Abstract: Techniques to train a model with machine learning and use the trained model to select a bounding box that represents an object are described. For example, a system may implement various techniques to generate multiple bounding boxes for an object in an environment. Each bounding box may be slightly different based on the technique and data used. To select a bounding box that most closely represents an object (or is best used for tracking the object), a model may be trained. The model may be trained by processing sensor data that has been annotated with bounding boxes that represent ground truth bounding boxes. The model may be implemented to select a most appropriate bounding box for a situation (e.g., a given velocity, acceleration, distance, location, etc.). The selected bounding box may be used to track an object, generate a trajectory, or otherwise control a vehicle.

Abstract: An action support device includes a controller and a notification unit. The controller is configured to acquire action information of a user, the action information being extracted based on an action history of the user, and including a route having a start point and an end point, and a departure time at the start point, acquire traffic information, and determine whether or not a road obstacle or an operation obstacle indicated in the traffic information acquired before the departure time occurs on the route indicated in the action information. The notification unit is configured to, when the controller determines that the road obstacle or the operation obstacle indicated in the traffic information acquired before the departure time occurs on the route indicated in the action information, notify the user of information relating to the traffic information.

Abstract: A control device for a vehicle capable of operating in an automated driving mode for automatically controlling at least the accelerating/decelerating control of the steering control and the accelerating/decelerating control of a vehicle includes: a route information acquisition unit; and an automated driving control unit that decides an action plan on a basis of map information, the action plan includes a target vehicle speed sequence that defines a target vehicle speed at the respective predetermined points at least on a road along which the vehicle will travel next, and the automated driving control unit calculates requested braking force that is braking force for decelerating the vehicle to target vehicle speed when the target vehicle speed is achieved by deceleration, calculates a predicted temperature of a brake device when the requested braking force is achieved, and decides a utilization proportion of the brake device for the requested braking force.

Abstract: A system may include one or more sensors that acquire location information associated with the one or more sensors. The system may also include a processor that receives a first set of data comprising environmental information associated with a location, receives the location information from the one or more sensors, and determines whether a risk of damage to property associated with at least one of the one or more sensors is greater then a threshold based on the location information and the environmental information. When the risk is greater than the threshold, the processor may send a notification including the risk of damage to the property to a computing device that may provide an audio or visual indication of the notification.

Abstract: A system including a plurality of warning devices (100) each with a radio transmitter (111) and a positioning system (109). Each warning device is arranged to communicate with at least one other of the warning devices so that at least one of the plurality of warning devices can determine the mutual positions of the plurality of warning devices, determine a pattern from the mutual positions and transmit a specific message corresponding to the pattern.

Abstract: In one embodiment, a system generates a plurality of trajectory candidates for an autonomous driving vehicle (ADV) from a starting point to an end point of a particular driving scenario. The system generates a reference trajectory corresponding to the driving scenario based on a current state of the ADV associated with the starting point and an end state of the ADV associated with the end point, where the reference trajectory is associated with an objective. For each of the trajectory candidates, the system compares the trajectory candidate with the reference trajectory to generate an objective cost representing a similarity between the trajectory candidate and the reference trajectory. The system selects one of the trajectory candidates as a target trajectory for driving the ADV based on objective costs of the trajectory candidates.

Abstract: Disclosed is a method of providing driving information of a vehicle, including tracking and recognizing driver gaze of the vehicle, checking whether the driver gaze is directed toward a display of the vehicle, upon checking that the driver gaze is directed toward the display of the vehicle, checking coordinates of an actual position corresponding to a point on the display, toward which the driver gaze is directed, acquiring an image corresponding to the checked coordinates, and displaying the acquired image using an augmented reality provision unit included in the vehicle.

Abstract: Smart car operations are detailed including capturing a point cloud from a vehicle street view and converting the point cloud to a 3D model; applying a trained neural network to detect street signs, cross walks, obstacles, or bike lanes; and updating a high definition (HD) map with the neural network output.

Abstract: A processor of a vehicle is programmed to send a message to a mobile device connected to the processor to request an application permissions update for the vehicle from a remote server, responsive to the vehicle lacking application permissions for a vehicle-enabled mobile application executed by a mobile device. The processor is further programmed to receive, from the server, the application permissions update including both the application permissions and a diagnostic request to receive data from the vehicle.

