KR20240080044A - Unmanned car network system and vehicle control method using unmanned car network - Google Patents

Abstract

The unmanned car network system and method according to the embodiment collects data such as speed, distance between vehicles, surrounding environmental conditions, and obstacles using various sensor data from the vehicle ECU (Electronic Control Unit), and uses a beacon to collect data from surrounding ECUs. transmit data to In the embodiment, the data received from the ECU is used to transmit the data to the unmanned car system, and flexible unmanned operation such as setting the distance between vehicles, setting speed, and changing lanes is performed based on the transmitted data. In an embodiment, central beacons that can collect and manage key information such as the car's destination, current speed, and surrounding conditions are installed at several points on the highway, such as toll gates and rest areas. In an embodiment, the central beacon provides information for smooth traffic by analyzing the main movement locations of vehicles and whether there are currently road accidents or obstructions. In addition, in the embodiment, a central beacon that can acquire the current target location of cars is installed around a traffic light and learned through deep learning to flexibly adjust the signal system according to traffic volume.

Description

Unmanned car network system and vehicle control method using unmanned car network {UNMANNED CAR NETWORK SYSTEM AND VEHICLE CONTROL METHOD USING UNMANNED CAR NETWORK}

This disclosure relates to a driverless car network system and method, and more specifically, to a system and method for providing a driverless car network capable of data communication with the surrounding environment, such as cars and traffic lights, by incorporating a beacon into the car ECU.

Unless otherwise indicated herein, the material described in this section is not prior art to the claims of this application, and is not admitted to be prior art by inclusion in this section.

A self-driving car (autonomous vehicle, AV, driverless car, robo-car) or self-driving car is a car that can drive on its own without driver intervention. Driverless cars drive autonomously by simply recognizing the surrounding environment using radar, LIDAR (light detection and ranging), GPS, and cameras and specifying a destination. Driverless cars that are already in practical use include unmanned vehicles that patrol preset routes operated by the Israeli military and unmanned operation systems such as dump trucks that are operated in overseas mines and construction sites.

Autonomous driving is a driving method for unmanned vehicles, and is a system in which cars used as a means of transportation make their own decisions and drive without human intervention. Autonomous driving can be divided into stages from level 0 to level 5. SAE (Society of Automotive Engineers) defined autonomous driving technology by dividing it into six stages, and is currently used as a global standard.

Stage 0 is the No Automation stage, which is the most basic stage of the autonomous driving system that requires driver intervention. To put it simply, the driver controls and takes responsibility for everything, and the autonomous driving system only performs simple assist functions to notify emergency situations such as forward collision-avoidance assist (FCA) and rear cross-collision warning (BCW). Stage 1 is the driver assistance stage, where the autonomous driving system begins to assist the driver little by little. It plays an auxiliary role in maintaining the car's speed and distance and preventing lane departure. It is still assumed that the driver must hold the steering wheel and steer. The second stage is the partial automation stage, where the driver operates the steering wheel and constant monitoring is essential. This is a slightly upgraded level from the first stage. If the autonomous driving system simply assisted the driver in the first stage, in the second stage, assistive driving such as steering in natural curves or maintaining the distance from the car in front is possible. The third stage that is commonly applied to newly released cars is the conditional automation stage. Starting with the third stage, the autonomous driving system can control driving and detect variables while driving. The autonomous driving system is responsible for driving in sections where it is possible to drive without special interference, such as on highways. Unlike stage 2, it does not require constant monitoring, but when risk factors or variables occur, the autonomous driving system requests driver intervention. Level 4 is High Automation, which enables autonomous driving on most roads as well as sections with specific conditions such as highways. Driving control and driving responsibility are all given to the autonomous driving system. Driver intervention is unnecessary except in situations such as bad weather, and it is a step that indicates that the autonomous driving system has gradually become more advanced.

Lastly, stage 5 is the full automation stage, which is the stage where fully autonomous driving is possible without a driver. Passengers, rather than the driver, enter a destination and the autonomous driving system operates the car entirely without any intervention required. This is the stage where the driver's seat and all control devices are no longer needed.

