Ramp scene extraction method and device and electronic equipment

Abstract

The present application provides a ramp scene extraction method, device and electronic equipment, comprising: determining all ramp area ranges in a high-precision map; continuously acquiring position information of a current vehicle; determining whether the position information at a first target time meets a preset ramp behavior starting point condition based on the ramp area range; if so, taking the first target time as the starting time of the ramp behavior; determining whether the position information at a second target time meets a preset ramp behavior ending point condition based on the ramp area range; if so, taking the second target time as the ending time of the ramp behavior; and extracting ramp scene data from driving data collected by the current vehicle according to the starting time of the ramp behavior and the ending time of the ramp behavior. The extraction method of the present application can automatically extract ramp scene data of a driving vehicle, saving time and effort, improving efficiency, and the extraction standard is unified, and the extracted ramp scene data is standard enough.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and in particular to a method, apparatus and electronic device for extracting ramp scenes. Background Technology

[0002] The goal of autonomous driving is to enable vehicles to be driven as well as, or even better than, human drivers. Therefore, the first step is to learn how human drivers operate vehicles, which requires a large amount of real-world driving data from human drivers.

[0003] Currently, the primary method for acquiring specific data is through manual annotation. For example, data on on-ramps and off-ramps is extracted from collected driving data by a large number of staff who label the data. This method is not only time-consuming, labor-intensive, and inefficient, but the annotations also vary from person to person, resulting in inconsistent data quality and unsatisfactory performance.

[0004] In summary, existing methods for extracting ramp scenes are time-consuming, labor-intensive, inefficient, and produce inconsistent data. Summary of the Invention

[0005] In view of this, the purpose of the present invention is to provide a method, apparatus and electronic device for extracting ramp scenes, so as to alleviate the technical problems of existing ramp scene extraction methods being time-consuming, labor-intensive, inefficient and producing inconsistent data of the extracted ramp scenes.

[0006] In a first aspect, embodiments of the present invention provide a method for extracting ramp scenes, comprising:

[0007] Determine the range of all ramp areas in the high-precision map, wherein the ramp area range includes: the range of the on-ramp area and the range of the off-ramp area;

[0008] Continuously acquire the current vehicle's location information;

[0009] Based on the range of the ramp area, determine whether the location information at the first target time meets the preset ramp behavior start point condition, wherein the first target time is any time;

[0010] If the location information at the first target time satisfies the preset ramp behavior start point condition, then the first target time is taken as the start time of the ramp behavior.

[0011] Based on the range of the ramp area, determine whether the location information at the second target time satisfies the preset ramp behavior endpoint condition, wherein the second target time is any time after the first target time;

[0012] If the location information at the second target time satisfies the preset ramp behavior endpoint condition, then the second target time is taken as the endpoint time of the ramp behavior.

[0013] Data on the ramp scene is extracted from the driving data collected by the current vehicle based on the start time and end time of the ramp behavior.

[0014] Furthermore, the extent of all ramp areas in the high-precision map is determined, including:

[0015] Obtain the current road in the high-precision map, wherein the current road is any road among all roads in the high-precision map;

[0016] Determine the forward road and the backward road connected to the current road, wherein the forward road is the road located in front of the current road, and the backward road is the road located behind the current road;

[0017] Determine whether the forward road meets the preset on-ramp scenario conditions;

[0018] If the forward road meets the preset on-ramp scenario conditions, then the current road is determined to be an on-ramp scenario. Then, a circle with the intersection of the current road and the target forward road with fewer lanes is taken as the center and the circle with a preset distance as the radius is taken as the on-ramp area. Within the on-ramp area, the current road is the main road and the target forward road is the ramp.

[0019] Determine whether the back road meets the preset off-ramp scenario conditions;

[0020] If the back road meets the preset off-ramp scenario conditions, then the position of the current road is determined to be an off-ramp scenario. Then, a circle with the intersection of the current road and the target back road with fewer lanes in the back road as the center and the preset distance as the radius is defined as the off-ramp area. Within the off-ramp area, the current road is the main road and the target back road is the ramp.

[0021] Further, determining whether the forward road meets the preset on-ramp scenario conditions includes:

[0022] If the number of forward roads is a first preset value, and there is one forward road with a number of lanes not greater than the first preset value and another forward road with a number of lanes not less than the second preset value, then the forward road is determined to meet the preset on-ramp scenario conditions.

[0023] Otherwise, it is determined that the forward road does not meet the preset on-ramp scenario conditions.

[0024] Furthermore, determining whether the rear road meets the preset off-ramp scenario conditions includes:

[0025] If the number of back roads is a first preset value, and there is a back road with a number of lanes not greater than the first preset value and another back road with a number of lanes not less than the second preset value, then the back road is determined to meet the preset off-ramp scenario conditions.

[0026] Otherwise, it is determined that the backward road does not meet the preset off-ramp scenario conditions.