Abstract: Systems and methods for control systems for facilitating situational awareness of a vehicle are provided. Sensors located around a stationary vehicle may detect moving objects that pose potentially dangerous situations for the vehicle occupants and for the object. This can cause the doors to lock automatically in order to make the situation safer. Additionally, electromagnetic radiation sensors located around the vehicle may detect the lights and sounds of emergency vehicles. If the electromagnetic data from the electromagnetic radiation sensors match a known pattern of electromagnetic data emitted by emergency vehicles stored in a library an alarm may be sounded through the speakers of the vehicle in order to alert the vehicle occupants of an emergency vehicle in the vicinity.

Abstract: A method of operating a vehicle, such as an autonomous vehicle, includes the steps of receiving a message from roadside infrastructure via an electronic receiver and providing, by a computer system in communication with said electronic receiver, instructions based on the message to automatically implement countermeasure behavior by a vehicle system. Additionally or alternatively, the method may include the steps of receiving a message from another vehicle via an electronic receiver and providing, by a computer system in communication with said electronic receiver, instructions based on the message to automatically implement countermeasure behavior by a vehicle system.

Abstract: An automatic alarm system for a vehicle includes a sensor adapted to detect electromagnetic data, a computer system, and an automatic alarm mechanism. The computer system receives data from the sensor. A computer processor compares the electromagnetic data detected by the sensor with known patterns of electromagnetic data emitted by emergency vehicles that are stored in a library. The automatic alarm mechanism activates in response to the processor determining that the comparison matches a known pattern of electromagnetic data for an emergency vehicle resulting in the computer processor sending a first signal to activate an alarm of the vehicle.

Abstract: A vehicle control apparatus includes: an information acquisition unit acquiring feature information indicating a feature regarding vehicle driving of an occupant of a vehicle; and a control unit changing at least one property included in a driving property or a manipulation property in the vehicle. Further, the control unit changes at least one property included in the driving property or the manipulation property of the vehicle, from a basic property of the vehicle to a property reflecting the feature information, based on the feature information, and brings the changed property close to the basic property of the vehicle in accordance with at least one of an integrated value of boarding hours, an integrated value of running distances, and the number of boardings of the vehicle of the occupant.

Abstract: A method and system for modeling and processing vehicular traffic data and information, comprising: (a) transforming a spatial representation of a road network into a network of spatially interdependent and interrelated oriented road sections, for forming an oriented road section network; (b) acquiring a variety of the vehicular traffic data and information associated with the oriented road section network, from a variety of sources; (c) prioritizing, filtering, and controlling, the vehicular traffic data and information acquired from each of the variety of sources; (d) calculating a mean normalized travel time (NTT) value for each oriented road section of said oriented road section network using the prioritized, filtered, and controlled, vehicular traffic data and information associated with each source, for forming a partial current vehicular traffic situation picture associated with each source; (e) fusing the partial current traffic situation picture associated with each source, for generating a single co

Abstract: Disclosed herein are methods, systems, and apparatus, including computer programs encoded on computer storage media, for charging toll fees. One of the computer-implemented methods includes obtaining information of a vehicle traveling on a road, where the vehicle is associated with a user account on a payment platform. In response to determining that a distance the vehicle is driven on the road reaches a predetermined distance, initiating a toll fee charging request for the vehicle to the payment platform to charge a toll fee corresponding to the predetermined distance.

Abstract: Global position system tagging the movement of an object and extrapolating its direction and speed can be used for various services including emergency-based services. Location data can be computed using edge computing nodes. The extrapolation system can account for feedback from responding user devices and utilize the user device's location at the time of reporting to facilitate determining the direction, location, and/or speed of a moving object. This data can then be utilized to generate augmented reality displays for mobile devices and/or vehicles that utilize the system. The ability to calculate directional information with edge computing nodes can comprise an ability to add enriched data by predicting an object's whereabouts, route, and/or final destination.

Abstract: Provided are a magnetic marker and a magnetic marker detection system with a reduced magnetic force. The magnetic marker detection system (1S) in which magnetism generated from the magnetic marker (1) laid on a road surface (53) is detected by a magnetic sensor (2) attached to a vehicle's body floor (50) of a vehicle (5) is a system with the magnetic marker (1) and the magnetic sensor (2) in combination, the magnetic marker having a magnetism reach ratio Gh/Gs, which is a ratio of a magnetic flux density Gh at a position at a height of 250 mm with respect to a magnetic flux density Gs of a surface, being equal to or larger than 0.5% and the magnetic sensor using a magneto-impedance element including a magneto-sensitive body with impedance changing in accordance with an external magnetic field.