Currently, driverless car systems are at the conditional autonomous driving stage, which is level 3 according to the SAE classification. Sensors can recognize and respond to surrounding situations, but if there are exceptional situations in which information outside the sensor range occurs, driver intervention is required. The ultimate autonomous vehicle system (level 5 according to the SAE classification standard) must be able to respond to all situations without any driver intervention. Even if sensor technology improves dramatically, information outside the sensor's range, such as when it is too far away or blocked by an obstacle, cannot be acquired. In addition, although the current traffic light system is very detailed and flexible, it is often considered that traffic lights operate somewhat inefficiently in areas where traffic volume changes are large. For example, when a driver is standing to make a left turn, there are overwhelmingly few cars going straight in the opposite lane, but the straight signal is long, so there are situations where the driver has to wait at the signal longer than necessary.

1. Korean Patent Registration No. 10-1526343 (2015.06.01) 2. Korean Patent Registration No. 10-2324154 (2021.11.03)

The unmanned car network system and method according to the embodiment collects data such as speed, distance between vehicles, surrounding environmental conditions, and obstacles using various sensor data from the vehicle ECU (Electronic Control Unit), and uses a beacon to collect data from surrounding ECUs. transmit data to In the embodiment, the data received from the ECU is transmitted to the unmanned car system, and flexible unmanned operation such as setting the distance between vehicles, setting speed, and changing lanes is performed based on the transmitted data.

In an embodiment, central beacons that can collect and manage key information such as the car's destination, current speed, and surrounding conditions are installed at several points on the highway, such as toll gates and rest areas. In an embodiment, the central beacon provides information for smooth traffic by analyzing the main movement locations of vehicles and whether there are currently road accidents or obstructions.

In addition, in the embodiment, a central beacon that can acquire the current target location of cars is installed around a traffic light and learned through deep learning to flexibly adjust the signal system according to traffic volume.

In addition, during data communication between vehicles through an embodiment, if an event occurs that interferes with the driving of a specific vehicle, such as an accident or road construction, a warning signal is transmitted to surrounding vehicles to also transmit a warning signal to other vehicles on the road where the event that interferes with driving occurs. Lets you know the location and type of event.

Additionally, in the embodiment, cars that share information around a specific accident area are grouped together to perform group movement where they can reduce their speed or change lanes together.

The unmanned car network system according to the embodiment collects autonomous driving data including speed, distance between vehicles, surrounding environmental conditions, and obstacle information, and transmits the autonomous driving data to a surrounding Electronic Control Unit (ECU) using a beacon. The first autonomous vehicle transmitting to; a second autonomous vehicle that receives autonomous driving data from the first autonomous vehicle and transmits the autonomous driving data to an autonomous driving control server; Central beacons that collect and manage key road information, including the car's destination, current speed, and surrounding situation information, at point points on the highway, including toll gates and rest areas; and an autonomous driving control server that receives autonomous driving data from the autonomous vehicle, collects key road information from the central beacon, and sets detailed autonomous driving information including inter-vehicle distance, speed, and lane change. Includes.

In an embodiment a central beacon; Detects the current major movement locations of vehicles, current road accident information, and road obstacle information, and when road accident information and obstacle information is detected, predicts the expected congestion time, which is the time it takes to resolve the detected accident and obstacle. .

In an embodiment, an autonomous driving control server; predicts the traffic volume for each section by deep learning the direction data of the unmanned vehicle transmitted from the central beacon, and controls the traffic lights and autonomous vehicles installed in the section according to the predicted traffic volume.

In an embodiment, an autonomous driving control server; Groups unmanned cars that share accident information around the accident area and controls group movement so that the grouped unmanned cars reduce their speed or change lanes together.

In an embodiment, an autonomous driving control server; A deep learning neural network including at least one of a Deep Neural Network (DNN), a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), and a Bidirectional Recurrent Deep Neural Network (BRDNN) that includes autonomous driving data and key road information. A traffic prediction model and an unmanned vehicle control model are implemented by learning with a training data set.

The unmanned car network system and vehicle control method using the unmanned car network as described above allows for a wide range of data to be collected, such as long-distance road conditions that are difficult to collect with sensors, and the road condition of the car ahead, providing information on surrounding situations. By increasing the information acquisition range, the unmanned vehicle system can be operated flexibly.

