Server and server-based vehicle intelligent driving control device and method

Abstract

A server and a server-based vehicle intelligent driving control apparatus and method are provided. The system of server-based vehicle intelligent driving control includes a vehicle driving control apparatus configured to receive a satellite navigation signal transmitted from a satellite navigation system and to generate location information of a vehicle. The system further includes a server configured to receive the location information of the vehicle from the vehicle driving control apparatus and to transmit a speed limit corresponding to the location information of the vehicle to the vehicle driving control apparatus. The vehicle driving control apparatus is configured to control the vehicle to drive at or below a maximum speed of the vehicle and to set the maximum speed limit of the vehicle as the received speed limit.

Description

[0001] Cross-reference to related applications

[0002] This application claims the benefit and priority of Korean Patent Application No. 10-2024-0186672, filed on December 16, 2024, with the Korean Intellectual Property Office, the entire contents of which are incorporated herein by reference. Technical Field

[0003] This disclosure relates to systems and methods for server-based intelligent driving control of vehicles. More specifically, this disclosure relates to systems and methods for server-based intelligent vehicle driving control that control vehicle movement via a server. Background Technology

[0004] Advanced driver assistance systems refer to technologies that support drivers to enhance the safety and convenience of driving a vehicle.

[0005] For example, advanced driver assistance systems can provide features such as automatic inter-vehicle distance control, constant speed maintenance, lane keeping assist, emergency braking, lane change assist, parking assist, and intelligent speed limit assist.

[0006] Intelligent speed limit assist is a service that provides warning alerts to the driver when the vehicle's speed exceeds the speed limit of each road link. However, existing intelligent speed limit assist devices have the problem of providing outdated speed limit data. Therefore, drivers must continuously monitor the road ahead to check the real-time speed limits in the gear shifting zone, causing inconvenience.

[0007] Furthermore, because existing intelligent speed limit assist devices perform computational processing within navigation devices, the hardware requirements for vehicles increase, processing time is prolonged, and large-scale data analysis is impossible. Therefore, it makes it impossible to provide map matching results based on big data analysis.

[0008] In addition, existing intelligent speed limit assist devices suffer from low map matching accuracy, meaning they fail to accurately match vehicle locations on the map.

[0009] Furthermore, existing intelligent speed limit assist devices have the following problem: they only provide an audible warning when the speed limit for each road link is exceeded, thus requiring the driver to manually adjust the speed. The topics described in this Background section are intended to facilitate an understanding of the background art of this disclosure and therefore may include topics unknown to those skilled in the art. The statements in this section are provided only as background information in relation to this disclosure and may not constitute prior art. Summary of the Invention

[0010] This disclosure relates to a server-based intelligent driving control system and method for vehicles. The system and method can extract real-time speed limits corresponding to the vehicle's location and control the vehicle based on the extracted speed limits.

[0011] Furthermore, this disclosure relates to a server-based intelligent driving control system and method for vehicles. The system and method can perform computational processing in a server to extract real-time speed limits, and can control the vehicle based on the extracted speed limits.

[0012] Furthermore, this disclosure relates to a server-based intelligent driving control system and method for vehicles. The system and method can analyze a large number of Global Navigation Satellite System (GNSS) tracks linked to an electronic map server to extract real-time speed limits, and can control the vehicle based on the extracted speed limits.

[0013] Furthermore, this disclosure relates to a server-based intelligent driving control system and method for vehicles. The system and method can automatically control the vehicle based on the speed limit of each road link.

[0014] The aspects of this invention are not limited to those mentioned above. Other aspects and advantages not mentioned above should be understood from the following description and should become more apparent from the embodiments. Furthermore, aspects of this disclosure can be achieved by the means and combinations thereof indicated in the claims.

[0015] One aspect of this disclosure provides an apparatus for server-based intelligent driving control of a vehicle. The apparatus includes a location information generation unit configured to receive satellite navigation signals transmitted from a satellite navigation system and generate vehicle location information. The apparatus further includes a transmission unit configured to transmit the vehicle location information to a server via a communication network. The apparatus further includes a receiving unit configured to receive a speed limit from the server based on the vehicle location information. The apparatus further includes a control unit configured to set the maximum speed limit of the vehicle to the received speed limit and control the vehicle to drive at or below the maximum speed.

