KR20240077619A - Method, Apparatus and Computer-readable Recording Medium for Simulating an Autonomous Vehicle - Google Patents

Abstract

A simulation method of an autonomous vehicle according to an embodiment of the present disclosure includes generating an autonomous vehicle and surrounding vehicles to which an autonomous driving algorithm is applied as a vehicle traveling along a virtual road included in a virtual map; determining a visible region according to a driving position of the autonomous vehicle and setting a scenario for the autonomous vehicle based on the visible region; and performing a simulation for the autonomous driving algorithm by starting driving of the autonomous vehicle and the surrounding vehicles based on the scenario. Includes.

Description

{Method, Apparatus and Computer-readable Recording Medium for Simulating an Autonomous Vehicle}

The present invention relates to a simulation method, apparatus, and computer-readable recording medium for an autonomous vehicle.

Smartization of vehicles is rapidly progressing due to the convergence of information and communication technology and the vehicle industry. Due to smartization, vehicles are evolving from simple mechanical devices to smart cars, and in particular, autonomous driving is attracting attention as a core technology for smart cars. Autonomous driving is a technology that allows a vehicle to reach its destination on its own without the driver having to operate the steering wheel, accelerator pedal, or brakes.

Meanwhile, the operation of an autonomous vehicle can be accomplished through three stages: ‘cognition-judgment-control’. At each stage, multiple autonomous driving algorithms can be organically connected and used. In order for the autonomous driving algorithm to be accurate and to operate the autonomous vehicle safely, significant data for the algorithm must be secured, and there is a need to verify the algorithm.

However, acquiring data for algorithm development on actual roads can require significant time and financial costs, and the vehicles themselves can pose a potential threat to drivers. Accordingly, the need for simulation technology to verify autonomous driving algorithms in a virtual environment is increasing.

The above-mentioned background technology is technical information that the inventor possessed for deriving the present invention or acquired in the process of deriving the present invention, and cannot necessarily be said to be known art disclosed to the general public before filing the application for the present invention.

Some embodiments according to the present disclosure seek to provide a simulation method, apparatus, and computer-readable recording medium of an autonomous vehicle. The problem to be solved by the present invention is not limited to the problems mentioned above, and other problems and advantages of the present invention that are not mentioned can be understood through the following description and can be understood more clearly through the embodiments of the present invention. It will be. In addition, it will be appreciated that the problems and advantages to be solved by the present invention can be realized by the means and combinations thereof indicated in the patent claims.

As a technical means for achieving the above-described technical problem, the first aspect of the present disclosure is a simulation method of an autonomous vehicle, which is a vehicle traveling along a path included in a virtual map, and an autonomous vehicle to which an autonomous driving algorithm is applied. and generating surrounding vehicles; determining a visible area according to a driving position of the autonomous vehicle and setting a scenario for the autonomous vehicle based on the visible area; and performing a simulation for the autonomous driving algorithm by starting driving of the autonomous vehicle and the surrounding vehicles based on the scenario. A method including a may be provided.

A second aspect of the present disclosure provides a simulation device for an autonomous vehicle, the device comprising: at least one memory; and at least one processor; It includes, wherein the processor generates an autonomous vehicle and surrounding vehicles to which an autonomous driving algorithm is applied as a vehicle traveling along a path included in the virtual map, determines a visible area according to the driving position of the autonomous vehicle, and , A device that performs simulation for the autonomous driving algorithm by setting a scenario for the autonomous vehicle based on the visible area and starting driving of the autonomous vehicle and the surrounding vehicles based on the scenario. can be provided.

A third aspect of the present disclosure may provide a computer-readable recording medium recording a program for executing the method according to the first aspect on a computer.

In addition, another method for implementing the present invention, another system, and a computer-readable recording medium storing a computer program for executing the method may be further provided.

Other aspects, features and advantages in addition to those described above will become apparent from the following drawings, claims and detailed description of the invention.

According to the problem-solving means of the present disclosure described above, when simulating an autonomous driving algorithm mounted on an autonomous vehicle, simulation can be performed considering the visible and invisible areas of the autonomous vehicle.

1 to 3 are diagrams for explaining an example of an autonomous driving method according to an embodiment.
Figure 4 is a diagram for explaining an example of setting a simulation environment according to an embodiment.
Figure 5 is a diagram for explaining an example of setting a scenario according to an embodiment.
Figure 6 is a diagram for explaining an example of setting a scenario according to an embodiment.
Figure 7 is a diagram for explaining an example of setting a scenario according to an embodiment.
8A and 8B are diagrams to explain an example in which an autonomous driving algorithm determines the behavior of an autonomous vehicle according to an embodiment.
FIG. 9 is a flowchart illustrating an example of a simulation method for an autonomous vehicle according to an embodiment.
FIG. 10 is a configuration diagram illustrating an example of the internal configuration of a simulation device for an autonomous vehicle according to an embodiment.

The advantages and features of the present invention and methods for achieving them will become clear by referring to the embodiments described in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments presented below, but may be implemented in various different forms, and should be understood to include all conversions, equivalents, and substitutes included in the spirit and technical scope of the present invention. . The embodiments presented below are provided to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the scope of the invention. In describing the present invention, if it is determined that a detailed description of related known technologies may obscure the gist of the present invention, the detailed description will be omitted.

