KR102643655B1 - Autonomous driving simulation method and device - Google Patents

Abstract

An autonomous driving simulation method and apparatus are disclosed. The autonomous driving simulation method according to an embodiment disclosed includes the steps of acquiring traffic accident-related data, extracting scenario element items for autonomous driving from the traffic accident-related data, and creating an autonomous driving scenario based on the extracted scenario element items. A step of generating, a step of executing an autonomous driving simulation according to an autonomous driving scenario, while the autonomous driving simulation is running, obtaining basic information for index calculation including target vehicle-related information, information about surrounding vehicles of the target vehicle, and traffic network information. It includes a step of calculating a traffic operation-related index for the autonomous driving scenario based on the index calculation basic information.

Description

Autonomous driving simulation method and device {AUTONOMOUS DRIVING SIMULATION METHOD AND DEVICE}

Embodiments of the present invention relate to autonomous driving simulation technology.

Recently, much research related to autonomous driving has been conducted in the automobile field. In particular, self-driving car test modules using simulation are being developed to test the performance and functions of self-driving cars, but there are limits to simulation-based testing for various traffic situations due to the difficulty of implementing simulations for a large number of test scenarios. there is.

Korean Patent Publication No. 10-2107466 (2020.05.07)

Embodiments of the present invention are intended to provide an autonomous driving simulation method and device that can perform simulation-based testing for various traffic situations.

Embodiments of the present invention are intended to provide an autonomous driving simulation method and device that can calculate traffic operation-related indicators in an autonomous driving scenario.

An autonomous driving simulation method according to an embodiment disclosed is a method performed on a computing device having one or more processors and a memory that stores one or more programs executed by the one or more processors, wherein traffic accident-related data Obtaining a; Extracting scenario element items for autonomous driving from the traffic accident-related data; generating an autonomous driving scenario based on the extracted scenario element items; Executing an autonomous driving simulation according to the autonomous driving scenario; Obtaining basic index calculation information including target vehicle-related information, surrounding vehicle-related information of the target vehicle, and traffic network information while the autonomous driving simulation is being executed; and calculating a traffic operation-related index for the autonomous driving scenario based on the index calculation basic information.

The step of extracting the scenario element items includes accident type, offender vehicle type, victim vehicle type, accident date and time, accident day, accident time, weather condition, road surface condition, day and night classification, road type, and accident from the traffic accident-related data. One or more scenario element items can be extracted among the type of violation of the law and the degree of personal injury.

The step of generating the autonomous driving scenario includes generating a first detailed scenario related to the perpetrator, victim, and accident type of a traffic accident based on the extracted scenario element items; Generating a second detailed scenario related to the accident date and environmental factors of a traffic accident based on the extracted scenario element items; Creating a third detailed scenario related to the accident occurrence point, accident law violation, and degree of accident damage based on the extracted scenario element items; and generating an autonomous driving scenario by combining the first detailed scenario, the second detailed scenario, and the third detailed scenario.

The information related to the target vehicle includes the model of the target vehicle, the weight of the target vehicle, the location of the target vehicle, the speed of the target vehicle, the acceleration of the target vehicle, the distance between the target vehicle and the vehicle in front, and the fuel consumption and exhaust gas amount of the target vehicle. Includes one or more, and information related to surrounding vehicles of the target vehicle includes the model of each surrounding vehicle, the weight of each surrounding vehicle, the location of each surrounding vehicle, the speed of each surrounding vehicle, the acceleration of each surrounding vehicle, and the number of each surrounding vehicle. It includes one or more of the following: the distance between vehicles in front, the fuel consumption and the amount of exhaust gases of each surrounding vehicle, and the traffic network information includes the starting and ending positions of the road section, the speed limit for each road section, the length of the intersection, and the angle of the intersection. It may include one or more of the following information: signal display time, whether each road is a protected zone, and safety sign information installed around each road.

The step of calculating the traffic operation-related index includes calculating a traffic efficiency index based on the index calculation basic information; Calculating a traffic safety index based on the index calculation basic information; And it may include calculating a traffic environmental index based on the index calculation basic information.

The step of calculating the traffic efficiency index is based on the index calculation basic information: total number of vehicles, average speed of total vehicles, total number of stops for total vehicles, average number of stops per vehicle, total travel time for total vehicles, and total vehicles. Calculating efficiency judgment factors, respectively, including one or more of the total delay time and the average delay time per vehicle; And it may include assigning an efficiency score to each of the efficiency determination factors and calculating a traffic efficiency index for the autonomous driving scenario by adding up the assigned efficiency scores.

The step of calculating the traffic safety index includes safety judgment factors including one or more of the distance between vehicles, speed deviation between vehicles, expected collision time, average number of vehicle collisions, and average acceleration of vehicles based on the index calculation basic information. Each calculation step; And it may include assigning a safety score to each of the safety determination elements and calculating a traffic safety index for the autonomous driving scenario by adding up the assigned safety scores.

The step of calculating the traffic environmental index includes calculating environmental judgment factors including one or more of vehicle fuel consumption, nitrogen oxide emissions, and carbon oxide emissions based on the index calculation basic information; And it may include assigning an environmental score to each of the environmental judgment factors and calculating a traffic environmental index for the autonomous driving scenario by adding up the assigned environmental scores.

The autonomous driving simulation method may further include calculating a traffic operation evaluation degree for the autonomous driving scenario based on the traffic efficiency index, the traffic safety index, and the traffic environmentality index.

