's inability to pass an upcoming structure. The warning subsystem may also perform a variety of other tasks, such as, for example, logging a variety of information about the vehicle and the incident, sending data about the incident locally to a central command, and generating reports.

Abstract: An automatic speed control device includes: an upper limit speed setting part for setting a first speed as an upper limit speed during running on a main road and setting a second speed slower than the first speed as the upper limit speed during running on a connecting road; a target speed setting part for setting a target speed to less than or equal to the upper limit; and a speed control part for controlling a vehicle speed based on the target speed. The speed control part makes the vehicle accelerate according to a depression amount of the accelerator pedal when the pedal is depressed. The upper limit speed setting part sets the upper limit speed to a speed faster than the second speed and less than the first speed when the vehicle speed has become faster than the second speed due to depression of the pedal.

Abstract: A system and method for automatically negotiating Internet access between a user and one of a plurality of Internet connection providers. Users can buy or bid for Internet bandwidth, for example, through a server or website or by direct communications with an Internet access point such as, for example, a WIFI access point.

Abstract: A road information providing system includes: a first traffic state recognition unit that recognizes a first traffic state that is a traffic state of first-type movable bodies; a second traffic state recognition unit that recognizes a second traffic state that is a traffic state of second-type movable bodies smaller in size than the first-type movable bodies; a specific road area extraction unit that extracts, as a specific road area, a road area satisfying traffic determination conditions including a determination condition that the first traffic state shows that a traffic volume of the first-type movable bodies has decreased and a determination condition that the second traffic state shows that the second-type movable body is traveling; and a traveling obstruction information providing unit that provides traveling obstruction information serving as notification that an event has occurred which obstructs the traveling of the first-type movable bodies in the specific road area.

Abstract: Methods, computer programs, apparatuses, a transportation vehicle, and a control center for resolving a deadlock traffic situation of a transportation vehicle. The method includes detecting the deadlock traffic situation, reporting the deadlock traffic situation to a control center, entering a tele-operated driving session in coordination with the control center, determining information on an identification of the deadlock traffic situation in coordination with the control center, forwarding the information on the identification of the deadlock situation to other transportation vehicles, and resolving the deadlock traffic situation using tele-operation by the control center.

Abstract: Systems and techniques are described for consuming data in an intelligent transport system. In some implementations, a system includes a display screen device and sensors. The sensors generates data describing sensor observations of a roadway at a first location and provides data describing the observations to the display screen device. The display screen device receives the data and determines an event and a type of the event. The display screen device displays second data indicative of the type of event, the second data being of a format that is consumable by a sensor on a vehicle traversing the roadway towards the first location, the sensor (i) located within a first resolution distance from the display screen device and (ii) located outside a second resolution distance of detecting the event, wherein the second data is used by an on-board processing system of the vehicle to adjust its driving behavior.

Abstract: An on-vehicle recording control apparatus includes a video data acquiring unit to acquire video data of surroundings of a vehicle; a voice data acquiring unit to acquire outside-vehicle-cabin voice data from an outside-vehicle-cabin voice collecting unit; an event detecting unit to detect an event for the vehicle; a stop detecting unit to detect a stop of the vehicle; a person detecting unit to detect a person in a vicinity of the vehicle from the video data; and a recording control unit to store, when the event is detected, first event recording data based on the video data and to store, when the person is detected after the stop of the vehicle is detected within a predetermined time period after the event is detected, second event recording data based on the video data and the outside-vehicle-cabin voice data until a predetermine time period has elapsed after the person is detected.

Abstract: A system and method for providing real-time current-operator or insurance policy updates for a vehicle based on current operating characteristics and an operator profile. A current operating pattern is generated from the current operating characteristics and is compared to an operating pattern of another vehicle that was involved in an incident to generate a current profile of the vehicle. The profile is adjusted based on an operator profile for the current operator of the vehicle. As the operator operates the vehicle, the current-operator or insurance policy is automatically adjusted in real time as the profile changes in response to changes in the operating characteristics of the vehicle.

Abstract: An example system learns from traffic disturbances or perturbations to improve overall traffic flow. The perturbations may be related to specific times such as morning rush hour, or for all times of day. The improvement to overall traffic flow may be measured by time lost in traffic delays, or by time of travel, or by risk of accidents.