[0016] The control unit can be configured to monitor the speed of the vehicle; and when the speed of the vehicle exceeds the speed limit, to control at least one of the vehicle's electric motor output, fuel injection quantity, fuel injection timing, or braking device to reduce the speed of the vehicle to or below the speed limit.

[0017] Another aspect of this disclosure provides a server for intelligent driving control of a vehicle. The server includes: a receiving unit configured to receive vehicle location information from a vehicle driving control device. The server further includes a matching unit configured to match the vehicle location information with a road map including road nodes and road links. The server also includes an identifier extraction unit that extracts identifiers for road links corresponding to the matched location information. The server further includes a speed limit detection unit that detects speed limits corresponding to the road link identifiers from a database. The server further includes a sending unit configured to send the detected speed limits to the vehicle driving control device.

[0018] The matching unit can be configured to determine the vehicle's speed based on the vehicle's location information and the time point at which the location information is received; determine whether the vehicle's location information is incorrect based on the determined vehicle speed; and delete the location information that is determined to be incorrect.

[0019] The matching unit can be configured to extract road links existing within a predetermined radius of the location information based on location information. The matching unit can be configured to determine the initial probability of the extracted road links. The matching unit can be configured to update the initial probability of each road link in chronological order of the received location information by determining the probability that the vehicle will move from a road link extracted based on currently received location information to a road link extracted based on subsequently received location information. The matching unit can be configured to, as the update is completed with the determination of the probability that the vehicle will move to a road link extracted based on the final location information, start from the road link with the highest probability among the road links extracted based on the final location information and select the road link with the highest probability for each location information in reverse chronological order to generate a vehicle trajectory. The matching unit can be configured to detect overlapping paths in the vehicle trajectory. The matching unit can be configured to correct overlapping paths.

[0020] The matching unit can be configured to generate vehicle trajectories based on vehicle location information and road links via a machine learning model, which is trained using location information accumulated in a database as training data and vehicle trajectories.

[0021] Based on real-time weather data and variable speed limit zones, the speed limit of each road link in the database can be updated. Variable speed limit zones include at least one of the following: frequent fog zones, frequent rain zones, frequent snowfall zones, frequent icing zones, frequent traffic congestion zones, time-based child protection zones, time-based elderly protection zones, and construction zones.

[0022] Another aspect of this disclosure provides a server-based intelligent driving control system for a vehicle. The system includes a vehicle driving control unit configured to receive satellite navigation signals transmitted from a satellite navigation system and generate vehicle position information. The system further includes a server configured to receive the vehicle position information from the vehicle driving control unit and send a speed limit corresponding to the vehicle position information to the vehicle driving control unit. The vehicle driving control unit is configured to set the maximum speed limit of the vehicle to the speed limit received from the server and control the vehicle to drive at or below the vehicle's maximum speed.

[0023] The server can be configured to determine the vehicle's speed based on the vehicle's location information and the time point at which the location information is received; determine whether the vehicle's location information is incorrect based on the determined vehicle speed; and delete the location information determined to be incorrect.

[0024] The server can be configured to extract road links existing within a predetermined radius of the location information based on location information. The server can be further configured to determine the initial probability of the extracted road links. The server can be further configured to update the initial probability of each road link in chronological order of the received location information by determining the probability that a vehicle will move from a road link extracted based on currently received location information to a road link extracted based on subsequently received location information. The server can be further configured to, as the update is completed with the determination of the probability that the vehicle will move to a road link extracted based on the final location information, generate a vehicle trajectory by selecting the road link with the highest probability from the road links extracted based on the final location information, in reverse chronological order, for each location information. The server can be further configured to detect overlapping paths in the vehicle's trajectory. The server can be further configured to correct overlapping paths.

[0025] The vehicle driving control device may be configured to monitor the speed of the vehicle; and when the speed of the vehicle exceeds the speed limit, to control at least one of the vehicle's electric motor output, fuel injection quantity, fuel injection timing, or braking device to reduce the speed of the vehicle to or below the speed limit.