The step of calculating the traffic operation-related indicators includes the total number of vehicles, average speed of total vehicles, total number of stops for total vehicles, average number of stops per vehicle, total travel time of total vehicles, and total number of stops per vehicle, based on the basic information for calculating the index. Calculating efficiency determination factors, respectively, including one or more of the total delay time of the vehicle and the average delay time per vehicle; And it may include assigning an efficiency score to each of the efficiency determination factors and calculating a traffic efficiency index for the autonomous driving scenario by adding up the assigned efficiency scores.

The step of calculating the traffic operation-related index is a safety judgment element including one or more of the distance between vehicles, speed deviation between vehicles, expected collision time, average number of vehicle collisions, and average acceleration of vehicles based on the index calculation basic information. calculating each of them; And it may include assigning a safety score to each of the safety determination elements and calculating a traffic safety index for the autonomous driving scenario by adding up the assigned safety scores.

The step of calculating the traffic operation-related index includes calculating environmental judgment factors including one or more of vehicle fuel consumption, nitrogen oxide emissions, and carbon oxide emissions based on the index calculation basic information; And it may include assigning an environmental score to each of the environmental judgment factors and calculating a traffic environmental index for the autonomous driving scenario by adding up the assigned environmental scores.

An autonomous driving simulation device according to an embodiment disclosed is an autonomous driving simulation device having one or more processors and a memory that stores one or more programs executed by the one or more processors, and acquires traffic accident-related data. a data acquisition module; an element extraction module that extracts scenario element items for autonomous driving from the traffic accident-related data; a scenario creation module that generates an autonomous driving scenario based on the extracted scenario element items; a simulation module that executes an autonomous driving simulation according to the autonomous driving scenario; And while the autonomous driving simulation is running, obtain basic index calculation information including target vehicle-related information, information about surrounding vehicles of the target vehicle, and traffic network information, and perform the autonomous driving scenario based on the index calculation basic information. It includes an indicator calculation module that calculates indicators related to transportation operations.

The information related to the target vehicle includes the model of the target vehicle, the weight of the target vehicle, the location of the target vehicle, the speed of the target vehicle, the acceleration of the target vehicle, the distance between the target vehicle and the vehicle in front, and the fuel consumption and exhaust gas amount of the target vehicle. Includes one or more, and information related to surrounding vehicles of the target vehicle includes the model of each surrounding vehicle, the weight of each surrounding vehicle, the location of each surrounding vehicle, the speed of each surrounding vehicle, the acceleration of each surrounding vehicle, and the number of each surrounding vehicle. It includes one or more of the following: the distance between vehicles in front, the fuel consumption and the amount of exhaust gases of each surrounding vehicle, and the traffic network information includes the starting and ending positions of the road section, the speed limit for each road section, the length of the intersection, and the angle of the intersection. It may include one or more of the following information: signal display time, whether each road is a protected zone, and safety sign information installed around each road.

The indicator calculation module may calculate one or more of a transport efficiency indicator, a transport safety indicator, and a transport environmentality indicator based on the indicator calculation basic information.

The indicator calculation module is based on the indicator calculation basic information: total number of vehicles, average speed of total vehicles, total number of stops of total vehicles, average number of stops per vehicle, total travel time of total vehicles, and total delay time of total vehicles. , and average delay time per vehicle are calculated, respectively, an efficiency score is assigned to each of the efficiency judgment elements, and the assigned efficiency scores are summed to obtain a traffic efficiency index for the autonomous driving scenario. It can be calculated.

The index calculation module calculates safety judgment factors including one or more of inter-vehicle distance, inter-vehicle speed deviation, expected collision time, average number of vehicle collisions, and average vehicle acceleration based on the index calculation basic information, A safety score is assigned to each of the safety determination factors, and the assigned safety scores can be added to calculate a traffic safety index for the autonomous driving scenario.

The index calculation module calculates environmental judgment factors including one or more of vehicle fuel consumption, nitrogen oxide emissions, and carbon oxide emissions based on the index calculation basic information, and assigns an environmental score to each of the environmental judgment factors. And, by adding up the given environmental scores, a traffic environmental index for the autonomous driving scenario can be calculated.

The index calculation module may calculate a traffic operation evaluation degree for the autonomous driving scenario based on the traffic efficiency index, the traffic safety index, and the traffic environmental index.

An autonomous driving simulation method according to another disclosed embodiment is a method performed on a computing device having one or more processors and a memory that stores one or more programs executed by the one or more processors, wherein the autonomous driving simulation method is Executing an autonomous driving simulation according to a driving scenario; Obtaining basic index calculation information including target vehicle-related information, surrounding vehicle-related information of the target vehicle, and traffic network information while the autonomous driving simulation is being executed; and calculating a traffic operation-related index for the autonomous driving scenario based on the index calculation basic information.

According to the disclosed embodiment, by generating an autonomous driving algorithm based on data related to traffic accidents that occurred in the past, it is possible to perform simulation-based tests for various traffic situations.

In addition, by calculating traffic operation-related indicators of the traffic network while the autonomous driving simulation is running, it is possible to evaluate the traffic operation efficiency, safety, and environmental friendliness of the autonomous driving algorithm. In addition, the traffic operation evaluation degree for each autonomous driving algorithm can be quantitatively expressed and displayed in numbers.