Abstract: A vehicle display control device includes a memory and a processor coupled to the memory. The processor is configured to: recognize a traffic regulation mark provided on a traveling path of a car, the traffic regulation mark indicating traffic regulation; specify a valid regulation range used as a valid range of regulation indicated by the traffic regulation mark based on the recognized traffic regulation mark; and control a display device mounted on the car to display regulations information on a display area, the regulations information including contents of regulation indicated by the recognized traffic regulation mark. The processor is configured to switch displaying the regulations information into another upon satisfying a predetermined condition in a case where the valid regulation range is not specified.

Abstract: A sheet-shaped magnetic marker (1) to be laid on a road surface so as to be able to be detected by a magnetic sensor attached to a vehicle to achieve assist for driving operation of the vehicle by a driver or control on a vehicle side to achieve automatic driving independently from operation of the driver is divided into a plurality of regions in a matrix shape by a cut line (1C) cutting a magnet sheet (11) and a nonskid layer (181), with an adhesive layer being left. Thus, if peeling partially occurs, a region including the peeled part can be isolated, and expansion of peeling can be prevented.

Abstract: A driving assistance method of assisting driving of a vehicle, includes, by a computer, acquiring biological information of a driver who is driving the vehicle, acquiring environment information of the driver, acquiring operation information of the driver, generating biological index data from the biological information, generating integrated information by aligning and combining time series of the biological index data, the environment information, and the operation information, calculating accident risk information after a predetermined time, by inputting the integrated information to an accident risk prediction model set in advance, and calculating factor information of the accident risk information by inputting the accident risk information, the integrated information, and accident risk judge information set in advance to a factor calculation model set in advance.

Abstract: A target device is associated with a source device. A system includes a target device that enters an association mode, obtains an identification code, and broadcasts the identification code. A source device receives the broadcast, obtains authorization to associate with the target device, and provides a message to an association server. The association server receives the message and associates the target device and the source device in response thereto.

Abstract: A method for safely ascertaining infrastructure data for driving a motor vehicle in at least partially automated fashion. The method includes receiving data signals, which represent infrastructure sensor data generated by at least one infrastructure sensor and/or motor vehicle data generated by at least one source motor vehicle, receiving safety condition signals, which represent at least one safety condition for safely ascertaining infrastructure data based on the data, checking whether the at least one safety condition is fulfilled, ascertaining infrastructure data, on the basis of which it is possible to drive a destination motor vehicle in at least partially automated fashion, based on the data as a function of a result of the check as to whether the at least one safety condition is fulfilled, generating infrastructure data signals, which represent the ascertained infrastructure data, outputting the generated infrastructure data signals.

Abstract: A system and method of adjusting a field of view in an imaging system includes transmitting light across a transmission optical path and defining a field of view encompassing both uniform and spatially tenuous target objects within the transmitted light. A sensor within a return optical path of reflected light from at least a portion of one of the target objects allows a data processing computer to compile an image from a series of data outputs from the sensor. The image is analyzed to determine a region of interest within the image and by dynamically adjusting the light source, the computer is configured to change the field of view of the light source such that the image includes a higher resolution and/or signal intensity for the region of interest. The region of interest may include at least one spatially tenuous target object.

Abstract: A steering control device includes a distance calculation unit which calculates a distance between a front gaze point, which is on a straight line extending forward of a vehicle from a center of the vehicle, and a center line indicating the center of a lane where a vehicle is traveling, a steering angle detection unit which detects a steering angle of the vehicle, and a steering control unit which causes a motor, which assists steering of the vehicle, to assist the steering based on an angle formed by the lane and the straight line extending forward of the vehicle when the distance is larger than a predetermined distance, and causes the motor to assist the steering so as to fix the steering angle when the distance is the predetermined distance or smaller.

Abstract: Apparatus and methods are provided for extracting and displaying information and data from a stream of information on a pair of smart glasses. One or more content filters describing the desired information and data may be communicated to a content filtering module. The content filtering module may process the stream of information to search for the desired information and data. When the desired information is found within the stream of information, the content filtering module may highlight the desired information, while blurring all other information, within a display on the pair of smart glasses.

Abstract: Disclosed is an electronic apparatus for detecting risk factors around a vehicle. The present electronic apparatus comprises a communicator, a memory storing at least one computer-executable instruction, and a processor for executing the at least one computer-executable instruction, wherein the processor receives, through the communicator, an image obtained from a camera located to capture the outside of the vehicle, calculates a rollover index of an external vehicle on the basis of an image of the external vehicle included in the obtained image, and performs a preset operation according to the calculated rollover index.

Abstract: An optical sensor system operative for receiving, by a processor, a first image captured by a visible light camera, determining a value of a characteristic of the first image, determining an environmental condition in response to the value being less than a threshold, activating an infrared camera in response to the environmental condition, capturing a second image by the visible light camera and a third image by the infrared camera, generating a fused image in response to the second image and the third image, detecting an object in response to the fused image, and controlling a vehicle in response to the detection of the object.