[0026] Another aspect of this disclosure provides a server-based intelligent driving control method for a vehicle. The method includes receiving satellite navigation signals transmitted from a satellite navigation system via a vehicle driving control device to generate vehicle location information. The method further includes: the vehicle driving control device sending the vehicle location information to a server via a communication network. The method further includes: the server matching the vehicle location information with a road map including road nodes and road links. The method also includes: the server detecting a speed limit corresponding to the matched location information. The method further includes: the server sending the speed limit to the vehicle driving control device via a communication network. The method further includes: the vehicle driving control device controlling the vehicle to travel at or below its maximum speed. The method further includes: the vehicle driving control device controlling the vehicle's maximum speed to the received speed limit.

[0027] Matching vehicle location information with a road map may include determining the vehicle's speed based on the vehicle's location information and the time the location information was received. Matching vehicle location information with a road map may further include determining whether the vehicle's location information is incorrect based on the determined vehicle speed. Matching vehicle location information with a road map may include deleting location information determined to be incorrect.

[0028] Matching vehicle location information with a road map may include: extracting road links existing within a predetermined radius of the location information based on the location information. Matching vehicle location information with a road map may include determining an initial probability of the extracted road links. Matching vehicle location information with a road map may include: updating the initial probability of each road link in chronological order of the received location information by determining the probability that the vehicle will move from a road link extracted based on currently received location information to a road link extracted based on subsequently received location information. Matching vehicle location information with a road map may include: generating a vehicle trajectory by selecting the road link with the highest probability from the road links extracted based on the final location information in reverse chronological order for each location information, as the update is completed with determining the probability that the vehicle will move to a road link extracted based on the final location information.

[0029] Matching vehicle location information with road maps may include detecting overlapping paths in the vehicle trajectory and correcting the vehicle trajectory by removing overlapping paths.

[0030] Matching vehicle location information with road maps can further include generating vehicle trajectories based on vehicle location information and road links via a machine learning model, which is trained using location information and vehicle trajectories accumulated in a database as training data.

[0031] The method may further include updating the speed limit of each road link in the database based on real-time weather data and variable speed limit zones, which include at least one of frequent fog zones, frequent rainfall zones, frequent snowfall zones, frequent icing zones, frequent traffic congestion zones, time-based child protection zones, time-based elderly protection zones, and construction zones.

[0032] Detecting speed limits may include: the server extracting the identifier of the road link corresponding to the matched location information; the server detecting the speed limit corresponding to the identifier of the road link from the database.

[0033] According to this disclosure, by automatically providing real-time speed limits corresponding to the vehicle's location, the server-based intelligent driving control apparatus, system, and method for vehicles according to this disclosure reduce the burden on drivers to monitor road signs, make vehicle control based on the latest real-time speed limits possible, and thus enhance driving convenience.

[0034] Furthermore, by performing computational processing on a server for intelligent driving control of server-based vehicles according to this disclosure, the need for onboard computing processing devices is eliminated, processing time is shortened, and manufacturing costs and vehicle weight are reduced.

[0035] Furthermore, the server-based intelligent driving control apparatus, system, and method for vehicles disclosed herein analyze a large number of GNSS trajectories, using big data to enhance map matching performance, and thereby enabling real-time vehicle control based on speed limits obtained from more accurate location data.

[0036] Furthermore, according to this disclosure, driving convenience can be improved because the vehicle is automatically controlled based on the speed limit of each road link. Attached Figure Description

[0037] The foregoing and other aspects, features, and advantages, as well as the following detailed description of embodiments, should be better understood when read in conjunction with the accompanying drawings. However, this disclosure is not intended to be limited to the details shown in the drawings, and various modifications and structural changes may be made without departing from the spirit of this disclosure and within the scope and equivalents of the claims. In the various drawings, the same reference numerals and symbols denote the same elements.

[0038] Figure 1 This is a block diagram of a server-based intelligent vehicle driving control system according to an embodiment of the present disclosure.

[0039] Figure 2 This is a flowchart illustrating a method for server-based intelligent vehicle driving control according to an embodiment of the present disclosure.

[0040] Figure 3 This is an illustration showing an example of a map service within an infotainment service.

