Method for determining whether autonomous vehicle can traverse at intersection in parking lot

Abstract

A method of determining whether to allow an autonomous vehicle to traverse at an intersection in a parking lot includes: in response to the vehicle approaching the intersection, obtaining travel route information of the vehicle and information about a risk group; setting a risk assessment area in the intersection; obtaining the occupancy probability of the risk group; determining a collision risk between the vehicle and the risk group by using the risk assessment zone and the occupancy probability; and determining whether to allow the vehicle to traverse the intersection based on the collision risk.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Korean Patent Application No. 10-2023-0172976, filed on Dec. 4, 2023, which is incorporated herein by reference in its entirety for all purposes. Technical Field

[0003] The present disclosure relates to a method for determining whether to allow an autonomous driving vehicle to traverse at an intersection in a parking lot. Background Art

[0004] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute relevant art.

[0005] An autonomous vehicle (AV) can perform a remote-controlled automatic parking function by following a memorized parking driving route or a designated route in a parking lot.

[0006] At the same time, since a large number of vehicles are packed into a limited space in a parking lot, the roads in the parking lot are usually grid-shaped with multiple intersections. Therefore, it is actually difficult for an autonomous vehicle to simply drive through the route points at a constant speed, and the autonomous vehicle needs to perform behavior control by considering the surrounding dynamic / static obstacles and traffic flow at every moment.

[0007] When an autonomous vehicle is driving at an intersection in a parking lot without a traffic signal system, it may collide with other vehicles going straight, turning left or right, or unexpected pedestrians. To avoid the current risk of collision, the autonomous vehicle needs to explore yielding driving strategies, such as slowing down when entering an intersection in a parking lot, or stop-and-go. For example, Figure 1A As shown, when a vehicle attempting to turn or cross an intersection in a parking lot detects a dynamic obstacle approaching the intersection from the side, the vehicle may be controlled to stop before entering the intersection in consideration of the risk of collision with the dynamic obstacle, and to drive after the risk is eliminated, as shown in FIG. Figure 1B shown.

[0008] Considering the characteristics of parking lots that there is no signal system (such as traffic lights) and no designated driving direction on the road, it is necessary to provide an appropriate method to determine whether an entering autonomous driving vehicle can cross the intersection by utilizing information such as the predicted travel position, predicted travel time and surrounding dynamic / static obstacles of the autonomous driving vehicle.

[0009] The information contained in the background of the disclosure is only for enhancement of understanding of the general background of the disclosure and should not be taken as an admission or any form of suggestion that this information constitutes the prior art already known to a person skilled in the art. Summary of the invention

[0010] Various aspects of the present disclosure are directed to providing a method for determining whether an intersection in a parking lot is traversable by using a collision risk assessment based on a probability model.

[0011] The objects of the present disclosure are not limited to the above objects, and other objects not mentioned herein will be clearly understood by those skilled in the art from the following description.

[0012] According to at least one exemplary embodiment of the present disclosure, the present disclosure provides a method for evaluating the collision risk of an autonomous driving vehicle crossing an intersection, including: in response to a vehicle approaching an intersection, obtaining the vehicle's driving route information and risk group information, setting a risk assessment area within the intersection, deriving an occupancy probability of the risk group, calculating the collision risk between the vehicle and the risk group by using the risk assessment area and the occupancy probability, and determining whether to allow the vehicle to cross the intersection based on the collision risk.

[0013] According to another exemplary embodiment of the present disclosure, the present disclosure provides a computing device, including at least one processor and an operation memory connected to the at least one processor, wherein the memory stores instructions, and in response to the at least one processor executing the instructions, the instructions cause the at least one processor to perform operations. Here, the operations include: in response to a vehicle approaching an intersection, obtaining the vehicle's driving route information and information about a risk group, setting a risk assessment area within the intersection, deriving an occupancy probability of the risk group, calculating a collision risk between the vehicle and the risk group by using the risk assessment area and the occupancy probability, and determining whether to allow the vehicle to cross the intersection based on the collision risk.

[0014] According to various exemplary embodiments of the present disclosure, it may be more accurately determined whether an autonomous driving vehicle is allowed to cross an intersection in a parking lot.

[0015] According to various exemplary embodiments of the present disclosure, the collision risk of a parking lot intersection may be assessed more accurately even if sensor data is less reliable.