1 is a block diagram showing the configuration of an autonomous driving simulation device according to an embodiment of the present invention.
Figure 2 schematically shows the state of generating an autonomous driving scenario by extracting scenario element items from traffic accident-related data and converting the data file of the autonomous driving scenario into an input data file of a traffic simulator according to an embodiment of the present invention. floor plan
Figure 3 is a diagram showing a state of executing an autonomous driving scenario in one embodiment of the present invention.
Figure 4 is a diagram showing basic indicator calculation information obtained through real-time monitoring in an embodiment of the present invention.
Figure 5 is a flowchart illustrating an autonomous driving simulation method according to an embodiment of the present invention.
6 is a block diagram illustrating and illustrating a computing environment including a computing device suitable for use in example embodiments.

Hereinafter, specific embodiments of the present invention will be described with reference to the drawings. The detailed description below is provided to provide a comprehensive understanding of the methods, devices and/or systems described herein. However, this is only an example and the present invention is not limited thereto.

In describing the embodiments of the present invention, if it is determined that a detailed description of the known technology related to the present invention may unnecessarily obscure the gist of the present invention, the detailed description will be omitted. In addition, the terms described below are terms defined in consideration of functions in the present invention, and may vary depending on the intention or custom of the user or operator. Therefore, the definition should be made based on the contents throughout this specification. The terminology used in the detailed description is merely for describing embodiments of the present invention and should in no way be limiting. Unless explicitly stated otherwise, singular forms include plural meanings. In this description, expressions such as “comprising” or “comprising” are intended to indicate certain features, numbers, steps, operations, elements, parts or combinations thereof, and one or more than those described. It should not be construed to exclude the existence or possibility of any other characteristic, number, step, operation, element, or part or combination thereof.

Additionally, terms such as first and second may be used to describe various components, but the components should not be limited by the terms. The above terms may be used for the purpose of distinguishing one component from another component. For example, a first component may be referred to as a second component, and similarly, the second component may also be referred to as a first component without departing from the scope of the present invention.

Figure 1 is a block diagram showing the configuration of an autonomous driving simulation device according to an embodiment of the present invention.

Referring to FIG. 1, the autonomous driving simulation device 100 includes a data acquisition module 102, an element extraction module 104, a scenario creation module 106, a file conversion module 108, a simulation module 110, and an indicator. It may include a calculation module 112.

The data acquisition module 102 can acquire traffic accident-related data. Here, traffic accident-related data refers to data related to traffic accidents that occurred in the past. Data related to traffic accidents may include information about objective facts about the traffic situation and information about subjective statements (for example, descriptions of accident situations by police officers or witnesses, etc.). The data acquisition module 102 may acquire traffic accident-related data from an external server (e.g., Korea Transportation Safety Authority, etc.), but is not limited to this and may also acquire traffic accident-related data through an administrator's input.

The element extraction module 104 can extract items related to scenario elements for autonomous driving from traffic accident-related data. In an exemplary embodiment, the element extraction module 104 extracts traffic accident-related data from accident type, offender vehicle type, victim vehicle type, accident date and time, accident day, accident time, weather condition, road surface condition, day and night classification, and road type. , items related to scenario elements such as type of violation of accident laws and degree of human injury can be extracted. The element extraction module 104 can extract items related to scenario elements for autonomous driving based on code information of traffic accident-related data.

Here, accident types may include, for example, vehicle-to-vehicle-collision-while parked, vehicle-to-vehicle-person-crossing, vehicle-to-vehicle-side right-angle collision, vehicle-to-vehicle-collision-in-progress, vehicle-to-person-trafficking-roadway, vehicle-only-workpiece collision, etc. there is. For example, the offender's vehicle type and the victim's vehicle type may include passenger cars, motor vehicles, pedestrians, vans, cargo, two-wheeled vehicles, bicycles, special vehicles, and construction machinery. Weather conditions may include, for example, clear weather, rain, cloudiness, snow, etc. Road surface conditions may include, for example, pavement-freezing, pavement-dry, pavement-wet, pavement-snow, unpaved-dry, unpaved-snow, unpaved-iced, unpaved-wet, etc.

In addition, the road type may be, for example, intersection-near intersection, intersection-in intersection, single road-near crosswalk, single road-on crosswalk, single road-tunnel, etc. Types of accident law violations may include, for example, failure to drive safely, lane violations, crossing the center line, traffic signals, violations of intersection driving methods, speeding, failure to secure a safe distance, violation of pedestrian protection obligations, and illegal U-turns. The level of human injury may include, for example, minor injury accidents, serious injury accidents, accidents with reported injuries, and fatal accidents.

The scenario creation module 106 may generate an autonomous driving scenario based on items related to the scenario elements extracted by the element extraction module 104 (hereinafter referred to as scenario element items). In an example embodiment, the scenario creation module 106 may generate a first detailed scenario, a second detailed scenario, and a third detailed scenario, respectively, based on scenario element items.

The first detailed scenario may be a scenario related to the perpetrator, victim, and accident type of the traffic accident. The second detailed scenario may be a scenario related to the accident date and environmental factors of a traffic accident. The third detailed scenario may be a scenario related to the point of accident occurrence, violation of accident laws, and degree of accident damage.

The scenario creation module 106 may generate a first detailed scenario using scenario element items that can form the first detailed scenario from the scenario element items extracted by the element extraction module 104. For example, the scenario creation module 106 uses the perpetrator vehicle type, victim vehicle type, and accident type among the scenario element items to indicate "a passenger vehicle (offender) causes a passenger vehicle (victim) to cause a collision - accident while parked." A first detailed scenario called “occurrence” may be created.

