Abstract: The present disclosure relates to systems and methods for monitoring traffic congestion. The systems may perform the methods to obtain traffic data associated with speeds or locations of a plurality of vehicles at a first time point; determine a plurality of congested links based on the traffic data; determine one or more congested areas by searching for congested links that are topologically close and clustering the congested links generated by the search; for each of the one or more congested areas, determine whether the congested area is a normal congested area or an abnormal congested area; and display congestion information associated with at least one of the one or more congested areas, wherein the congestion information may include a designation indicating whether the at least one of the one or more congested areas is the normal congested area or the abnormal congested area.

Abstract: The present disclosure relates to systems and methods for determining a path of a moving vehicle. The systems may perform the methods to obtain a plurality of location points relating to a moving device; determine at least one average velocity of the moving device between two of the plurality of location points; remove at least one interfering location point from the plurality of location points based on the at least one average velocity; determine remainders of the plurality of location points as a set of effective location points based on the at least one average velocity; determine a path of the moving device based on the set of effective location points; and store data for the path of the moving device in the one or more storage media.

Abstract: The disclosed embodiments illustrate methods and systems for predicting demand of vehicles in a transportation network. The method includes determining demand events at each of one or more locations for time intervals based on historical demand data. The demand events correspond to a demand of vehicles at one or more locations during plurality of time intervals throughout a day. The method includes creating a graph comprising nodes, and edges connecting nodes, each node being representative of a demand event from demand events. An edge is representative of dependency between two demand events from demand events. The method includes predicting demand of vehicles at a location from one or more locations during a predetermined time interval based on the graph and a real time demand of vehicles associated with other demand event. The method includes displaying demand prediction on a computing device at one or more locations of transportation network.

Abstract: The present disclosure provides an obstacle type recognizing method and apparatus, a device and a storage medium, wherein the method comprises: obtaining 3D point cloud data corresponding to a to-be-recognized obstacle; mapping the 3D point cloud data and its dimension data to a four-dimensional array; recognizing a type of the obstacle through a deep learning algorithm based on the four-dimensional array. The solution of the present disclosure can be applied to determine the type of the obstacle such as a person, a bicycle or a motor vehicle; and recognize a small-sized vehicle, a medium-sized vehicle and a large-sized vehicle; and improve the accuracy of a recognition result.

Abstract: Embodiments are disclosed for systems for a vehicle. An example system for a vehicle includes a central unit and an input device, wherein the central unit has a first interface for connecting to a first mobile device and a second interface for connecting to a second mobile device, wherein the central unit is configured to assign the first mobile device to a driver and the second mobile device to a passenger in the vehicle, wherein the central unit is configured to output information on a call directed to the first mobile device, wherein the central unit is configured to detect an input by means of the input device during the outputting of information, and wherein the central unit is configured, based on the detection of the input, to redirect the call to the second mobile device.

Abstract: Systems and methods for characterizing a driving style of an autonomous vehicle are presented. A system may include one or both of: (i) one or more sensors configured to collect information concerning driving characteristics, and (ii) a user interface configured for receiving feedback from an occupant of the autonomous vehicle concerning the operation of the autonomous vehicle; a memory containing computer-readable instructions for evaluating the driving characteristics and/or occupant feedback for a pattern(s) correlatable with driving style of the autonomous vehicle and for characterizing aspects of driving style based on the one or more patterns; and a processor configured to read the computer-readable instructions from the memory, evaluate the driving characteristics and/or the occupant feedback for one or more patterns correlatable with driving style, and characterize aspects of driving style based on the pattern(s). Corresponding methods and non-transitory media are disclosed.

Abstract: A system includes a first information exchange device associated with a first automobile, where the first information exchange device is configured to provide a first data set indicative of first information relating to the first automobile. The system includes a second information exchange device associated with a second automobile, where the second information exchange device is configured to provide a second data set indicative of second information relating to the second automobile. The system also includes one or more officiating components configured to, based on a determination that the first data set and the second data set meet a threshold data requirement, transmit a third data set indicative of third information relating to the first automobile to the second information exchange device, and a fourth data set indicative of fourth information relating to the second automobile to the first information exchange device.

