KR102505533B1 - Dynamic autonomous driving assistant system using v2i communication - Google Patents

Abstract

A dynamic autonomous driving support system using V2I communication is disclosed, and a method for supporting dynamic autonomous driving using V2I communication according to an embodiment of the present invention includes driving including an operation design domain (ODD) and a driving route of a vehicle. Receiving data and sensor data collected by a sensor installed in the vehicle, collecting driving environment data associated with the driving route, and designing the driving based on the driving data, the sensor data, and the driving environment data. Dynamically changing an area and transmitting information on the changed driving design area to the vehicle.

Description

Dynamic autonomous driving support system using V2I communication {DYNAMIC AUTONOMOUS DRIVING ASSISTANT SYSTEM USING V2I COMMUNICATION}

The present application relates to a dynamic autonomous driving support system using V2I communication. For example, the present disclosure relates to a dynamic autonomous driving support apparatus and method using V2I (Vehicle to Infrastructure) communication and a dynamic autonomous driving method using V2I communication.

Based on the level of self-driving according to the Society of Automotive Engineers (SAE), self-driving cars with a level of Level 5 (completely autonomous driving) or lower can autonomously drive only within the Operation Design Domain (ODD) assigned by the manufacturer of the car. It is possible, and autonomous driving is usually impossible when it is out of the driving design area (ODD). In other words, the driving design area (ODD) is used as a static concept that means a section in which manufacturers of autonomous vehicles specify situations in which autonomous driving is possible.

However, environmental factors such as traffic conditions, weather, and illumination of roads that various self-driving vehicles can pass through can change flexibly according to the passage of time and circumstances, and accordingly set within the driving design area (ODD) where autonomous driving is possible. Even in the section, a situation in which autonomous driving is difficult may occur due to road conditions such as weather, illumination, existence of shadows, obstacles, and accidents.

Therefore, it is required to develop and introduce an autonomous driving support system that can improve the stability and reliability of autonomous driving by interacting with the infrastructure and autonomous vehicles through V2I communication.

The background technology of the present application is disclosed in Korean Patent Registration No. 10-2107466.

The present application is intended to solve the problems of the prior art described above, and provides a dynamic autonomous driving support system using V2I communication that supports autonomous driving by actively determining the driving design area (ODD) for autonomous vehicles according to road conditions, etc. intended to do

The present application is to solve the problems of the prior art described above, and an object of the present application is to provide a dynamic autonomous driving support system using V2I communication that supports safe and reliable autonomous driving.

However, the technical problem to be achieved by the embodiments of the present application is not limited to the technical problems described above, and other technical problems may exist.

As a technical means for achieving the above technical problem, a method for supporting dynamic autonomous driving using V2I communication according to an embodiment of the present application includes driving data including an Operation Design Domain (ODD) and a driving route of a vehicle. and receiving sensor data collected by a sensor installed in the vehicle. Collecting driving environment data associated with the driving route. The driving design area based on the driving data, the sensor data, and the driving environment data. and transmitting information on the changed driving design area to the vehicle.

In addition, the dynamically changing step may generate determination information on autonomous driving availability for each section of the driving route based on the driving data, the sensor data, and the driving environment data.

In addition, the determination information includes first determination information indicating that the vehicle is capable of autonomous driving based on the sensor data, and second determination information indicating that the vehicle is capable of autonomous driving based on the sensor data and the driving environment data. information or third determination information indicating a state in which autonomous driving of the vehicle is impossible.

In addition, the generating of the determination information may include dividing the driving route into link units and generating the determination information for each of the divided links.

In addition, in the dynamic self-driving support method using V2I communication according to an embodiment of the present application, after the transmitting step, the driving environment data collected with respect to the link in which the second determination information is generated is transmitted to the vehicle. steps may be included.

In addition, the generating of the determination information for each link may include predicting road surface condition information and shade information for a link through which the vehicle will pass based on the driving environment data, and the predicted road surface condition information and shade information Based on the method, generating the determination information for the corresponding link may be included.

In addition, the driving environment data may include time-series data about the road surface condition of the link.

In the predicting step, the road surface condition information may be predicted based on a long short-term memory (LSTM)-based model pre-learned to predict a change in the road surface condition when the time-series data is input.

Also, the driving environment data may include image data of the road surface of the link.

In addition, in the predicting step, the shadow information may be predicted based on a You Only Look Once (YOLO)-based model trained in advance to predict whether a shadow exists on the road surface and a change in shadow length when the image data is input. .

On the other hand, in the dynamic autonomous driving method using V2I communication according to an embodiment of the present application, driving data including an Operation Design Domain (ODD) and a driving route of a vehicle and sensors collected by sensors installed in the vehicle Transmitting data to a dynamic autonomous driving support device, determining information on autonomous driving per section of the driving route generated based on the driving data, the sensor data, and the driving environment data collected in association with the driving route Receiving from the dynamic self-driving support device and determining whether to perform autonomous driving for each section of the vehicle based on the determination information.

In addition, the determination information is individually generated for each link included in the driving route, and the determining step determines whether autonomous driving is performed for each link based on the determination information received for each link. can decide

In addition, the dynamic self-driving method using V2I communication according to an embodiment of the present invention includes transmitting a driving environment data request signal for a link in which the second determination information is generated to the dynamic self-driving support device, the dynamic self-driving The method may include receiving the driving environment data from a driving support device and performing autonomous driving on a corresponding link based on the sensor data and the driving environment data.

On the other hand, in the dynamic autonomous driving support device using V2I communication according to an embodiment of the present application, driving data including an operation design domain (ODD) and a driving route of a vehicle and collected by a sensor installed in the vehicle A communication unit for receiving sensor data, a collection unit for collecting driving environment data associated with the driving route, and a determination unit for dynamically changing the driving design area based on the driving data, the sensor data, and the driving environment data. can

Also, the communication unit may transmit information about the changed driving design area to the vehicle.

