Autonomous travel test scenario generation system for data infrastructure for testing and evaluating autonomous travel system, and method

Abstract

To provide an autonomous travel test scenario generation system for data infrastructure for testing and evaluating an autonomous travel system, and a method.SOLUTION: An autonomous travel test scenario generation system includes: a tracking object processing part that generates a tracking objet by using tracking object data acquired by an autonomous vehicle while traveling, and identifies some of untracked objects among the tracked objects; an untracked factor reflection part that reflects untracked factors to untracked object data; and a scenario generation part that generates autonomous travel test scenarios by using elements within an operational design scope of the autonomous travel test scenarios and the untracked object data obtained by reflecting the untracked factors. Accordingly, scenarios that can test not only decision-making and control functions but also cognitive functions based on data obtained from autonomous travel are generated, enabling more comprehensive and delicate testing and evaluation of autonomous travel systems that perform dynamic driving tasks.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to the generation of autonomous driving test scenarios, and more particularly, to a system and method for processing data collected from autonomous vehicles to generate scenarios for autonomous driving tests and evaluations.

Background Art

[0002] In order to introduce a vehicle equipped with an autonomous driving system to the market, reasonable verification and evaluation of the autonomous driving system are necessary. For testing the autonomous driving system, a scenario-based testing method is used.

[0003] In scenario-based testing, various scenarios are generated and tested to confirm whether there is any abnormality in operating within the operating design range (range with respect to roads, weather, and traffic), which is the range in which an autonomous driving system that performs dynamic driving tasks including recognition, judgment, and control functions that can replace the driver's driving can operate.

[0004] Conventional scenario-based testing has focused only on testing the judgment and control of the autonomous driving system, and has not generated situations in which recognition errors occur from the scenarios.

[0005] However, for the correct judgment and control of the autonomous driving system, accurate recognition must be a prerequisite, so a measure to supplement it is necessary. In particular, it is required to conduct a recognition test based on data corresponding to the autonomous driving situation, rather than a recognition test based on general data.

Summary of the Invention

Problems to be Solved by the Invention

[0006] Therefore, the present invention has been made in view of the above problems, and an object of the present invention is to provide a system and method for generating a scenario capable of evaluating an autonomous driving system that performs a dynamic driving task including recognition, judgment, and control functions based on data that can be obtained from autonomous driving.

Means for Solving the Problems

[0007] An autonomous driving test scenario generation method according to an embodiment of the present invention for achieving the above object includes steps of generating a tracking object using tracking object data acquired while an autonomous driving vehicle is traveling, discriminating an untracked object and complementing an untracked section, reflecting an untracked factor in the untracked object data, identifying elements within the operation design range of the autonomous driving test scenario, and generating an autonomous driving test scenario using the identified elements and the untracked object data in which the untracked factor is reflected.

[0008] The identified elements may include dynamic elements, static elements, and environmental elements.

[0009] The generating step may use, for an untracked object among the dynamic elements identified at the time of generating the autonomous driving test scenario, the untracked object data in which the untracked factor is reflected, using the identified elements.

[0010] The complementing step may discriminate, as an untracked object, a tracking object whose interval between the tracking start time points is equal to or less than a certain time after the tracking end time point and whose interval between the tracking end point and the subsequent tracking start point is equal to or less than a certain distance.

[0011] The reflecting step may include steps of analyzing the untracked factor of the untracked object and reflecting the analyzed untracked factor in the untracked object data.

[0012] The untracked factor may include the color and reflectivity of the untracked object.

[0013] The autonomous driving test scenario generation method according to the present invention may further include a step of discriminating and filtering mis-tracked objects.

[0014] The filtering step may be to discriminate mis-tracked objects based on the motion status of the tracked objects.

[0015] The autonomous driving test scenario generation method according to the present invention may further include a step of arranging tracking object data for the filtered and complemented tracking objects.