[0016] The effects of the present disclosure are not limited to the above-mentioned effects, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

[0017] The methods and apparatus of the present disclosure have other features and advantages which will be apparent from or set forth in more detail in the accompanying drawings, which are incorporated herein and in the following detailed description, and which together serve to explain certain principles of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1A and Figure 1Bis a schematic diagram showing a vehicle stop considering the risk of collision with a dynamic obstacle when the vehicle attempts to turn at an intersection.

[0019] Figure 2A and Figure 2B is a schematic diagram illustrating risk assessment using occupancy probability before a vehicle enters an intersection according to at least one exemplary embodiment of the present disclosure.

[0020] Figure 3 The present invention is a flowchart of a method for evaluating the collision risk of an autonomous driving vehicle crossing an intersection according to at least one exemplary embodiment of the present disclosure.

[0021] Figure 4A , Figure 4B and Figure 4C is a schematic diagram showing node lines for establishing a risk assessment zone according to at least one exemplary embodiment of the present disclosure.

[0022] Figure 5A and Figure 5B is a schematic diagram illustrating a collision risk assessment point of each node line and a risk assessment area of ​​each node line according to at least one exemplary embodiment of the present disclosure.

[0023] Fig. 6A and Figure 6B is the explanation time T according to at least one exemplary embodiment of the present disclosure. 0 Schematic diagram of the derivation of the initial occupancy probability of the risk group at .

[0024] Figure 7 FIG. 1 is a diagram showing a method configured to derive a risk group at time T according to at least one exemplary embodiment of the present disclosure. n The occupation probability of time T 0 Schematic diagram of the occupancy probability array and velocity information array.

[0025] It is to be understood that the drawings are not necessarily drawn to scale, but rather represent various features illustrating the basic principles of the present disclosure in a somewhat simplified manner. The specific design features included in the present disclosure, including, for example, specific dimensions, directions, locations, and shapes, will be determined in part by the specific intended application and use environment.

[0026] In the drawings, reference numbers refer to the same or equivalent parts of the present disclosure throughout the several figures of the drawing. DETAILED DESCRIPTION

[0027] Reference will now be made in detail to various embodiments of the present disclosure, examples of which are shown in the accompanying drawings and described below. Although the present disclosure will be described in conjunction with exemplary embodiments of the present disclosure, it should be understood that this description is not intended to limit the present disclosure to those exemplary embodiments of the present disclosure. On the other hand, the present disclosure is intended to cover not only exemplary embodiments of the present disclosure, but also various alternatives, modifications, equivalents and other embodiments, which may be included in the spirit and scope of the present disclosure defined by the appended claims. Various exemplary embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. In the following description, the same reference numerals represent the same elements, although these elements are shown in different figures. In addition, for clarity and brevity, the following description of various exemplary embodiments will omit the detailed description of related known components and functions, because these detailed descriptions are considered to obscure the subject matter of the present disclosure. Various ordinal numbers or letter codes, such as first, second, i), ii), a), b), etc., are used as prefixes only to distinguish one component from another, rather than to imply or suggest the substance, order or sequence of the components. Throughout the specification, when a component "includes" or "comprises" a component, the component is meant to also include other components, and other components are not excluded unless there is a specific description to the contrary. Terms such as "unit", "module" and the like refer to units in which at least one function or operation is processed, and they can be implemented by hardware, software or a combination thereof.

[0028] The following description of the present disclosure in conjunction with the accompanying drawings is intended to describe exemplary embodiments of the present disclosure, and is not intended to represent the only embodiment in which the technical concept of the present disclosure can be practiced.

[0029] The present disclosure relates to a method for determining whether an autonomous vehicle is allowed to cross an intersection in a parking lot. The method includes: using information related to a predicted travel position of the autonomous vehicle, a travel time to the predicted travel position, and surrounding dynamic and static obstacles, to determine whether the vehicle is allowed to cross the intersection and a waiting time before entering the intersection.

[0030] The basic definitions in this disclosure are as follows.

[0031] First, static and dynamic obstacles observed near the intersection before entering the intersection are jointly defined as a risk group.

[0032] Second, the observed position and velocity values ​​of static / dynamic obstacles are not defined as a single value, but as a Gaussian distribution form taking into account sensor noise and observation errors.