Abstract: Methods, systems, and computer storage media for generating a visual representation of crime-related information on a map are provided. The crime-related information is gathered from a variety of sources and evaluated to ensure there is no bias when generating metrics that describe individual events within the information. The evaluation involves normalization of a crime's location (e.g., longitude and latitude) and statistical analysis of a crime's severity (e.g., vandalism vs. car theft). Once the metrics are derived, they are employed to generate map that plots the individual events in a visually intuitive manner, such as heat map. In one instance, the map is used to route travelers to their destination optimizing for the safest route, while also considering timing of the trip. In another instance, the map is used to alert a user when s/he enters into an area with event(s) designated as having severe criminal events.

Abstract: A method for speed prediction may include obtaining current vehicle speeds associated with first vehicles that pass through a target road section in a current time interval. The method may also include determining a current road speed associated with the target road section in the current time interval based on the current vehicle speeds. The method may also include determining a predicted speed difference between the current road speed and a future road speed associated with the target road section in a future time interval based on the current road speed and a trained prediction model, which is based on prior speed differences, wherein the current time interval and the future time interval are separated by a first time period. The method may also include estimating the future road speed based on the predicted speed difference and the current road speed.

Abstract: A method includes receiving an incoming biometric identification request on a first device from a user. First location data for the first device is determined. Second location data associated with at least one previous biometric identification request associated with the user is retrieved. A second level identification request is selectively initiated on the first device based on at least the first and second location data. A device includes a location module to determine first location data for the device, a biometric sensor to generate an incoming biometric identification request from a user, and a processor to retrieve second location data associated with at least one previous biometric identification request associated with the user and selectively initiate a second level identification request on the device based on at least the first and second location data.

Abstract: A method for providing a route in response to a request includes receiving a request for a route, comprising a start location and an end location. The method further includes determining a source based at least in part on the request and obtaining route segments from the source. Additionally, the method includes generating a suggested route, comprising a plurality of the route segments, and transmitting the suggested route in response to the request. The suggested route is generated based at least in part on the start location, the end location, and the route segments. Systems for carrying out the method are also disclosed.

Abstract: One or more braking event detection computing devices and methods are disclosed herein based on fused sensor data collected during a window of time from various sensors of a mobile device found within an interior of a vehicle. The various sensors of the mobile device may include a GPS receiver, an accelerometer, a gyroscope, a microphone, a camera, and a magnetometer. Data from vehicle sensors and other external systems may also be used. The braking event detection computing devices may adjust the polling frequency of the GPS receiver of the mobile device to capture non-consecutive data points based on the speed of the vehicle, the battery status of the mobile device, traffic-related information, and weather-related information. The braking event detection computing devices may use classification machine learning algorithms on the fused sensor data to determine whether or not to classify a window of time as a braking event.

Abstract: A method for coordinating a meeting point of a self-driving transportation vehicle and of a user including entering a desired meeting point by the user by a communication-capable terminal, transmitting the desired meeting point to a central station or to a self-driving transportation vehicle, receiving the desired meeting point by the central station or the self-driving transportation vehicle, checking current environmental data of the meeting point and/or of a route from the current location of the self-driving transportation vehicle to the desired meeting point, assessing the desired meeting point by using the environmental data, confirming the originally desired meeting point or at least one alternative meeting point by the user, receiving the confirmation by the central station or the self-driving transportation vehicle, and implementing an automated journey of the self-driving transportation vehicle to the confirmed meeting point according to the method.

Abstract: A device, system and method for dispatching responders to patrol routes is provided. A device accesses: historical patrol route information indicating patrol routes taken for each of a plurality of time periods, each of the patrol routes taken by a respective uniquely identified responder; and historical crime information indicating actual crime rates for the patrol routes taken. The device receives a request to assign responders to respective patrol routes and responsively: determines available responders for the upcoming time period; determines, based on the available responders and the historical crime information, a mapping of the available responders to the respective patrol routes that reduces and/or minimizes an expected crime rate for the upcoming time period across the respective patrol routes; and based on the mapping, causes the available responders to be dispatched to the respective patrol routes for the upcoming time period.

Abstract: A driving assistance system for vehicle, which provides a vehicle with assistance information to pass an intersection, includes: a traffic light information acquisition unit for acquiring turn-on time information of a traffic light arranged at the intersection, a running lane information acquisition unit for acquiring traffic lane configuration and traffic lane-use specification at the intersection, a direction indicator operation detection unit detecting an operation of the direction indicator, and a traffic light passage assistance control unit outputting assistance information including information on possibility to pass through the intersection is obtained based on the turn-on time information of the traffic light corresponding to the traffic lane-use specification of the expected running lane for the vehicle, the expected running lane which is determined based on the traffic lane configuration acquired by the running lane information acquisition unit and on a direction indication of detected by the direc

Abstract: A system and method is provided that creates a multimodal transportation routing that originates using a road-based vehicle which then requires parking. Parking is not necessarily near the destination, but is determined based on user preferences and specification of the relative importance of speed of travel and monetary cost and/or safety. Other factors can also influence the route selection and comprise: parking availability, user preference for parking type, vehicle restrictions, maximum distance a user is willing to walk or bike and what types of public transportation a user is willing to use. Monetary factors include: fuel costs, parking costs, tolls, and public transportation costs.