[0027] Furthermore, determining whether the location information at the first target time satisfies the preset ramp behavior start point condition based on the ramp area range includes:

[0028] Based on the location information, determine whether the current vehicle has entered the ramp area;

[0029] If the current vehicle enters the on-ramp area and the lane identifier corresponding to the location information is the same as the ramp identifier in the on-ramp area, then the location information at the first target time satisfies the preset ramp behavior start condition.

[0030] If the current vehicle enters the off-ramp area and the lane identifier corresponding to the location information is the same as the main lane identifier in the off-ramp area, then the location information at the first target time satisfies the preset ramp behavior start condition.

[0031] Furthermore, determining whether the location information at the second target time satisfies the preset ramp behavior endpoint condition based on the ramp area range includes:

[0032] Based on the location information, determine whether the current vehicle has left the ramp area;

[0033] If the current vehicle exits the ramp area and the lane identifier corresponding to the location information is the same as the main lane identifier in the ramp area, then the location information at the second target time satisfies the preset ramp behavior endpoint condition.

[0034] If the current vehicle exits the off-ramp area and the lane identifier corresponding to the location information is the same as the ramp identifier in the off-ramp area, then the location information at the second target time satisfies the preset ramp behavior endpoint condition.

[0035] Furthermore, the method also includes:

[0036] The autonomous driving algorithm for ramp behavior is trained using data from the aforementioned ramp scenario.

[0037] Secondly, embodiments of the present invention also provide a device for extracting ramp scenes, comprising:

[0038] The first determining unit is used to determine the range of all ramp areas in the high-precision map, wherein the range of ramp areas includes: the range of the upper ramp area and the range of the lower ramp area;

[0039] The acquisition unit is used to continuously acquire the current vehicle's location information;

[0040] The second determining unit is used to determine whether the location information at the first target time satisfies the preset ramp behavior start point condition based on the range of the ramp area, wherein the first target time is any time.

[0041] The first setting unit is configured to take the first target time as the start time of the ramp behavior if the location information at the first target time satisfies the preset ramp behavior start condition.

[0042] The third determining unit is used to determine whether the location information at the second target time satisfies the preset ramp behavior endpoint condition based on the range of the ramp area, wherein the second target time is any time after the first target time;

[0043] The second setting unit is used to set the second target time as the end time of the ramp behavior if the location information at the second target time satisfies the preset ramp behavior end condition.

[0044] The extraction unit is used to extract ramp scene data from the driving data collected by the current vehicle based on the start time and end time of the ramp behavior.

[0045] Thirdly, embodiments of the present invention also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method described in any of the first aspects above.

[0046] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing machine-executable instructions, which, when invoked and executed by a processor, cause the processor to perform the method described in any of the first aspects above.

[0047] In this embodiment of the invention, a method for extracting ramp scenes is provided, comprising: determining the range of all ramp areas in a high-precision map, wherein the ramp area range includes: an upper ramp area range and an lower ramp area range; continuously acquiring the current vehicle's location information; determining whether the location information at a first target time satisfies a preset ramp behavior start condition based on the ramp area range, wherein the first target time is any time; if the location information at the first target time satisfies the preset ramp behavior start condition, then the first target time is taken as the start time of the ramp behavior; determining whether the location information at a second target time satisfies a preset ramp behavior end condition based on the ramp area range, wherein the second target time is any time after the first target time; if the location information at the second target time satisfies the preset ramp behavior end condition, then the second target time is taken as the end time of the ramp behavior; and extracting ramp scene data from the driving data collected by the current vehicle based on the start time and end time of the ramp behavior. As described above, the ramp scene extraction method of the present invention can automatically extract ramp scene data of driving vehicles, saving time and effort and improving efficiency. In addition, it is extracted based on preset ramp behavior start conditions and preset ramp behavior end conditions, with unified extraction standards. As a result, the extracted ramp scene data is sufficiently standardized, alleviating the technical problems of existing ramp scene extraction methods being time-consuming, labor-intensive, inefficient, and producing inconsistent ramp scene data. Attached Figure Description

[0048] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0049] Figure 1 A flowchart illustrating a method for extracting a ramp scene according to an embodiment of the present invention;

[0050] Figure 2 A schematic diagram of the ramp area provided in an embodiment of the present invention;

[0051] Figure 3 A flowchart for determining the range of all ramp areas in a high-precision map provided in an embodiment of the present invention;

[0052] Figure 4 A schematic diagram of a ramp scene extraction device provided in an embodiment of the present invention;

[0053] Figure 5 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0054] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0055] Traditional solutions for acquiring data in ramp scenarios typically involve a large number of staff extracting data from collected driving data by labeling it. This process is time-consuming, labor-intensive, inefficient, and the labeling varies from person to person, resulting in inconsistent data quality and poor usability.