Additionally, the reliability of the driverless car system can be improved by establishing a network between cars.

In addition, when an event such as an accident or construction that interferes with vehicle driving occurs, we predict the location and type of the event and the time required to resolve it, inform the vehicle of this, and guide detour routes to prevent traffic congestion in the area around the event. do.

The effects of the present invention are not limited to the effects described above, and should be understood to include all effects that can be inferred from the configuration of the invention described in the detailed description or claims of the present invention.

1 is a diagram showing the configuration of an unmanned vehicle network system according to an embodiment.
Figure 2 is a diagram showing the data processing configuration of a central beacon according to an embodiment
Figure 3 is a diagram showing the data processing configuration of an unmanned vehicle according to an embodiment
Figure 4 is a diagram showing the data processing configuration of the autonomous driving control server according to an embodiment
Figure 5 is a diagram showing the data processing configuration of a central beacon installed at a traffic light according to an embodiment
Figure 6 is a diagram showing a data processing process for responding to an accident situation in an unmanned vehicle network system according to an embodiment.
Figure 7 is a diagram showing the data processing flow when driving in the city of an unmanned vehicle according to an embodiment
Figure 8 is a diagram showing a data processing process for traffic light control in an unmanned vehicle network system according to an embodiment
Figure 9 is a diagram showing the speeding vehicle enforcement process of the unmanned vehicle network system according to an embodiment.

The advantages and features of the present invention and methods for achieving them will become clear by referring to the embodiments described in detail below along with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below and may be implemented in various different forms. The present embodiments are merely provided to ensure that the disclosure of the present invention is complete and to provide common knowledge in the technical field to which the present invention pertains. It is provided to fully inform those who have the scope of the invention, and the present invention is only defined by the scope of the claims. Like reference numerals refer to like elements throughout the specification.

In describing embodiments of the present invention, if it is determined that a detailed description of a known function or configuration may unnecessarily obscure the gist of the present invention, the detailed description will be omitted. The terms described below are terms defined in consideration of functions in embodiments of the present invention, and may vary depending on the intention or custom of the user or operator. Therefore, the definition should be made based on the contents throughout this specification.

Figure 1 is a diagram showing the configuration of an unmanned vehicle network system according to an embodiment.

Referring to FIG. 1, the unmanned car network system according to the embodiment includes a first autonomous vehicle 101, a second autonomous vehicle 103, a central beacon 300, an autonomous driving control server 200, and a traffic light 500. ) and a smart terminal 400.

The first autonomous vehicle 101 collects autonomous driving data including speed, distance between vehicles, surrounding environmental conditions, and obstacle information, and transmits the autonomous driving data to a surrounding ECU using a beacon. The second autonomous vehicle 103 receives autonomous driving data from the unmanned vehicle and transmits the autonomous driving data to the autonomous driving control server 200.

The central beacon 300 collects and manages key road information, including the car's destination, current speed, and surrounding situation information, at point points on the highway, including toll gates and rest areas.

The autonomous driving control server 200 receives autonomous driving data from the autonomous vehicle, collects key road information from the central beacon, and sets detailed autonomous driving information including distance between vehicles, speed, and lane change. In an embodiment, the autonomous driving control server 200 transmits the set autonomous driving details to the unmanned vehicle so that the unmanned vehicle can be controlled according to the autonomous driving details set in the autonomous driving control server.

The traffic light 500 adjusts the signal maintenance time according to the set autonomous driving details. For example, the traffic light 500 can receive autonomous driving data and situation information from central beacons around the traffic lights, and control the type of signal and the maintenance time of each signal according to the received information. Additionally, the traffic light 500 may operate according to a control signal from the autonomous driving control server.

The smart terminal 400 is a user or pedestrian terminal riding in an unmanned vehicle. It outputs detailed autonomous driving information set by the control server according to the location of the terminal and provides driving information such as the vehicle's location, speed, and real-time status of the vehicle. It can be printed and provided to the user.