The terms used in this application are only used to describe specific embodiments and are not intended to limit the invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, terms such as “comprise” or “have” are intended to designate the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, but are not intended to indicate the presence of one or more other features. It should be understood that this does not exclude in advance the possibility of the existence or addition of elements, numbers, steps, operations, components, parts, or combinations thereof.

Some embodiments of the present disclosure may be represented by functional block configurations and various processing steps. Some or all of these functional blocks may be implemented in various numbers of hardware and/or software configurations that perform specific functions. For example, the functional blocks of the present disclosure may be implemented by one or more microprocessors or by circuit configurations for certain functions. Additionally, for example, functional blocks of the present disclosure may be implemented in various programming or scripting languages. Functional blocks may be implemented as algorithms running on one or more processors. Additionally, the present disclosure may employ conventional technologies for electronic environment setup, signal processing, and/or data processing. Terms such as “mechanism,” “element,” “means,” and “configuration” may be used broadly and are not limited to mechanical and physical components.

Additionally, connection lines or connection members between components shown in the drawings merely exemplify functional connections and/or physical or circuit connections. In an actual device, connections between components may be represented by various replaceable or additional functional connections, physical connections, or circuit connections.

Hereinafter, 'vehicle' may refer to any type of transportation used to move people or objects with engine, such as a car, bus, motorcycle, kickboard, or truck.

Below, the embodiment will be described in detail with reference to the attached drawings. However, the embodiments may be implemented in various different forms and are not limited to the examples described herein.

1 is a diagram for explaining an autonomous driving method according to an embodiment.

Referring to FIG. 1, the autonomous driving device according to an embodiment of the present invention can be mounted on a vehicle to implement an autonomous vehicle 10. The autonomous driving device mounted on the autonomous vehicle 10 may include various sensors for collecting surrounding situation information. For example, the autonomous driving device may detect the movement of the preceding vehicle 20 running in front through an image sensor and/or an event sensor mounted on the front of the autonomous vehicle 10. The autonomous driving device may further include sensors for detecting not only the front of the autonomous vehicle 10, but also other vehicles 30 running in the lane next to the autonomous vehicle 10 and pedestrians around the autonomous vehicle 10.

At least one of the sensors for collecting situational information around the autonomous vehicle may have a predetermined field of view (FoV), as shown in FIG. 1 . For example, when a sensor mounted on the front of the autonomous vehicle 10 has a field of view (FoV) as shown in FIG. 1, information detected at the center of the sensor may have relatively high importance. This may be because the information detected at the center of the sensor includes most of the information corresponding to the movement of the preceding vehicle 20.

The self-driving device processes information collected by the sensors of the self-driving vehicle 10 in real time to control the movement of the self-driving vehicle 10, while storing at least some of the information collected by the sensors in a memory device. .

Figure 2 is a block diagram showing hardware included in an autonomous driving device according to an embodiment.

Referring to FIG. 2 , the autonomous driving device 40 may include a sensor unit 41, a processor 46, a memory system 47, and a vehicle body control module 48. The sensor unit 41 includes a plurality of sensors 42-45, and the plurality of sensors 42-45 may include an image sensor, an event sensor, an illumination sensor, a GPS device, an acceleration sensor, etc.

Data collected by sensors 42-45 may be transmitted to processor 46. The processor 46 stores the data collected by the sensors 42-45 in the memory system 47 and controls the vehicle body control module 48 based on the data collected by the sensors 42-45 to control the vehicle. movement can be determined. The memory system 47 may include two or more memory devices and a system controller for controlling the memory devices. Each of the memory devices may be provided as one semiconductor chip.

In addition to the system controller of the memory system 47, each of the memory devices included in the memory system 47 may include a memory controller, and the memory controller may include an artificial intelligence (AI) operation circuit such as a neural network. The memory controller may generate calculation data by assigning a predetermined weight to data received from the sensors 42 - 45 or the processor 46 and store the calculation data in a memory chip.

FIG. 3 is a diagram illustrating an example of image data acquired by sensors (including cameras) of an autonomous vehicle equipped with an autonomous driving device according to an embodiment.

Referring to FIG. 3, image data 50 may be data acquired by a sensor mounted on the front of an autonomous vehicle. Therefore, the image data 50 may include the front part 51 of the autonomous vehicle, the preceding vehicle 52 in the same lane as the autonomous vehicle, the vehicles 53 and the background 54 around the autonomous vehicle. .

In the image data 50 according to the embodiment shown in FIG. 3, the data in the area where the front part 51 and the background 54 of the autonomous vehicle appear are data that are unlikely to affect the operation of the autonomous vehicle. It can be. In other words, the front 51 and background 54 of the autonomous vehicle can be considered data with relatively low importance.

On the other hand, the distance to the preceding vehicle 52 and the lane change movement of the driving vehicle 53 may be very important factors in the safe operation of an autonomous vehicle. Accordingly, in the image data 50, data in an area including the preceding vehicle 52 and the driving vehicle 53 may have relatively high importance in the operation of the autonomous vehicle.

The memory device of the autonomous driving device may store the image data 50 received from the sensor by assigning different weights to each region. For example, a high weight is given to data in an area that includes the preceding vehicle 52 and the driving vehicle 53, and a low weight is given to data in an area where the front 51 and background 54 of an autonomous vehicle appear. can be given.

Meanwhile, the operation of an autonomous vehicle can be accomplished through three stages: ‘cognition-judgment-control’. At each stage, multiple autonomous driving algorithms can be organically connected and used. In order for the autonomous driving algorithm to be accurate and to operate the autonomous vehicle safely, significant data for the algorithm must be secured, and there is a need to verify the algorithm.