[0056] Based on this, the ramp scene extraction method of the present invention can automatically extract ramp scene data of driving vehicles, saving time and effort and improving efficiency. In addition, it is extracted based on preset ramp behavior start conditions and preset ramp behavior end conditions, with unified extraction standards, and thus the extracted ramp scene data is sufficiently standardized.

[0057] To facilitate understanding of this embodiment, a method for extracting ramp scenes disclosed in this embodiment of the invention will first be described in detail.

[0058] Example 1:

[0059] According to an embodiment of the present invention, an embodiment of a method for extracting a ramp scene is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0060] Figure 1 This is a flowchart of a method for extracting a ramp scene according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0061] Step S102: Determine the range of all ramp areas in the high-precision map, wherein the ramp area range includes: the range of the on-ramp area and the range of the off-ramp area;

[0062] In an optional embodiment of the present invention, the above-described ramp scene extraction method can be applied to the current vehicle. By analyzing a high-precision map, the range of all ramp areas can be determined. The ramp area range includes: the area of ​​the upper ramp and the area of ​​the lower ramp, such as... Figure 2 As shown, a schematic diagram of the ramp area is presented. Figure 2In terms of the lanes in the middle, the lanes marked with numbers on the right are in the direction from 184 to 187. That is, when vehicles travel in the middle, they travel in the direction from 184 to 187 (determined based on the principle that vehicles travel on the right).

[0063] It should be noted that the so-called on-ramp refers to the process of vehicles merging from the ramp into the main road, while the so-called off-ramp refers to the process of vehicles entering the ramp from the main road.

[0064] Step S104: Continuously acquire the current vehicle's location information;

[0065] Specifically, the current vehicle's location information can be continuously obtained through the positioning module, which can be achieved through onboard sensors installed on the vehicle.

[0066] Step S106: Determine whether the location information of the first target time meets the preset ramp behavior start point condition based on the ramp area range; wherein, the first target time is any time.

[0067] The process will be described in detail below, and will not be repeated here.

[0068] Step S108: If the location information of the first target time satisfies the preset ramp behavior start point condition, then the first target time is taken as the start time of the ramp behavior.

[0069] Step S110: Determine whether the location information of the second target time meets the preset ramp behavior endpoint condition based on the ramp area range, wherein the second target time is any time after the first target time;

[0070] The process will be described in detail below, and will not be repeated here.

[0071] Step S112: If the location information of the second target time satisfies the preset ramp behavior endpoint condition, then the second target time is taken as the endpoint time of the ramp behavior.

[0072] Step S114: Extract ramp scene data from the driving data collected by the current vehicle based on the start time and end time of the ramp behavior.

[0073] Specifically, in the driving data collected by the vehicle, the data between the start time and the end time of the ramp behavior within the same on-ramp or off-ramp area is considered as ramp scene data.

[0074] In this embodiment of the invention, a method for extracting ramp scenes is provided, comprising: determining the range of all ramp areas in a high-precision map, wherein the ramp area range includes: an upper ramp area range and an lower ramp area range; continuously acquiring the current vehicle's location information; determining whether the location information at a first target time satisfies a preset ramp behavior start condition based on the ramp area range, wherein the first target time is any time; if the location information at the first target time satisfies the preset ramp behavior start condition, then the first target time is taken as the start time of the ramp behavior; determining whether the location information at a second target time satisfies a preset ramp behavior end condition based on the ramp area range, wherein the second target time is any time after the first target time; if the location information at the second target time satisfies the preset ramp behavior end condition, then the second target time is taken as the end time of the ramp behavior; and extracting ramp scene data from the driving data collected by the current vehicle based on the start time and end time of the ramp behavior. As described above, the ramp scene extraction method of the present invention can automatically extract ramp scene data of driving vehicles, saving time and effort and improving efficiency. In addition, it is extracted based on preset ramp behavior start conditions and preset ramp behavior end conditions, with unified extraction standards. As a result, the extracted ramp scene data is sufficiently standardized, alleviating the technical problems of existing ramp scene extraction methods being time-consuming, labor-intensive, inefficient, and producing inconsistent ramp scene data.

[0075] The above provides a brief overview of the method for extracting ramp scenes according to the present invention. The specific details involved are described in detail below.

[0076] In an alternative embodiment of the present invention, reference is made to... Figure 3 Determining the extent of all ramp areas in the high-precision map involves the following steps:

[0077] Step S301: Obtain the current road in the high-precision map, where the current road is any road among all roads in the high-precision map;

[0078] Step S302: Determine the forward road and the backward road connected to the current road, wherein the forward road is the road located in front of the current road, and the backward road is the road located behind the current road;

[0079] Specifically, the forward and backward roads connected to the current road are determined through the general interface of the high-precision map, such as... Figure 2As shown, if the current road is at position 186, then the forward road connected to road 186 can be determined to be 185 (for road 186, road 185 is the road that has already been traveled, that is, the road that has already been traveled in front of it, because the road direction is from 184 to 187), and the backward road connected to road 186 is 187 (for road 186, road 187 is the road that will be traveled, that is, the road that will be traveled behind it, because the road direction is from 184 to 187).