Abstract: One or more techniques and/or systems are provided for parking space routing. For example, parking data for a parking region, such as a parking lot, may be obtained from one or more data sources (e.g., vehicle sensor data, a parking lot camera, parking meter transaction data, etc.). Routes from a current location of a vehicle to available parking spaces within the parking region may be computed. The routes may be ranked based upon various criteria, such as convenience, congestion, travel time, travel distance, a parking space fill order, etc. A route, having a rank above a threshold (e.g., a highest ranked route), may be provided to a driver of the vehicle, such as through a vehicle navigation unit, a mobile device, a wearable device, etc. The route may be provided to autonomous driving functionality of the vehicle for automatic routing and navigation of the vehicle to the parking space.

Abstract: A method, apparatus and computer program product are provided for predicting a state of visibility for a road object. For example, at least one processor receives road sign attribute data indicating at least one attribute of a road sign. The processor further receives weather forecast data indicating a weather forecast of a location in which the road sign is disposed, and using the road sign attribute data and the weather forecast data, a state of visibility for the road sign is identified.

Abstract: A method for monitoring a vehicle includes determining that the vehicle is stopped and determining a location where the vehicle is stopped. Traffic congestion corresponding to the location where the vehicle is stopped may also be determined. A safety action may be taken based at least in part on whether the vehicle is stopped on a highway and whether the traffic congestion is causing the vehicle to be stopped.

Abstract: A detection system for a vehicle comprises a blind spot detection module and a glasses module. The blind spot detection module comprises a first video recording device recording a vehicle surrounding image; a first identification device generating a blind spot identification result; a first determination device determining whether to transmit the vehicle surrounding image and/or a blind spot warning message; and a transmitting device transmitting the vehicle surrounding image and/or the blind spot warning message.

Abstract: A method for reducing processing power of a data processing hardware executing one or more applications is provided. The method includes receiving communication messages and identifying a first application outputting a first message based on at least one communication message. The first application is associated with a first priority value. The method includes determining a group of high-priority applications where each application has a priority value being higher than or equal to the first priority value and determining a group of low-priority applications where each application has a priority value being lower than the first priority value. The method includes discarding one or more communication messages that are not relied on by the group of high-priority applications for a predefined period of time. The method may also include sending, to the group of low-priority applications, instructions causing the one or more applications of the low-priority group to stop executing.

Abstract: A HUD apparatus that is an AR display apparatus mounted on an on-vehicle system includes: an image selection unit configured to input an image photographed by a camera, select and extract an area of an object from the image; a visibility judgment unit configured to judge visibility of a user with respect to the area of the object on a basis of an index value; an AR image generator unit configured to generate an AR image regarding the object by subjecting the area to image processing for improving the visibility on a basis of the visibility of the area of the object; and an AR display unit configured to superimpose and display the AR image onto a screen. The visibility judgment unit controls whether the AR image is to be displayed or not and content of the image processing to be changed in accordance with the visibility.

Abstract: An abnormality detection device 1 includes: a vibration acquisition unit 11 configured to acquire an acoustic signal generated during passage of a vehicle on a road; a frequency domain conversion unit 12 configured to convert the acquired acoustic signal into a frequency domain signal; an unexpectedness determination unit 13 configured to determine whether there is unexpectedness at each predetermined frequency using the frequency domain signal; and an abnormality determination unit 14 configured to determine whether there is an abnormality in the road based on the number of frequencies at which it is determined that there is the unexpectedness.

Abstract: An information providing method is performed in an information providing system. The information providing method includes: acquiring pieces of speed information of a vehicle in association with identification information of an in-vehicle device from the in-vehicle device via roadside antennas, each of the pieces of speed information having been stored in the in-vehicle device each time the vehicle moves a prescribed distance before the vehicle passes by the roadside antennas; and causing an information display device to display evaluation information in association with the identification information, the evaluation information indicating a frequency of occurrence of sudden acceleration or deceleration events of the vehicle obtained from a proportion of differences between calculation values outside a threshold range, the calculation values being calculated on the basis of the pieces of speed information in a prescribed period corresponding to the pieces of speed information stored in the in-vehicle device.