[0033] Third, when crossing an intersection, the vehicle travels at a constant speed specified by the user.

[0034] In at least one exemplary embodiment of the present disclosure, in order to determine whether to allow a vehicle to cross at an intersection in a parking lot, the risk is evaluated based on a quantized occupancy probability result of a risk group around a predicted travel area of ​​the vehicle, which is obtained by a probability-based model considering a performance indicator. Various exemplary embodiments of the present disclosure set environmental information of the vehicle, select a collision risk assessment point, set a risk assessment area, obtain an occupancy probability of a risk group, and evaluate the risk to determine whether the vehicle should stop before entering the intersection or cross the intersection.

[0035] For example, Figure 2A As shown, when the vehicle 10 attempts to enter the intersection of the parking lot, it may 0 A risk group 20 is detected approaching an intersection. At this moment, Figure 2B As shown, various exemplary embodiments of the present disclosure may derive the risk group 20 at time T n The occupancy probability of the vehicle 10 is determined, a collision risk between the vehicle 10 and the risk group 20 is evaluated based on the occupancy probability, and a determination is made based on the evaluated risk whether the vehicle 10 should stop before entering the intersection or whether the vehicle 10 can cross the intersection.

[0036] Figure 3 The present invention is a flowchart of a method for evaluating the collision risk of an autonomous driving vehicle crossing an intersection according to at least one exemplary embodiment of the present disclosure.

[0037] When the vehicle approaches the intersection within a threshold distance, or if the predicted time for the vehicle to enter the intersection is less than or equal to a threshold time, a method for assessing the collision risk of the vehicle crossing the intersection is performed.

[0038] refer to Figure 3 In response to a vehicle approaching an intersection, the vehicle's driving route information and risk group information are obtained (S310).

[0039] The driving route information is a set of route points that the vehicle will travel within the intersection, including the location and estimated arrival time of the corresponding route points. For example, the driving route information may include a set of predicted driving route points P n The location of (n=1,2,.,N) and the predicted arrival time T of the predicted driving route point n (n=1,2,.,N), the front center part of the vehicle will travel along these points. The driving route information can be obtained through the route generation algorithm.

[0040] The information about the risk group includes at least one of the position, direction and speed of surrounding dynamic and / or static obstacles in the detection area. The information about the risk group can be obtained by a sensor processing algorithm that processes sensor data detected using sensors provided on the vehicle (e.g., camera, radio detection and ranging (RADAR), LiDAR, ultrasonic sensor, etc.).

[0041] The speed of a vehicle crossing an intersection can be fixed to a user-preset speed (V user ). The method may receive the speed V from the user via one or more input / output interfaces (eg, a user setting mode of the AVN). user , and the speed of the vehicle crossing the intersection is preset to speed V user The input / output interface may be equipment for interfacing with an input / output device. For example, the input device may include devices such as a vehicle AVN, a microphone, a keyboard, and a mouse, and the output device may include devices such as a vehicle AVN, a display, and a speaker. As an exemplary embodiment of the present disclosure, the input / output interface may be equipment for interfacing with a device that integrates input and output functions, such as a touch screen.

[0042] This method defines the initial position of entering the intersection as P 0 , the estimated arrival time is defined as T 0 .

[0043] Using the driving route information of the vehicle 10 and the information of the risk group 20, the method includes setting a risk assessment area within the intersection (S320). The method includes setting one or more node lines within the intersection area, and setting a risk assessment area by each node line. The risk is assessed by selecting a risk assessment area including a collision risk assessment point, because assessing the risk of all driving routes of vehicles in the intersection will require a lot of calculations.

[0044] First, the method includes setting one or more node lines in the intersection area. Node lines are virtual lines set on the road of the parking lot, and the number of node lines is determined by the width of the road. For example, if the road is at least 4 meters wide, the method can set two vertical and / or horizontal node lines that divide the width of the road into three equal parts, such as Figure 4A For example, if the road is less than 4 meters wide, the method may set a vertical and / or horizontal node line that bisects the width of the road, such as Figure 4B shown.

[0045] In order to quantify the occupancy probability of the risk group 20, the area of ​​each node line is subdivided into sub-areas. For each node line, the initial point P closest to the vehicle 10 entering the intersection is selected. 0 The point is taken as the initial position (n [l,0]), and then subdivide each node line at intervals of a certain distance (for example, 0.2 meters). The position of each subdivision of each node line is defined as n [l,i] (l=1, 2, . . 4, i=1, 2, . . , M) Here, l means the index of each node line, and i means the index of the subdivided position of each node line. Figure 4C The first node line n of the four node lines is shown. 1 of segmentation.