[0016] According to another aspect of the invention, there is provided an autonomous driving test scenario generation system including an object generation unit that generates a tracking object using tracking object data acquired while an autonomous driving vehicle is running, a complementing unit that discriminates an untracked object and complements an untracked section, a reflecting unit that reflects an untracked factor in the untracked object data, an identifying unit that identifies elements within the operation design range of the autonomous driving test scenario, and a scenario generation unit that generates an autonomous driving test scenario using the identified elements and the untracked object data in which the untracked factor is reflected.

Effects of the Invention

[0017] As described above, according to the present invention, based on data that can be acquired by autonomous driving, by generating a scenario that can test not only judgment and control functions but also cognitive functions, it becomes possible to perform more comprehensive and delicate tests and evaluations on an autonomous driving system that performs dynamic driving tasks.

Brief Description of the Drawings

[0018]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Embodiments for Carrying Out the Invention

[0019] Hereinafter, the present invention will be described in more detail with reference to the drawings.

[0020] In an embodiment of the present invention, an autonomous driving test scenario generation system and method for a data base for testing and evaluating an autonomous driving system are presented.

[0021] Based on the actual data that can be obtained from autonomous driving, by generating a scenario that can test not only judgment and control functions but also cognitive functions, it is a technology that enables more comprehensive and delicate testing and evaluation of an autonomous driving system that performs dynamic driving tasks.

[0022] FIG. 1 is a diagram showing an autonomous driving test scenario generation system according to an embodiment of the present invention. The autonomous driving test scenario generation system according to an embodiment of the present invention includes, as shown in the figure, an autonomous driving DB 110, a tracking object processing unit 120, an untracked factor reflection unit 130, a precise map DB 140, a scenario area identification unit 150, a scenario generation unit 160, and a scenario DB 170.

[0023] The autonomous driving DB 110 is a database in which sensor data, tracking object data, internal / external status data, and weather data collected while an autonomous driving vehicle actually runs are stored.

[0024] The tracking object processing unit 120 generates tracking objects using the tracking object data stored in the autonomous driving DB 110 and performs subsequent necessary processing on them. The detailed configuration of the tracking object processing unit 120 is shown in FIG. 2.

[0025] As shown in the figure, the tracking object processing unit 120 includes a tracking object generation unit 121, a false tracking object filtering unit 122, a non-tracked object completion unit 123, and a tracking object arrangement unit 124.

[0026] The tracking object generation unit 121 generates tracking objects using the tracking object data stored in the autonomous driving DB 110. The attributes of the tracking object data include object classification data, size data, and position data, and do not include data regarding specific shapes, colors, or materials.

[0027] The false tracking object filtering unit 122 discriminates and filters (removes) false tracking objects among the multiple objects generated by the tracking object generation unit 121. The discrimination of false tracking objects is performed based on the motion status of the tracking objects.

[0028] Specifically, it discriminates the states of unreasonable individual tracking objects and the states between unreasonable tracking objects, and removes the tracking objects that are considered to be falsely tracked. In the state of unreasonable individual tracking objects, there are a short maximum tracking time, a realistically unreasonable speed change, etc. In the state between unreasonable tracking objects, there are a continuous collision for a certain period of time, a collision with multiple tracking objects, etc.

[0029] The untracked object completion unit 123 filters the objects through the mis-tracked object filtering 122, discriminates some of the untracked objects among the remaining objects, and completes the untracked intervals. Some of the untracked objects are objects in the situation of tracking → untracked → tracked, such as those whose interval between the end time of tracking and the start time of tracking is less than or equal to a certain time, and 2) the interval between the end point of tracking and the subsequent start point of tracking is less than or equal to a certain distance.

[0030] For such objects, the untracked object completion unit 123 completes / interpolates the untracked intervals to generate tracking object data regarding continuous intervals.

[0031] The tracking object sorting unit 124 collates the tracking object data regarding the tracking objects that have been filtered by the mis-tracked object filtering unit 122 and interpolated by the untracked object completion unit 123.

[0032] Specifically, for the attributes of the tracking object data that have one value, such as size, the tracking object sorting unit 125 selects one value by statistical methods such as the median value or the average value, and collates the tracking object data.

[0033] Returning to FIG. 1 to continue the explanation. The untracked factor reflection unit 130 reflects the untracked factors in the untracked object data and transmits them to the scenario generation unit 160. The detailed configuration of the untracked factor reflection unit 130 is shown in FIG. 3.