In addition, the determination unit may generate determination information about autonomous driving per section of the driving route based on the driving data, the sensor data, and the driving environment data.

In addition, the determination unit may divide the travel path into link units and generate the determination information for each divided link.

Also, the communication unit may transmit the driving environment data collected with respect to the link in which the second determination information is generated to the vehicle.

In addition, the determination unit predicts road surface condition information and shade information for a link through which the vehicle will pass based on the driving environment data, and the determination information for the corresponding link based on the predicted road surface condition information and shade information. can create

The above-described problem solving means are merely exemplary and should not be construed as intended to limit the present disclosure. In addition to the exemplary embodiments described above, additional embodiments may exist in the drawings and detailed description of the invention.

According to the above-described problem solving means of the present application, it is possible to provide a dynamic autonomous driving support system using V2I communication that supports autonomous driving by actively determining an operation design area (ODD) for an autonomous vehicle according to road conditions, etc.

According to the above-described problem solving means of the present application, it is possible to provide a dynamic autonomous driving support system using V2I communication that supports safe and reliable autonomous driving.

However, the effects obtainable herein are not limited to the effects described above, and other effects may exist.

1 is a schematic configuration diagram of a dynamic autonomous driving support system using V2I communication according to an embodiment of the present invention.
2 is a conceptual diagram for explaining an LSTM-based model pre-learned to predict changes in road surface conditions.
3 is a conceptual diagram for explaining a YOLO-based model pre-learned to predict a change in shade information of a road.
4 is a schematic configuration diagram of an apparatus for supporting dynamic autonomous driving using V2I communication according to an embodiment of the present disclosure.
5 is a schematic configuration diagram of an apparatus for performing dynamic self-driving using V2I communication according to an embodiment of the present disclosure.
6 is an operational flowchart for a method for supporting dynamic autonomous driving using V2I communication according to an embodiment of the present disclosure.
7 is an operational flowchart for a dynamic autonomous driving method using V2I communication according to an embodiment of the present disclosure.
8 is a detailed operational flowchart of a method of operating a dynamic autonomous driving support system using V2I communication according to an embodiment of the present disclosure.

Hereinafter, embodiments of the present application will be described in detail so that those skilled in the art can easily practice with reference to the accompanying drawings. However, the present disclosure may be implemented in many different forms and is not limited to the embodiments described herein. And in order to clearly describe the present application in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the present specification, when a part is said to be “connected” to another part, it is not only “directly connected”, but also “electrically connected” or “indirectly connected” with another element in between. "Including cases where

Throughout the present specification, when a member is referred to as being “on,” “above,” “on top of,” “below,” “below,” or “below” another member, this means that a member is located in relation to another member. This includes not only the case of contact but also the case of another member between the two members.

Throughout the present specification, when a certain component is said to "include", it means that it may further include other components without excluding other components unless otherwise stated.

The present application relates to a dynamic autonomous driving support system using V2I communication. For example, the present disclosure relates to a dynamic autonomous driving support apparatus and method using V2I (Vehicle to Infrastructure) communication and a dynamic autonomous driving method using V2I communication.

1 is a schematic configuration diagram of a dynamic autonomous driving support system using V2I communication according to an embodiment of the present invention.

Referring to FIG. 1 , a dynamic autonomous driving support system 10 using V2I communication according to an embodiment of the present application (hereinafter referred to as 'dynamic autonomous driving support system 10') is may include a dynamic self-driving support device 100 using V2I communication according to the present invention (hereinafter referred to as 'dynamic self-driving support device 100'), a dynamic self-driving performance device 200, and an infrastructure 300.

The dynamic self-driving support device 100 , the dynamic self-driving device 200 , and the infrastructure 300 may communicate with each other through the network 20 . The network 20 refers to a connection structure capable of exchanging information between nodes such as terminals and servers, and examples of such a network 20 include a 3rd Generation Partnership Project (3GPP) network and a Long LTE (LTE) network. Term Evolution (Term Evolution) network, 5G network, WIMAX (World Interoperability for Microwave Access) network, Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network) Network), wifi network, Bluetooth network, satellite broadcasting network, analog broadcasting network, DMB (Digital Multimedia Broadcasting) network, etc. are included, but are not limited thereto.

According to an embodiment of the present application, at least one of the dynamic self-driving support device 100 and the dynamic self-driving device 200 is mounted (installed) on a user terminal (not shown) or linked to (not shown) a user terminal (not shown). It may be operated in the form of pairing). User terminals (not shown) include, for example, a smart phone, a smart pad, a tablet PC, and the like and PCS (Personal Communication System), GSM (Global System for Mobile communication), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) It may be any kind of wireless communication device such as a terminal. As another example, the dynamic self-driving support device 100 may be implemented in the form of a server that transmits and receives necessary data based on V2I communication between the vehicle 1 and the infrastructure 300 .

According to an embodiment of the present disclosure, the dynamic self-driving device 200 may be installed in the vehicle 1 . For example, the apparatus 200 for performing dynamic self-driving includes various devices mounted in the vehicle 1 such as a navigation module, a high-pass module, or a connected car mobility service module and capable of collecting driving information of the vehicle 1; It can be variously implemented in the form of a sub-module that can be mounted in the above-described device.

Illustratively, the connected car mobility service module is illustratively mounted inside a vehicle to provide remote starting services such as Blue Link and UVO, remote air conditioner control services, etc. It may refer to a terminal that communicates and helps the driver's convenience and traffic safety.

In addition, the dynamic self-driving device 200 is a driving record storage device that is installed under the driver's seat or on the dashboard of the vehicle to store vehicle status, fuel economy information, fuel information, acceleration information, vehicle breakdown history, and the like. It may be associated with a self-diagnosis device (not shown).