Abstract: Methods and systems for determining risk associated with operation of autonomous vehicles using autonomous communication are provided. According to certain aspects, autonomous operation features associated with a vehicle may be determined, including features associated with autonomous communication between vehicles or with infrastructure. This information may be used to determine risk levels for a plurality of features, which may be based upon test data regarding the features or actual loss data. Expected use levels and autonomous communication levels may further be determined and used with the risk levels to determine a total risk level associated with operation of the vehicle. The autonomous communication levels may indicate the types of communications, the levels of communication with other vehicles or infrastructure, or the frequency of autonomous communication. The total risk level may be used to determine or adjust aspects of an insurance policy associated with the vehicle.

Abstract: A method includes determining that a prioritized vehicle plans to traverse an intersection and receiving sensor data from a plurality of sources in a vicinity of the intersection. The method also includes, based on the sensor data, determining a traffic solution to enable the prioritized vehicle to traverse the intersection, the traffic solution identifying a traffic lane and, based on the traffic solution, controlling a traffic light to cause traffic in the traffic lane to disperse and controlling a second traffic light to instruct traffic in an adjacent traffic lane to stop. The method includes instructing the prioritized vehicle to travel via the traffic lane. The traffic in the traffic lane and the traffic in the adjacent traffic lane are traveling in a same direction.

Abstract: Methods, systems, apparatus, and non-transitory computer readable media are described for using a vehicle as a payment device. Various aspects may include receiving a selection of a stored financial card or financial account at a vehicle head unit. The selected financial card or financial account may be transmitted to a point-of-sale (POS) terminal for making a payment by transmitting a tokenized card number to the POS terminal. The tokenized card number may be transmitted over a very short-range communication link to ensure that the transmission is secure. For example, electronic circuitry may be attached to the exterior of the vehicle, where the electronic circuitry may be within a threshold distance (e.g. one inch, three inches, six inches, one foot, three feet, etc.) of the POS terminal. The tokenized card number may be transmitted from the vehicle head unit to the electronic circuitry and then to the POS terminal.

Abstract: Among other things, equipment is located at an intersection of a transportation network. The equipment includes an input to receive data from a sensor oriented to monitor ground transportation entities at or near the intersection. A wireless communication device sends to a device of one of the ground transportation entities, a warning about a dangerous situation at or near the intersection, there is a processor and a storage for instructions executable by the processor to perform actions including the following. A machine learning model is stored that can predict behavior of ground transportation entities at or near the intersection at a current time. The machine learning model is based on training data about previous motion and related behavior of ground transportation entities at or near the intersection.

Abstract: Systems and methods for electronically providing fitness activity feedback to a user are disclosed. The method may include collecting performance data, generating comparison data by comparing the respective performance and including identifying comparison performance data representative of performance differences, and displaying the comparison data and the comparison performance data.

Abstract: An information provision system has a vehicle-mounted device, server, and mobile terminal, which send and receive information to and from one another. The vehicle-mounted device has an imaging unit that images a vicinity of a vehicle, and a first transmitting unit that sends position information, vehicle condition information, and captured image data, to the server. The server has a dangerous spot information creating unit that creates dangerous spot information having a danger level and associated with position information, based on the vehicle condition information and captured image data, and a second transmitting unit that sends the dangerous spot information to the mobile terminal. The mobile terminal has a third transmitting unit that sends position information to the server, a receiving unit that receives the dangerous point information corresponding to the position information of the mobile terminal, and an output unit that outputs a warning based on the dangerous spot information.

Abstract: Systems and methods related to stop signs with traffic control features are provided. A traffic signaling device signals a vehicle to proceed or wait. A controller receives data from a vehicle detection device indicating arrival of the vehicle within signaling range of the vehicle detection device. The controller receives an arrival time for the vehicle from a time keeping device and transmits the arrival time to a command center. A signal indicating permission to proceed is received at the controller from the command center and the controller instructs the traffic signaling device to signal the vehicle to proceed.

Abstract: The present disclosure generally relates to apparatus, software and methods for predicting future network traffic. The disclosed apparatus, software and methods alleviate congestion and/or increase overall traffic flow by providing methods for reallocating future idle capacity.