However, acquiring data for algorithm development on actual roads can require significant time and financial costs, and the vehicles themselves can pose a potential threat to drivers.

Accordingly, a method of performing simulation of an autonomous vehicle in a virtual environment will be described below with reference to FIGS. 4 to 10.

Figure 4 is a diagram for explaining an example of setting a simulation environment according to an embodiment.

Performing a simulation for an autonomous vehicle in a virtual environment may mean performing a simulation on each process of perception, judgment, and control corresponding to the operation process of the autonomous vehicle described above.

For example, performing a simulation on an autonomous vehicle in a virtual environment involves setting various driving conditions such as traffic environment, time, and weather conditions, and controlling each process of perception, judgment, and control while adjusting the set driving conditions. This may mean verifying autonomous driving algorithms.

To perform a simulation, it may be necessary to set up a simulation environment that includes a virtual environment.

Referring to FIG. 4, the simulation device can set a simulation environment for simulation of an autonomous vehicle.

As an example, a simulation device can generate a virtual map for simulation of an autonomous vehicle.

The virtual map may include a virtual road and a virtual lane included in the virtual road. For example, a virtual road may be a road that includes an intersection, or it may be a non-signalized intersection that passes without traffic lights.

Additionally, the virtual map may include a virtual signage system that controls the virtual roads. For example, the simulation device can set the type of signal, signal interval, etc. for the virtual signal system.

Additionally, the virtual map may include virtual surroundings associated with virtual roads. For example, the virtual surroundings may include virtual overpasses, virtual crosswalk reports, virtual pedestrian presence, etc.

As another example, the virtual surrounding environment may include objects adjacent to the road, such as buildings adjacent to the road or virtual work vehicles working on the road.

As an example, a simulation device can create a vehicle for simulation of an autonomous vehicle.

The vehicle may refer to a virtual vehicle for simulation of an autonomous vehicle. For example, a virtual vehicle may mean a vehicle driving along a virtual road included in the above-described virtual map.

Here, the vehicle may include an autonomous vehicle to which an autonomous driving algorithm is applied and surrounding vehicles around the autonomous vehicle.

According to one embodiment, the above-described surrounding vehicles may include autonomous vehicles to which autonomous driving algorithms are applied. That is, vehicles traveling along a virtual road may include multiple autonomous vehicles. Each autonomous vehicle may refer to a vehicle to which an autonomous driving algorithm is applied.

Meanwhile, examples of the simulation environment are not limited to the above. If it is something that must be set as default for simulation of autonomous vehicles, it can be included in the simulation environment without restrictions.

Referring to FIG. 4, the simulation device can generate a virtual map including a virtual road. For example, a virtual road could be a two-lane, non-signalized intersection.

Additionally, the simulation device can generate an autonomous vehicle 410 and surrounding vehicles 431 and 432 to which an autonomous driving algorithm is applied as a vehicle driving on a virtual road.

Additionally, the simulation device may generate objects 451 and 452 adjacent to the road on the virtual map.

As mentioned above, the simulation environment is not limited to the virtual road, vehicles, and objects adjacent to the road shown in FIG. 4. Additionally, in the example shown in FIG. 4, objects adjacent to the road are expressed in the form of a rectangular parallelepiped for convenience of explanation, but the present invention is not limited thereto.

Hereinafter, examples of scenario settings will be described with reference to FIGS. 5 to 7.

Figure 5 is a diagram for explaining an example of setting a scenario according to an embodiment.

Referring to FIG. 5, the simulation device can determine a visible region according to the driving position of the autonomous vehicle and set a scenario for the autonomous vehicle based on the visible region.

Here, the visible area may refer to the range of areas that can be detected by an autonomous vehicle among the areas included in the virtual map. Accordingly, if surrounding vehicles driving on a virtual road are included in the visible area of the autonomous vehicle, the simulation device can set a scenario for the autonomous vehicle in which the surrounding vehicles are recognized by the autonomous vehicle. there is.

For example, determining the visible area by the simulation device may include determining the visible area for each virtual sensor by assigning sensing parameters to each of a plurality of virtual sensors provided in the autonomous vehicle.

Autonomous vehicles may be equipped with many different types of sensors to obtain information about lanes, surrounding vehicles, and the surrounding environment while driving on actual roads. For example, sensors provided in autonomous vehicles may include cameras, ultrasonic devices, radar, lidar, etc.

Likewise, in a method of simulating an autonomous vehicle in a virtual environment, an autonomous vehicle driving on a virtual road may be equipped with a plurality of virtual sensors. Here, the virtual sensor may include a virtual camera, a virtual ultrasonic device, a virtual radar, a virtual lidar, etc.

The simulation device can provide sensing parameters to each of a plurality of virtual sensors. For example, sensing parameters may include the location where the virtual sensor is installed in the autonomous vehicle, the angle at which it is installed, the angle at which it can be sensed, and the distance at which it can be sensed. As another example, if the virtual sensor is a camera, the sensing parameters may include camera internal parameters including focal length, principal point, skew coefficient, etc., and external parameters related to coordinate system transformation. there is.

The simulation device can determine the visible area for each virtual sensor by assigning the above-described sensing parameters to each virtual sensor. The visible area for each virtual sensor may mean an area that the virtual sensor can monitor among areas included in the virtual map.