Abstract: A method and system of aggregating and converting data in a vehicle network is provided. An example method includes receiving a plurality of streams of sensor data over two or more Camera Serial Interface (CSI). The method further includes rearranging the plurality of streams of sensor data into an aggregate stream. The method further includes packetizing the aggregate stream by arranging transmission format bits at appropriate bit positions of the aggregate stream to form a packet data stream. The method further includes transmitting the packet data stream over a vehicle on-board packet data link.

Abstract: A plurality of items of environmental information, which are used for distribution control of plural items of vehicle information that are received using wireless communication by an external communication device from a plurality of surrounding vehicles, are made into an environmental information list by an environmental information setting mechanism and managed. Based on the environmental information list, for the plural items of vehicle information received by the external equipment communication device, selection is performed using a dynamic filtering part of a dynamic distribution controller and distribution control is performed using the priority level according to a dynamic priority controller. A driving assistance device that receives this information assists a driver in driving, and environmental information set in the environmental information list is generated.

Abstract: A method for point-to-point traffic prediction comprises: obtaining, from a plurality of computing devices, time-series locations of a plurality of vehicles respectively associated with the computing devices, wherein: the time-series locations form first trajectory data comprising corresponding trajectories at least passing from a first point O to a second point D within a first time interval; obtaining a traffic volume between O and D for a second time interval that is temporally after the first time interval; training one or more weights of a neural network model by inputting the first trajectory data and the traffic volume to the neural network model and using the obtained traffic volume as ground truth to obtain a trained neural network model; and inputting second trajectory data between O and D to the trained neural network model to predict a future traffic volume between O and D for the a future time interval.

Abstract: Aspects of the present disclosure relate to redirection of autonomous vehicles. Communication is initiated between a master node and an autonomous vehicle. A location of a new lane is then received from the master node, the new lane comprised of a plurality of lane nodes. Communication is then initiated between the plurality of lane nodes and the autonomous vehicle. The autonomous vehicle is then guided through the new lane by the plurality of lane nodes.

Abstract: System, methods, and other embodiments described herein relate to determining traffic flow along a roadway segment. In one embodiment, a method includes collecting, in an electronic data store from reporting vehicles that travel over the roadway segment, traffic data about at least surrounding vehicles of the reporting vehicles. The method includes analyzing the traffic data to identify a traffic flow for the respective lanes of the roadway segment. The method includes providing a signal identifying the traffic flow.

Abstract: A navigation system includes: a communication unit configured to receive vehicle environment information of a user vehicle for identifying a proximately located vehicle relative to the user vehicle during operation of the user vehicle; a control unit, coupled to the communication unit, configured to: determine proximate vehicle information of the proximately located vehicle, including a relative location and a relative distance from the user vehicle, from the vehicle environment information; and generate a navigation interface including a proximate vehicle representation of the proximately located vehicle and a user vehicle representation of the user vehicle on an interface map based on the relative location and the relative distance of the proximately located vehicle, wherein the proximate vehicle representation and the user vehicle representation are presented based on an interface scaled distance for displaying on a device.

Abstract: A train operation control system includes: a headcount estimation device that estimates the number of people in a train and the number of people on a platform by using video data outputted from a plurality of on-board cameras and a plurality of ground cameras; and a train rescheduling device that predicts a dwell time required for passengers to board and detrain from the train using the estimated headcount information estimated by the headcount estimation device and schedule information stored in an operation management device, and accordingly performs train operation rescheduling. The train operation control system can predict the dwell time accurately and accordingly perform train operation rescheduling even when the number of passengers fluctuates.

Abstract: Methods and systems are provided for performing dynamic mapping between a virtual environment and a real-world space. During dynamic mapping, a current virtual scene of the virtual environment that is within view of a user is prioritized over areas of the virtual environment that are out of view. The dynamic mapping between the virtual environment and the real-world space can be utilized to render a virtual scene for user in real-time. As a user interacts and/or moves within the virtual environment, dynamic mapping can be performed in real-time to capture any dynamic changes to the real-world space and/or the virtual environment.