[0080] For Route 184, its following roads are 185 and 188; for Route 190, its forward roads are 187 and 189.

[0081] Step S303: Determine whether the forward road meets the preset on-ramp scenario conditions;

[0082] Specifically, if the number of forward roads is the first preset value, and one forward road has a number of lanes not greater than the first preset value, and another forward road has a number of lanes not less than the second preset value, then the forward roads meet the preset on-ramp scenario conditions; otherwise, the forward roads do not meet the preset on-ramp scenario conditions.

[0083] The first preset value can be 2, and the second preset value can be 3. If the number of forward roads is 2, and one forward road has no more than 2 lanes while the other forward road has no less than 3 lanes, then the forward roads meet the preset on-ramp scenario conditions. Otherwise, the forward roads do not meet the preset on-ramp scenario conditions.

[0084] For example, for road 190, its forward roads are 187 and 189, which means there are 2 forward roads. Among the forward roads, there is one forward road 189 with no more than 2 lanes (only 189_1 and 189_2), and the other forward road 187 with no less than 3 lanes (187_1, 187_2, 187_3 and 187_4). Then it is determined that forward roads 187 and 189 meet the preset on-ramp scenario conditions.

[0085] Step S304: If the forward road meets the preset on-ramp scenario conditions, the current road position is determined to be an on-ramp scenario. Then, a circle with the intersection of the current road and the target forward road with fewer lanes is taken as the center and the preset distance is taken as the on-ramp area. Within the on-ramp area, the current road is the main road and the target forward road is the ramp.

[0086] As in the example above, if forward roads 187 and 189 meet the preset on-ramp scenario conditions, then the position of the current road 190 is determined as the on-ramp scenario. Then, a circle with the center of the junction between the current road 190 and the target forward road 189 with fewer lanes is taken as the center and the circle with a preset distance (which can be 50 meters, and this value can be configured by the user) as the on-ramp area is defined. The identifiers of the current road (main road) 190 and the target forward road (ramp) 189 are recorded in the circle for the next step of automatic extraction of the ramp scenario.

[0087] Step S305: Determine whether the following road meets the preset off-ramp scenario conditions;

[0088] Specifically, if the number of back roads is the first preset value, and there is one back road with a number of lanes not greater than the first preset value and another back road with a number of lanes not less than the second preset value, then the back road is determined to meet the preset off-ramp scenario conditions; otherwise, the back road is determined not to meet the preset off-ramp scenario conditions.

[0089] The first preset value can be 2, and the second preset value can be 3. If the number of back roads is 2, and one back road has no more than 2 lanes while the other has no less than 3 lanes, then the back road meets the preset off-ramp scenario conditions. Otherwise, the back road does not meet the preset off-ramp scenario conditions.

[0090] For example, for road 184, its downstream roads are 185 and 188, which means there are 2 downstream roads. Among the downstream roads, there is one downstream road 188 with no more than 2 lanes (only 188_1 and 188_2), and the other downstream road 185 with no less than 3 lanes (185_1, 185_2, 185_3 and 185_4). Then it is determined that downstream roads 185 and 188 meet the preset off-ramp scenario conditions.

[0091] Step S306: If the back road meets the preset off-ramp scenario conditions, the current road is determined to be the off-ramp scenario. Then, the off-ramp area is defined as the circle centered at the junction of the current road and the target back road with fewer lanes, with a preset distance as the radius. Within the off-ramp area, the current road is the main road and the target back road is the ramp.

[0092] As in the example above, if the following roads 185 and 188 meet the preset off-ramp scenario conditions, then the position of the current road 184 is determined as the off-ramp scenario. Then, the off-ramp area is defined as the circle with the center of the intersection between the current road 184 and the target following road 188 (which has fewer lanes) as the center and a preset distance (which can be 50 meters, and this value can be configured by the user) as the center. The identifiers of the current road (main road) 184 and the target following road (ramp) 188 are recorded in the circle for the next step of automatic extraction of the off-ramp scenario.

[0093] In an optional embodiment of the present invention, determining whether the location information at the first target time satisfies the preset ramp behavior start-up condition based on the ramp area range specifically includes the following steps:

[0094] (1) Determine whether the current vehicle has entered the ramp area based on location information;

[0095] Specifically, the distance between the aforementioned location information and the center of the specific ramp area can be calculated, and the calculated distance can be compared with the radius of the ramp area to determine whether the vehicle has entered the ramp area. For example, if the initially calculated distance is greater than the radius of the ramp area, it means that the vehicle is outside the ramp area. If at a later moment the calculated distance is equal to the radius of the ramp area, it means that the vehicle is on the boundary of the ramp area. If the calculated distance is less than the radius of the ramp area after that, it means that the vehicle has completely entered the ramp area. The location information corresponding to the distance equal to the radius of the ramp area is then used as the marker that the vehicle has entered the ramp area.