[0034] As shown in the figure, the untracked factor reflection unit 130 includes an untracked factor analysis unit 131 and an untracked object data completion unit 132.

[0035] The untracked cause analysis unit 131 analyzes the untracked causes of the untracked objects identified by the untracked object completion unit 123. To do so, the untracked cause analysis unit 131 acquires and analyzes sensor data and the internal status data of the autonomous vehicle at the time when the untracked object becomes untracked from the autonomous driving DB 110.

[0036] Specifically, the untracked cause analysis unit 131 determines whether the untracked cause is any of the sensor performance limits (such as maximum recognition distance, recognition dead angle, etc.), object characteristics (such as object color, reflectivity, etc.), or causes due to other objects (such as blockage).

[0037] The untracked object data completion unit 132 reflects the analyzed untracked causes in the untracked object data. Specifically, if the untracked cause analyzed by the untracked cause analysis unit 131 is an object characteristic (such as object color, reflectivity, etc.), the untracked object data completion unit 132 gives the object color and reflectivity to the tracked object data of the untracked object, reflecting the untracked cause in the untracked object.

[0038] Returning to FIG. 1 to continue the explanation. The precise map DB 140 is a database in which precise map data representing the road in terms of lanes used by the autonomous vehicle during driving is stored.

[0039] The scenario area identification unit 150 identifies elements within the operational design range of the autonomous driving test scenario. The operational design range means the ODD (Operational Design Domain) according to the ISO 34503:2023 standard.

[0040] The detailed configuration of the scenario area identification unit 150 is shown in FIG. 4. As shown in the figure, the scenario area identification unit 150 includes a dynamic element identification unit 151, an environmental element identification unit 152, and a static element identification unit 153.

[0041] The dynamic element identification unit 151 identifies the detailed items of the dynamic elements within the operation design range from the tracking object data grouped by the tracking object organization unit 124.

[0042] The environmental element identification unit 152 identifies the detailed items of the environmental conditions within the operation design range from the weather data in the autonomous driving DB 110.

[0043] The static element identification unit 153 identifies the detailed items of the static area (scenery) within the operation design range from the external status data in the autonomous driving DB 110 and the precise map data in the precise map DB 140.

[0044] Returning to FIG. 1 to continue the explanation. The scenario generation unit 160 generates an autonomous driving test scenario using the dynamic elements, environmental elements, and static elements identified by the scenario area identification unit 150. However, when generating the scenario, for the untracked objects among the dynamic elements, the untracked object data reflected with the untracked factors by the untracked object data completion unit 132 is used.

[0045] The autonomous driving test scenario generated by the scenario generation unit 160 is stored in the scenario DB 170 and utilized for the test and evaluation of the overall dynamic driving tasks including the perception, judgment, and control functions of the autonomous driving system.

[0046] FIGS. 5 and 6 are flowcharts showing an autonomous driving test scenario generation method according to another embodiment of the present invention.

[0047] For generating the autonomous driving test scenario, as shown in FIG. 5, first, sensor data, tracking object data, internal / external status data, weather data, etc., collected while the autonomous driving vehicle is actually driving, are stored in the autonomous driving DB 110 (S210).

[0048] Then, the tracking object generation unit 121 of the tracking object processing unit 120 generates a tracking object using the tracking object data saved in step S210 (S220), and the false tracking object filtering unit 122 discriminates and filters false tracking objects among the objects generated in step S220 (S230).

[0049] Next, the untracked object completion unit 123 discriminates some of the remaining objects after filtering in step S230 as untracked objects and completes the untracked intervals (S240). Then, the tracking object arrangement unit 124 collates the tracking object data for the tracking objects for which the filtering in step S230 and the completion in step S240 have been completed (S250).

[0050] On the other hand, as shown in FIG. 6, the untracked factor analysis unit 131 of the untracked factor reflection unit 130 analyzes the untracked factors of the untracked objects discriminated in step S240 (S260), and the untracked object data completion unit 132 completes the untracked factors of the tracking object data of the untracked objects (S270).