Referring to FIG. 5, the autonomous vehicle 510 may be equipped with a plurality of virtual sensors. For example, each virtual sensor may be installed on one of the front, side, and rear of the autonomous vehicle 510 to sense surrounding vehicles and the surrounding environment.

The simulation device may determine a visible area according to the driving position of the autonomous vehicle 510 and set a scenario for the autonomous vehicle based on the visible area.

For example, the simulation device may determine the visible area 530 of a virtual sensor 530 by assigning sensing parameters to the virtual sensor 530 .

Accordingly, the simulation device can set a scenario in which a nearby vehicle 570 driving on a virtual road is included in the visible area 530 of the corresponding virtual sensor.

That is, according to the set scenario, the autonomous vehicle 510 can recognize the surrounding vehicle 570 at the current driving position.

Meanwhile, FIG. 5 shows an example of the number and arrangement of virtual sensors and the range of the visible area of the virtual sensor, but the above-mentioned examples are not limited to those shown in FIG. 5.

Figure 6 is a diagram for explaining an example of setting a scenario according to an embodiment.

Referring to FIG. 6, the simulation device can determine a visible area according to the driving position of the autonomous vehicle and set a scenario for the autonomous vehicle based on the visible area.

For example, the simulation device may create an object that obstructs the view of the virtual sensor on a virtual road, and determine an invisible region due to the above-mentioned object from the visible area of the first virtual sensor among the plurality of virtual sensors. there is. The simulation device can set a scenario based on the invisible area.

Here, the object refers to an object that may obstruct the view of the virtual sensor on the virtual road, such as an accident vehicle or a surrounding vehicle driving in the next lane. Additionally, the above-mentioned objects may include objects located adjacent to the virtual road. For example, objects may include buildings adjacent to a virtual road, virtual work vehicles working adjacent to the virtual road, etc. Meanwhile, an object may mean multiple objects.

Contrary to the visible area, the invisible area of the virtual sensor may refer to an area that cannot be sensed by any one virtual sensor among the areas included in the virtual map. Specifically, the invisible area of the virtual sensor may mean a range of areas that cannot be sensed due to the above-mentioned object among the visible areas of the first virtual sensor.

The simulation device can set a scenario based on the invisible area. For example, when a nearby vehicle driving on a virtual road is included in the invisible area of the first virtual sensor, the simulation device may set a scenario in which the surrounding vehicle cannot be recognized by the first virtual sensor.

According to one embodiment, the simulation device may specify the location of the above-described object and determine whether the object is included in the visible area of the first virtual sensor based on the specified location. Additionally, the simulation device may determine the area obscured by the object as the invisible area of the first virtual sensor based on the determination result.

Referring to FIG. 6 , the simulation device can create an object 630 that obstructs the view of the virtual sensor 620 on a virtual road and specify the location of the object 630. For example, in FIG. 6, the location of the object 630 is designated as adjacent to a virtual road, but the location of the object 630 is not limited to this and may be located on a virtual road.

As an example, the simulation device determines whether the object 630 is included in the visible area of the virtual sensor 620 and, based on the determination result, selects the area obscured by the object as the invisible area of the virtual sensor 620 ( 640).

That is, among the visible areas of the virtual sensor 620 before the object 630 is created, the area obscured by the object 630 may be determined as the invisible area 640, and the remaining visible area may be determined as the visible area 651 and 652).

As an example, the simulation device may set a scenario for the autonomous vehicle 610 based on the invisible area of the virtual sensor 620. For example, the simulation device may set a scenario in which a nearby vehicle 670 driving on a virtual road is included in the invisible area 640 of the virtual sensor 620.

That is, according to the set scenario, the autonomous vehicle 610 cannot recognize the surrounding vehicle 670 at the current driving position.

Figure 7 is a diagram for explaining an example of setting a scenario according to an embodiment.

Referring to FIG. 7, the simulation device can determine a visible area according to the driving position of the autonomous vehicle and set a scenario for the autonomous vehicle based on the visible area.

For example, the simulation device determines the visible area of the autonomous vehicle by determining the visible and invisible areas according to the driving position of the autonomous vehicle based on the visible area for each virtual sensor and the invisible area for each virtual sensor. It can be included.

Here, the visible area for each virtual sensor refers to the visible area determined for each virtual sensor according to the details described above in FIG. 5, and the invisible area for each virtual sensor refers to the visible area provided in the autonomous vehicle according to the details described above in FIG. 6. It may mean an invisible area determined for each virtual sensor.

According to one embodiment, the simulation device may determine an area included in one of the visible area of the first virtual sensor and the visible area of the second virtual sensor as the visible area of the autonomous vehicle. Additionally, the simulation device may determine an area that is not included in any of the visible areas of the first virtual sensor and the visible area of the second virtual sensor as the invisible area of the autonomous vehicle.

In an embodiment, the first virtual sensor and the second virtual sensor may refer to any virtual sensor included in a plurality of virtual sensors provided in an autonomous vehicle. Additionally, in the embodiment, only the first virtual sensor and the second virtual sensor are included for convenience of explanation, but a third virtual sensor, a fourth virtual sensor, etc. may be included.

According to another embodiment, the simulation device may determine an area where the visible area of the first virtual sensor and the visible area of the second virtual sensor overlap as the visible area of the autonomous vehicle. The simulation device may determine an area where the invisible area of the first virtual sensor and the invisible area of the second virtual sensor overlap as the invisible area of the autonomous vehicle.