Abstract: This disclosure provides a method for road condition prediction. The method comprises receiving, for at least one source vehicle, sensor data collected by a sensor associated with the source vehicle. The method further comprises identifying, based on the sensor data, at least a location with an abnormal road condition and a responsive action taken by the source vehicle. The method further comprises notifying, the location with the abnormal road condition and the responsive action to at least one target vehicle that is expected to pass the location. This disclosure also provides a computer system and a computer software product for road condition prediction.

Abstract: Exemplary embodiments described in this disclosure are generally directed to systems and methods for displaying visual content in an automobile. In an exemplary implementation, an onboard computer of an automobile receives wireless signals from a roadside unit located near the traffic intersection. The wireless signals provide information about how much time is remaining before a traffic light turns from a red state to a green state. The onboard computer uses this information to display visual content on an infotainment system in the automobile as long as the automobile is in a stopped condition. The onboard computer stops displaying the content before the traffic light turns green. In one case, the wireless signals transmitted from the roadside unit include a Signal Phase and Timing (SPaT) signal and a traffic intersection map that provides details about a topography of the traffic intersection.

Abstract: Systems and methods for determining an order accepting mode for a target service provider are provided. A method includes receiving a request for determining an order accepting mode for the target service provider. The method also includes obtaining an order accepting evaluation parameter with respect to the target service provider in response to the request. The method also includes determining an order accepting mode for the target service providers based on the order accepting evaluation parameter. The order accepting mode includes at least one of an order designating mode, an order striving mode, or an order quick-accepting mode.

Abstract: Location positioning methods, devices, systems, and computer-readable mediums are provided. One of the methods includes: receiving a vehicle identification and location information from at least one client terminal; and determining a location of a target vehicle corresponding to the vehicle identification according to the location information. The determining the location of the target vehicle corresponding to the vehicle identification according to the location information comprises: determining location information corresponding to the vehicle identification of the target vehicle received from the at least one client terminal within a set time period; determining a number of occurrences of each piece of the determined location information; and determining the location of the target vehicle corresponding to the vehicle identification according to a piece of the determined location information with a number of occurrences larger than a set threshold.

Abstract: A work machine management system includes: an operation range setting unit that sets an operation range in which a direction indicator of a work machine is operated; a traveling condition data generation unit that generates traveling condition data of the work machine; a blinker data setting unit that generates blinker data for controlling the direction indicator on the basis of the operation range and the traveling condition data; and an output device that outputs the blinker data to the work machine.

Abstract: An apparatus includes a reproducing unit configured to reproduce and display video data captured by an imaging apparatus in a predetermined display area on a display device; a feature area detecting unit configured to detect a plurality of feature areas based on feature information that is registered in advance for a tracking target, in a first frame of the video data displayed by the reproducing unit; and a tracking area detecting unit configured to detect an area including the plurality of feature areas as a tracking area that includes the tracking target, based on a distance between the plurality of feature areas detected by the feature area detecting unit.

Abstract: The present disclosure relates to systems and methods for determining an estimated time of arrival (ETA) for a route, based on a model of ETA. The systems may perform the methods to obtain a first electrical signal associated with at least one route having at least one road section; generate and save first structured data of at least one global feature vector and at least one historical duration associated with the at least one route based on the first electrical signal; generate second structured data of a model of ETA by training the model based on the at least one global feature vector and the at least one historical duration; and save the second structured data of the model of ETA in the at least one non-transitory computer-readable storage medium.

Abstract: A system and method for providing position information of a transit object to a computing device is provided. Global positioning satellite (GPS) information of a transit object can be periodically received. For each of some of the GPS information, one or more candidate points of a transit system can be identified based on the GPS information. Using the one or more candidate points, a most likely path of travel can be determined. Additional position points along the most likely path of travel can be extrapolated and transmitted to a computing device.

Abstract: A method for controlling driving of a hybrid vehicle using dynamic traffic information includes: determining whether the hybrid vehicle passes through a traffic light based on the dynamic traffic information including traffic light information and traffic situation information, and determining a driving mode of the hybrid vehicle that is used on a road disposed between the hybrid vehicle and the traffic light based on whether the hybrid vehicle passes through the traffic light.