[0096] (2) If the current vehicle enters the ramp area and the lane identifier corresponding to the location information is the same as the ramp identifier in the ramp area, then the location information at the first target time satisfies the preset ramp behavior start condition.

[0097] Specifically, if the current vehicle enters Figure 2 Within the on-ramp area, by inputting the aforementioned location information into the general interface of a high-precision map, the lane identifier corresponding to that location information can be obtained. If the lane identifier corresponding to the location information is 189, then this 189 identifier is... Figure 2 If the ramps in the on-ramp area have the same identifier (indicating that the current vehicle is in the on-ramp), then the location information of the first target moment satisfies the preset ramp behavior starting point condition.

[0098] (3) If the current vehicle enters the off-ramp area and the lane markings corresponding to the location information are the same as the markings of the main lanes in the off-ramp area, then the location information at the first target time satisfies the preset off-ramp behavior start point condition.

[0099] Specifically, if the current vehicle enters Figure 2 Within the off-ramp area, by inputting the aforementioned location information into the general interface of a high-precision map, the lane identifier corresponding to that location information can be obtained. If the lane identifier corresponding to the location information is 184, then this 184 identifier is... Figure 2 If the markers on the main road within the off-ramp area are the same (indicating that the vehicle is currently on the main road but has not yet reached the ramp entrance), then the location information at the first target moment is determined to meet the preset ramp behavior start point condition.

[0100] In an optional embodiment of the present invention, determining whether the location information of the second target time satisfies the preset ramp behavior endpoint condition based on the ramp area range specifically includes the following steps:

[0101] (1) Determine whether the current vehicle has left the ramp area based on location information;

[0102] Specifically, the distance between the aforementioned location information and the center of the specific ramp area can be calculated, and the calculated distance can be compared with the radius of the ramp area to determine whether the vehicle has left the ramp area. For example, if the initially calculated distance is less than the radius of the ramp area, it means that the vehicle is within the ramp area. If at some point the calculated distance is equal to the radius of the ramp area, it means that the vehicle is on the boundary of the ramp area. If the calculated distance is greater than the radius of the ramp area after that, it means that the vehicle is outside the ramp area. The location information corresponding to the distance equal to the radius of the ramp area is then used as the marker that the vehicle has left the ramp area.

[0103] (2) If the current vehicle leaves the ramp area and the lane identifier corresponding to the location information is the same as the main lane identifier in the ramp area, then the location information at the second target time satisfies the preset ramp behavior endpoint condition.

[0104] Specifically, if the current vehicle leaves Figure 2 Within the on-ramp area, by inputting the aforementioned location information into the general interface of a high-precision map, the lane identifier corresponding to that location information can be obtained. If the lane identifier corresponding to the location information is 190, this 190 identifier is... Figure 2If the main road markers within the on-ramp area are identical (indicating that the current vehicle has passed the on-ramp and entered the main road), then the location information at the second target time satisfies the preset ramp behavior endpoint condition.

[0105] By observing the process from when the vehicle enters the ramp area to when it exits the ramp area, we can see that the vehicle travels from 189 to 190. The moment when the vehicle enters the ramp area and is at the same position as the 189 marker is taken as the start time of the ramp behavior, and the moment when the vehicle enters the ramp area and is at the same position as the 189 marker is taken as the end time of the ramp behavior. In this way, we obtain a complete process of the start and end of the ramp behavior.

[0106] (3) If the current vehicle exits the off-ramp area and the lane identifier corresponding to the location information is the same as the ramp identifier in the off-ramp area, then the location information at the second target time satisfies the preset ramp behavior endpoint condition.

[0107] Specifically, if the current vehicle enters Figure 2 Within the off-ramp area, by inputting the aforementioned location information into the general interface of a high-precision map, the lane identifier corresponding to that location information can be obtained. If the lane identifier corresponding to this location information is 188, then this 188 identifier is... Figure 2 If the ramps in the off-ramp area are identified by the same identifier (indicating that the current vehicle is leaving from the main road via the off-ramp), then the location information of the second target time satisfies the preset ramp behavior endpoint condition.

[0108] From the process described above, from the current vehicle entering the off-ramp area to the current vehicle exiting the off-ramp area, we know that the current vehicle traveled from 184 to 188. Finally, the time corresponding to the position of entering the off-ramp area and being the same as the 184 marker is taken as the start time of the ramp behavior, and the time corresponding to the position of entering the off-ramp area and being the same as the 188 marker is taken as the end time of the ramp behavior. In this way, we obtain another complete process of the start and end of the ramp behavior. Only by successfully recording the start time of entering the ramp area and the end time of exiting the ramp area can we have a complete ramp behavior record, which can be used to extract subsequent ramp scene data. Using the start time (T1) and end time (T2) as the start and end times, we can complete the automatic tagging of the ramp scene.