As an example, the simulation device is configured to generate an autonomous vehicle based on the reliability of the first virtual sensor and the second virtual sensor for a predetermined area included in the visible area of the first virtual sensor and the invisible area of the second virtual sensor. It can be decided to be either the visible area or the invisible area.

Here, the predetermined area may mean an area on a virtual map. Additionally, the reliability of each sensor can be determined according to the sensing parameters described above in FIG. 5. For example, a case where an area on the virtual map is included in the visible area of virtual sensor A and the invisible area of virtual sensor B will be described as an example. If the virtual sensor A can accurately sense a relatively long distance, high reliability can be given to the virtual sensor A, and based on this, a certain area described above can be determined to be included in the visible area of the autonomous vehicle.

As another example, the reliability of each sensor may be determined based on the relationship with the object, such as the distance to the object described above and the extent to which the object is included in the visible area. For example, a case where a predetermined area on the virtual map is included in the invisible area of the virtual sensor C and the visible area of the virtual sensor D will be described. If virtual sensor C is closer to the object than virtual sensor D, higher reliability may be given to virtual sensor C, and based on this, a predetermined area may be determined as an invisible area of the autonomous vehicle.

Referring to FIG. 7, the simulation device can determine the visible area and the invisible area according to the driving position of the autonomous vehicle 710 based on the visible area for each virtual sensor and the invisible area for each virtual sensor, and the autonomous vehicle (710) 710) A scenario can be set based on the visible and invisible areas.

For example, the simulation device may perform a first operation on a predetermined area 760 included in the invisible area 740 of the first virtual sensor 721 and the visible area 750 of the second virtual sensor 722. Based on the reliability of the virtual sensor 721 and the second virtual sensor 722, it can be determined to be either a visible area or an invisible area of the autonomous vehicle 710.

For example, as shown in FIG. 7, when the distance between the first virtual sensor 721 and the object 730 is closer than the distance between the second virtual sensor 722 and the object 730, the first virtual sensor 721 ) can be given high reliability.

Accordingly, the simulation device may determine that the predetermined area 760 is included in the invisible area of the autonomous vehicle 710, and the surrounding vehicle 770 driving on the virtual road may be included in the invisible area of the autonomous vehicle 710. You can set scenarios included in the invisible area. That is, according to the set scenario, the autonomous vehicle 710 cannot recognize the surrounding vehicle 770 at the current driving position.

As another example, when the sensing parameter assigned to the second virtual sensor 722 has a higher value than the sensing parameter assigned to the first virtual sensor 721, higher reliability is granted to the second virtual sensor 722. It can be.

In this case, the simulation device may determine that the predetermined area 760 is included in the visible area of the autonomous vehicle 710, and the surrounding vehicle 770 driving on the virtual road may be within the visible area of the autonomous vehicle 710. You can set scenarios included in the area. That is, according to the set scenario, the autonomous vehicle 710 can recognize the surrounding vehicle 770 at the current driving position.

8A and 8B are diagrams to explain an example in which an autonomous driving algorithm determines the behavior of an autonomous vehicle according to an embodiment.

According to an embodiment of the present disclosure, a simulation device may perform a simulation of an autonomous driving algorithm by starting driving of the autonomous vehicle and surrounding vehicles based on the above-described scenario.

In other words, the autonomous vehicle and surrounding vehicles start driving based on the set scenario.

For example, an autonomous vehicle can perceive the surrounding environment and surrounding vehicles through virtual sensors while driving on a virtual road. Depending on the location of the autonomous vehicle, the visible and invisible areas of the autonomous vehicle can be newly determined, and the autonomous vehicle can recognize surrounding vehicles in the visible area.

As an example, the self-driving algorithm may determine the behavior of the self-driving vehicle corresponding to the recognition result according to a preset algorithm and transmit a control signal for operating the determined action to the self-driving vehicle.

Here, the autonomous driving algorithm according to an embodiment of the present disclosure may include an algorithm that determines the behavior of the autonomous vehicle based on the distance from the invisible area of the autonomous vehicle. For example, the autonomous driving algorithm may determine the behavior of the autonomous vehicle based on the distance between the autonomous vehicle and an invisible area and a preset safety distance. Here, the safety distance may mean the minimum distance required for the autonomous driving algorithm to control the operation of the autonomous vehicle. For example, if the autonomous driving algorithm requires 1 second to control the operation of the autonomous vehicle, and the autonomous vehicle moves 3 meters during 1 second, the safety distance may be set to 3 meters.

For example, the autonomous driving algorithm may include an algorithm that determines the behavior of the autonomous vehicle by maintaining the driving speed and driving acceleration of the autonomous vehicle when the distance between the autonomous vehicle and the non-visible area is greater than a safe distance. there is. If the autonomous vehicle is at a sufficient distance from the unseen area, even if surrounding vehicles suddenly appear out of the unseen area, the self-driving algorithm will have enough time to recognize the surrounding vehicles and decide the autonomous vehicle's behavior accordingly. This allows the speed and acceleration of the autonomous vehicle to be maintained.

As another example, the autonomous driving algorithm may include an algorithm that determines the behavior of the autonomous vehicle by reducing the driving speed and driving acceleration of the autonomous vehicle when the distance between the autonomous vehicle and the unseen area is less than a safe distance. there is. If the autonomous vehicle is close to an invisible area and surrounding vehicles suddenly appear in the invisible area, there may not be enough time to determine the behavior of the autonomous vehicle as it recognizes the surrounding vehicles, so the autonomous driving algorithm The speed of the vehicle can be adjusted in advance.