The unmanned car network system and method according to the embodiment collects data such as speed, distance between vehicles, surrounding environmental conditions, and obstacles using various sensor data from the vehicle ECU (Electronic Control Unit), and uses a beacon to collect data from surrounding ECUs. transmit data to In the embodiment, the data received from the ECU is transmitted to the unmanned car system, and flexible unmanned operation such as setting the distance between vehicles, setting speed, and changing lanes is performed based on the transmitted data.

In an embodiment, central beacons that can collect and manage key information such as the car's destination, current speed, and surrounding conditions are installed at several points on the highway, such as toll gates and rest areas. In an embodiment, the central beacon provides information for smooth traffic by analyzing the main movement locations of vehicles and whether there are currently road accidents or obstructions.

In addition, in the embodiment, a central beacon that can acquire the current target location of cars is installed around a traffic light and learned through deep learning to flexibly adjust the signal system according to traffic volume.

In addition, during data communication between vehicles through an embodiment, if an event occurs that interferes with the driving of a specific vehicle, such as an accident or road construction, a warning signal is transmitted to surrounding vehicles to also transmit a warning signal to other vehicles on the road where the event that interferes with driving occurs. Lets you know the location and type of event.

Additionally, in the embodiment, cars that share information around a specific accident area are grouped together to perform group movement where they can reduce their speed or change lanes together.

Figure 2 is a diagram showing the data processing configuration of a central beacon according to an embodiment.

Referring to FIG. 2, the central beacon according to the embodiment may be configured to include a wireless communication unit, a central processing unit, a control unit, a beacon communication unit, and a camera control device connected to a network communication network.

In an embodiment, central beacons are installed at several points on the highway, such as toll gates and rest areas, and collect key information such as the car's destination, current speed, and surrounding conditions.

The wireless communication unit is connected to the network communication network and communicates with vehicles entering the area where the central beacon is installed to receive autonomous driving data generated by the vehicle. In an embodiment, autonomous driving data may include the speed of the driving vehicle, current location, distance between vehicles, surrounding environmental conditions, obstacle information, speed change, steering angle, vehicle status, movement path, etc. Based on the received autonomous driving data, the central processing unit detects the main movement location of vehicles, current road accident information, and obstacle information on the road, and when road accident information and obstacle information are detected, the detected accident and obstacle information Predict the expected congestion time, which is the time it takes to resolve. The beacon communication unit transmits recognized accident information, obstacle information, and expected congestion time information to vehicle and pedestrian terminals in the area where the central beacon is installed. The control unit controls the cameras and traffic lights in the area where the central beacon is installed according to detected road accident information, obstacle information, etc., and the camera control device sets detailed settings such as camera on/off, rotation, zoom, etc. through the camera control information received from the control unit. control.

Figure 3 is a diagram showing the data processing configuration of an unmanned vehicle according to an embodiment.

Referring to FIG. 3, the unmanned vehicle according to the embodiment includes a beacon and a wireless communication unit that communicates with nearby vehicles equipped with beacons and a central beacon, and includes a data collection unit, a central processing unit, a sensor unit, an input/output processing unit, and a central control unit. , can be configured to include an unmanned vehicle system, a driving assistance system, and a photography unit.

In an embodiment, the first autonomous vehicle collects autonomous driving data including speed, distance between vehicles, surrounding environmental conditions, and obstacle information through sensors installed in the vehicle, and collects autonomous driving data from surrounding areas using a beacon. Transmit to ECU. The second autonomous vehicle that communicates with the first autonomous vehicle receives autonomous driving data from the unmanned car and transmits the autonomous driving data to the autonomous driving control server.

Figure 4 is a diagram showing the data processing configuration of an autonomous driving control server according to an embodiment.

Referring to FIG. 4, the autonomous driving control server 200 according to the embodiment may be configured to include a data collection module 210, a deep learning module 220, a control module 230, and a feedback module 240. . The term 'module' used in this specification should be interpreted to include software, hardware, or a combination thereof, depending on the context in which the term is used. For example, software may be machine language, firmware, embedded code, and application software. As another example, hardware may be a circuit, processor, computer, integrated circuit, integrated circuit core, sensor, Micro-Electro-Mechanical System (MEMS), passive device, or a combination thereof.