In addition, according to an embodiment of the present application, the infrastructure 300 is installed in an area of a driving road, such as Internet of Things (IoT) equipment, speed detectors, toll gate equipment, high-pass terminals, and surveillance cameras to detect driving information of vehicles traveling nearby. It can be understood as a concept that broadly includes various devices that can be collected. More specifically, the infrastructure 300 may include a photographing device 301 that obtains image data of a road surface. For example, the photographing device 301 may be a CCTV terminal installed at a predetermined location around a road.

Additionally, according to an embodiment of the present disclosure, infrastructure 300 may include a city traffic information system 302 . Here, the city traffic information system 302 may refer to a traffic information system that produces and provides traffic information for each city or a server associated therewith, and specifically, a traffic information center provided in each major city, a collection and provision device, It may refer to a system or server that produces, processes, and provides various traffic information in connection with road-based facilities such as surveillance cameras and variable electric signage (VMS).

Hereinafter, functions and operations of the dynamic self-driving support device 100 and the dynamic self-driving device 200 will be described in detail.

The dynamic autonomous driving support device 100 may receive driving data including an Operation Design Domain (ODD) and a driving route of the vehicle 1 and sensor data collected by a sensor installed in the vehicle 1. there is. For example, the dynamic self-driving support device 100 may receive driving data and sensor data from the dynamic self-driving device 200 . As another example, the apparatus 100 for supporting dynamic autonomous driving may operate to receive driving data from the apparatus 200 for performing autonomous driving and sensor data from sensors installed in the vehicle 1 .

For reference, since an autonomous vehicle drives on its own without driver intervention or with minimal driver intervention, a driving design area predefined which functions should be executed when various constraints such as road types and weather occur during operation. (ODD) to drive. That is, the operation design area (ODD) in the present application may be understood as a concept in which limits of control performance and safety of the vehicle 1 are set in advance based on similar cases, driving scenarios, and the like.

In addition, according to an embodiment of the present disclosure, sensors installed in the vehicle 1 to obtain sensor data include, for example, a radar sensor, a LiDAR sensor, a vision sensor, an obstacle detection sensor, a lane detection sensor, and a speed sensor. It may include a sensor, a pressure sensor, an acceleration sensor, and the like.

In addition, the apparatus 100 for supporting dynamic autonomous driving may collect driving environment data associated with a driving route of the vehicle 1 . For example, the dynamic self-driving support device 100 acquires driving environment data from the infrastructure 300 at preset unit time intervals, and among the acquired driving environment data, driving environment data associated with the driving path of the vehicle 1 is selected. It may be to collect necessary driving environment data in a screening method.

In addition, according to an embodiment of the present application, the dynamic self-driving support apparatus 100 includes detailed types of the infrastructure 300 that provided driving environment data (eg, the photographing device 301 and the road traffic information system 302). etc.) may have reliability information corresponding to In addition, when driving environment data for the same road (link) is received from a plurality of subjects (infrastructure terminals), the apparatus 100 for supporting dynamic self-driving determines which driving environment data is inconsistent according to the collection subject based on the reliability information possessed. It can be allocated as data corresponding to one collection entity. Illustratively, in the case of the photographing device 301 , the reliability information may be set based on area information and resolution information of a road (road surface) photographed by the photographing device 301 . For better understanding, with respect to the photographing device 301 installed to photograph a road (road surface) in a wider area, the photographing device 301 photographs the road (road surface) in a smaller area than the corresponding photographing device 301. ) may be given high reliability.

In addition, according to an embodiment of the present application, the driving environment data obtained by the infrastructure 300 and transmitted to the dynamic self-driving support apparatus 100 include temperature information of the road (road surface), condition information of the road (road surface), road It may include image (video) information on (road surface), obstacle information, road facility information, traffic volume information, accident area information, and the like. In other words, the driving environment data collected through the infrastructure 300 may affect the driving of the vehicle 1 but may include various types of information that are difficult to obtain using only vehicle sensors installed in the vehicle 1 . In particular, the road (road surface) condition information may include a result of analyzing a road (road surface) condition that may greatly affect driving and braking of the vehicle 1, such as a dry state, a wet state, and an icy state. In particular, the condition information of the road (road surface) may include location information of an icy section on the corresponding road.

In addition, the apparatus 100 for supporting dynamic autonomous driving may dynamically change the driving design area ODD preset for the vehicle 1 based on the received driving data, sensor data, and driving environment data. More specifically, the apparatus 100 for supporting dynamic autonomous driving may generate information for determining autonomous driving for each section of a driving route of the vehicle 1 based on driving data, sensor data, and driving environment data. For reference, in the description of the embodiment of the present application, a section of a driving route, which is a unit for dividing a driving route, may have a 'link', which means an intersection and a road between the intersections, as a unit. In other words, each section of the driving route may be divided to include at least one link according to an embodiment of the present disclosure.

In addition, the apparatus 100 for supporting dynamic autonomous driving may transmit information about the changed driving design area (ODD) to the vehicle 1 . More specifically, the dynamic self-driving support device 100 may transmit, to the dynamic self-driving device 200 , determination information on the availability of autonomous driving for each section, which is information about the changed driving design area (ODD). In this regard, the apparatus 200 for performing autonomous driving may determine whether or not to perform (continue) autonomous driving based on information or judgment information on the changed driving design area (ODD) received as will be described later.

In addition, according to an embodiment of the present application, the determination information generated by the dynamic self-driving support apparatus 100 is first generated when it is determined that the vehicle 1 is in a state capable of self-driving based on sensor data. Determination information, second judgment information generated when it is determined that the vehicle 1 is in a state capable of autonomous driving based on sensor data and driving environment data, or when it is determined that the vehicle 1 is in a state where autonomous driving is impossible It may include third judgment information generated in .