The scenario creation module 106 may generate a second detailed scenario using scenario element items that can configure the second detailed scenario from the scenario element items extracted by the element extraction module 104. For example, the scenario creation module 106 uses the accident date and time, accident day, accident time, weather condition, day and night classification, and road surface condition among the scenario element items to create “At 20:00 at night on Wednesday, January 13, 2010.” A second detailed scenario can be created: “An accident occurred, the weather conditions are clear, and the road surface conditions are paved and icy.”

The scenario creation module 106 may generate a third detailed scenario using scenario element items that can configure the third detailed scenario from the scenario element items extracted by the element extraction module 104. For example, the scenario creation module 106 uses the road type, type of violation of accident regulations, and degree of human injury among the scenario element items to create a third detailed scenario called “Intersection - minor injury occurs due to failure to drive safely within the intersection.” can be created.

Table 1 is a table showing various examples of the first detailed scenario, second detailed scenario, and third detailed scenario generated in the scenario creation module 106.

1st detailed scenario Second detailed scenario Third detailed scenario A motor vehicle (motor bike or larger) strikes a passenger car (motor bike or larger), resulting in a vehicle-to-wheel collision at right angles to the side. 2010-04-23 The accident occurred at 13:00 on Friday (weekday), the weather was clear, the road surface was paved - dry. Single road - Serious accident occurred due to failure to drive safely in other areas
Cargo (motorcycle or larger) hits the motor (motorcycle or larger) causing a car-to-wheel collision at right angles to the side. 2010-04-23 Accident occurred at 14:00 on Friday (weekday), weather conditions were cloudy, road surface conditions were paved - dry. Intersection - Injuries reported due to failure to drive safely near intersections
A pedestrian (pedestrian) hits a vehicle (motorcycle or larger), resulting in a pedestrian-crossing accident. 2010-03-22 Accident occurred at 22:00 on Monday (at night), weather conditions were clear, road surface condition was paved - dry. Intersection - Minor accident occurs due to failure to drive safely within the intersection

Here, the scenario creation module 106 may finally generate an autonomous driving scenario by combining the first detailed scenario, the second detailed scenario, and the third detailed scenario. The scenario creation module 106 may generate an autonomous driving scenario in a preset data file format (eg, json, etc.).

The file conversion module 108 may convert the data file of the autonomous driving scenario generated by the scenario generation module 106 into an input data file of a traffic simulator (eg, VISSIM, etc.). That is, the file conversion module 108 can convert a data file of an autonomous driving scenario into an input data file in a form executable on a traffic simulator.

Figure 2 schematically shows the state of generating an autonomous driving scenario by extracting scenario element items from traffic accident-related data and converting the data file of the autonomous driving scenario into an input data file of a traffic simulator according to an embodiment of the present invention. It is a drawing.

The simulation module 110 can execute the converted data file of the autonomous driving scenario as an autonomous driving simulation in a traffic simulator. The simulation module 110, for example, states, "A situation in which an ego vehicle is driving at 50 per hour in rain and wet road conditions in the first lane of an intersection approach link with a total of three lanes, violates the center line and impacts a vehicle across the street." The autonomous driving scenario can be run in a traffic simulator as shown in FIG. 3.

The simulation module 110 may execute an autonomous driving simulation by rendering virtual 3D objects (eg, roads, traffic lights, vehicles, etc.) according to the autonomous driving scenario. The simulation module 110 can load a data file of an autonomous driving scenario into a traffic simulator, then render a virtual 3D object according to the autonomous driving scenario and display it on the screen.

The simulation module 110 may perform environment settings for autonomous driving simulation according to user input. The simulation module 110 may provide various screen interfaces so that users can input various setting values. The simulation module 110 can control the movement of the 3D object in the lyrics according to the autonomous driving scenario.

The indicator calculation module 112 may acquire basic indicator calculation information including information related to the target vehicle (i.e., ego vehicle), information related to surrounding vehicles of the target vehicle, and traffic network information while the autonomous driving simulation is being executed. The indicator calculation module 112 can obtain basic indicator calculation information through real-time monitoring while the autonomous driving simulation is running. Figure 4 is a diagram showing basic indicator calculation information obtained through real-time monitoring in an embodiment of the present invention.

Here, the information related to the target vehicle in the simulation includes the model of the target vehicle, the weight of the target vehicle, the location of the target vehicle, the speed of the target vehicle, the acceleration of the target vehicle, and the distance between the target vehicle and the car in front, the fuel consumption of the target vehicle, and It may include the amount of exhaust gas, etc. The target vehicle may refer to a vehicle that is the target of autonomous driving simulation.

Information related to surrounding vehicles of the target vehicle includes the model of each surrounding vehicle, the weight of each surrounding vehicle, the location of each surrounding vehicle, the speed of each surrounding vehicle, the acceleration of each surrounding vehicle, and the distance between each surrounding vehicle and the vehicle in front of each surrounding vehicle. It may include fuel consumption and exhaust gas amount of surrounding vehicles. The surrounding vehicle may refer to a vehicle located within a preset distance around the target vehicle.

In addition, traffic network information includes the starting and ending positions of road sections, speed limits for each road section, length of intersections, display time of each signal at intersections, whether each road is a protection zone, and safety sign information installed around each road. It can be included.