[0041] Figure 4 This is a diagram illustrating an example of server-based vehicle driving control according to an embodiment of the present disclosure. Detailed Implementation

[0042] In the following, the embodiments disclosed herein will be described in detail with reference to the accompanying drawings. The same reference numerals refer to the same elements, and redundant descriptions have been omitted. Furthermore, terms such as “module” and “unit” as used in this disclosure are intended to describe components and do not have a distinguishing meaning or function from one another. Additionally, in describing the embodiments disclosed in this document, detailed descriptions of the prior art included herein are omitted if it is determined that such detailed descriptions unnecessarily obscure the essential points of the embodiments. Moreover, it should be understood that the accompanying drawings are merely intended to aid in understanding the embodiments disclosed herein and do not limit the technical principles and scope of this disclosure. Rather, it should be understood that the drawings include all modifications, equivalents, or substitutions described by the technical principles and falling within the technical scope of this disclosure.

[0043] Although terms such as first, second, etc., may be used herein to describe various elements, these elements should not be limited by these terms. These terms are generally used only to distinguish one element from another.

[0044] When an element or layer is referred to as being "on," "attached to," "connected to," or "coupled to" another element or layer, the element or layer may be directly on, attached to, connected to, or coupled to the other element or layer, or intermediate elements or layers may be present. Conversely, when an element is referred to as being "directly on," "directly attached to," "directly connected to," or "directly coupled to" another element or layer, intermediate elements or layers may not be present. When the controllers, devices, modules, components, equipment, elements, etc., of this disclosure are described as having a purpose or performing an operation, function, etc., the controllers, devices, modules, components, equipment, elements, etc., herein should be considered as being "configured" to satisfy that purpose or perform that operation or function. Each controller, device, module, component, equipment, element, etc., may individually embody a processor and memory (such as a non-transitory computer-readable medium) or be included together with a processor and memory as part of a device.

[0045] In the following text, refer to Figure 1 and Figure 2 The system and method for server-based intelligent driving control of vehicles according to this disclosure are described in detail.

[0046] Figure 1This is a block diagram of a server-based intelligent driving control system for vehicles according to embodiments of the present disclosure, and Figure 2 This is a flowchart illustrating a server-based intelligent driving control method for a vehicle according to an embodiment of the present disclosure.

[0047] Reference Figure 1 According to embodiments of the present disclosure, the server-based intelligent vehicle driving control system 10 may include a server-based intelligent vehicle driving control device 100 and a server 200.

[0048] The server-based intelligent vehicle driving control device 100 may include a location information generation unit 110, a sending unit 120, a receiving unit 130, a control unit 140, etc.

[0049] The location information generation unit 110 receives satellite navigation signals transmitted from the satellite navigation system and generates the vehicle's location information (see [reference]). Figure 2 (S210).

[0050] For example, the location information generation unit 110 can calculate or determine the signal propagation time by comparing the location and time information transmitted by the satellite with the current time information, and can determine the distance between the satellite and the vehicle based on the signal propagation time.

[0051] A satellite navigation system refers to a satellite system that provides signals for sending position and time information to satellite navigation receivers.

[0052] Satellite navigation systems may include, for example, Europe's Galileo, the United States' Global Positioning System (GPS), Russia's Global Navigation Satellite System (GLONASS), and China's BeiDou Navigation Satellite System.

[0053] For example, the location information generation unit 110 receives multiple satellite signals from multiple GNSS satellites using multiple antennas. The location information generation unit 110 can also use dead reckoning (DR) sensors to detect vehicle movement.

[0054] The DR sensor can be configured to detect the vehicle's rotation angle using a gyroscope sensor and to calculate or determine the number of revolutions per hour of the wheel or axle using an encoder mounted on the wheel or axle, thereby allowing the determination of the vehicle's speed.

[0055] When the received satellite signal conditions are stable, multiple location information can be combined to generate vehicle location information.

[0056] On the other hand, when the received satellite signal conditions are unstable, vehicle position information can be estimated based on vehicle movement detected by the DR sensor.

[0057] In addition, the position information generation unit 110 can use correction information received from the reference station in accordance with the Radio Technology Maritime Committee (RTCM) standard format to correct the position information.

[0058] The sending unit 120 sends the vehicle location information to the server 200 via the communication network (see...). Figure 2 (S220).

[0059] For example, when a vehicle is subscribed to a mobile communication network, the sending unit 120 can send the vehicle location information to the server 200 using a vehicle mobile communication modem. When the vehicle is not subscribed to a mobile communication network, the sending unit 120 can send the vehicle location information to the server 200 using the network sharing function of a mobile communication terminal that is subscribed to the mobile communication network.