Specifically, the dynamic self-driving support apparatus 100 uses only sensor data obtained within the vehicle 1 without various information (driving environment data) collected by the infrastructure 300 for the vehicle 1 in the corresponding section (link). When it is determined that autonomous driving is possible, first determination information may be generated. In other words, it can be understood that the first determination information is generated when it is determined that the vehicle 1 is in the autonomous driving 'capable' stage.

In addition, the dynamic self-driving support device 100 adds various information (driving environment data) collected by the infrastructure 300 even though autonomous driving is difficult only with sensor data collected by the vehicle 1 itself in the corresponding section (link). and when it is determined that autonomous driving is possible by fusion of sensor data and driving environment data (sensor fusion), second determination information may be generated. In other words, it can be understood that the second determination information is generated when it is determined that the vehicle 1 is in the 'normal' level of autonomous driving. Also, according to an embodiment of the present disclosure, the autonomous driving step corresponding to the second determination information may be otherwise referred to as a 'infrastructure cooperation required' step.

In addition, even if the dynamic self-driving support device 100 utilizes the sensor data collected by the vehicle 1 itself and the driving environment data collected by the infrastructure 300 together in the corresponding section (link), autonomous driving is performed by the road surface condition, etc. If it is determined that this is not possible, third decision information may be generated. In other words, it can be understood that the third determination information is generated when it is determined that the vehicle 1 is in an autonomous driving 'impossible' stage.

In summary, the apparatus 100 for supporting dynamic autonomous driving divides the driving route received from the vehicle 1 into link units, and determines whether autonomous driving is possible for each divided link or for each unit section including at least one link. Determination information including a result may be generated.

More specifically, the apparatus 100 for supporting dynamic autonomous driving may predict road surface condition information and shadow information for a link through which the vehicle 1 will pass based on the driving environment data received from the infrastructure 300 . Hereinafter, a process in which the dynamic self-driving support apparatus 100 predicts road surface condition information and shadow information based on a pre-constructed artificial intelligence model will be described in detail.

2 is a conceptual diagram for explaining an LSTM-based model pre-learned to predict changes in road surface conditions.

Referring to FIG. 2 , the apparatus 100 for supporting dynamic autonomous driving includes time-series data about the road surface condition of the link (eg, weather information such as temperature, temperature, and humidity of the road surface) from the infrastructure 300 . Environmental data can be received. In addition, when predetermined time-series data is input, the dynamic self-driving support device 100 uses an LSTM (which is pre-learned to predict a change in road surface condition (in other words, a road surface condition predicted for the next time unit) based on the corresponding time-series data) Road surface condition information can be predicted based on an artificial intelligence model based on long short-term memory.

The LSTM (Long-Short Term Memory) algorithm is one of the artificial recursive neural network (RNN) architectures used in the field of deep learning. Unlike feed-forward neural networks, feedback connections exist. Therefore, according to the LSTM algorithm, learning and processing can be performed not only for a single data point but also for an entire data sequence.

These LSTM algorithms are suitable for classifying, processing, and predicting predictions based on time series data, and LSTM has the advantage of solving the vanishing gradient problem that can occur in training through traditional RNN.

However, the type of artificial intelligence model for predicting changes in road surface conditions is not limited to the above-described LSTM algorithm, and according to the implementation of the present application, the dynamic autonomous driving support device 100 includes an attention algorithm, a transformer, in addition to the LSTM algorithm Algorithm, BERT (Bidirectional Encoder Representations from Transformers) algorithm, etc. Based on artificial intelligence algorithm based on time series data analysis that can predict future road surface conditions through analysis of time series data reflecting the road surface condition of the link from the past to the present. Thus, road surface condition information can be predicted. That is, in the present application, algorithm models based on various time-series data analysis previously known or developed in the future may be applied.

3 is a conceptual diagram for explaining a YOLO-based model pre-learned to predict a change in shade information of a road.

Referring to FIG. 3 , the apparatus 100 for supporting dynamic autonomous driving may receive driving environment data including image data of a road surface of a link from the infrastructure 300 . In addition, when predetermined image data (Images in FIG. 3 ) is input, the dynamic self-driving support device 100 pre-learns YOLO (You Shadow information may be predicted based on a model based on Only Look Once.

The YOLO algorithm is an example of an object detection algorithm that is trained to detect a semantic region of an image in real time. The semantic region is exemplarily a preset object such as a face, a car, a tree, glasses, etc. that may be included in predetermined image data. It may be an image pattern corresponding to . In particular, according to the YOLO algorithm, it can be determined whether a predetermined object is included in video data (image) or whether a predetermined object does not appear and only the background exists alone.

Specifically, the YOLO algorithm is a supervised learning machine learning algorithm that generates training data by pairing a semantic domain to be recognized with classification information (i.e., labeling), and is a learning model that uses a large number of training data as input parameters. It is possible to perform object classification to extract the learned semantic region from an arbitrary image by generating

In addition, according to an embodiment of the present application, when object classification is performed by the YOLO algorithm, the extracted semantic region may be provided in the form of a bounding box, and classification information for each bounding box (Object Class) can be provided together. Since this YOLO algorithm has high performance and accuracy and fast execution speed in the field of machine learning image recognition, it can be used in the field of real-time object recognition such as self-driving cars and person detection in images. The dynamic self-driving support device disclosed herein (100 ) uses the YOLO algorithm to determine the presence or absence of shadows in the image data of the road surface, as well as changes in the presence or absence of shadows and changes in the length of shadows after that point in time (the point of determining whether shadows exist) trends can be predicted.

In addition, the apparatus 100 for supporting dynamic self-driving may generate determination information for a corresponding link based on the predicted road surface condition information and shadow information.

In addition, the apparatus 100 for supporting dynamic autonomous driving may transmit information about the changed driving design area (ODD) to the vehicle 1 . More specifically, the apparatus 100 for supporting dynamic self-driving provides determination information (for example, any one of the first to third determination information) on whether autonomous driving is permitted or not generated for each link or for each unit section including at least one link. ) may be transmitted to the dynamic self-driving apparatus 200 mounted in the vehicle 1. In addition, the type of decision information generated for each link or for each unit section including at least one link may be different according to circumstances.