Specifically, the indicator calculation module 112 may calculate a traffic operation-related indicator based on the indicator calculation basic information. Here, the traffic operation-related indicator may include one or more of a transport efficiency indicator, a transport safety indicator, and a transport environmentality indicator. Through traffic operation-related indicators, it is possible to know how efficient, stable, and environmentally friendly the traffic operation according to the autonomous driving algorithm is, making it possible to evaluate the autonomous driving algorithm.

The indicator calculation module 112 may calculate a plurality of efficiency judgment factors based on the indicator calculation basic information. In an exemplary embodiment, the efficiency determination factors include the total number of vehicles, the average speed of the total vehicles, the total number of stops per vehicle, the average number of stops per vehicle, the total travel time of the total vehicles, the total delay time of the total vehicles, and the total number of stops per vehicle. May include average delay time.

Here, the total number of vehicles may mean the total number of vehicles existing in the traffic environment (hereinafter referred to as a traffic network) of a preset virtual area implemented through autonomous driving simulation. In the disclosed embodiment, the traffic network may refer to a traffic environment in a virtual area implemented through autonomous driving simulation. The average speed of all vehicles may refer to the average speed of all vehicles in the transportation network. The total number of stops for all vehicles may refer to the total number of stops for all vehicles in the transportation network. At this time, stopping of buses, etc. at public transportation stops may not be counted, and vehicles parked on the side of the road may not be counted.

The average number of stops per vehicle may refer to the average number of stops for all vehicles in a transportation network. The total travel time of all vehicles may refer to the total travel time of all vehicles in the transportation network. The total delay time of all vehicles may refer to the total delay time of all vehicles in the transportation network due to waiting at a signal or traffic jam. Average delay time per vehicle may refer to the average delay time of all vehicles in a transportation network.

The index calculation module 112 can calculate a transportation efficiency index by assigning an efficiency score to each efficiency determination element. For example, the index calculation module 112 assigns a first efficiency score to the total number of vehicles, a second efficiency score to the average speed of the total vehicles, and a third efficiency score to the total number of stops of the total vehicles. A fourth efficiency score is assigned to the average number of stops per vehicle, a fifth efficiency score is assigned to the total travel time of total vehicles, a sixth efficiency score is assigned to the total delay time of total vehicles, and the average delay per vehicle is assigned. After assigning a seventh efficiency score to time, the transportation efficiency index can be calculated by adding them up. At this time, the indicator calculation module 112 may assign separate weights to each efficiency determination element.

Additionally, the index calculation module 112 may calculate a plurality of safety judgment factors based on the index calculation basic information. In an exemplary embodiment, safety determination factors may include distance between vehicles, speed deviation between vehicles, expected collision time, average number of vehicle collisions, and average acceleration of vehicles.

Here, the distance between vehicles may mean the distance between the target vehicle and a vehicle located in front and behind the target vehicle. Speed deviation between vehicles may refer to the deviation between the driving speeds of each vehicle existing in the transportation network. The expected collision time may refer to the expected time until a collision with a vehicle located in front or behind the target vehicle, based on the target vehicle. The expected collision time can be calculated using the distance between the vehicles, the speed of the target vehicle, and the speed of the vehicle located in front or behind the target vehicle.

The average number of vehicle collisions may refer to the average number of times vehicles existing in a transportation network are at risk of collision (e.g., collision risk resulting from lane cutting, sudden stopping, etc.). Vehicle acceleration may mean the average acceleration of all vehicles existing in a transportation network or vehicles surrounding the target vehicle.

The index calculation module 112 can calculate a traffic safety index by assigning a safety score to each safety judgment element. For example, the index calculation module 112 assigns a first safety score to the distance between vehicles, a second safety score to the speed deviation between vehicles, a third safety score to the expected collision time, and a vehicle collision. A fourth safety score can be assigned to the average number of times, a fifth safety score can be assigned to the average vehicle acceleration, and the traffic safety index can be calculated by adding them together. At this time, the index calculation module 112 may assign separate weights to each safety determination element.

Additionally, the indicator calculation module 112 may calculate a plurality of environmental judgment factors based on the indicator calculation basic information. In an exemplary embodiment, environmental judgment factors may include vehicle fuel consumption, nitrogen oxide emissions, and carbon oxide emissions.

Here, vehicle fuel consumption may be the total fuel consumption or average fuel consumption of all vehicles in the transportation network. Nitrogen oxide emissions can be the total nitrogen oxide (NO _x ) emissions or the average nitrogen oxide emissions of all vehicles in the transport network. Carbon oxide emissions can be the total carbon oxide (CO _x ) emissions or the average carbon oxide emissions of all vehicles in the transport network.

The index calculation module 112 can calculate a traffic environmental index by assigning a safety score to each environmental judgment element. For example, the index calculation module 112 assigns a first environmental score to vehicle fuel consumption, a second environmental score to nitrogen oxide emissions, and a third environmental score to carbon oxide emissions, and then adds them up to determine the traffic Environmental indicators can be calculated. At this time, the indicator calculation module 112 may assign separate weights to each environmental judgment factor.

In an exemplary embodiment, the indicator calculation module 112 may calculate a transport operation evaluation degree based on a transport efficiency indicator, a transport safety indicator, and a transport environmentality indicator. The index calculation module 112 may calculate a transportation operation evaluation degree by averaging the transportation efficiency index, transportation safety index, and transportation environmental index, but is not limited to this.