[0060] The sending unit 120 converts the location information into a suitable format for transmission, and when the vehicle is connected to the Internet, the sending unit 120 can send the location information to the server according to a specific protocol and request method.

[0061] Server 200 may include receiving unit 210, matching unit 220, identifier extraction unit 230, rate limit detection unit 240, and sending unit 250.

[0062] The receiving unit 210 receives vehicle location information from the communication terminal in the vehicle (see...). Figure 2 (S220).

[0063] Matching unit 220 matches vehicle location information with a road map including road nodes and road links (see...). Figure 2 (S230).

[0064] A node is a point where a vehicle's speed changes while traveling on a road.

[0065] For example, node types may include intersections, bridge start and end points, grade-separated interchange start and end points, road start and end points, underpass start and end points, tunnel start and end points, administrative boundaries, and IC / JC (interchange / junction).

[0066] A link is a line that connects two nodes, and in the real world, it represents a road.

[0067] For example, the types of links can include roads, bridges, overpasses, underpasses, and tunnels.

[0068] Matching unit 220 can filter location information data collected from the GNSS module.

[0069] Typically, unavailable location information data is characterized by coordinates that are randomly recorded over a short period of time.

[0070] Therefore, the matching unit 220 can determine the vehicle speed based on the coordinates in the location information and the time point when the location information is received, and can delete the location information collected in road sections where the vehicle speed is recorded as abnormally high.

[0071] The matching unit 220 can calculate or determine the probability that each location information point collected in chronological order can be connected based on the road map and vehicle location information.

[0072] Therefore, the matching unit 220 can determine the vehicle route based on the final determined probability value, and can improve the accuracy of the current location information based on the determined route. The vehicle trajectory refers to the path formed by connecting each vehicle location information point in chronological order.

[0073] The matching unit 220 can set the time step based on the time point when the vehicle location information is received.

[0074] For example, when a total of six GNSS measurements are received, six time steps can be set, such as k-3, k-2, ..., k+2.

[0075] Based on each received location information, multiple possible coordinates (and the road links where each coordinate is located) of a vehicle within a predetermined radius can be extracted for each time step, based on a road map. The initial probabilities of these extracted coordinates (and the road links where each coordinate is located) can also be determined. The time step is set corresponding to the time point when the location information is received, and the multiple coordinates extracted for each time step refer to coordinates existing within a predetermined distance on the road links based on the location information received in chronological order.

[0076] For example, five road links can be extracted to match GNSS measurements at time step k-3. Six road links can be extracted to match GNSS measurements at time step k-2. Five road links can be extracted to match GNSS measurements at time step k-1. Seven road links can be extracted to match GNSS measurements at time step k. Four road links can be extracted to match GNSS measurements at time step k+1. Five road links can be extracted to match GNSS measurements at time step k+2.

[0077] The initial probability of a road link can be higher when the distance between the GNSS measurement and the road link is shorter.

[0078] Matching unit 220 can determine the probability of a vehicle moving from each coordinate (or the road link where the coordinate is located) in the previous time step to a given coordinate (or the road link where the given coordinate is located) in the current time step, and can update the initial probability accordingly.

[0079] The probability of a vehicle moving may decrease as the actual distance traveled on the road from a coordinate in the previous time step to a given coordinate in the current time step becomes greater than the straight-line distance between GNSS measurements.

[0080] For example, when the matching unit 220 estimates vehicle movement based on measurements at time step k-3 and time step k+2, it can be assumed that the vehicle has traveled along the shortest path available for travel from the position estimated based on the measurements at time step k-3 to the position estimated based on the measurements at time step k+2.

[0081] At the final time step (k+2 time step), the matching unit 220 can start from the coordinate with the highest probability (or the road link where the coordinate is located) at the final time step, and select the coordinate with the highest probability (or the road link where the coordinate is located) for each time step in reverse time order, thereby generating the vehicle trajectory.

[0082] As an example of generating a trajectory by selecting coordinates (or the road links where the coordinates are located) in reverse time order, when the road link with the highest probability in the last time step (k+2) is called the k+2 maximum probability link, the road link with the highest probability of connecting to the k+2 maximum probability link in the k+1 time step can be called the k+1 maximum probability link.

[0083] Therefore, when the generated vehicle trajectories are represented sequentially, they can be represented as [k-3 maximum probability link, k-2 maximum probability link, k-1 maximum probability link, k maximum probability link, k+1 maximum probability link, k+2 maximum probability link].