However, the dynamic self-driving support apparatus 100 determines if the type of determination information for all links or unit sections on the driving route of the vehicle 1 is the first determination information (in other words, the vehicle 1 is on the entire driving route). When self-driving is determined to be in an autonomous driving 'enabled' state), determination information on the entire driving route may be integrated as first determination information and transmitted to the dynamic self-driving apparatus 200 .

In addition, according to an embodiment of the present application, the apparatus 100 for supporting dynamic self-driving may transmit driving environment data collected with respect to a link in which the second determination information is generated to the vehicle 1 .

In this regard, the dynamic self-driving device 200 receiving the information on the changed operation design area (ODD) from the dynamic self-driving support device 100 performs autonomous driving on the link where the second determination information is finally generated. When it is determined to perform (in other words, to activate the self-driving function of the vehicle 1), the dynamic self-driving support device 100 drives on the link for which the second determination information is generated from the dynamic self-driving performance device 200. An environment data request signal may be received. In addition, the dynamic autonomous driving support apparatus 100 transmits information necessary for autonomous driving of the vehicle 1 among driving environment data collected for a link in which second determination information is generated in response to the received driving environment data request signal. By transmitting to the driving performance device 200 , the vehicle 1 may support autonomous driving by integrating sensor data and driving environment data, which is infrastructure cooperation information collected through the infrastructure 300 .

In addition, according to an embodiment of the present application, the driving environment data transmitted to the vehicle 1 (specifically, the device 200 for performing dynamic autonomous driving) in response to the driving environment data request signal includes a corresponding link. Information on the location of obstacles on the road, location information of the shadow on the link determined based on the above-described shadow information, and information on the location of icing on the road of the corresponding link determined based on the above-described road surface condition information may be included. .

4 is a schematic configuration diagram of an apparatus for supporting dynamic autonomous driving using V2I communication according to an embodiment of the present disclosure.

Referring to FIG. 4 , the apparatus 100 for supporting dynamic autonomous driving may include a communication unit 110 , a collection unit 120 and a determination unit 130 .

The communication unit 110 may receive driving data including an Operation Design Domain (ODD) and a driving route of the vehicle 1 and sensor data collected by sensors installed in the vehicle 1 . Also, the communication unit 110 may transmit information on the changed driving design area ODD to the vehicle 1 .

The collecting unit 120 may collect driving environment data associated with the driving route of the vehicle 1 .

The determination unit 130 may dynamically change the driving design area ODD of the vehicle 1 based on driving data, sensor data, and driving environment data. In detail, the determination unit 130 may generate determination information on autonomous driving per section of the driving route of the vehicle 1 based on the received and collected driving data, sensor data, and driving environment data. In particular, the determination information generated by the determination unit 130 includes first determination information indicating that the vehicle 1 is in a state in which autonomous driving is possible based on sensor data, and the vehicle 1 is autonomously driven based on sensor data and driving environment data. It may include second determination information in a state in which driving is possible or third determination information in a state in which autonomous driving of the vehicle 1 is impossible.

5 is a schematic configuration diagram of an apparatus for performing dynamic self-driving using V2I communication according to an embodiment of the present disclosure.

Referring to FIG. 5 , the apparatus 200 for performing dynamic autonomous driving may include a sensor unit 210 , a communication unit 220 and a determination unit 230 .

The sensor unit 210 may include various sensors installed in the vehicle 1 and collect sensor data based on the sensors described above. For example, the sensor unit 210 may include a radar sensor, a LiDAR sensor, a vision sensor, an obstacle detection sensor, a lane detection sensor, a speed sensor, a pressure sensor, an acceleration sensor, and the like.

The communication unit 220 may transmit driving data including an Operation Design Domain (ODD) and a driving route of the vehicle and sensor data acquired by the sensor unit 210 to the dynamic autonomous driving support device 100. .

In addition, the communication unit 220 transmits determination information on autonomous driving per section of the driving route generated based on driving data, sensor data, and driving environment data collected in association with the driving route from the dynamic autonomous driving support device 100. can receive

The determination unit 230 may determine whether to perform autonomous driving for each section of the vehicle 1 based on the determination information received from the apparatus 100 for supporting dynamic autonomous driving. In particular, determination information is individually generated for each link included in the driving route, and the determination unit 230 may determine whether to perform autonomous driving for each link based on the determination information received for each link.

In addition, according to an embodiment of the present application, the determination unit 230 may include a display unit (not shown) provided in the apparatus 200 for performing dynamic self-driving or a user terminal (not shown) interworking with the apparatus 200 for performing dynamic self-driving. Displays an interface that visualizes and provides the judgment information received through the user (eg, driver), and autonomous driving for each link based on the user input based on the displayed interface and the autonomous driving selection input for each link. It may be to decide whether Exemplarily, the autonomous driving selection input is a display corresponding to the determination information generated for each link (eg, a section in which the first determination information is generated is green, a section in which the second determination information is generated is yellow, and a third The section in which the determination information is generated may be a touch input for selecting a section to perform autonomous driving from among a map-type interface displaying a driving route by categorizing it in red. As another example, the autonomous driving selection input may be a voice input.