Abstract: A method for a traffic volume publication system to publish traffic volumes in a road traffic network includes: receiving traffic information including information on a plurality of road segments and original traffic volume data for the road segments at a first timestamp and calculating a first window size for each road segment for the first timestamp; predicting a second window size for a third timestamp subsequent to the first timestamp, either based on the first window size calculated at the first timestamp or based on the first window size and a window size calculated in advance at a second timestamp prior to the first timestamp; determining a privacy budget allocated to the first timestamp based on the first window size and the second window size; and returning noisy traffic volume data which is obtained by inserting noise into the original traffic volume data, based on the determined privacy budget.

Abstract: A method, apparatus and computer program product selectively qualify trajectories for utilization in regards to the determination of the travel time for a maneuver. In the context of a method, it is determined whether a trajectory intersects both first and second gate lines disposed at opposite ends of a maneuver that includes first and second sections. If the trajectory intersects both the first and second gate lines, the method determines whether a candidate probe point is within a respective distance threshold of at least one of the first section or the second section. The method also includes selectively identifying the trajectory as either a qualified trajectory or a disqualified trajectory in regards to a determination of a travel time for the maneuver based upon whether the candidate probe point is determined to be within the respective distance threshold of at least one of the first section or the second section.

Abstract: In some implementations, a mobile device transmits traffic information to a server for analysis. The traffic information includes movement information including detected stops and durations of detected stops. The traffic information is analyzed to detect traffic patterns that indicate locations of stop signs and/or stop lights. The traffic information is analyzed to determine durations of stops at stop signs and/or stop lights. The durations of stops are associated with a time of day and/or day of the week. In some implementations, navigational routes are determined based stop sign and/or stop light information, including the delays attributable to detected stop signs and/or stop lights.

Abstract: The present invention relates to a method and an apparatus for a first device transmitting and receiving data to/from one or more devices in a wireless communication system supporting vehicle to everything (V2X) service, and is characterised by the first device measuring an energy level of a first resource region for supporting the V2X service and transmitting a particular message via one or more resource regions of the first resource region and a second resource region based on the measurement result, wherein the second resource region represents a resource region for the first device transmitting the particular message to a second device via a network and the first resource region represents a resource region for the first device transmitting the particular message directly to the second device.

Abstract: A display control device configured to control a projection device that projects an image on a windshield of a vehicle includes a circuitry. The circuitry is configured to determine a target ground object that is a ground object other than an object which a driver of the vehicle is to be warned of, the target ground object being used to provide the driver with a sense of distance to the object, and project, using the projection device, an image for indicating a presence of the object in a manner that allows the driver to perceive a sense of distance to the object on a windshield of the vehicle, such that a first part of the image and the target ground object overlap each other and a second part of the image and the target ground object do not overlap each other when viewed from the driver.

Abstract: Provided is a navigation apparatus with which a user or the like is able to be aware of an avoidance recommended region or the like on a route and is also able to be aware of specific avoidance recommendation property. With a navigation apparatus, a route search portion searches a route to a destination, and a communication control portion acquires avoidance recommended region information from an avoidance recommended region database that stores the avoidance recommended region information acquired from a server. Furthermore, based on the avoidance recommended region on the route searched by the route search portion, the indication portion indicates the presence of the avoidance recommended region on the route.

Abstract: An approach is provided for detecting false positive slippery road reports. For example, the approach involves receiving a slippery road report from a vehicle. The slippery road report, for instance, indicates that a slippery road event is detected at a location based on sensor information collected by the vehicle. The approach also involves map matching the location of the slippery road report to the mapping data to evaluate a proximity of the location to at least one geographic feature that is designated as an area where driver behavior is expected to be at least one cause of the slippery road event. The approach further involves classifying the slippery road report as the slippery road false positive report based on the evaluation.

Abstract: To address problems that video imaging systems and platforms face when analyzing image and video content for detection and feature extraction, a solution is provided in which accumulating significant amounts of data suitable for training and learning analytics is leveraged to improve over time, the classifiers used to perform the detection and feature extraction, by employing a larger search space and generate additional and more complex classifiers through distributed processing. A distributed learning platform is therefore provided, which is configured for operating on large scale data, in a true big data paradigm. The learning platform is operable to empirically estimate a set of optimal feature vectors and a set of discriminant functions using a parallelizable learning algorithm. A method of adding new data into a database utilized by such a learning platform is also provided.