[0046] The method includes setting a risk assessment area through each node line. The method selects a collision risk assessment point for each node line, and establishes a risk assessment area around the collision risk assessment point. Here, the collision risk assessment point is located on each node line and refers to a point for checking whether a collision with the risk group 20 may occur when the vehicle 10 crosses the intersection. The collision risk assessment point is used to set the risk assessment area between the sub-areas of each node line.

[0047] The method includes: based on each node line n located at the intersection l The predicted travel route point P of the vehicle 10 n The method may include determining a collision risk assessment point based on the relationship between the positions of the vehicle 10 and the vehicle 10 in the intersection. A representative driving route point is determined among the predicted driving route points of the vehicle 10 in the intersection, and the collision risk assessment point is determined based on the representative driving route point. For example, the method may include determining a point having the minimum distance (d min ) as a representative driving route point. For example, the method may include determining a collision risk assessment point by a contact point, the contact point being: a point where a vertical line is drawn from the representative driving route point to the corresponding node line and the vertical line intersects the corresponding node line. Figure 5A It shows that at the first node line n 1 Example collision risk assessment points selected above.

[0048] In order to represent the occupancy probability of the risk group 20, the method includes setting a risk assessment area around the collision risk assessment point through each node line. In the current case, the risk assessment area is set to a Gaussian distribution around the collision risk assessment point. This is because according to the reliability of the sensor data, at the predicted arrival time T n Point-based determination of collision risk between vehicles and risk groups can lead to misjudgment. Therefore, probability-based risk assessment is applied to more accurately determine collision risk. Figure 5B It shows that at the first node line n 1 Example risk assessment area set up on.

[0049] The method may include defining the window size of the risk assessment area as 2*m, where m is a variable user-settable value. In the present case, the weights in the corresponding window size include a Gaussian distribution K as shown in Equation 1 i , and the standard deviation σ which can be derived from the user's predetermined vehicle speed information [l,i] For example, the greater the predicted vehicle speed Vn at the representative driving route point, the lower the standard deviation result.

[0050] (Equation 1)

[0051] K i ~N(n [l，i] , σ [l，i] )

[0052]

[0053] Here, V max Refers to the maximum speed set by the user.

[0054] The method includes deriving the occupancy probability of the risk group through each node line (S330). The method includes calculating the time T when the vehicle travels to the representative driving route point. n The predicted occupancy position of the risk group within is represented as a probabilistic model. In order to find n The method includes representing the initial occupancy positions and velocities of the risk groups as a probabilistic model.

[0055] In order to pass through each obstacle O j Each node line of (j=1,2,..) derives the initial occupancy probability of each sub-area. The method includes using the initial position P of the vehicle 0 The information received about the risk group, i.e., about each obstacle O j The initial occupancy probability of each node line in each sub-area is based on the node line n l The correlation with the risk group is shown.

[0056] The method includes at an initial time T 0 Derive the initial occupancy probabilities for the risk groups.

[0057] First, take the node line n l The starting position n [l,0] is the origin, around the starting position n [l,0] Draw a circle with a radius equal to the window size m of the risk assessment area. If the predicted arrival time T n , then the predicted arrival position of the risk group is outside the circle, and the initial occupancy probability of the risk group is set to 0. Fig. 6A An example of setting the initial occupancy probability to 0 is shown.

[0058] If the initial occupancy probability is not zero, the method includes projecting the first node line n 1 The risk group O on the Kth zone 1 With node line n 1 Vertical distance and risk group O 1 With the first node line n 1 Based on this, the initial occupancy probability is represented by the direction difference between the first node line n 1 represents the Gaussian distribution on the Kth zone of . represents the direction of travel of the occupancy probability exclusively belonging to the risk group. Figure 6B An example derivation of the initial occupancy probability is shown. Risk Group O 1 The initial occupancy probability It can be determined as shown in Equation 2.

[0059] (Equation 2)

[0060]

[0061] σ [l，K] =F D (d error )×F H (H error )

[0062]

[0063]

[0064] Here, Risk group O 1 At the node line n l The occupancy probability in the Kth zone, and d Max ,d Min , H Max , H Min , d and λ H Is a user-specified value.