In addition, according to an embodiment of the present application, the determination unit 230 may set the autonomous driving previously received through the dynamic self-driving device 200 or a user terminal (not shown) interworking with the dynamic self-driving device 200. Based on the type of determination information received based on the input, autonomous driving may be selectively applied. Exemplarily, when the vehicle 1 is preset to perform autonomous driving only for the section in which the first determination information is generated based on the previously received autonomous driving setting input, the apparatus 200 for performing dynamic autonomous driving can control the vehicle 1 so that the autonomous driving function is activated without receiving a separate autonomous driving selection input for the section (link) in which the first determination information is generated. As another example, when the vehicle 1 is preset to perform autonomous driving for both sections in which the first determination information and the second determination information are generated, the dynamic self-driving apparatus 200 performs the first determination information or The vehicle 1 can be controlled so that the autonomous driving function is activated without receiving a separate autonomous driving selection input for the section (link) where the second decision information is generated, and the section (link) where the second decision information is generated. It is possible to operate to transmit the driving environment data request signal to the dynamic self-driving support device 100 without receiving a separate user input.

Hereinafter, based on the details described above, the operation flow of the present application will be briefly reviewed.

6 is an operational flowchart for a method for supporting dynamic autonomous driving using V2I communication according to an embodiment of the present disclosure.

The method for supporting dynamic autonomous driving using V2I communication shown in FIG. 6 may be performed by the apparatus 100 for supporting dynamic autonomous driving described above. Therefore, even if the content is omitted below, the description of the dynamic self-driving support device 100 can be equally applied to the description of the dynamic self-driving support method using V2I communication.

Referring to FIG. 6 , in step S11, the communication unit 110 receives driving data including the driving design area (ODD) and driving route of the vehicle 1 and sensor data collected by sensors installed in the vehicle 1. can do.

Next, in step S12 , the collection unit 120 may collect driving environment data associated with the driving route of the vehicle 1 . Specifically, in step S12 , the collecting unit 120 may receive collected driving environment data about a road corresponding to a driving route of the vehicle 1 from the infrastructure 300 .

Next, in step S13, the determination unit 130 may dynamically change the driving design area ODD based on the received driving data, sensor data, and collected driving environment data. Specifically, in step S13, the determination unit 130 may generate determination information on whether autonomous driving is permitted for each section of the driving route of the vehicle 1 based on the received driving data, sensor data, and collected driving environment data. there is.

According to an embodiment of the present application, in step S13, the determination unit 130 may divide the driving route into link units. Also, in step S13, the determination unit 130 may generate determination information for each divided link.

Also, in step S13, the determination unit 130 may predict road surface condition information and shadow information for a link through which the vehicle 1 will pass based on the driving environment data. Also, in step S13, the determination unit 130 may generate the determination information for the corresponding link based on the predicted road surface condition information and shade information.

Next, in step S14 , the communication unit 110 may transmit information on the changed driving design area ODD to the vehicle 1 .

In the foregoing description, steps S11 to S14 may be further divided into additional steps or combined into fewer steps, depending on an embodiment of the present invention. Also, some steps may be omitted if necessary, and the order of steps may be changed.

7 is an operational flowchart for a dynamic autonomous driving method using V2I communication according to an embodiment of the present disclosure.

The dynamic self-driving method using V2I communication shown in FIG. 7 may be performed by the dynamic self-driving apparatus 200 described above. Therefore, even if the content is omitted below, the description of the dynamic self-driving device 200 can be equally applied to the description of the dynamic self-driving method using V2I communication.

Referring to FIG. 7 , in step S21, the communication unit 220 transmits driving data including an Operation Design Domain (ODD) and a driving route of the vehicle, and a sensor unit including at least one sensor installed in the vehicle 1. Sensor data associated with the driving of the vehicle 1 collected through 210 may be transmitted to the dynamic self-driving support device 100 .

Next, in step S22, the communication unit 220 transmits information for determining autonomous driving for each section of the driving route of the vehicle 1 generated based on the driving data, sensor data, and driving environment data collected in association with the driving route. It can be received from the dynamic self-driving support device 100 .

Next, in step S23, the determination unit 230 determines whether to perform autonomous driving for each section of the vehicle 1 based on the received determination information, and selectively activates functions related to autonomous driving of the vehicle 1 according to the section. Or you can disable it.

In the foregoing description, steps S21 to S23 may be further divided into additional steps or combined into fewer steps, depending on the implementation of the present application. Also, some steps may be omitted if necessary, and the order of steps may be changed.

8 is a detailed operational flowchart of a method of operating a dynamic autonomous driving support system using V2I communication according to an embodiment of the present disclosure.

The operation method of the dynamic self-driving support system using V2I communication shown in FIG. 8 may be performed by the dynamic self-driving support system 10 described above. Therefore, even if omitted below, the description of the dynamic self-driving support system 10 can be equally applied to the description of FIG. 8 .

Referring to FIG. 8 , in step S31 , the communication unit 110 may receive driving data of the vehicle 1 .

Next, in step S32, the collection unit 120 may extract information corresponding to (corresponding to) the driving route of the vehicle 1 from among the driving environment data collected from the infrastructure 300.

Next, in step S33, the determination unit 130 may generate determination information on whether autonomous driving is permitted for each section of the driving route of the vehicle 1 based on the driving data, sensor data, and driving environment data.

Next, in step S34, the determination unit 130 determines whether the vehicle 1 is capable of autonomous driving only with sensor data in all links (or unit sections including at least one link) on the driving route of the vehicle 1 (autonomous driving). whether or not driving is 'available') can be determined.

Next, in step S35, the communication unit 110 determines that the vehicle 1 is capable of autonomous driving in all links (or unit sections including at least one link) on the driving route of the vehicle 1 by the determination unit 130. If determined to be true, first determination information including the determination result may be transmitted to the dynamic self-driving device 200 .

Conversely, as a result of the determination in step S34, when it is determined that autonomous driving is not possible in all links (or unit sections including at least one link) on the driving route of the vehicle 1, the determination unit 130 in step S36 may derive a link (section) in which autonomous driving is not possible by the vehicle 1 alone and a cause of unavailability of autonomous driving in the corresponding link (section).