Abstract: The present disclosure is directed to automatically receiving, modifying, sequencing, and displaying vehicle images for marketing to prospective buyers. A seller uploads images of a vehicle to the system, which system uses artificial intelligence and machine learning to classify the images, identify objects within the images, add backgrounds, banners, and hotspots, and generate metadata associating the results of the foregoing processes with the particular images. The system uses the stored metadata to sequence the images in a format predetermined by the seller and upload the sequenced images for display to a prospective buyer.

Abstract: A system that determines a nominal path based on interpolated lane edge data can include a processor and a memory. The memory includes instructions such that the processor is configured to receive a sensor data representing a perceived lane edge; receive map data including a lane edge; interpolate the sensor data and interpolate the map data; fuse the interpolated sensor data and the interpolated map data; and generate predicted lane edge lane edge centers based on the fused interpolated sensor data.

Abstract: An apparatus for assisting driving of a host vehicle includes: a camera mounted on the host vehicle and having a field of view outside of the host vehicle, the camera configured to acquire image data; and a controller configured to: process the image data, identify a speed limit of a road on which the host vehicle is driving and whether there is a speed enforcement for the host vehicle based on the image data; and provide information about the speed limit of the road to a driver of the host vehicle based on the speed limit of the road and whether there is the speed enforcement for the host vehicle. Thereby, the vehicle can be prevented from driving in excess of the speed limit.

Abstract: A method for controlling an automated driving operation of a vehicle involves authorizing the automated driving operation according to a number of predetermined conditions. Traffic information and event information is received by the vehicle. The traffic information contains place- and time-referenced information about a traffic jam on a part of the route lying ahead of the vehicle and the event information contains place- and time-referenced information about an event on the part of the route lying ahead. The traffic information and the event information are evaluated by the vehicle as belonging together if these are close together in terms of place and time. The automated driving operation of the vehicle is not authorized if event information and traffic information is available for a predetermined prediction horizon, but only then if these are evaluated as not belonging together.

Abstract: An operating method of a massage chair comprising: driving the massage chair according to a massage mode; acquiring a user state; when he user state has a sleep mode, changing the massage mode to the sleep mode and driving the massage chair according to the changed sleep mode, and controlling an object related to the sleep mode to be adjusted; and driving the massage chair according to an optimal sleep mode by learning an artificial neural network (ANN) so as to acquire the optimal sleep mode corresponding to sleep habit pattern data in the sleep mode.

Abstract: Systems, methods, and apparatus related to determining ice hazards on roads based on crowdsourced data from vehicles. In one approach, a server receives weather data and location data from each of several vehicles. The weather data is timestamped when received. The server determines, using the location data, a geographic region in which each vehicle is located. The weather data is stored in a database associated with the respective geographic region for the vehicle that transmitted the weather data. The server periodically scans the database to select weather data received over a selected time period. The selected data is analyzed to determine whether an ice hazard exists for one or more regions. A communication is sent to vehicles in those regions having the determined ice hazard.

Abstract: A system includes sensors deployed along a vehicle pathway to detect the presence of a plurality of vehicles. An embodiment of a method for detecting speed may include generating from the sensors presence data of each of the plurality of vehicles and transmitting the detected presence data to a base station. The transmitting may include transmitting the detected presence data from the sensors to an access point and transmitting the detected presence data from the access point to the base station. The base station determines a speed of each of the plurality of vehicles. The speed may be determined at a periodic interval responsive to a predetermined distance between the sensors and a difference in the detection time of each of the plurality of vehicles at each of the sensors.

Abstract: A system for determining a vehicle queue length in a connected vehicle infrastructure environment includes a vehicle traffic data evaluation module with a processor configured via executable instructions to receive vehicle traffic data of multiple vehicles, the vehicle traffic data comprising basic safety messages, create a geometric representation of a vehicle queue, the vehicle queue comprising one or more segments, each segment comprising a set length, extract data of speed, location, date and time from the basic safety messages, aggregate extracted data with the geometric representation of the vehicle queue, assign a speed value of a basic safety message of a vehicle to a segment when the vehicle is identified to be located within the segment of the vehicle queue, detect a sequence of segments comprising assigned speed values, and determine a vehicle queue length based on the set length of each segment.

Abstract: Proposed herein are a signal control apparatus and method based on reinforcement learning. The signal control apparatus includes: a photographing unit configured to acquire an intersection image by capturing an image of an intersection; a control unit configured to calculate the congestion level information of the intersection by analyzing the intersection image acquired by the photographing unit, and to calculate control information for a subsequent signal by using a reinforcement learning model, trained by using state information calculated based on the congestion level of the intersection and reward information as input values, and the congestion level information; and a drive unit configured to drive traffic lights according to the control information for a subsequent signal calculated by the control unit.