[0065] Furthermore, the method includes deriving a velocity distribution of an initial risk group for each node line. The velocity distribution is represented by a Gaussian distribution that is identical to the occupancy probability previously derived based on the observed velocity of the risk group, where the location of the risk group (Kth zone) is projected onto the node line n l The velocity distribution is used to find the time T n The predicted occupancy probability distribution after that. Risk Group O 1 Speed ​​distribution It can be expressed by Equation 3.

[0066] (Equation 3)

[0067]

[0068] Here, Risk group O 1 The initial velocity, and σ [l,K] As described in Equation 2 above.

[0069] The method includes deriving a time T n The occupancy probability of the risk group at time t

[0070] To find the time T n The predicted occupancy probability distribution in the past tense includes using the initial occupancy probability and velocity distribution information of each risk group as shown above. The method is relative to the starting position n of each node line [l,0] Configure an occupancy probability array and an array of speed information Its columns are equal to the length of the subregion, such as Figure 7 The method includes updating the occupancy probability array at a certain time interval (for example, 0.2 seconds) and speed information array To obtain the risk group at time T n The probability of occupancy.

[0071] The method includes: deriving a final occupancy probability of a risk group for each sub-area of ​​each node line by summing the occupancy probabilities of all obstacles. As shown in Equation 4, the final occupancy probability of the risk group is determined.

[0072] (Equation 4)

[0073]

[0074] Here, P(C [l,K] ) is the final occupancy probability of the risk group, and is the node line n l Each of the obstacles in the Kth zone O obs The probability of occupancy.

[0075] The method includes determining the risk by using the risk assessment area and the final occupancy probability of the risk group of each node line (S340). The method may include determining the risk by using the risk assessment area set in step S320 and the final occupancy probability of the risk group of each node line at time T n The weight of the risk group of each node line and the final occupancy probability determine the final risk of each node line. For example, the final risk of each node line can be determined as shown in Equation 5.

[0076] (Equation 5)

[0077] P Risk=∑ 2m P(C l )·K i

[0078] Here, P Risk is the final risk on the lth node line, P(C l ) is the final occupancy probability of the risk group on the lth node line, and K i is the weight at the risk assessment area.

[0079] The collision risk of each node line may be evaluated based on the vehicle speed and the predicted arrival time at a representative driving route point corresponding to a risk assessment area set for each node line.

[0080] Based on the risk, the method includes determining whether to allow the vehicle to cross the intersection (S350). The method may use the final risk P determined by each node line. Risk , to determine whether the vehicle can cross the intersection.

[0081] For example, if the final risk of each of all node lines is 0.2 or less, it can be determined that the intersection is traversable by the vehicle. In the current case, the method can notify the user that the intersection is traversable and control the vehicle to cross the intersection. The method can generate response data indicating that the intersection is traversable in response to the intersection being determined to be traversable. The response data can be at least one of audio data, image data, or text data. The method can output the response data to the user on one or more output devices (e.g., speakers, displays, AVNs).

[0082] For example, if the final risk of at least one node line is greater than 0.2, the method may include determining that a collision may occur between the vehicle and the risk group to stop the vehicle and repeat steps S310 to S340. The method may stop the vehicle by reducing the vehicle speed at a preset deceleration rate. The method may use a braking control system such as an autonomous emergency braking system, a collision avoidance system, etc. to stop the vehicle. Until the final risk of each of all node lines is 0.2 or less, the method may include keeping the vehicle stopped. At this point, the method may notify the user that the intersection cannot be crossed. The method may generate response data indicating that the intersection cannot be crossed in response to determining that a collision may occur between the vehicle and the risk group. The response data may be at least one of audio data, image data, or text data. The method may output the response data to the user on one or more output devices (e.g., a speaker, a display, an AVN).