The indicator calculation module 112 may calculate a transport operation evaluation degree by assigning weights to each transport efficiency indicator, transport safety indicator, and transport environmentality indicator. For example, the index calculation module 112 assigns a first weight to the transportation efficiency index, a second weight to the transportation safety index, and a third weight to the transportation environmentality index, and then sums them to obtain a transportation operation evaluation. can also be calculated. At this time, the sum of the first weight, the second weight, and the third weight may be 1. The indicator calculation module 112 can quantitatively quantify and visualize the traffic operation evaluation degree.

According to the disclosed embodiment, by generating an autonomous driving algorithm based on data related to traffic accidents that occurred in the past, it is possible to perform simulation-based tests for various traffic situations.

In addition, by calculating traffic operation-related indicators of the traffic network while the autonomous driving simulation is running, it is possible to evaluate the traffic operation efficiency, safety, and environmental friendliness of the autonomous driving algorithm. In addition, the traffic operation evaluation degree for each autonomous driving algorithm can be quantitatively expressed and displayed in numbers.

In this specification, a module may mean a functional and structural combination of hardware for carrying out the technical idea of the present invention and software for driving the hardware. For example, the “module” may mean a logical unit of a predetermined code and hardware resources for executing the predetermined code, and does not necessarily mean a physically connected code or a single type of hardware.

Figure 5 is a flowchart for explaining an autonomous driving simulation method according to an embodiment of the present invention. In the illustrated flow chart, the method is divided into a plurality of steps, but at least some of the steps are performed in a different order, combined with other steps, omitted, divided into detailed steps, or not shown. One or more steps may be added and performed.

Referring to FIG. 5, the autonomous driving simulation device 100 can acquire traffic accident-related data (S 101). Next, the autonomous driving simulation device 100 may extract scenario element items from traffic accident-related data (S 103). Next, the autonomous driving simulation device 100 may generate an autonomous driving scenario using the extracted scenario element items (S 105). Next, the autonomous driving simulation device 100 may convert the data file of the autonomous driving scenario into an input data file of a traffic simulator (S 107).

Next, the autonomous driving simulation device 100 may execute an autonomous driving simulation according to the autonomous driving scenario (S 109). Next, the autonomous driving simulation device 100 may acquire basic index calculation information including target vehicle-related information, surrounding vehicle-related information of the target vehicle, and traffic network information while the autonomous driving simulation is running (S 111 ). Next, the autonomous driving simulation device 100 may calculate preset traffic operation-related indicators of the target vehicle based on the indicator calculation basic information (S 113).

FIG. 6 is a block diagram illustrating and illustrating a computing environment 10 including computing devices suitable for use in example embodiments. In the illustrated embodiment, each component may have different functions and capabilities in addition to those described below, and may include additional components in addition to those described below.

The illustrated computing environment 10 includes a computing device 12 . In one embodiment, computing device 12 may be an autonomous driving simulation device 100.

Computing device 12 includes at least one processor 14, a computer-readable storage medium 16, and a communication bus 18. Processor 14 may cause computing device 12 to operate in accordance with the example embodiments noted above. For example, processor 14 may execute one or more programs stored on computer-readable storage medium 16. The one or more programs may include one or more computer-executable instructions, which, when executed by the processor 14, cause computing device 12 to perform operations according to example embodiments. It can be.

Computer-readable storage medium 16 is configured to store computer-executable instructions or program code, program data, and/or other suitable form of information. The program 20 stored in the computer-readable storage medium 16 includes a set of instructions executable by the processor 14. In one embodiment, computer-readable storage medium 16 includes memory (volatile memory, such as random access memory, non-volatile memory, or an appropriate combination thereof), one or more magnetic disk storage devices, optical disk storage devices, flash It may be memory devices, another form of storage medium that can be accessed by computing device 12 and store desired information, or a suitable combination thereof.

Communication bus 18 interconnects various other components of computing device 12, including processor 14 and computer-readable storage medium 16.

Computing device 12 may also include one or more input/output interfaces 22 and one or more network communication interfaces 26 that provide an interface for one or more input/output devices 24. The input/output interface 22 and the network communication interface 26 are connected to the communication bus 18. Input/output device 24 may be coupled to other components of computing device 12 through input/output interface 22. Exemplary input/output devices 24 include, but are not limited to, a pointing device (such as a mouse or trackpad), a keyboard, a touch input device (such as a touchpad or touch screen), a voice or sound input device, various types of sensor devices, and/or imaging devices. It may include input devices and/or output devices such as display devices, printers, speakers, and/or network cards. The exemplary input/output device 24 may be included within the computing device 12 as a component constituting the computing device 12, or may be connected to the computing device 12 as a separate device distinct from the computing device 12. It may be possible.

Although representative embodiments of the present invention have been described in detail above, those skilled in the art will understand that various modifications can be made to the above-described embodiments without departing from the scope of the present invention. . Therefore, the scope of the present invention should not be limited to the described embodiments, but should be determined not only by the claims described later but also by equivalents to the claims.