In the embodiment, the data collection module 210 collects direction data of the unmanned vehicle and autonomous driving data of the unmanned vehicle transmitted from the central beacon. The deep learning module 220 predicts traffic volume for each section by deep learning the collected data.

In an embodiment, the deep learning module 220 operates an autonomous deep learning neural network including at least one of a Deep Neural Network (DNN), a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), and a Bidirectional Recurrent Deep Neural Network (BRDNN). Traffic volume prediction models and unmanned vehicle control models can be implemented by learning with a training data set containing driving data and key road information. The control module 230 controls traffic lights and autonomous vehicles according to predicted traffic volume and traffic conditions. For example, the control module 230 controls traffic lights installed in a section according to the predicted traffic volume. In addition, in the embodiment, the control module 230 groups unmanned cars that share accident information around the accident area and allows the unmanned cars to move as a group to reduce their speed or change lanes together. can be controlled.

Additionally, in the embodiment, the control module 230 may control autonomous driving of the unmanned vehicle by considering map attribute information of the area in which the vehicle is driving. In the embodiment, the map attribute information is detailed information of the driving area map, which is traffic regulations and environmental information that must be considered when driving autonomously on the road, such as lanes, road facilities, traffic signs, traffic lights, road curvature, slope, vehicle speed limit, presence of a stop, and stop line. , crosswalk, left bias, right bias, careful driving, school zone, protection zone, intersection and V2X communication information, speed limit information, etc. In the embodiment, V2X communication information is information for exchanging or sharing information with surrounding vehicles and road infrastructure using a wired or wireless communication network. In an embodiment, V2X communication information includes vehicle to vehicle (V2V), vehicle to infrastructure (V2I), vehicle to pedestrian (V2P), and vehicle to mobile device (V2N). Vehicle to Nomadic Device) communication information may be included. For example, when an unmanned vehicle drives in a slow-moving area such as a school zone, the control module 230 can recognize the location of pedestrian terminals around the unmanned vehicle in the school zone and adjust the speed of the unmanned vehicle in consideration of the location of the pedestrian terminal. Let it happen. In addition, when waiting for a traffic light, if a pedestrian terminal or pedestrian that has not completely crossed the traffic light during the green signal maintenance time is recognized, the vehicle can start again after the pedestrian has completely crossed the traffic light.

The feedback module 240 collects traffic conditions and autonomous driving data of each unmanned vehicle according to the results of controlling autonomous vehicles and traffic lights, and determines the traffic situation for each section. Afterwards, the traffic situation before and after the control server controls the unmanned vehicle can be compared, and the traffic volume prediction model can be fed back according to changes in the traffic situation. For example, in a traffic situation after control of autonomous vehicles and traffic lights by a control server, when road complexity increases above a certain level and the moving speed of autonomous vehicles decreases by more than a certain percentage, the control process of the traffic volume prediction model can be fed back. That is, in the embodiment, if the complexity of the traffic situation increases or the driving time of each unmanned vehicle increases after the control server controls the unmanned vehicle, the traffic volume prediction model and the unmanned vehicle control model generated through the artificial neural network can be fed back.

Figure 5 is a diagram showing the data processing configuration of a central beacon installed at a traffic light according to an embodiment.

Referring to FIG. 5, the central beacon installed at the traffic light may include a wireless communication unit connected to a network communication network, a beacon communication unit, a central processing unit, a control unit, and a traffic light control device. In an embodiment, the wireless communication unit receives autonomous driving data and control signals collected from the vehicle and server through the network communication network and the beacon communication unit, and transmits the received data and signals to the central processing unit. The central processing unit generates a traffic light control signal based on the received autonomous driving data and control signals and transmits it to the control unit. The control unit transmits the traffic light control signal to the traffic light control device, allowing control by changing the signal type and signal maintenance time according to the driving situation in the area where the traffic light is installed.

Figure 6 is a diagram showing a data processing process for responding to an accident situation in an unmanned vehicle network system according to an embodiment.