[0051] Then, the scenario area identification unit 150 identifies dynamic elements, environmental elements, and static elements within the operation design range of the autonomous driving test scenario (S280).

[0052] Then, the scenario generation unit 160 generates an autonomous driving test scenario using the dynamic elements, environmental elements, and static elements identified in step S280. For the untracked objects among the dynamic elements, the untracked object data with the untracked factors reflected in step S270 is used (S290).

[0053] Next, the autonomous driving test scenario generated in step S290 is saved in the scenario DB 170 (S295).

[0054] So far, a data-based autonomous driving test scenario generation system and method for testing and evaluating an autonomous driving system have been provided.

[0055] In the above embodiment, by generating a scenario that can test not only judgment and control functions but also cognitive functions based on data that can be obtained from autonomous driving, more comprehensive and delicate data and evaluation can be performed on an autonomous driving system that performs dynamic driving tasks.

[0056] On the other hand, the technical idea of the present invention can also be applied to a computer-readable recording medium incorporating a computer program that causes a computer to perform the functions of the apparatus and method according to the present embodiment. Note that the technical idea according to various embodiments of the present invention may be realized in a computer-readable code format recorded on a computer-readable recording medium. A computer-readable recording medium can be any data storage device that can be read by a computer and store data. For example, a computer-readable recording medium may be a ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical disk, hard disk drive, or the like. Note that a computer-readable code or program stored in a computer-readable recording medium may be transmitted via a network connected between computers.

[0057] As described above, the preferred embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the above embodiments. It is obvious that those having ordinary knowledge in the technical field to which the present invention pertains can conceive of various modification examples or correction examples within the scope of the technical gist described in the claims, and these are naturally understood to belong to the technical scope of the present invention.

Claims

1. generating a tracked object using tracked object data acquired while the autonomous vehicle is traveling; Identifying an untracked object and completing an untracked section; A step of reflecting the non-tracking factor in the non-tracked object data; Identifying elements within an operational design scope of an autonomous driving test scenario; generating an autonomous driving test scenario using the untracked object data reflecting the identified elements and the untracked factors; An autonomous driving test scenario generation method comprising:

2. The identified elements are:

2. The method for generating an autonomous driving test scenario according to claim 1, further comprising: a dynamic element; a static element; and an environmental element.

3. The generating step includes: The autonomous driving test scenario generation method according to claim 2, characterized in that, using the identified elements, for untracked objects among the dynamic elements identified when generating the autonomous driving test scenario, untracked object data reflecting the untracked factors is used.

4. The completion steps are: The autonomous driving test scenario generation method according to claim 1, characterized in that a tracked object is determined to be an untracked object if, after the tracking end point, the interval between the tracking start points is less than a certain time, and the interval between the tracking end point and the subsequent tracking start point is less than a certain distance.

5. The reflection steps are: Analyzing a cause of an untracked object; A step of reflecting the analyzed untracked factor in the untracked object data; 5. The autonomous driving test scenario generation method according to claim 4, further comprising:

6. The reasons for not tracking are: The autonomous driving test scenario generation method according to claim 5, further comprising the step of: determining whether the untracked object is a color or a reflectance of the untracked object;

7. The autonomous driving test scenario generating method according to claim 1 , further comprising: identifying and filtering mistracked objects.

8. The filtering step includes: The autonomous driving test scenario generating method according to claim 7, characterized in that the mistracked object is determined based on the operation status of the tracked object.

9. The autonomous driving test scenario generating method according to claim 7, further comprising the step of organizing the tracking object data for the filtered and completed tracking objects.

10. an object generation unit that generates a tracking object using tracking object data acquired while the autonomous vehicle is traveling; a completion unit that identifies an untracked object and completes an untracked section; a reflection unit for reflecting the untracked cause in the untracked object data; An identification unit that identifies elements within an operational design scope of an autonomous driving test scenario; a scenario generation unit that generates an autonomous driving test scenario using the identified elements and the untracked object data reflecting the untracked factors; An autonomous driving test scenario generation system comprising:

Images