[0083] For example, if the sum of the final risks of the corresponding node lines is greater than or equal to 1, the method may include determining that a collision may occur between the vehicle and the risk group to stop the vehicle and repeat steps S310 to S340. The method may stop the vehicle by reducing the vehicle speed at a preset deceleration rate. The method may use a braking control system such as an autonomous emergency braking system, a collision avoidance system, etc. to stop the vehicle. Until the final risk of each of all node lines is 0.2 or less, the method may include keeping the vehicle stopped. At this point, the method may notify the user that the intersection cannot be crossed. The method may generate response data indicating that the intersection cannot be crossed in response to determining that a collision may occur between the vehicle and the risk group. The response data may be at least one of audio data, image data, or text data. The method may output the response data to the user on one or more output devices (e.g., a speaker, a display, an AVN).

[0084] At least some of the components described in the exemplary embodiments of the present disclosure may be implemented as hardware elements, including at least one or a combination of a digital signal processor (DSP), a processor, a controller, an application specific integrated circuit (ASIC), a programmable logic device (FPGA, etc.), and other electronic devices. In addition, at least some of the functions or processes described in the exemplary embodiments of the present disclosure may be implemented as software, and the software may be stored in a recording medium. At least some of the components, functions, and processes described in the exemplary embodiments of the present disclosure may be implemented by a combination of hardware and software.

[0085] The method according to the exemplary embodiment of the present disclosure may be written as a program executable on a computer, and may also be implemented in various recording media such as a magnetic storage medium, an optical reading medium, and a digital storage medium.

[0086] The implementation of the various techniques described herein can be implemented by digital electronic circuit devices or computer hardware, firmware, software or a combination thereof. Embodiments can be implemented as a computer program tangibly embodied in a computer program product, i.e., an information carrier, such as a machine-readable storage device (computer-readable medium) or a radio signal, for processing or controlling its operation by a data processing device such as a programmable processor, a computer or multiple computers. Computer programs such as the above-mentioned computer program (one or more) can be written in any form of programming language, including compiled or interpreted languages, and can be deployed in any form as a stand-alone program or as a module, component, subroutine or other unit suitable for a computing environment. The computer program can be processed on one or more computers at one location, or distributed at multiple locations, and developed to be interconnected through a communication network.

[0087] For example, processors suitable for processing computer programs include special-purpose microprocessors and any one or more processors of any type of digital computer. Typically, the processor will receive instructions and data from a read-only memory or a random access memory or both. The elements of a computer may include at least one processor that executes instructions and one or more storage devices that store instructions and data. In general, a computer may include one or more large-capacity storage devices that store data, such as a magnetic disk, a magneto-optical disk, or an optical disk, or may be coupled to a large-capacity storage device to receive data from it and / or send data to it. Information carriers suitable for containing computer program instructions and data include, for example, semiconductor storage devices, magnetic media such as hard disks, floppy disks, and tapes, optical media such as CD-ROMs (Compact Disc Read Only Memory), DVDs (Digital Video Disks), magneto-optical media such as optical floppy disks, read-only memories (ROMs), random access memories (RAMs), flash memories, erasable programmable ROMs (EPROMs), and electrically erasable programmable ROMs (EEPROMs). The processor and memory may be supplemented by or included in a dedicated logic circuit device.

[0088] The processor may execute an operating system and software applications executed on the operating system. In addition, the processor device may access, store, manipulate, process and generate data in response to the execution of the software. For ease of understanding, the processor device may be referred to as being used as a single processor device, but those skilled in the art will appreciate that the processor device may include multiple processing elements and / or multiple types of processing elements. For example, the processor device may include multiple processors or a processor and a controller. In addition, other processing configurations such as parallel processors are also possible.

[0089] Furthermore, non-transitory computer-readable media may be any available media that can be accessed by a computer and may include computer storage media and transmission media.

[0090] This specification includes details of multiple specific implementations, but it should be understood that the details do not limit any invention or the content claimed in this specification, but rather describe the features of specific example embodiments. Features described in the specification in the context of various exemplary embodiments may be implemented as combinations in a single exemplary embodiment. Conversely, various features described in the specification in the context of a single exemplary embodiment of the present disclosure may be implemented individually or in appropriate sub-combinations in multiple exemplary embodiments. In addition, these features may operate in a specific combination and may initially be described as required in the combination, but in some cases, one or more features may be excluded from the required combination, and the required combination may be changed to a sub-combination or a modification of the sub-combination.

[0091] Similarly, even if operations are described in a particular order on the drawings, it should not be understood that the operations need to be performed in a particular order or sequence to obtain the desired results, or that all operations need to be performed. In certain circumstances, multitasking and parallel processing may be advantageous. In addition, it should not be understood that the various device components in the above exemplary embodiments need to be separated in all exemplary embodiments, and it should be understood that the above program components and devices can be combined into a single software product, or can be packaged in multiple software products.