[0084] Furthermore, during the process of selecting road links in reverse chronological order to generate a trajectory, the matching unit 220 can adjust the probability of the road link at the previous time step based on at least one of the separation distance between the maximum probability link determined at the current time step and the road link at the previous time step and the angle between them.

[0085] Meanwhile, when map matching is performed based on vehicle trajectories recorded in chronological order, more accurate map matching can be achieved because accessible roads are selected based on the vehicle's driving direction.

[0086] Furthermore, the matching unit 220 can determine similarity by comparing the collected vehicle location information with the location information of other vehicles stored in the server 200. When the similarity is equal to or greater than a predetermined threshold, the matching unit 220 can correct the vehicle location information based on pre-generated corrected location information of other vehicles.

[0087] For example, matching unit 220 can use a transformer machine learning model including an encoder-decoder structure to output map matching results that reflect the internal connectivity probabilities between multiple location coordinates and the external connectivity probabilities between multiple road links.

[0088] The matching unit 220 can vectorize location information (including latitude, longitude, time, speed and angle of movement) and input the vectorized location information into a machine learning model.

[0089] The input location information is processed by a decoder to output the vehicle trajectory. The output values ​​after map matching can include latitude, longitude, and vehicle driving direction.

[0090] A common error found in the trajectories generated after map matching is the appearance of duplicate trajectories in directions parallel or perpendicular to the vehicle's axis of travel.

[0091] Therefore, the matching unit 220 can filter the generated vehicle trajectory by removing duplicate segments.

[0092] In addition, road link-related data can be managed by clustering the data based on regions.

[0093] Identifier extraction unit 230 extracts the identifier of the road link corresponding to the matched location information (see...). Figure 2 (S240).

[0094] For example, the corrected location information can correspond to a road link located between nodes, and the ID of that road link, with each node as the start and end node, can be extracted as an identifier.

[0095] Speed ​​limit detection unit 240 detects the speed limit corresponding to the identifier of the road link from the database (see...). Figure 2 (S250).

[0096] The database can be an ISA database, which includes real-time speed limit data for each road link collected through an Intelligent Transportation System (ITS). An ITS system is a system that integrates electronic, control, and communication technologies to provide traffic information and services.

[0097] For example, the database can be configured to store and update the real-time speed limit for each road link, and allow the speed limit detection unit 240 to retrieve the latest speed limit value.

[0098] For example, data stored in a database can include information about multiple road links with multiple attributes.

[0099] The types of attributes may include road link identifier, start node identifier, end node identifier, number of lanes, road gradient, road type, road number, road name, designation as a shared road segment, ramp code, maximum speed limit, vehicle limit, load limit, height limit, and remarks.

[0100] The speed limit for each road link in the database can be updated based on real-time weather data and changing speed limit zones, which include at least one of the following: frequent fog zones, frequent rain zones, frequent snowfall zones, frequent icing zones, frequent traffic congestion zones, time-based child protection zones, time-based elderly protection zones, and construction zones.

[0101] Figure 3 This is an illustration showing an example of a map service within an infotainment service.

[0102] Reference Figure 3 In existing vehicles, drivers typically operate the vehicle manually; therefore, map data, including road nodes and links, speed limits for each link, etc., is important to drivers. Furthermore, since the process of matching satellite signals received from the GPS module with the map is also performed in the vehicle, a navigation system that performs map matching is necessary.

[0103] At the same time, due to the widespread adoption of mobile navigation applications, consumers are increasingly choosing to use mobile navigation services instead of purchasing separate in-vehicle navigation systems.

[0104] However, with the introduction of autonomous driving technology, the demand for navigation services for drivers has decreased.

[0105] The method for server-based intelligent vehicle driving control according to embodiments of this disclosure uses data stored on a data processing server therein, enabling it to be applied to vehicles without navigation systems and reducing the capacity and performance required for data processing.

[0106] The server's sending unit 250 sends the speed limit to the vehicle driving control device 100.

[0107] The vehicle's receiving unit 130 receives the speed limit based on vehicle location information from the server 200 via a communication network (see...). Figure 2 (S260).

[0108] For example, receiving unit 130 may include a communication modem.