Next, in step S37, the determination unit 130 determines that each link (section) is an infrastructure (section) based on the identified cause of autonomous driving impossibility for the link (section) for which it is determined that autonomous driving is not possible with the vehicle 1 alone. 300), it is possible to determine whether autonomous driving is possible (whether autonomous driving is in a 'normal' state) through sensor data and driving environment data.

If, as a result of the determination in step S37, if there is a link (section) corresponding to the autonomous driving 'normal' state, in step S38, the communication unit 110 determines that the second determination information for the corresponding link is the dynamic autonomous driving device 200 ) or through a user terminal (not shown) linked with the dynamic self-driving device 200.

Conversely, as a result of the determination in step S37, if the link (section) corresponding to the autonomous driving 'normal' state does not exist, in step S39, the communication unit 110 operates in all links (or unit sections including at least one link). The vehicle 1 may transmit third determination information including a determination result that it is determined that autonomous driving is impossible to the dynamic autonomous driving performance device 200 .

In the foregoing description, steps S31 to S39 may be further divided into additional steps or combined into fewer steps, depending on an embodiment of the present invention. Also, some steps may be omitted if necessary, and the order of steps may be changed.

The dynamic self-driving support method using V2I communication and/or the dynamic self-driving method using V2I communication according to an embodiment of the present application may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. can The computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. Program instructions recorded on the medium may be those specially designed and configured for the present invention or those known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. - includes hardware devices specially configured to store and execute program instructions, such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, as well as machine language codes such as those produced by a compiler. The hardware devices described above may be configured to act as one or more software modules to perform the operations of the present invention, and vice versa.

In addition, the above-described dynamic autonomous driving support method using V2I communication and/or dynamic autonomous driving method using V2I communication may be implemented in the form of a computer program or application stored in a recording medium and executed by a computer.

The above description of the present application is for illustrative purposes, and those skilled in the art will understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present application. Therefore, the embodiments described above should be understood as illustrative in all respects and not limiting. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined form.

The scope of the present application is indicated by the following claims rather than the detailed description above, and all changes or modifications derived from the meaning and scope of the claims and equivalent concepts thereof should be construed as being included in the scope of the present application.

10: Dynamic autonomous driving support system using V2I communication
100: Dynamic autonomous driving support device
110: communication department
120: collection unit
130: judgment unit
200: dynamic self-driving device
210: sensor unit
220: communication department
230: decision unit
300: infrastructure
20: Network

Claims (16)