[0092] It should be understood that the exemplary embodiments included herein are illustrative only and are not intended to limit the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications may be made to the exemplary embodiments without departing from the spirit and scope of the claims and their equivalents.

[0093] Furthermore, terms such as “unit”, “module” and the like included in the specification mean a unit for processing at least one function or operation, which can be implemented by hardware, software or a combination thereof.

[0094] In the flowcharts described with reference to the accompanying drawings, the flowcharts may be executed by a controller or a processor. The order of operations in the flowcharts may be changed, multiple operations may be combined, or any operation may be divided, and specific operations may not be performed. In addition, the operations in the flowcharts may be performed sequentially, but not necessarily sequentially. For example, the order of the operations may be changed, and at least two operations may be performed in parallel.

[0095] Hereinafter, the fact that hardware components are operably coupled may include the fact that a direct and / or indirect connection is established between the hardware components by wired and / or wireless means.

[0096] In an exemplary embodiment of the present disclosure, a vehicle may be referred to as being based on a concept including various types of transportation equipment. In some cases, a vehicle may be interpreted as being based on a concept including not only various types of land transportation equipment such as cars, motorcycles, trucks, and buses that travel on roads, but also various types of transportation equipment such as airplanes, drones, ships, and the like.

[0097] For ease of explanation and accurate definition in the appended claims, the terms "upper", "lower", "inner", "outer", "up", "down", "upwards", "downwards", "front", "rear", "back", "inside", "outside", "inwardly", "outwardly", "interior", "exterior", "internal", "external", "forwards" and "backwards" are used to describe features of the exemplary embodiments with reference to the locations of such features shown in the figures. It should also be understood that the term "connect" or its derivatives refer to both direct and indirect connections.

[0098] The term "and / or" may include a combination of a plurality of related listed items or any one of a plurality of related listed items. For example, "A and / or B" includes all three cases, such as "A", "B" and "A and B".

[0099] In exemplary embodiments of the present disclosure, “at least one of A and B” may refer to “at least one of A or B” or “at least one of a combination of at least one of A and B”. In addition, “one or more of A and B” may refer to “one or more of A or B” or “one or more of a combination of one or more of A and B”.

[0100] In this specification, unless otherwise stated, a singular expression includes a plural expression unless the context clearly states otherwise.

[0101] In the exemplary embodiments of the present disclosure, it should be understood that terms such as “include” or “have” refer to the existence of features, numbers, steps, operations, elements, parts, or a combination thereof described in the specification, and do not exclude the possibility of adding or existing one or more other features, numbers, steps, operations, elements, parts, or a combination thereof.

[0102] According to an exemplary embodiment of the present disclosure, components may be combined with each other to be implemented as one component, or some components may be omitted.

[0103] For the purpose of illustration and description, the foregoing descriptions have been made of specific exemplary embodiments of the present disclosure. They are not intended to be exhaustive or to limit the present disclosure to the precise form disclosed, and it is apparent that many modifications and variations are possible in light of the above teachings. The exemplary embodiments are selected and described in order to explain certain principles of the present invention and their practical applications, so that other persons skilled in the art can make and utilize various exemplary embodiments of the present disclosure and various substitutions and modifications thereof. The scope of the present disclosure is intended to be defined by the appended claims and their equivalents.

Claims

1. A computer-implemented method for assessing the risk of a collision of an autonomous vehicle crossing an intersection, the method comprising the following steps: In response to the vehicle approaching the intersection, obtaining driving route information of the vehicle and information about risk groups, the driving route information including a position and a predicted arrival time of each route point traveled by the vehicle, and the information about the risk groups including at least one of a position, a direction, and a speed of surrounding obstacles; providing a risk assessment area within said intersection; deriving an occupancy probability for the risk group; determining a collision risk between a vehicle and the risk group by using the risk assessment area and the occupancy probability; as well as A determination is made whether to allow the vehicle to cross the intersection based on the collision risk.

2. The method according to claim 1, wherein the step of obtaining the driving route information and the information about the risk group comprises: In response to the vehicle approaching the intersection within a threshold distance, or in response to an estimated time for the vehicle to enter the intersection being less than or equal to a threshold time, driving route information of the vehicle and information about the risk group are obtained.