100: Autonomous driving simulation device
102: Data acquisition module
104: element extraction module
106: Scenario creation module
108: File conversion module
110: Simulation module
112: Indicator calculation module

Claims (20)

one or more processors, and
A method performed on a computing device having a memory that stores one or more programs executed by the one or more processors, comprising:
Obtaining traffic accident-related data;
Extracting scenario element items for autonomous driving from the traffic accident-related data;
generating an autonomous driving scenario based on the extracted scenario element items;
Executing an autonomous driving simulation according to the autonomous driving scenario;
Obtaining basic index calculation information including target vehicle-related information, surrounding vehicle-related information of the target vehicle, and traffic network information while the autonomous driving simulation is being executed; and
Comprising a step of calculating traffic operation-related indicators for the autonomous driving scenario based on the indicator calculation basic information,
The step of calculating the traffic operation-related indicators is,
Calculating a traffic efficiency index based on the index calculation basic information;
Calculating a traffic safety index based on the index calculation basic information; and
An autonomous driving simulation method comprising calculating a traffic environmental index based on the index calculation basic information.
In claim 1,
The step of extracting the scenario element items is,
From the above traffic accident-related data, one of the following is accident type, offender vehicle type, victim vehicle type, accident date and time, accident day, accident time, weather conditions, road surface condition, day and night classification, road type, type of accident law violation, and degree of personal injury. An autonomous driving simulation method that extracts the above scenario element items.
In claim 2,
The step of generating the autonomous driving scenario is,
Generating a first detailed scenario related to the perpetrator, victim, and accident type of a traffic accident based on the extracted scenario element items;
Generating a second detailed scenario related to the accident date and environmental factors of a traffic accident based on the extracted scenario element items;
Creating a third detailed scenario related to the accident occurrence point, accident law violation, and degree of accident damage based on the extracted scenario element items; and
An autonomous driving simulation method comprising generating an autonomous driving scenario by combining the first detailed scenario, the second detailed scenario, and the third detailed scenario.
In claim 1,
The information related to the target vehicle includes the model of the target vehicle, the weight of the target vehicle, the location of the target vehicle, the speed of the target vehicle, the acceleration of the target vehicle, the distance between the target vehicle and the vehicle in front, and the fuel consumption and exhaust gas amount of the target vehicle. contains one or more,
Information related to surrounding vehicles of the target vehicle includes the model of each surrounding vehicle, the weight of each surrounding vehicle, the location of each surrounding vehicle, the speed of each surrounding vehicle, the acceleration of each surrounding vehicle, the inter-vehicle distance from the vehicle in front of each surrounding vehicle, Includes one or more of the fuel consumption and emissions of each surrounding vehicle,
The traffic network information includes the starting and ending positions of road sections, speed limits for each road section, length of intersections, display time of each signal at intersections, whether each road is a protection zone, and safety sign information installed around each road. An autonomous driving simulation method comprising one or more.
delete In claim 1,
The step of calculating the transportation efficiency index is,
Based on the above index calculation basic information, the total number of vehicles, the average speed of all vehicles, the total number of stops of total vehicles, the average number of stops per vehicle, the total travel time of total vehicles, the total delay time of total vehicles, and the average delay per vehicle. calculating efficiency judgment factors each including one or more of time; and
An autonomous driving simulation method comprising the step of assigning an efficiency score to each of the efficiency determination factors and calculating a traffic efficiency index for the autonomous driving scenario by adding up the given efficiency scores.
In claim 1,
The step of calculating the traffic safety index is,
Calculating safety judgment factors including one or more of inter-vehicle distance, inter-vehicle speed deviation, expected collision time, average number of vehicle collisions, and average vehicle acceleration based on the index calculation basic information; and
An autonomous driving simulation method comprising the step of assigning a safety score to each of the safety determination factors and calculating a traffic safety index for the autonomous driving scenario by adding up the assigned safety scores.
In claim 1,
The step of calculating the traffic environmental index is,
Calculating environmental judgment factors including one or more of vehicle fuel consumption, nitrogen oxide emissions, and carbon oxide emissions based on the indicator calculation basic information; and
An autonomous driving simulation method comprising the step of assigning an environmental score to each of the environmental judgment factors and calculating a traffic environmental index for the autonomous driving scenario by adding up the assigned environmental scores.
In claim 1,
The autonomous driving simulation method is,
An autonomous driving simulation method further comprising calculating a traffic operation evaluation degree for the autonomous driving scenario based on the traffic efficiency index, the traffic safety index, and the traffic environmentality index.
In claim 1,
The step of calculating the traffic operation-related indicators is,
Based on the above index calculation basic information, the total number of vehicles, the average speed of all vehicles, the total number of stops of total vehicles, the average number of stops per vehicle, the total travel time of total vehicles, the total delay time of total vehicles, and the average delay per vehicle. calculating efficiency judgment factors each including one or more of time; and
An autonomous driving simulation method comprising the step of assigning an efficiency score to each of the efficiency determination factors and calculating a traffic efficiency index for the autonomous driving scenario by adding up the given efficiency scores.
one or more processors, and
A method performed on a computing device having a memory that stores one or more programs executed by the one or more processors, comprising:
Obtaining traffic accident-related data;
Extracting scenario element items for autonomous driving from the traffic accident-related data;
generating an autonomous driving scenario based on the extracted scenario element items;
Executing an autonomous driving simulation according to the autonomous driving scenario;
Obtaining basic index calculation information including target vehicle-related information, surrounding vehicle-related information of the target vehicle, and traffic network information while the autonomous driving simulation is being executed; and