Abstract: A vehicle and a control method for providing a notification of a collision of a vehicle and providing information on an object causing the collision are provided. The vehicle includes a communication unit communicating with a user terminal, a sensor acquiring distance information between the vehicle and at least one surrounding object and acceleration information of the vehicle, and a camera acquiring a vehicle surrounding image. A controller starts acquiring the vehicle surrounding image when the distance between the vehicle and the at least one surrounding object is less than a predetermined distance, acquires information about the at least one surrounding object approaching the vehicle and transmits the information about the at least one surrounding object to the user terminal.

Abstract: Systems and methods are disclosed for adjusting autonomous vehicle driving behavior. A controller of the autonomous vehicle may utilize an aggression factor to adjust control of the autonomous vehicle. The autonomous vehicle may detect one or more characteristics of proximate vehicles, analyze the one or more characteristics to estimate an aggression level of the proximate vehicles, and adjust the aggression factor based on the estimated aggression level.

Abstract: An approach is provided for determining a negative observation of a road feature (e.g., traffic sign). The approach involves, for example, querying a spatial data structure for a set of location points based on a spatial radius around a location of the road feature. The spatial data structure stores a plurality of location points from a plurality of location traces that did not have a road feature observation. The approach also involves map matching each location trace in the set of location points to a matched path of road links. The approach further involves determining that said each location trace is a negative observation of the road feature based on determining that the location of the road feature falls between two map-matched location points of said each location trace that are on the matched path of road links.

Abstract: Systems and methods for using a plurality of probe reports to augment a geographic database with traffic volume data. The plurality of probe reports are identified for a road segment for a time period. A probe value is determined for the road segment for the time period based on the plurality of probe reports. A probe probability value is calculated for the road segment for the time period based on the probe value. The probe probability value is adjusted using road attributes. The adjusted probe probability value is used to estimate traffic volume. The geographic database is augmented with the estimated traffic volume.

Abstract: A vehicle control system applied to a column traveling system includes: a communication unit that is disposed in a host vehicle, and configured to be able to transmit/receive communication information to/from another vehicle in a column that travels while being included in the column as a group together with the host vehicle; an output unit that is disposed in the host vehicle, and configured to be able to output a visual system output related to the sense of sight to the outside of the host vehicle; and a controller configured to be able to perform intra-column cooperation processing of controlling the output unit to cause a plurality of the visual system outputs to cooperate with each other in the entire column based on the communication information. As a result, the vehicle control system applied to the column traveling system enables appropriate column traveling to be performed.

Abstract: In one embodiment, an inventory conveyance system has at least one longitudinal track that is elongate along a longitudinal direction. The system has at least one transverse track that extends from the at least one longitudinal track along a transverse direction that is angularly offset from the longitudinal direction. The transverse track can ride along the at least one longitudinal track along the longitudinal direction. The system has at least one inventory transfer vehicle that is coupled to the transverse track such that the transfer vehicle can ride along the at least one transverse track along the transverse direction. The at least one inventory transfer vehicle has a body, and at least one end effector supported by the body. The at least one end effector can removably couple to an inventory storage container.

Abstract: A method for providing information about traffic regulations in a vehicle is disclosed. The method comprises identifying a road sign in a surrounding area of the vehicle (e.g. by means of a perception system of the vehicle). Further, the method comprises identifying a traffic regulation associated with the identified road sign, in a current jurisdiction of vehicle, and retrieving traffic regulation data comprising information about a set of predefined road signs and associated predefined traffic regulations in a predefined jurisdiction. Still further, the method comprises comparing the identified traffic regulation with the retrieved traffic regulation data in order to determine if the identified road sign is not comprised in the set of predefine road signs, or if the identified traffic regulation differs from the associated predefined traffic regulations.

Abstract: An approach is provided for automatically detecting a merge lane traffic jam. The approach involves, for example, determining a plurality of road links in proximity to a merge point comprising a highway and a ramp. The method also involves processing probe data collected from the plurality of road links to classify the plurality of road links, one or more sublinks of the plurality of road links, or a combination thereof into at least one of a highway upstream class, a merging area class, a highway downstream class, a ramp downstream class, and a ramp upstream class. The method further involves determining vehicle speed data for the highway upstream class, the merging area class, the highway downstream class, the ramp downstream class, the ramp upstream class, or a combination thereof. The method further involves automatically determining an occurrence of the merge lane traffic jam based on the vehicle speed data.