[0109] Figure 4 This illustrates a server-based vehicle driving control according to an embodiment of the present disclosure.

[0110] Reference Figure 4 The vehicle driving control device 100 sends the vehicle's location information to the server 200 and can receive road speed limit information from the server 200. This road speed limit information is the speed limit of the road corresponding to the vehicle's location information.

[0111] When controlling the vehicle's speed, the control unit 140 limits the vehicle's maximum speed to the received speed limit (see...). Figure 2 (S270).

[0112] When the vehicle speed exceeds the speed limit, the control unit 140 can control the vehicle driving by adjusting the electric motor output, engine injection quantity, or braking system.

[0113] For example, the control unit 140 can be implemented as an ISA controller that monitors the vehicle's speed, generates control information, and continuously controls the vehicle's electric motor output, fuel injection quantity, fuel injection timing, and braking system to reduce the vehicle speed to or below the speed limit when the vehicle speed exceeds the received speed limit.

[0114] As used in this disclosure (especially in the appended claims), the terms “an” and “the” include both singular and plural references unless the context clearly indicates otherwise. Furthermore, it should be understood that any numerical ranges listed in this disclosure are intended to include all subranges contained therein (unless otherwise expressly indicated), and therefore, the disclosed numerical ranges include each individual value between the minimum and maximum values ​​of the numerical range.

[0115] The steps of the method according to this disclosure can be performed in a suitable order unless a particular order is described or otherwise specified. In other words, this disclosure is not necessarily limited to the order in which the steps are described. All examples described in this disclosure or their indicative terms (“e.g.,” “such as”) are used only to describe this disclosure in more detail. Therefore, it should be understood that the scope of this disclosure is not limited to the above-described embodiments or the use of such terms, unless limited by the appended claims. Moreover, those skilled in the art will understand that various modifications, combinations, and substitutions can be made within the scope of the appended claims or their equivalents, depending on design conditions and factors.

[0116] Therefore, this disclosure is not limited to the exemplary embodiments described above, but is intended to include the appended claims, and all modifications, equivalents and substitutions should fall within the spirit and scope of the appended claims.

Claims

1. A server-based intelligent driving control device for vehicles, the device comprising: The location information generation unit is configured as follows: Receive satellite navigation signals transmitted from the satellite navigation system; and Generate the location information of the vehicle; The sending unit is configured to send the location information of the vehicle to a server via a communication network; The receiving unit is configured to receive a speed limit based on the location information of the vehicle from the server; as well as The control unit is configured as follows: The maximum speed of the vehicle is limited to the received speed limit; and Control the vehicle to travel at or below the maximum speed of the vehicle.

2. The apparatus according to claim 1, wherein, The control unit is configured to: Monitor the speed of the vehicle; and When the speed of the vehicle exceeds the speed limit, at least one of the following is controlled: the output of the vehicle's electric motor, the amount of fuel injection, the timing of fuel injection, and the braking device, to reduce the speed of the vehicle to or below the speed limit.

3. A server for intelligent driving control of a vehicle, the server comprising: The receiving unit is configured to receive the vehicle's location information from the vehicle driving control device; The matching unit is configured to match the vehicle's location information with a road map, which includes road nodes and road links, based on a database within the server. The identifier extraction unit is configured to extract the identifier of the road link corresponding to the matched location information from the database within the server; The speed limit detection unit is configured to detect the speed limit corresponding to the identifier of the road link from the database within the server; as well as The transmitting unit is configured to send the detected speed limit to the vehicle driving control device. The database is configured to store and update the real-time speed limits of the road links.

4. The server according to claim 3, wherein, The matching unit is configured as follows: The speed of the vehicle is determined based on the vehicle's location information and the time when the location information was received; Based on the determined speed of the vehicle, determine whether the vehicle's position information is incorrect; and Delete the location information that has been determined to be incorrect.

5. The server according to claim 4, wherein, The matching unit is configured as follows: Based on the location information, extract the road links that exist within a predetermined radius of the location information; Determine the initial probability of the extracted road links; The initial probability of each road link is updated according to the chronological order in which the location information is received, by determining the probability that the vehicle will move from the road link extracted based on the currently received location information to the road link extracted based on the subsequently received location information. When the update is completed as the probability of the vehicle moving to the road link extracted based on the last location information is determined, starting from the road link with the highest probability among the road links extracted based on the last location information, the road link with the highest probability is selected for each location information in reverse chronological order to generate the vehicle trajectory. Detect overlapping paths in the vehicle trajectory; and The vehicle trajectory is corrected by removing the overlapping paths.