[0109] In an optional embodiment of the present invention, the method further includes:

[0110] The autonomous driving algorithm for ramp behavior is trained using data from ramp scenarios.

[0111] The ramp scene extraction method of the present invention can be deployed on the current vehicle and automatically annotate the ramp scene in parallel during the driving process of the current vehicle, without the need for subsequent manual annotation; it transforms manual operation into automated ramp scene extraction, improving efficiency and reducing human and material costs; the ramp scene extraction standard is uniform, while manual annotation results in inconsistent ramp scene extraction standards due to individual differences among annotators.

[0112] Example 2:

[0113] This invention also provides a ramp scene extraction device, which is mainly used to execute the ramp scene extraction method provided in Embodiment 1 of this invention. The following is a detailed description of the ramp scene extraction device provided in this invention.

[0114] Figure 4 This is a schematic diagram of a ramp scene extraction device according to an embodiment of the present invention, such as... Figure 3 As shown, the device mainly includes: a first determining unit 10, an acquiring unit 20, a second determining unit 30, a first setting unit 40, a third determining unit 50, a second setting unit 60, and an extraction unit 70, wherein:

[0115] The first determining unit is used to determine the range of all ramp areas in the high-precision map, wherein the ramp area range includes: the range of the upper ramp area and the range of the lower ramp area;

[0116] The acquisition unit is used to continuously acquire the current vehicle's location information;

[0117] The second determining unit is used to determine whether the location information of the first target time meets the preset ramp behavior start point condition based on the range of the ramp area; wherein the first target time is any time.

[0118] The first setting unit is used to set the first target time as the start time of the ramp behavior if the location information of the first target time meets the preset ramp behavior start condition.

[0119] The third determining unit is used to determine whether the location information of the second target time meets the preset ramp behavior endpoint condition based on the range of the ramp area, wherein the second target time is any time after the first target time;

[0120] The second setting unit is used to set the second target time as the end time of the ramp behavior if the location information of the second target time meets the preset ramp behavior end condition.

[0121] The extraction unit is used to extract ramp scene data from the driving data collected by the current vehicle based on the start time and end time of the ramp behavior.

[0122] In this embodiment of the invention, a device for extracting ramp scenes is provided, comprising: determining the range of all ramp areas in a high-precision map, wherein the ramp area range includes an upper ramp area range and an lower ramp area range; continuously acquiring the current vehicle's location information; determining whether the location information at a first target time satisfies a preset ramp behavior start condition based on the ramp area range, wherein the first target time is any time; if the location information at the first target time satisfies the preset ramp behavior start condition, then the first target time is taken as the start time of the ramp behavior; determining whether the location information at a second target time satisfies a preset ramp behavior end condition based on the ramp area range, wherein the second target time is any time after the first target time; if the location information at the second target time satisfies the preset ramp behavior end condition, then the second target time is taken as the end time of the ramp behavior; and extracting ramp scene data from the driving data collected by the current vehicle based on the start time and end time of the ramp behavior. As described above, the ramp scene extraction device of the present invention can automatically extract ramp scene data of driving vehicles, saving time and effort and improving efficiency. In addition, it is extracted based on preset ramp behavior start conditions and preset ramp behavior end conditions, with uniform extraction standards. As a result, the extracted ramp scene data is sufficiently standardized, alleviating the technical problems of existing ramp scene extraction methods being time-consuming, labor-intensive, inefficient, and producing inconsistent ramp scene data.

[0123] Optionally, the first determining unit is further configured to: obtain the current road in the high-precision map, wherein the current road is any road among all roads traversed in the high-precision map; determine the forward road and the backward road connected to the current road, wherein the forward road is the road located in front of the current road, and the backward road is the road located behind the current road; determine whether the forward road meets the preset on-ramp scenario conditions; if the forward road meets the preset on-ramp scenario conditions, then determine the position of the current road as an on-ramp scenario, and then determine the junction between the current road and the target forward road with fewer lanes in the forward road. The area defined by the current road and the target road is the ramp area, with the current road as the center and a preset distance as the radius. Within the ramp area, the current road is the main road and the target road ahead is the ramp. The system then determines whether the following road meets the preset exit ramp scenario conditions. If the following road meets the preset exit ramp scenario conditions, the current road is determined to be the exit ramp scenario. The area defined by the intersection of the current road and the target road behind (which has fewer lanes) is then defined as the exit ramp area, with the preset distance as the center. Within the exit ramp area, the current road is the main road and the target road behind is the ramp.

[0124] Optionally, the first determining unit is further configured to: if the number of forward roads is a first preset value, and there is a forward road with a number of lanes not greater than the first preset value and another forward road with a number of lanes not less than the second preset value, then determine that the forward road meets the preset on-ramp scenario conditions; otherwise, determine that the forward road does not meet the preset on-ramp scenario conditions.