In the dynamic autonomous driving support method using V2I communication,
Receiving driving data including an Operation Design Domain (ODD) and a driving route of the vehicle and sensor data collected by a sensor installed in the vehicle;
collecting driving environment data associated with the driving route;
dynamically changing the driving design area based on the driving data, the sensor data, and the driving environment data; and
Transmitting information about the changed driving design area to the vehicle;
including,
The step of dynamically changing the driving design area,
Dividing the travel path into link units; and
Generating determination information on autonomous driving availability for each section of the driving route based on the driving data, the sensor data, and the driving environment data in consideration of the divided links;
including,
Generating the determination information,
For a link in which it is determined that the vehicle is capable of autonomous driving only with the sensor data without the driving environment data, first determination information for determining that the vehicle is capable of autonomous driving based on the sensor data is generated;
For a link in which the vehicle cannot perform autonomous driving only with the sensor data, but is determined to be capable of autonomous driving by fusing the sensor data and the driving environment data, the vehicle performs autonomous driving based on the sensor data and the driving environment data. generating second determination information for determining that the vehicle is in a driving state;
Third determination information for determining that autonomous driving of the vehicle is impossible is generated for a link in which autonomous driving is determined to be impossible even when the vehicle fuses the sensor data and the driving environment data;
The first decision information to the third decision information,
Characterized in that it is individually generated for each unit section including the link or at least one link,
Collecting the driving environment data,
Among the driving environment data acquired from the infrastructure, driving environment data associated with the driving path of the vehicle is selected, but if the driving environment data is repeatedly received from a plurality of infrastructures for one link, the reliability information of each of the plurality of infrastructures. Allocate data corresponding to any one of the plurality of infrastructures as the driving environment data based on, and if the reliability information is a photographing device type, the road corresponding to the link is photographed over a relatively large area. It is characterized in that the higher the shooting device installed to be,
An interface visualizing the first determination information to the third determination information is visualized through a display unit provided in a dynamic self-driving device provided in the vehicle or a user terminal interworking with the dynamic self-driving device, and the interface Whether or not autonomous driving for each link is determined based on an autonomous driving selection input for each link received based on
When an autonomous driving setting input is received in advance to perform autonomous driving for a section in which a specific type of determination information is generated among the first to third determination information, the determination information of the specific type is generated. wherein an autonomous driving function is activated even if the autonomous driving selection input is not received for at least one of a link and the unit section. delete delete delete According to claim 1,
After the sending step,
Transmitting the driving environment data collected for the link in which the second determination information is generated to the vehicle;
To further include, dynamic self-driving support method. According to claim 1,
Generating the determination information,
predicting road surface condition information and shadow information for a link through which the vehicle will pass based on the driving environment data; and
Generating the determination information for a corresponding link based on the predicted road surface condition information and shade information;
To include, dynamic self-driving support method. According to claim 6,
The driving environment data,
Including time series data on the road surface condition of the link,
The predicting step is
When the time series data is input, the road surface condition information is predicted based on a long short-term memory (LSTM)-based model learned in advance to predict a change in the road surface condition. According to claim 6,
The driving environment data,
Including image data for the road surface of the link,
The predicting step is
When the image data is input, the shadow information is predicted based on a You Only Look Once (YOLO)-based model pre-learned to predict the existence of a shadow on the road surface and a change in shadow length. In the dynamic autonomous driving method using V2I communication,
Transmitting driving data including an Operation Design Domain (ODD) and a driving route of the vehicle and sensor data collected by a sensor installed in the vehicle to a dynamic autonomous driving support device;
receiving, from the dynamic autonomous driving support device, determination information on whether or not autonomous driving is allowed for each section of the driving route, which is generated based on the driving data, the sensor data, and driving environment data collected in association with the driving route; and
Determining whether to perform autonomous driving for each section of the vehicle based on the determination information;
including,
The dynamic autonomous driving support device,
Dividing the driving route into link units, and generating determination information on autonomous driving availability for each section of the driving route based on the driving data, the sensor data, and the driving environment data in consideration of the divided links;
The dynamic autonomous driving support device,
For a link in which it is determined that the vehicle is capable of autonomous driving only with the sensor data without the driving environment data, first determination information for determining that the vehicle is capable of autonomous driving based on the sensor data is generated;
For a link in which the vehicle cannot perform autonomous driving only with the sensor data, but is determined to be capable of autonomous driving by fusing the sensor data and the driving environment data, the vehicle performs autonomous driving based on the sensor data and the driving environment data. generating second determination information for determining that the vehicle is in a driving state;
Third determination information for determining that autonomous driving of the vehicle is impossible is generated for a link in which autonomous driving is determined to be impossible even when the vehicle fuses the sensor data and the driving environment data;
The first decision information to the third decision information,
Characterized in that it is individually generated for each unit section including the link or at least one link,
The dynamic autonomous driving support device,
Among the driving environment data acquired from the infrastructure, driving environment data associated with the driving path of the vehicle is selected, but if the driving environment data is repeatedly received from a plurality of infrastructures for one link, the reliability information of each of the plurality of infrastructures. Allocate data corresponding to any one of the plurality of infrastructures as the driving environment data based on, and if the reliability information is a photographing device type, the road corresponding to the link is photographed over a relatively large area. It is characterized in that the higher the shooting device installed to be,
After the receiving step,
displaying an interface for visualizing the first to third determination information through a display unit provided in a device for performing dynamic self-driving provided in the vehicle or a user terminal interworking with the device for performing dynamic self-driving; and
Receiving an autonomous driving selection input and an autonomous driving setting input for each link based on the interface;
Including more,
The step of determining whether to perform autonomous driving,
Based on the autonomous driving selection input for each link, whether or not autonomous driving is determined for each link,
When an autonomous driving setting input is received in advance to perform autonomous driving for a section in which a specific type of determination information is generated among the first to third determination information, the determination information of the specific type is generated. The dynamic self-driving method, wherein an autonomous driving function is activated even when the autonomous driving selection input is not received for at least one of a link and the unit section. delete According to claim 9,
The judgment information,
Individually generated for each link included in the driving route,
The determining step is
And determining whether or not to perform autonomous driving for each link based on the determination information received for each link. According to claim 11,
transmitting a driving environment data request signal for a link where the second determination information is generated to the dynamic autonomous driving support device;
receiving the driving environment data from the dynamic autonomous driving support device; and
Performing autonomous driving for a corresponding link based on the sensor data and the driving environment data;
To further include, a dynamic self-driving method. In the dynamic self-driving support device using V2I communication,
A communication unit for receiving driving data including an Operation Design Domain (ODD) and a driving route of the vehicle and sensor data collected by a sensor installed in the vehicle;
a collection unit that collects driving environment data associated with the driving route; and
a determination unit that dynamically changes the driving design area based on the driving data, the sensor data, and the driving environment data;
including,
The judge,
Dividing the driving route into link units, and generating determination information on autonomous driving availability for each section of the driving route based on the driving data, the sensor data, and the driving environment data in consideration of the divided links;
The judge,
For a link in which it is determined that the vehicle is capable of autonomous driving only with the sensor data without the driving environment data, first determination information for determining that the vehicle is capable of autonomous driving based on the sensor data is generated;
For a link in which the vehicle cannot perform autonomous driving only with the sensor data, but is determined to be capable of autonomous driving by fusing the sensor data and the driving environment data, the vehicle performs autonomous driving based on the sensor data and the driving environment data. generating second determination information for determining that the vehicle is in a driving state;
Third determination information for determining that autonomous driving of the vehicle is impossible is generated for a link in which autonomous driving is determined to be impossible even when the vehicle fuses the sensor data and the driving environment data;
The first decision information to the third decision information,
Characterized in that it is individually generated for each unit section including the link or at least one link,
The communication department,
Transmitting information on the changed driving design area to the vehicle;
The collection unit,
Among the driving environment data acquired from the infrastructure, driving environment data associated with the driving path of the vehicle is selected, but if the driving environment data is repeatedly received from a plurality of infrastructures for one link, the reliability information of each of the plurality of infrastructures. Allocating data corresponding to any one of the plurality of infrastructures as the driving environment data based on
The reliability information is characterized in that, if the infrastructure is a type of photographing device, the higher the photographing device installed to photograph the road corresponding to the link in a relatively wide area,
An interface visualizing the first determination information to the third determination information is visualized through a display unit provided in a device for performing dynamic self-driving provided in the vehicle or a user terminal interworking with the device for performing dynamic self-driving, and displayed on the interface. Based on the autonomous driving selection input for each link received based on the basis, whether or not autonomous driving is determined for each link,
When an autonomous driving setting input is received in advance to perform autonomous driving for a section in which a specific type of determination information is generated among the first to third determination information, the determination information of the specific type is generated. wherein an autonomous driving function is activated even when the autonomous driving selection input is not received for at least one of a link and the unit section. delete According to claim 13,
The judge,
generating the determination information for each of the divided links;
The communication department,
and transmitting the driving environment data collected with respect to the link in which the second determination information is generated to the vehicle. According to claim 15,
The judge,
Predicting road surface condition information and shade information for a link through which the vehicle will pass based on the driving environment data, and generating the determination information for the corresponding link based on the predicted road surface condition information and shade information, Dynamic autonomous driving support device.

Images