6. The server according to claim 5, wherein, The matching unit is configured to generate a vehicle trajectory based on the vehicle's location information and the road links via a machine learning model, wherein the machine learning model is trained using the location information and the vehicle trajectory accumulated in the database as training data.

7. The server according to claim 6, wherein, Based on real-time weather data and changing speed limit zones, the speed limit for each road link in the database is updated. The changing speed limit zones include at least one of the following: frequent fog zones, frequent rainfall zones, frequent snowfall zones, frequent icing zones, frequent traffic congestion zones, time-based child protection zones, time-based elderly protection zones, and construction zones.

8. A server-based intelligent driving control method for vehicles, the method comprising: The vehicle driving control device receives satellite navigation signals sent from the satellite navigation system to generate the vehicle's location information; The vehicle driving control device sends the vehicle's location information to the server via a communication network; The server matches the vehicle's location information with a road map, which includes road nodes and road links. The server detects the rate limit corresponding to the matched location information; The server sends the speed limit to the vehicle driving control device via the communication network; The vehicle driving control device controls the maximum speed of the vehicle to the received speed limit, and The vehicle is controlled by the vehicle driving control device to travel at or below the maximum speed of the vehicle.

9. The method according to claim 8, wherein, Matching the vehicle's location information with the road map includes: The speed of the vehicle is determined based on the vehicle's location information and the time when the location information was received; Based on the determined speed of the vehicle, determine whether the vehicle's position information is incorrect; and Delete the location information that has been determined to be incorrect.

10. The method according to claim 9, wherein, Matching the vehicle's location information with the road map also includes: Based on the location information, extract the road links that exist within a predetermined radius of the location information; Determine the initial probability of the extracted road links; The initial probability of each road link is updated according to the chronological order in which the location information is received, by determining the probability that the vehicle will move from the road link extracted based on the currently received location information to the road link extracted based on the subsequently received location information. When the update is completed as the probability of the vehicle moving to the road link extracted based on the last location information is determined, starting from the road link with the highest probability among the road links extracted based on the last location information, the road link with the highest probability is selected for each location information in reverse chronological order to generate the vehicle trajectory. Detect overlapping paths in the vehicle trajectory; and The vehicle trajectory is corrected by removing the overlapping paths.

11. The method according to claim 10, wherein, Matching the vehicle's location information with the road map also includes: The vehicle trajectory is generated based on the vehicle's location information and the road links via a machine learning model, which is trained using accumulated location information and vehicle trajectories in a database as training data.

12. The method of claim 11, further comprising: Based on real-time weather data and changing speed limit zones, the speed limit for each road link in the database is updated. The changing speed limit zones include at least one of the following: frequent fog zones, frequent rainfall zones, frequent snowfall zones, frequent icing zones, frequent traffic congestion zones, time-based child protection zones, time-based elderly protection zones, and construction zones.

13. The method according to claim 12, wherein, Detecting the speed limit includes: The server extracts the identifier of the road link corresponding to the matched location information; and The server detects the speed limit corresponding to the identifier of the road link from the database.

14. The method of claim 8, further comprising: The vehicle speed is monitored by the vehicle driving control device; and When the speed of the vehicle exceeds the speed limit, the vehicle driving control device controls at least one of the vehicle's electric motor output, fuel injection quantity, fuel injection timing, and braking device to reduce the speed of the vehicle to or below the speed limit.

15. The method of claim 10, further comprising: In the process of generating the vehicle trajectory by selecting the road links in reverse chronological order, the updated initial probability of the road links at the previous moment is adjusted based on at least one of the separation distance and angle between the road link with the highest probability corresponding to the last location information and the road link at the previous moment extracted based on the location information received at the previous moment.

16. The method of claim 8, further comprising: The map matching results are output by using a machine learning model to reflect the probability of internal connections between location coordinates and the probability of external connections between road links.

17. The method of claim 16, further comprising: The location information is vectorized, and the location information includes the vehicle's latitude, longitude, time, speed, and angle of movement; and The vectorized location information is input into the machine learning model.

Images