Referring to FIG. 6, in step S10, an accident occurs while driving on the highway in an autonomous unmanned vehicle, or accident data is transmitted. In the S20 stage, a secondary accident prevention system is activated that performs speed control and recommends detour routes to prevent traffic flow disruption. In step S30, it is checked whether there is a central beacon around the area where the accident occurred. If there is no central beacon, step S40 is entered and the current location where the accident occurred and photos of exceptional situations are transmitted to surrounding vehicles. If there is a central beacon nearby, enter step S50 and transmit the current location and exception situation photos to the central beacon. In step S60, the transmitted data is transmitted to the traffic situation collection center and autonomous driving control server. In step S70, the severity of the situation is identified by analyzing the collected data, and the severity of the accident situation is transmitted to the central beacon included in the road where the accident occurred. In step S80, the accident location and severity are converted into signals and the converted signal is transmitted to the vehicle traveling on the driving path including the accident location.

Figure 7 is a diagram showing the data processing flow of an unmanned vehicle when driving in a city according to an embodiment.

Referring to FIG. 7, in step S15, the unmanned vehicle recognizes the amount of data exceeding the standard value, such as a large moving population or many parked vehicles while driving, or receives the amount of data exceeding the standard value from another unmanned vehicle. In step S25, it is checked whether a central beacon exists around the driving unmanned vehicle. If a central beacon exists, step S35 is entered and data and data amount exceeding the standard value received from the unmanned vehicle are transmitted to the central beacon. In step S45, the data collected from the beacon is analyzed and signals requesting appropriate vehicle control status are continuously transmitted to other unmanned vehicles and autonomous driving control servers. In an embodiment, an appropriate vehicle control state may include detour recommendation, low-speed driving, etc. In step S55, vehicles within the range of the central beacon are controlled according to control signals such as detour route recommendation and low-speed driving.

Figure 8 is a diagram showing a data processing process for traffic light control in an unmanned vehicle network system according to an embodiment.

Referring to FIG. 8, in step S100, when the unmanned vehicle enters the range of the central beacon while driving, the vehicle's direction of travel is transmitted to the central beacon. In the S200 stage, autonomous driving data such as vehicle direction is transmitted from the central beacon to the data center and autonomous driving control server, and in the S300 stage, traffic volume is predicted through deep learning based on data received from the autonomous driving control server. In the S400 stage, the traffic volume calculated by the autonomous driving control server is transmitted to the central beacon, and in the S500 stage, the signal type and maintenance time of the traffic light are controlled by considering the calculated traffic volume.

Figure 9 is a diagram showing a speeding vehicle enforcement process of an unmanned vehicle network system according to an embodiment.

Referring to FIG. 9, in step S11, when an unmanned vehicle enters the range of a central beacon for enforcement while driving, in step S21, it is confirmed whether the unmanned vehicle that entered from the central beacon is a vehicle that has been regulated in the corresponding central beacon area. In the case of a vehicle that has not been regulated, the current speed is transmitted from the unmanned vehicle to the central beacon in step S31, and in step S41, it is checked whether the collected speed exceeds the standard speed. If the collected speed exceeds the standard speed, in step S51, the enforcement camera is controlled to film the driving situation of the unmanned vehicle. In step S61, the captured unmanned vehicle crackdown photo is transmitted to the autonomous driving control server. In step S71, a breakpoint is temporarily created at the beacon terminal address of the controlled vehicle to prevent duplicate shooting. In step S81, it is checked whether the unmanned vehicle has left the central beacon range. If it does not escape, it re-enters step S11, and if the unmanned vehicle leaves the central beacon range, the speed control process ends. In the embodiment, if the unmanned vehicle that entered the central beacon is confirmed to be a vehicle controlled in the central beacon area in step S21, step S81 is entered to check whether the unmanned vehicle has left the central beacon range. If it does not escape, it re-enters step S11, and if the unmanned vehicle leaves the central beacon range, the speed control process ends.

The unmanned car network system and vehicle control method using the unmanned car network as described above allows for a wide range of data to be collected, such as long-distance road conditions that are difficult to collect with sensors, and the road condition of the car ahead, providing information on surrounding situations. By increasing the information acquisition range, the unmanned vehicle system can be operated flexibly.

Additionally, the reliability of the driverless car system can be improved by establishing a network between cars.

In addition, when an event such as an accident or construction that interferes with vehicle driving occurs, we predict the location and type of the event and the time required to resolve it, inform the vehicle of this, and guide detour routes to prevent traffic congestion in the area around the event. do.