[0125] Optionally, the first determining unit is further configured to: if the number of back roads is a first preset value, and there is a back road with a number of lanes not greater than the first preset value and another back road with a number of lanes not less than the second preset value, then determine that the back road meets the preset off-ramp scenario conditions; otherwise, determine that the back road does not meet the preset off-ramp scenario conditions.

[0126] Optionally, the second determining unit is further configured to: determine whether the current vehicle has entered the ramp area based on the location information; if the current vehicle has entered the ramp area and the lane identifier corresponding to the location information is the same as the ramp identifier in the ramp area, then determine that the location information at the first target time satisfies the preset ramp behavior start condition; if the current vehicle has entered the ramp area and the lane identifier corresponding to the location information is the same as the main lane identifier in the ramp area, then determine that the location information at the first target time satisfies the preset ramp behavior start condition.

[0127] Optionally, the third determining unit is further configured to: determine whether the current vehicle has exited the ramp area based on the location information; if the current vehicle has exited the ramp area and the lane identifier corresponding to the location information is the same as the main lane identifier in the ramp area, then determine that the location information at the second target time satisfies the preset ramp behavior endpoint condition; if the current vehicle has exited the off-ramp area and the lane identifier corresponding to the location information is the same as the ramp identifier in the off-ramp area, then determine that the location information at the second target time satisfies the preset ramp behavior endpoint condition.

[0128] Optionally, the device is also used to: train an autonomous driving algorithm for ramp behavior using data from ramp scenarios.

[0129] The device provided in this embodiment of the invention has the same implementation principle and technical effect as the aforementioned method embodiment. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the aforementioned method embodiment.

[0130] like Figure 5As shown in the embodiment of this application, an electronic device 600 includes a processor 601, a memory 602, and a bus. The memory 602 stores machine-readable instructions that can be executed by the processor 601. When the electronic device is running, the processor 601 communicates with the memory 602 via the bus, and the processor 601 executes the machine-readable instructions to perform the steps of the extraction method for the ramp scene described above.

[0131] Specifically, the memory 602 and processor 601 mentioned above can be general-purpose memory and processor, without any specific limitations. When the processor 601 runs the computer program stored in the memory 602, it can execute the above-mentioned method for extracting the ramp scene.

[0132] The processor 601 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of the processor 601 or by instructions in software form. The processor 601 may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory 602, and processor 601 reads the information from memory 602 and, in conjunction with its hardware, completes the steps of the above method.

[0133] Corresponding to the above-described method for extracting ramp scenarios, this application also provides a computer-readable storage medium storing machine-executable instructions. When these machine-executable instructions are invoked and executed by a processor, they cause the processor to perform the steps of the above-described method for extracting ramp scenarios.

[0134] The ramp scene extraction device provided in this application embodiment can be specific hardware on a device or software or firmware installed on the device. The implementation principle and technical effects of the device provided in this application embodiment are the same as those in the foregoing method embodiments. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the foregoing method embodiments. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can all be referred to the corresponding processes in the above method embodiments, and will not be repeated here.

[0135] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0136] For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0137] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0138] In addition, the functional units in the embodiments provided in this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0139] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause an electronic device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the vehicle marking method described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0140] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0141] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The protection scope of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this application; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application. All should be covered within the protection scope of this application. Therefore, the protection scope of this application should be determined by the protection scope of the claims.

Claims

1. A method for extracting ramp scenes, characterized in that, include: Determine the range of all ramp areas in the high-precision map, wherein the ramp area range includes: the range of the on-ramp area and the range of the off-ramp area; Continuously acquire the current vehicle's location information; Based on the range of the ramp area, determine whether the location information at the first target time meets the preset ramp behavior start point condition, wherein the first target time is any time; If the location information at the first target time satisfies the preset ramp behavior start point condition, then the first target time is taken as the start time of the ramp behavior. Based on the range of the ramp area, determine whether the location information at the second target time satisfies the preset ramp behavior endpoint condition, wherein the second target time is any time after the first target time; If the location information at the second target time satisfies the preset ramp behavior endpoint condition, then the second target time is taken as the endpoint time of the ramp behavior. Data on the ramp scene is extracted from the driving data collected by the current vehicle based on the start time and end time of the ramp behavior. The determination of whether the location information at the first target time satisfies the preset ramp behavior start point condition based on the ramp area range includes: Based on the location information, determine whether the current vehicle has entered the ramp area; If the current vehicle enters the on-ramp area and the lane identifier corresponding to the location information is the same as the ramp identifier in the on-ramp area, then the location information at the first target time satisfies the preset ramp behavior start condition. If the current vehicle enters the off-ramp area and the lane identifier corresponding to the location information is the same as the main lane identifier in the off-ramp area, then the location information at the first target time satisfies the preset ramp behavior start condition. The determination of whether the location information at the second target time satisfies the preset ramp behavior endpoint condition based on the ramp area range includes: Based on the location information, determine whether the current vehicle has left the ramp area; If the current vehicle exits the ramp area and the lane identifier corresponding to the location information is the same as the main lane identifier in the ramp area, then the location information at the second target time satisfies the preset ramp behavior endpoint condition. If the current vehicle exits the off-ramp area and the lane identifier corresponding to the location information is the same as the ramp identifier in the off-ramp area, then the location information at the second target time satisfies the preset ramp behavior endpoint condition.