Abstract: A parking garage system includes a plurality of parking garages. Each parking garage has a plurality of parking sectors and each parking sector has a plurality of parking spaces. A digital system tracks an occupancy level of each parking sector and an anticipated departure time of vehicles parked in each parking space. The digital system further directs vehicles to a particular parking sector based on the driver's anticipated departure time. The digital system also advises potential customers of occupancy level and parking rates and communicates information regarding occupancy level and parking rates to other parking garages.

Abstract: One or more devices in a data analysis computing system may be configured to receive and analyze movement data and driving data, and determine driving trips and associated drivers based on the received data. Movement data may be collected by one or more mobile devices, such as smartphones, tablet computers, and on-board vehicle systems. Drivers associated with driving trips may be identified based on the movement data collected by the mobile devices, such as speed data, acceleration data, or distance/location data. In some cases, driving patterns may be determined based on the movement data before and after stopping points, and the driving patterns may be compared to a set of previously stored driving patterns associated with various different drivers.

Abstract: A multi-day and multi-person trip planning system comprises a planning graph of nodes interconnected by transit arcs which both have associated time-variable costs and time. A user specifies user objectives within trip destinations and customizes a plurality of user preferences for a multi-day, multi-person, multi-modal trip. An optimizer compiles a plurality of permutations of visiting plans within the planning graph which satisfy the specified user objectives including routing to a plurality of trip destinations. The optimizer compares the permutations using mixed integer programming or constraint programming to identify at least one optimized visiting plan having a lowest aggregate associated cost or shortest travel time that also satisfies a plurality of constraints determined by the customizable user preferences or environment condition. Then the user interface presents at least one optimized visiting plan to a user or route related coupons.

Abstract: A trigger event is detected based on a vehicle malfunction that limits maneuverability of a vehicle. An alert message is generated based on the detected trigger event, and the alert message is broadcast via a Vehicle-to-Everything (V2X) communication. Based on the detected trigger event, a receive channel mask and a transmit channel mask are generated, and a channel mask flag is set. When the channel mask flag is set, one or more incoming message channels are selected based on the incoming channel mask and the channel mask flag, and incoming V2X messages are received and processed only on the selected one or more incoming message channels. When the channel mask flag is cleared, incoming V2X messages are received and processed on the selected one or more incoming message channels and at least one additional incoming message channel.

Abstract: A method, device and system for measuring the volume, classification, direction, and turning movement of vehicular and/or pedestrian traffic through a given location in a given time period. The device is portable and incorporates a touch screen. A set of buttons corresponding to each direction at the location are selected by the user to count particular types of vehicles. The buttons are mapped to fields in a database on a server. The fields correspond to a particular direction. When the orientation of the portable device changes, the buttons are remapped to different database fields than originally mapped. The new fields corresponding to the orientation. The collected data may be transmitted to a server.

Abstract: A step of determining, by a presentation mode determining unit (205), a presentation mode different from a presentation mode of first road sign information, as a presentation mode of second road sign information, is included. This step is performed when a determination result indicates that traveling according to a road sign was not performed, the determination result being associated with a set of the first road sign information and first classification information that coincides with a set of the second road sign information and second classification information.

Abstract: A computing system can receive contextual data corresponding to a particular user and execute context resolution and constraint evaluation processes with local data acquisition and/or derivation priority to classify the user in one or more groups and reduce network latency. Based on the classified group(s) of the user, the computing system can provide targeted, group-specific content through an executing application of the user's computing device to enhance user experience with the application service.

Abstract: An ECU as a driving assistance device has a traffic sign detection section, a lane entry detection section and a judgment section. The traffic sign detection section detects traffic signs including a speed limit symbol based on front-image data captured by an in-vehicle camera. The lane entry detection section detects that the own vehicle has entered a ramp lane to leave a highway. The judgment section detects an extent of a current driving lane as the ramp lane when following conditions (c1) and (c2) are satisfied after the lane entry detection section detects the entry of the own vehicle into the ramp lane: (c1) not less than two traffic signs are arranged along the current driving lane in forward direction of the vehicle; and (c2) an arrangement of speed limit symbols included in the detected traffic signs satisfy a predetermined speed reduction pattern.

Abstract: A vehicle display control device for a vehicle: controls a display device for displaying information in a display region in front of a driver's seat of a vehicle; identifies an effective range of a traffic regulation indicated by a traffic regulation mark; identifies a remaining amount, which is at least one of a remaining travel distance and a remaining travel time required from a vehicle position of the vehicle to an end point of the effective range; and controls the display device to display remaining amount information indicating the remaining amount, in addition to traffic regulation content information indicating a content of the traffic regulation in the effective range, in the display region when the vehicle enters into the effective range.