The disclosed content is merely an example and can be modified and implemented in various ways by those skilled in the art without departing from the gist of the claims, so the scope of protection of the disclosed content is limited to the above-mentioned specific scope. It is not limited to the examples.

Claims (10)

In the driverless car network system,
A first autonomous vehicle that collects autonomous driving data including speed, distance between vehicles, surrounding environmental conditions, and obstacle information, and transmits the autonomous driving data to a surrounding Electronic Control Unit (ECU) using a beacon;
a second autonomous vehicle that receives autonomous driving data from the first autonomous vehicle and transmits the autonomous driving data to an autonomous driving control server;
Central beacons that collect and manage key road information, including the car's destination, current speed, and surrounding situation information, at point points on the highway, including toll gates and rest areas; and
an autonomous driving control server that receives autonomous driving data from the autonomous vehicle, collects important road information from the central beacon, and sets detailed autonomous driving information including inter-vehicle distance, speed, and lane change; A driverless car network system including.
According to claim 1, The central beacon; silver
Detects the current major movement locations of vehicles, current road accident information, and road obstacle information, and when road accident information and obstacle information is detected, predicts the expected congestion time, which is the time required to resolve the detected accident and obstacle. Characterized by a driverless car network system.
The system of claim 1, further comprising: the autonomous driving control server; Is
An unmanned vehicle network system that predicts the traffic volume for each section by deep learning the direction data of the unmanned vehicle transmitted from the central beacon, and controls the traffic lights and autonomous vehicles installed in the section according to the predicted traffic volume.
The system of claim 1, further comprising: the autonomous driving control server; Is
An unmanned car network system that groups unmanned cars that share accident information around the accident area and controls the grouped unmanned cars to move together to reduce their speed or change lanes together.
The system of claim 1, further comprising: the autonomous driving control server; Is
Training a deep learning neural network including at least one of DNN (Deep Neural Network), CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), and BRDNN (Bidirectional Recurrent Deep Neural Network) including autonomous driving data and key road information. An unmanned vehicle network system that implements a traffic prediction model and an unmanned vehicle control model by learning from a data set.
In a vehicle control method through an unmanned car network,
(A) Collect autonomous driving data including speed, distance between vehicles, surrounding environmental conditions, and obstacle information from the first autonomous vehicle, and transmit the autonomous driving data to the surrounding Electronic Control Unit (ECU) using a beacon. Transferring to;
(B) receiving autonomous driving data from the first autonomous vehicle in a second autonomous vehicle and transmitting the autonomous driving data to an autonomous driving control server;
(C) collecting and managing key road information, including the car's destination, current speed, and surrounding situation information, at point points on the highway, including toll gates and rest areas, from the central beacon; and
(D) The autonomous driving control server receives autonomous driving data from the autonomous vehicle, collects key road information from the central beacon, sets autonomous driving details including inter-vehicle distance, speed, and lane changes, and sets autonomous driving data. Controlling the unmanned vehicle according to driving details; Vehicle control method through unmanned car network including.
The method of claim 6, wherein step (C); Is
Detects the current major movement locations of vehicles, current road accident information, and road obstacle information, and when road accident information and obstacle information is detected, predicts the expected congestion time, which is the time required to resolve the detected accident and obstacle. Characteristics of vehicle control method through unmanned car network.
The method of claim 6, wherein step (D); Is
A vehicle control method through an unmanned car network that predicts traffic volume for each section by deep learning the direction data of the unmanned vehicle transmitted from the central beacon, and controls traffic lights and autonomous vehicles installed in the section according to the predicted traffic volume.
The method of claim 1, wherein step (D); Is
A vehicle control method using an unmanned car network that groups unmanned cars that share accident information around the accident area and controls the grouped unmanned cars to move together to reduce their speed or change lanes together.
The method of claim 1, wherein step (D); Is
Training a deep learning neural network including at least one of DNN (Deep Neural Network), CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), and BRDNN (Bidirectional Recurrent Deep Neural Network) including autonomous driving data and key road information. A vehicle control method using an unmanned car network, characterized by implementing a traffic prediction model by learning from a data set.