2. The method according to claim 1, characterized in that, Determine the extent of all ramp areas in the high-precision map, including: Obtain the current road in the high-precision map, wherein the current road is any road among all roads in the high-precision map; Determine the forward road and the backward road connected to the current road, wherein the forward road is the road located in front of the current road, and the backward road is the road located behind the current road; Determine whether the forward road meets the preset on-ramp scenario conditions; If the forward road meets the preset on-ramp scenario conditions, then the current road is determined to be an on-ramp scenario. Then, a circle with the intersection of the current road and the target forward road with fewer lanes is taken as the center and the circle with a preset distance as the radius is taken as the on-ramp area. Within the on-ramp area, the current road is the main road and the target forward road is the ramp. Determine whether the back road meets the preset off-ramp scenario conditions; If the back road meets the preset off-ramp scenario conditions, then the position of the current road is determined to be an off-ramp scenario. Then, a circle with the intersection of the current road and the target back road with fewer lanes in the back road as the center and the preset distance as the radius is defined as the off-ramp area. Within the off-ramp area, the current road is the main road and the target back road is the ramp.

3. The method according to claim 2, characterized in that, Determining whether the forward road meets the preset on-ramp scenario conditions includes: If the number of forward roads is a first preset value, and there is one forward road with a number of lanes not greater than the first preset value and another forward road with a number of lanes not less than the second preset value, then the forward road is determined to meet the preset on-ramp scenario conditions. Otherwise, it is determined that the forward road does not meet the preset on-ramp scenario conditions.

4. The method according to claim 2, characterized in that, Determining whether the following road meets the preset off-ramp scenario conditions includes: If the number of back roads is a first preset value, and there is a back road with a number of lanes not greater than the first preset value and another back road with a number of lanes not less than the second preset value, then the back road is determined to meet the preset off-ramp scenario conditions. Otherwise, it is determined that the backward road does not meet the preset off-ramp scenario conditions.

5. The method according to claim 1, characterized in that, The method further includes: The autonomous driving algorithm for ramp behavior is trained using data from the aforementioned ramp scenario.

6. A device for extracting ramp scenes, characterized in that, include: The first determining unit is used to determine the range of all ramp areas in the high-precision map, wherein the range of ramp areas includes: the range of the upper ramp area and the range of the lower ramp area; The acquisition unit is used to continuously acquire the current vehicle's location information; The second determining unit is used to determine whether the location information at the first target time satisfies the preset ramp behavior start point condition based on the range of the ramp area, wherein the first target time is any time. The first setting unit is configured to take the first target time as the start time of the ramp behavior if the location information at the first target time satisfies the preset ramp behavior start condition. The third determining unit is used to determine whether the location information at the second target time satisfies the preset ramp behavior endpoint condition based on the range of the ramp area, wherein the second target time is any time after the first target time; The second setting unit is used to set the second target time as the end time of the ramp behavior if the location information at the second target time satisfies the preset ramp behavior end condition. The extraction unit is used to extract ramp scene data from the driving data collected by the current vehicle based on the start time and end time of the ramp behavior. The second determining unit is further configured to: determine whether the current vehicle has entered the ramp area based on the location information; if the current vehicle enters the upper ramp area and the lane identifier corresponding to the location information is the same as the ramp identifier in the upper ramp area, then determine that the location information at the first target time satisfies the preset ramp behavior start condition; if the current vehicle enters the lower ramp area and the lane identifier corresponding to the location information is the same as the main road identifier in the lower ramp area, then determine that the location information at the first target time satisfies the preset ramp behavior start condition. The third determining unit is further configured to: determine whether the current vehicle has exited the ramp area based on the location information; if the current vehicle has exited the upper ramp area and the lane identifier corresponding to the location information is the same as the main lane identifier in the upper ramp area, then determine that the location information at the second target time satisfies the preset ramp behavior endpoint condition; if the current vehicle has exited the lower ramp area and the lane identifier corresponding to the location information is the same as the ramp identifier in the lower ramp area, then determine that the location information at the second target time satisfies the preset ramp behavior endpoint condition.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores machine-executable instructions that, when invoked and executed by a processor, cause the processor to perform the method according to any one of claims 1 to 5.

Images