Abstract: In some implementations, a computing device evaluates map data used by a mapping application to determine whether the map data represents a current road. The computing device gets probe data from mobile devices including probe points representing location and compares probe data against the stored map data (e.g., for the road segment corresponding to the probe points). A vector field is generated across the probe points and road segment to induce directionality. The computing device calculates a normal distance from probe points to the road segment. The computing device calculates map accuracy values from the comparison and normal distance. The values include a vector shift and a cosine similarity value between the stored road segment and the actual road. In some implementations the values are used to conform the map data to the actual road. Road segment data is updated to reflect probe data.

Abstract: A method is disclosed for mitigating the risks associated with driving by assigning risk values to road segments and using those risk values to select less risky travel routes. Various approaches to helping users mitigate risk are presented. A computing device is configured to generate a database of risk values. That device may receive accident information, geographic information, vehicle information, and other information from one or more data sources and calculate a risk value for the associated road segment. Subsequently, the computing device may provide the associated risk value to other devices. Furthermore, a personal navigation device may receive travel route information and use that information to retrieve risk values for the road segments in the travel route. An insurance company may use this information to determine whether to adjust a quote or premium of an insurance policy.

Abstract: The present invention discloses a method and a system for computing street parking occupancy for a street segment. The computation comprises computing a baseline occupancy module (10) for the street segment using at least map data (120) and at least image data (110), computing a continuous time occupancy module (20) for the street segment using at least the baseline occupancy (10) and at least historical data (200), and computing a forecast occupancy module (30) for the street segment using the continuous time occupancy module (20) and at least real-time data (300). The system comprises at least a memory component storing data and a processing component configured to perform the computation of the baseline occupancy.

Abstract: A device may identify first content to be provided for display via a window system of a vehicle. The device may provide, for display via the window system of the vehicle, information associated with the first content as a first augmented reality overlay based on identifying the first content. The device may receive information associated with a user interaction with the window system of the vehicle based on providing, for display via the window system of the vehicle, the information associated with the first content as the first augmented reality overlay. The device may identify second content based on the information associated with the user interaction with the window system of the vehicle. The device may provide, for display via the window system of the vehicle, information associated with the second content based on identifying the second content.

Abstract: A vehicle has a plurality of control apparatuses, a user input, a geographic position component, an object detection apparatus, memory, and a display. A processor is also included and is programmed to receive the destination information, identify a route, and determine the current geographic location of the vehicle. The processor is also programmed to identify an object and object type based on object information received from the object detection apparatus and to determine at least one warning characteristic of the identified object based on at least one of: the object type, a detected proximity of the detected object to the vehicle, the location of the detected object relative to predetermined peripheral areas of the vehicle, the current geographic location of the vehicle, and the route. The processor is also configured to select and display on the display an object warning image based on the at least one warning characteristic.

Abstract: A map of an area can be generated describing an occupancy status for each of a plurality of sub-areas in the area. A first message including the map is transmitted. A second message is transmitted including an updated occupancy status for one or more of, and less than all, of the sub-areas.

Abstract: A method and system for enabling an automated vehicular navigational improvement is provided. The method includes monitoring traffic control devices located within a specified perimeter surrounding a vehicle and traffic control devices. Traffic control device data defining operational characteristics of the traffic control devices is retrieved and a distance between the vehicle a traffic control device is determined. Status data indicating a control status of the traffic control device and data defining distances and associated travel speeds of additional vehicles located within said perimeter are retrieved and analyzed. A predicted arrival time of the vehicle and predicted control status the traffic control device is determined and a resulting control command alert associated with driving functions of the vehicle.

Abstract: A lane keeping assistance system including position means for determining a first position of the vehicle in a network with a first accuracy; first interface for providing trajectory of the vehicle in the network; second interface for providing position data of right boundary objects and position data of left boundary objects, and radar signatures of these boundary objects; radar system to scan right and left lateral environments of the vehicle and determine distances to objects on a right of the vehicle and radar signatures thereof, and distances to objects on a left of the vehicle and radar signatures thereof; evaluation unit to perform identification of acquired objects based on the first position, the provided data, and the determined data, and to determine a second position of the vehicle with a second position accuracy; and control device to control the vehicle taking into consideration the target trajectory and the second position.