According to another embodiment, the autonomous driving algorithm may include an algorithm that determines the behavior of the autonomous vehicle based on recognition information obtained from the visible area of the autonomous vehicle and estimated information about the invisible area.

Specifically, the autonomous driving algorithm uses first recognition information obtained from the visible area at a first time point and second recognition information obtained from the visible area at a second time point after a predetermined time from the first time point to use the non-visible area. It may include an algorithm that obtains estimated information about and determines the behavior of the autonomous vehicle based on the estimated information.

Here, cognitive information may refer to information about the surrounding environment and surrounding vehicles perceived from the visible area of the autonomous vehicle. That is, the cognitive information may include information about the surrounding vehicle A driving on the virtual road, the driving direction of the surrounding vehicle A, and the driving speed of the surrounding vehicle A in the visible area. Additionally, the estimated information may refer to information about the surrounding environment and surrounding vehicles estimated for the invisible area of the autonomous vehicle. For example, the estimated information may include information about the presence or absence of surrounding vehicle B in the non-visible area, information about the expected driving direction of surrounding vehicle B, the expected traveling speed of surrounding vehicle B, etc. there is.

Unlike visible areas, autonomous vehicles cannot detect surrounding vehicles in the invisible area. However, if an autonomous vehicle drives on the road considering only surrounding vehicles that are recognized in the visible area, a dangerous situation may occur in which it cannot respond to surrounding vehicles that suddenly appear in the invisible area. Accordingly, the self-driving algorithm can use cognitive information to obtain estimated information such as the presence or absence of surrounding vehicles and the speed of surrounding vehicles in the non-visible area, and determine the behavior of the self-driving vehicle based on the estimated information. That is, the self-driving vehicle simulation method according to an embodiment of the present disclosure can verify the self-driving algorithm by further considering information about the invisible area that the self-driving vehicle cannot perceive.

The above-described embodiment will be described with the example shown in FIG. 8.

Referring to FIG. 8A , examples of cognitive information obtained from the visible area of the autonomous vehicle 810 at a first viewpoint 801 and a second viewpoint 802 are shown.

The autonomous driving algorithm can obtain cognitive information about the surrounding vehicles 830 from the visible area of the autonomous vehicle 810 and determine the behavior of the autonomous vehicle 810 based on the movement of the surrounding vehicles 830. there is.

For example, the autonomous driving algorithm may obtain recognition information that there are no surrounding vehicles driving in front or behind the object 850 from the visible area of the autonomous vehicle at the first viewpoint 801.

Likewise, the autonomous driving algorithm may obtain recognition information that there are no surrounding vehicles driving in front or behind the object 850 from the visible area of the autonomous vehicle at the second viewpoint 802.

Through this, the self-driving algorithm can obtain estimation information that surrounding vehicles will not exist in the invisible area of the self-driving vehicle 810 due to the object 850.

As an example, an autonomous driving algorithm may determine the behavior of an autonomous vehicle based on estimated information. For example, the autonomous driving algorithm may maintain the speed and acceleration of the autonomous vehicle based on information that estimates that there will be no surrounding vehicles in the invisible area.

Referring to FIG. 8B , examples of cognitive information obtained from the visible area of the autonomous vehicle 810 at a first viewpoint 803 and a second viewpoint 804 are shown.

For example, the autonomous driving algorithm may obtain cognitive information about surrounding vehicles 831 and 832 from the visible area of the autonomous vehicle at the first viewpoint 803.

For example, the autonomous driving algorithm may obtain information that the surrounding vehicle 831 is moving toward the object 850 and recognition information that the surrounding vehicle 832 is driving on the virtual road at the first viewpoint 803. .

Additionally, the autonomous driving algorithm may obtain cognitive information about the surrounding vehicle 832 driving on the virtual road at the second viewpoint 804. However, the autonomous driving algorithm cannot obtain recognition information about the surrounding vehicle 831 or may obtain recognition information including that it is not recognized in the visible area.

Through this, the autonomous driving algorithm can obtain estimated information that at least one surrounding vehicle may exist in the invisible area of the autonomous vehicle. In other words, the autonomous driving algorithm can estimate that the surrounding vehicle has become unrecognizable by the object because the surrounding vehicle driving around the object at the first time point has disappeared at the second time point.

And, the autonomous driving algorithm can determine the behavior of the autonomous vehicle based on the estimated information. For example, the autonomous driving algorithm may reduce the speed and acceleration of the autonomous vehicle based on estimated information that at least one surrounding vehicle may exist in an invisible area.

FIG. 9 is a flowchart illustrating an example of a simulation method for an autonomous vehicle according to an embodiment.

Referring to FIG. 9, the simulation method of an autonomous vehicle may include steps 910 to 930. However, it is not limited to this, and other general steps in addition to the steps shown in FIG. 9 may be further included in the simulation method of an autonomous vehicle.

First, in step 910, the simulation device may generate an autonomous vehicle to which an autonomous driving algorithm is applied and surrounding vehicles as vehicles traveling along a virtual road included in the virtual map.

Thereafter, in step 920, the simulation device may determine a visible area according to the driving position of the autonomous vehicle and set a scenario for the autonomous vehicle based on the visible area.