3. The method according to claim 1, wherein the step of setting the risk assessment area comprises: A risk assessment area is set within the intersection by using the driving route information of the vehicle.

4. The method according to claim 3, wherein the step of setting the risk assessment area comprises: Setting at least one node line in the intersection; Subdivide the area of ​​each node line into subareas; as well as A risk assessment area is set through each node line.

5. The method according to claim 4, wherein the step of setting the risk assessment area through each node line comprises: Determining a representative travel path point through each node line in the path point traveled by the vehicle in the intersection; Based on the representative driving route point, determining a collision risk assessment point on a corresponding node line; as well as Through each node line, a risk assessment area of ​​a predetermined size is set based on the collision risk assessment point.

6. The method according to claim 5, in, The representative driving route point is a route point closest to each node line among the route points that the vehicle travels in the intersection, and The collision risk assessment point is determined by the contact point, which is a point where a vertical line drawn from the representative driving route point to the corresponding node line intersects the corresponding node line. The method according to claim 4 , wherein the weight at the risk assessment area set through each node line has a Gaussian distribution.

8. The method according to claim 4, wherein the step of deriving the occupancy probability of the risk group comprises: deriving an occupancy probability of each node line for each obstacle by using information about the risk group; as well as The final occupancy probability of the risk group for each node line is obtained by summing the derived occupancy probabilities of the corresponding node lines of all obstacles.

9. The method according to claim 8, wherein the step of deriving the occupancy probability of each node line of each obstacle comprises: Obtain the initial occupancy probability in each obstacle; as well as Based on the initial occupancy probability in each obstacle and the predicted arrival time at the representative driving route point of the vehicle, the occupancy probability of each node line of each obstacle is obtained.

10. The method of claim 8, wherein the step of determining the risk of collision comprises: The risk of each node line is determined based on the risk assessment area of ​​each node line and the final occupancy probability of the risk group of each node line.

11. The method of claim 10, wherein the step of determining whether to allow a vehicle to cross the intersection comprises: Based on the risk determined for each node line, it is determined whether the vehicle can cross the intersection smoothly.

12. The method of claim 11, wherein the step of determining whether the vehicle is allowed to cross the intersection comprises: In response to the risk determined by all node lines being below a threshold, the intersection is determined to be clear for vehicle crossing. 13 . A non-transitory computer-readable storage medium having recorded thereon a program for executing the method of claim 1 .

14. A device for assessing the risk of collision of an autonomous vehicle crossing an intersection, the device comprising: at least one processor; as well as a memory operatively coupled to the at least one processor, wherein the memory stores instructions that cause the at least one processor to perform operations in response to execution of the instructions, and The operations include: In response to the vehicle approaching the intersection, obtaining driving route information of the vehicle and information about risk groups, the driving route information including a position and a predicted arrival time of each route point traveled by the vehicle, and the information about the risk groups including at least one of a position, a direction, or a speed of surrounding obstacles; providing a risk assessment area within said intersection; deriving an occupancy probability for the risk group; determining a collision risk between a vehicle and the risk group by using the risk assessment area and the occupancy probability; and A determination is made whether to allow the vehicle to cross the intersection based on the collision risk.

15. The apparatus of claim 14, wherein setting the risk assessment area comprises: The risk assessment area is set within the intersection by using the driving route information of the vehicle.

16. The apparatus of claim 15, wherein setting the risk assessment area comprises: Setting at least one node line in the intersection; Subdivide the area of ​​each node line into subareas; as well as A risk assessment area is set through each node line.

17. The apparatus according to claim 16, wherein deriving the occupancy probability of the risk group comprises: By using the information about the risk groups, the occupancy probability of each node line for each obstacle is derived; as well as The final occupancy probability of the risk group for each node line is obtained by summing the derived occupancy probabilities of the corresponding node lines of all obstacles.

18. The apparatus of claim 17, wherein determining the risk of collision comprises: The risk of each node line is determined based on the risk assessment area of ​​each node line and the final occupancy probability of the risk group of each node line.

19. The apparatus of claim 18, wherein determining whether to allow the vehicle to cross the intersection comprises: Based on the determined risk for each node line, it is determined whether the vehicle can traverse the intersection unimpeded.

Images