Abstract: A method for data communication between at least two mobile participants of a wireless communication system including observing the surroundings of an observer participant, periodically transmitting data concerning the surroundings observation by the observer participant, determining the amount of relative motion between at least the observer participant and one or more of the participants in the surroundings, and increasing or decreasing the period for sending a repeated transmission of the selected data concerning the surroundings observation by the observer participant based on the result of the determination of the amount of relative motion between at least the observer participant and one or more of the participants in the surroundings.

Abstract: A method and system are provided. The method includes performing, by at least a computer processing system having a hardware processor, a particulate mapping process to predict particulate exposure at a target location based on an estimated particulate source, an estimated particulate source output, and a fine-grained weather forecast for the target location. The performing step includes estimating the target location using a fine-grained weather hindcast and inverse modelling. The performing step further includes generating observations of particulate exposure for one or more specific particulates, using a set of particulate sensors.

Abstract: A work vehicle coordination system includes a traveling work parameter setting section (41) included in each work vehicle for setting a traveling work parameter to define a traveling work of each work vehicle, a communication processing section (71, 72) for effecting data communication between/among the plurality of work vehicles, a traveling work parameter acquisition section (42) for acquiring the traveling work parameter set in each work vehicle, a difference data generation section (43) for generating difference data indicative of a difference between/among the traveling work parameters set in the respective work vehicles, and an informing section (56) for informing the difference data.

Abstract: Method and apparatus are disclosed for mobile device tethering for vehicle systems based on variable time-of-flight and dead reckoning. An example vehicle includes a communication module to communicate with a mobile device using multiple frequency bands and a body control module. The body control module at an interval, estimates a location of the mobile device relative to the vehicle based on time-of-flight measurements using one of the multiple frequency bands selected based on a previous location estimate. Between the intervals, the body control module tracks the location of the mobile device using dead reckoning. Additionally, the body control system controls a subsystem of the vehicle based on the location of the mobile device.

Abstract: Acceleration data is received for each of a plurality of times t1 . . . tn, from one or more components in a host vehicle. A traffic jam assist (TJA) system is based on the acceleration data, thereby actuating one or more of steering, braking, and propulsion.

Abstract: A system and method for transportation services includes receiving customer preference data of a customer, including one or more favorite drivers or one or more preferred drivers, and one or more preset service zones for one or more drivers. In response to receipt of a service request, the system retrieves a set of driver data related to at least one favorite driver or preferred driver of the customer associated with one or more of the preset service zones containing a pickup location or a drop off location of the service request. One of the favorite drivers or preferred drivers of the customer is selected from the set based on compatibility. Preset service limitation data of drivers and blacklists of both a customer and one or more drivers are additionally or alternatively used to determine compatibility or incompatibility of drivers with a customer for matching purposes.

Abstract: Systems and methods of information corroboration are disclosed herein. The systems and methods can include receiving an initial report from at least one detecting party and receiving at least one secondary report from at least one corroborating party. The initial information set and the secondary information set can then be compared and applied to create a reliability factor for the initial information set. The reliability of the initial information set can be determined using the reliability factor; and providing virtual compensation to at least one of the at least one detecting party and the at least one corroborating party, when the initial information set is determined to be reliable.

Abstract: Methods and devices for detecting traffic signals and their associated states are disclosed. In one embodiment, an example method includes a scanning a target area using one or more sensors of a vehicle to obtain target area information. The vehicle may be configured to operate in an autonomous mode, and the target area may be a type of area where traffic signals are typically located. The method may also include detecting a traffic signal in the target area information, determining a location of the traffic signal, and determining a state of the traffic signal. Also, a confidence in the traffic signal may be determined. For example, the location of the traffic signal may be compared to known locations of traffic signals. Based on the state of the traffic signal and the confidence in the traffic signal, the vehicle may be controlled in the autonomous mode.

Abstract: A method of predicting traffic congestion and controlling traffic signals based on deep learning according to an embodiment of the present invention includes: analyzing regional network outflow behavior based on a per-intersection traffic demand pattern or traffic signal control, and determining a specific intersection to be a control target intersection based on the results of the analysis; generating 2D space-time images by analyzing the data of predetermined customized composite data corresponding to the control target intersection and a plurality of pieces of image data for the control target intersection in terms of time and space; generating a real-time traffic congestion index by using the 2D space-time image of the control target intersection and the 2D space-time image of the data of the customized composite data corresponding to the control target intersection; and controlling the traffic signals of the control target intersection based on the real-time traffic congestion index.