For example, determining the visible area by the simulation device may include determining the visible area for each virtual sensor by assigning sensing parameters to each of a plurality of virtual sensors provided in the autonomous vehicle.

As another example, the simulation device may create an object on a virtual road that obstructs the view of the virtual sensor, and determine an invisible region due to the above-mentioned object among the visible areas of the first virtual sensor among the plurality of virtual sensors. . The simulation device can set a scenario based on the invisible area.

According to one embodiment, the simulation device may specify the location of the above-described object and determine whether the object is included in the visible area of the first virtual sensor based on the specified location. The simulation device may determine the area obscured by the object as the invisible area of the first virtual sensor based on the decision result.

As another example, the simulation device determines the visible area of the autonomous vehicle by determining the visible and invisible areas according to the driving position of the autonomous vehicle based on the visible area for each virtual sensor and the invisible area for each virtual sensor. It can be included.

According to one embodiment, the simulation device may determine an area included in one of the visible area of the first virtual sensor and the visible area of the second virtual sensor as the visible area of the autonomous vehicle. Additionally, the simulation device may determine an area that is not included in any of the visible areas of the first virtual sensor and the visible area of the second virtual sensor as the invisible area of the autonomous vehicle.

According to another embodiment, the simulation device may determine an area where the visible area of the first virtual sensor and the visible area of the second virtual sensor overlap as the visible area of the autonomous vehicle. The simulation device may determine an area where the invisible area of the first virtual sensor and the invisible area of the second virtual sensor overlap as the invisible area of the autonomous vehicle.

As an example, the simulation device is configured to generate an autonomous vehicle based on the reliability of the first virtual sensor and the second virtual sensor for a predetermined area included in the visible area of the first virtual sensor and the invisible area of the second virtual sensor. It can be decided to be either the visible area or the invisible area.

Thereafter, in step 930, the simulation device may perform a simulation of the autonomous driving algorithm by starting driving of the autonomous vehicle and surrounding vehicles based on the scenario.

Here, the autonomous driving algorithm according to an embodiment of the present disclosure may include an algorithm that determines the behavior of the autonomous vehicle based on the distance from the invisible area of the autonomous vehicle. For example, an autonomous driving algorithm may determine the autonomous vehicle's behavior based on the distance between the autonomous vehicle and an unseen area and a predetermined safety distance.

For example, the autonomous driving algorithm may include an algorithm that determines the behavior of the autonomous vehicle by maintaining the driving speed and driving acceleration of the autonomous vehicle when the distance between the autonomous vehicle and the invisible area is greater than or equal to a safe distance. there is.

As another example, the autonomous driving algorithm may include an algorithm that determines the behavior of the autonomous vehicle by reducing the driving speed and driving acceleration of the autonomous vehicle when the distance between the autonomous vehicle and the invisible area is less than a safe distance. there is.

According to another embodiment, the autonomous driving algorithm may include an algorithm that determines the behavior of the autonomous vehicle based on recognition information obtained from the visible area of the autonomous vehicle and estimated information about the invisible area.

Specifically, the autonomous driving algorithm uses first recognition information acquired from the visible area at a first viewpoint and second recognition information obtained from the visible area at a second viewpoint after a predetermined time from the first viewpoint. It may include an algorithm that obtains estimated information about the area and determines the behavior of the autonomous vehicle based on the estimated information.

FIG. 10 is a configuration diagram illustrating an example of the internal configuration of a simulation device for an autonomous vehicle according to an embodiment.

Referring to FIG. 10, the simulation device 1000 may include a communication unit 1010, a processor 1030, and a database (DB) 1050. In the simulation device 1000 of FIG. 10, only components related to the embodiment are shown. Accordingly, those skilled in the art can understand that other general-purpose components may be included in addition to the components shown in FIG. 10.

The communication unit 1010 may include one or more components that enable wired/wireless communication with an external server or external device. For example, the communication unit 1010 may include at least one of a short-range communication unit (not shown), a mobile communication unit (not shown), and a broadcast receiver (not shown).

The database (DB) 1050 is hardware that stores various data processed within the simulation device 1000, and can store programs for processing and control of the processor 1030.

The database (DB) 1050 includes random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), such as dynamic random access memory (DRAM) and static random access memory (SRAM). ), CD-ROM, Blu-ray or other optical disk storage, hard disk drive (HDD), solid state drive (SSD), or flash memory.

The processor 1030 controls the overall operation of the simulation device 1000. For example, the processor 1030 executes programs stored in the database (DB) 1050, such as an input unit (not shown), a display (not shown), a communication unit 1010, a database (DB) 1050, etc. can be controlled overall. The processor 1030 may control the operation of the simulation device 1000 by executing programs stored in the database (DB) 1050.

The processor 1030 may control at least some of the operations of the simulation device 1000 described above with reference to FIGS. 4 to 9 .

The processor 1030 includes application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, and microcontrollers. It may be implemented using at least one of micro-controllers, microprocessors, and other electrical units for performing functions.

In one embodiment, the simulation device 1000 may be a mobile electronic device. For example, the simulation device 1000 may be implemented as a smartphone, tablet PC, PC, smart TV, personal digital assistant (PDA), laptop, media player, navigation, device equipped with a camera, and other mobile electronic devices. . Additionally, the simulation device 1000 may be implemented as a wearable device such as a watch, glasses, hair band, or ring equipped with a communication function and data processing function.