Comprising a step of calculating traffic operation-related indicators for the autonomous driving scenario based on the indicator calculation basic information,
The step of calculating the traffic operation-related indicators is,
Calculating safety judgment factors including one or more of inter-vehicle distance, inter-vehicle speed deviation, expected collision time, average number of vehicle collisions, and average vehicle acceleration based on the index calculation basic information; and
An autonomous driving simulation method comprising the step of assigning a safety score to each of the safety determination factors and calculating a traffic safety index for the autonomous driving scenario by adding up the assigned safety scores.
one or more processors, and
A method performed on a computing device having a memory that stores one or more programs executed by the one or more processors, comprising:
Obtaining traffic accident-related data;
Extracting scenario element items for autonomous driving from the traffic accident-related data;
generating an autonomous driving scenario based on the extracted scenario element items;
Executing an autonomous driving simulation according to the autonomous driving scenario;
Obtaining basic index calculation information including target vehicle-related information, surrounding vehicle-related information of the target vehicle, and traffic network information while the autonomous driving simulation is being executed; and
Comprising a step of calculating traffic operation-related indicators for the autonomous driving scenario based on the indicator calculation basic information,
The step of calculating the traffic operation-related indicators is,
Calculating environmental judgment factors including one or more of vehicle fuel consumption, nitrogen oxide emissions, and carbon oxide emissions based on the indicator calculation basic information; and
An autonomous driving simulation method comprising the step of assigning an environmental score to each of the environmental judgment factors and calculating a traffic environmental index for the autonomous driving scenario by adding up the assigned environmental scores.
one or more processors, and
An autonomous driving simulation device having a memory that stores one or more programs executed by the one or more processors,
A data acquisition module that acquires traffic accident-related data;
an element extraction module that extracts scenario element items for autonomous driving from the traffic accident-related data;
a scenario creation module that generates an autonomous driving scenario based on the extracted scenario element items;
a simulation module that executes an autonomous driving simulation according to the autonomous driving scenario; and
While the autonomous driving simulation is running, basic index calculation information including target vehicle-related information, information about surrounding vehicles of the target vehicle, and traffic network information is acquired, and based on the index calculation basic information, the autonomous driving scenario is Includes an indicator calculation module that calculates traffic operation-related indicators,
The indicator calculation module is,
An autonomous driving simulation device that calculates one or more of a traffic efficiency index, a traffic safety index, and a traffic environmental index based on the index calculation basic information.
In claim 13,
The information related to the target vehicle includes the model of the target vehicle, the weight of the target vehicle, the location of the target vehicle, the speed of the target vehicle, the acceleration of the target vehicle, the distance between the target vehicle and the vehicle in front, and the fuel consumption and exhaust gas amount of the target vehicle. contains one or more,
Information related to surrounding vehicles of the target vehicle includes the model of each surrounding vehicle, the weight of each surrounding vehicle, the location of each surrounding vehicle, the speed of each surrounding vehicle, the acceleration of each surrounding vehicle, the inter-vehicle distance from the vehicle in front of each surrounding vehicle, Includes one or more of the fuel consumption and emissions of each surrounding vehicle,
The traffic network information includes the starting and ending positions of road sections, speed limits for each road section, length of intersections, display time of each signal at intersections, whether each road is a protection zone, and safety sign information installed around each road. An autonomous driving simulation device comprising one or more.
delete In claim 13,
The indicator calculation module is,
Based on the above index calculation basic information, the total number of vehicles, the average speed of all vehicles, the total number of stops of total vehicles, the average number of stops per vehicle, the total travel time of total vehicles, the total delay time of total vehicles, and the average delay per vehicle. An autonomous driving simulation that calculates efficiency judgment elements including one or more of time, assigns an efficiency score to each of the efficiency judgment elements, and calculates a traffic efficiency index for the autonomous driving scenario by adding up the assigned efficiency scores. Device.
In claim 13,
The indicator calculation module is,
Based on the index calculation basic information, safety judgment factors including one or more of the distance between vehicles, speed deviation between vehicles, expected collision time, average number of vehicle collisions, and average vehicle acceleration are calculated, and each of the safety judgment elements is calculated. An autonomous driving simulation device that assigns safety scores and calculates traffic safety indicators for the autonomous driving scenario by adding up the given safety scores.
In claim 13,
The indicator calculation module is,
Based on the indicator calculation basic information, environmental judgment factors including one or more of vehicle fuel consumption, nitrogen oxide emissions, and carbon oxide emissions are calculated, an environmental score is assigned to each of the environmental judgment elements, and the assigned environmental score is An autonomous driving simulation device that calculates a traffic environmental index for the autonomous driving scenario by adding them up.
In claim 13,
The indicator calculation module is,
An autonomous driving simulation device that calculates a traffic operation evaluation degree for the autonomous driving scenario based on the traffic efficiency index, the traffic safety index, and the traffic environmentality index.
one or more processors, and
A method performed on a computing device having a memory that stores one or more programs executed by the one or more processors, comprising:
Executing an autonomous driving simulation according to a previously created autonomous driving scenario;
Obtaining basic index calculation information including target vehicle-related information, surrounding vehicle-related information of the target vehicle, and traffic network information while the autonomous driving simulation is being executed; and
Comprising a step of calculating traffic operation-related indicators for the autonomous driving scenario based on the indicator calculation basic information,
The step of calculating the traffic operation-related index is an autonomous driving simulation method in which one or more of a traffic efficiency index, a traffic safety index, and a traffic environmental index are calculated based on the index calculation basic information.