In another embodiment, the simulation device 1000 may be a server located outside the vehicle. A server may be implemented as a computer device or a plurality of computer devices that communicate over a network to provide commands, codes, files, content, services, etc. The server may receive various data necessary to perform simulation of an autonomous vehicle and perform simulation of an autonomous vehicle based on the received data.

In another embodiment, the process performed in the simulation device 1000 may be performed by at least some of a mobile electronic device and a server located outside the vehicle.

Embodiments according to the present invention may be implemented in the form of a computer program that can be executed through various components on a computer, and such a computer program may be recorded on a computer-readable medium. At this time, the media includes magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and ROM. , RAM, flash memory, etc., may include hardware devices specifically configured to store and execute program instructions.

Meanwhile, the computer program may be designed and configured specifically for the present invention, or may be known and available to those skilled in the art of computer software. Examples of computer programs may include not only machine language code such as that created by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like.

According to one embodiment, methods according to various embodiments of the present disclosure may be included and provided in a computer program product. Computer program products are commodities and can be traded between sellers and buyers. The computer program product may be distributed in the form of a machine-readable storage medium (e.g. compact disc read only memory (CD-ROM)) or through an application store (e.g. Play StoreTM) or between two user devices. It may be distributed in person or online (e.g., downloaded or uploaded). In the case of online distribution, at least a portion of the computer program product may be at least temporarily stored or temporarily created in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

Unless there is an explicit order or statement to the contrary regarding the steps constituting the method according to the invention, the steps may be performed in any suitable order. The present invention is not necessarily limited by the order of description of the above steps. The use of any examples or illustrative terms (e.g., etc.) in the present invention is merely to describe the present invention in detail, and unless limited by the claims, the scope of the present invention is limited by the examples or illustrative terms. It doesn't work. Additionally, those skilled in the art will recognize that various modifications, combinations and changes may be made depending on design conditions and factors within the scope of the appended claims or their equivalents.

Therefore, the spirit of the present invention should not be limited to the above-described embodiments, and the scope of the patent claims described below as well as all scopes equivalent to or equivalently changed from the claims are within the scope of the spirit of the present invention. It will be said to belong to

Claims (12)

In the simulation method of an autonomous vehicle,
Creating an autonomous vehicle and surrounding vehicles to which an autonomous driving algorithm is applied as vehicles traveling along a virtual road included in a virtual map;
determining a visible region according to a driving position of the autonomous vehicle and setting a scenario for the autonomous vehicle based on the visible region; and
performing a simulation for the autonomous driving algorithm by starting driving of the autonomous vehicle and the surrounding vehicles based on the scenario;
Method, including. According to claim 1,
Determining the visible area is,
A method comprising determining a visible area for each virtual sensor by assigning sensing parameters to each of a plurality of virtual sensors provided in the autonomous vehicle. According to clause 2,
The step of setting the scenario is,
creating an object on the virtual road that obstructs the view of the virtual sensor;
determining an invisible region due to the object among the visible regions of a first virtual sensor; and
setting the scenario based on the invisible area;
Method, including. According to clause 3,
The step of determining the invisible area is,
specifying the location of the object;
determining whether the object is included in a visible area of the first virtual sensor based on the designated location; and
Based on the determination result, determining an area obscured by the object as the invisible area for each virtual sensor;
Method, including. According to clause 3,
Determining the visible area of the autonomous vehicle includes:
A method comprising determining the visible area and the invisible area according to the driving position of the autonomous vehicle based on the visible area for each virtual sensor and the invisible area for each virtual sensor. According to clause 5,
The step of setting the scenario is,
determining an area where the visible area of a first virtual sensor and the visible area of a second virtual sensor overlap as the visible area of the autonomous vehicle;
determining an area where the invisible area of the first virtual sensor and the invisible area of the second virtual sensor overlap as the invisible area of the autonomous vehicle; and
setting the scenario based on the visible area and the invisible area of the autonomous vehicle;
Method, including. According to clause 6,
The step of setting up the scenario is,
The autonomous vehicle based on the reliability of the first virtual sensor and the second virtual sensor for a predetermined area included in the visible area of the first virtual sensor and the invisible area of the second virtual sensor. determining either the visible area or the invisible area; How to include more. According to clause 5,
The method wherein the autonomous driving algorithm includes an algorithm that determines the behavior of the autonomous vehicle based on recognition information obtained from the visible area and estimated information about the invisible area. According to clause 8,
The autonomous driving algorithm is,
Estimation of the invisible area using first recognition information obtained from the visible area at a first time point and second recognition information obtained from the visible area at a second time point after a predetermined time has passed from the first time point A method comprising an algorithm for obtaining information and determining behavior of the autonomous vehicle based on the estimated information. According to clause 8,
The method, wherein the autonomous driving algorithm includes an algorithm that determines the behavior of the autonomous vehicle based on a distance between the autonomous vehicle and the invisible area and a preset safety distance. In a simulation device for an autonomous vehicle,
The device is,
at least one memory; and
at least one processor; Including,
The processor,
As a vehicle driving along a virtual road included in a virtual map, an autonomous vehicle and surrounding vehicles with an autonomous driving algorithm are created,
Determining a visible region according to the driving position of the autonomous vehicle and setting a scenario for the autonomous vehicle based on the visible region,
An apparatus that performs a simulation for the autonomous driving algorithm by starting driving of the autonomous vehicle and the surrounding vehicles based on the scenario. A computer-readable recording medium that records a program for executing the method of claim 1 on a computer.

Images