Trajectory point screening and trajectory generation method, device, electronic device, and storage medium

Abstract

The embodiments of the present disclosure disclose a method, device, equipment, and storage medium for trajectory point screening and trajectory generation. The trajectory point screening method includes: obtaining M trajectory points of a real driving trajectory; obtaining the current key trajectory point from the M trajectory points, and determining the current basic slope based on the current key trajectory point; when the current trajectory point is not the Mth trajectory point, based on the current basic slope, the slope between the previous trajectory point and the current trajectory point in the M trajectory points, and the slope between the key trajectory point and the current trajectory point, determining the next key trajectory point and the next basic slope from the M trajectory points, until all the trajectory points to be screened in the M trajectory points are traversed, and N‑1 key trajectory points are obtained; the N‑1 key trajectory points and the Mth trajectory point are used to generate a simulated trajectory. Through the present disclosure, important key trajectory points can be screened out for use in generating accurate simulated trajectories, while reducing the amount of data transmitted to the cloud platform.

Description

Technical Field

[0001] The present disclosure relates to vehicle networking technology, and in particular to a method, device, electronic device, and storage medium for selecting and generating trajectory points. Background Art

[0002] The Internet of Vehicles (IoV), based on in-vehicle networks, inter-vehicle networks, and in-vehicle mobile internet, implements wireless communication and information exchange according to a defined architecture, communication protocols, and data exchange standards. It is an extension of the Internet of Things (IoT) within the field of intelligent transportation systems. Vehicle-to-Everything (V2X) wireless communication, a key information exchange technology for the IoV network, primarily enables information communication and coordinated control between vehicles and IoV cloud platforms, as well as between vehicles, roads, and people. Currently, it is primarily used for information communication between IoV cloud platforms and between vehicles and roads.

[0003] Vehicles need to collect information such as vehicle conditions and road conditions, and report them to the Internet of Vehicles cloud platform (hereinafter referred to as the "cloud platform") through the communication information interaction function of the on-board unit (OBU). The on-board unit is connected to the cloud platform through mobile network access capabilities.

[0004] Currently, due to bandwidth and cost limitations of mobile networks, it is necessary to minimize the amount of data uploaded while maintaining the upload of necessary information. The vehicle's trajectory is information that must be uploaded, but the amount of data is often very large; therefore, this type of data needs to be streamlined and compressed.

[0005] Currently, intelligent vehicles generally use high-precision maps. To accurately calculate the vehicle's route, the resulting trajectory data is often very large. For example, a route of approximately two kilometers can generate over several megabytes (MBytes) of data, or even more. However, due to network bandwidth and network costs, such large amounts of data can place a burden on cloud platforms for receiving, storing, processing, and displaying data on the front end. Summary of the Invention

[0006] The embodiments of the present disclosure provide a trajectory point screening and trajectory generation method, apparatus, electronic device, and storage medium, which can screen out important key trajectory points for generating accurate simulated trajectories while reducing the amount of data transmitted to the cloud platform. A trajectory generation method is also provided, which can improve the efficiency of generating simulated trajectories.

[0007] The technical solution of the embodiment of the present disclosure is implemented as follows:

[0008] The present disclosure provides a trajectory point screening method, including:

[0009] Obtain M trajectory points of the actual driving trajectory; M is an integer greater than 2;

[0010] Obtaining a current key trajectory point from the M trajectory points, and determining a current basic slope based on the current key trajectory point;

[0011] When the current trajectory point is not the Mth trajectory point, based on the current basic slope, the slope between the previous trajectory point and the current trajectory point among the M trajectory points, and the slope between the key trajectory point and the current trajectory point, the next key trajectory point and the next basic slope are determined from the M trajectory points, until all the trajectory points to be screened among the M trajectory points are traversed, and N-1 key trajectory points are obtained; N is an integer less than M; the N-1 key trajectory points are combined with the Mth trajectory point to generate a simulated trajectory corresponding to the real driving trajectory.

[0012] The present disclosure provides a trajectory generation method, including:

[0013] Obtain the original data corresponding to the actual driving trajectory;

[0014] Performing key trajectory point screening on the original data to obtain screened data;

[0015] The filtered data is sent to a cloud platform; the cloud platform is used to perform trajectory simulation on the filtered data to obtain a simulated trajectory.

[0016] The present disclosure provides a trajectory point screening device, comprising:

[0017] A first acquiring unit is configured to acquire M trajectory points of a real driving trajectory, where M is an integer greater than 2;

[0018] a first determining unit, configured to obtain a current key trajectory point from the M trajectory points, and determine a current basic slope based on the current key trajectory point;

[0019] The first screening unit is configured to, when the current trajectory point is not the Mth trajectory point, determine a next key trajectory point and a next basic slope from the M trajectory points based on the current basic slope, the slope between a previous trajectory point and the current trajectory point among the M trajectory points, and the slope between the key trajectory point and the current trajectory point, until all trajectory points to be screened among the M trajectory points are traversed, thereby obtaining N-1 key trajectory points; N is an integer less than M; and the N-1 key trajectory points are combined with the Mth trajectory point to generate a simulated trajectory corresponding to the actual driving trajectory.

[0020] The present disclosure provides a trajectory generation device, comprising:

[0021] A second acquisition unit is used to acquire raw data corresponding to the actual driving trajectory;

[0022] A second screening unit is used to screen the original data for key trajectory points to obtain screened data;

[0023] The second sending unit is used to send the filtered data to a cloud platform; the cloud platform is used to perform trajectory simulation on the filtered data to obtain a simulated trajectory.

[0024] An embodiment of the present disclosure provides an electronic device, including: a memory for storing an executable computer program; and a processor for implementing the above-mentioned trajectory point screening method or trajectory generation method when executing the executable computer program stored in the memory.

[0025] An embodiment of the present disclosure provides a computer-readable storage medium storing a computer program for causing a processor to execute the above-mentioned trajectory point screening method or trajectory generation method.

[0026] The technical solutions provided by the embodiments of the present disclosure have the following technical effects:

[0027] The trajectory point screening method provided by the embodiments of the present disclosure screens out trajectory points from the original trajectory points corresponding to the real trajectory. Therefore, the data volume of the screened trajectory points is smaller than that of the original trajectory points, thereby reducing the efficiency of transmitting or processing the trajectory points compared to transmitting or processing the original trajectory points. At the same time, since key trajectory points are screened out from the original trajectory points based on the slopes between the trajectory points, the screened key trajectory points are all important trajectory points in the original trajectory points. Therefore, the simulated trajectory subsequently generated based on the screened trajectory points is also accurate compared to the real trajectory.

[0028] The trajectory generation method provided by the embodiments of the present disclosure determines key trajectory points from the original data corresponding to the actual driving trajectory and transmits the key trajectory points to the cloud platform for trajectory simulation to generate a simulated trajectory. This reduces the amount of data transmitted to the cloud platform and improves the efficiency of data transmission to the cloud platform, thereby improving the efficiency of generating the simulated trajectory based on the key trajectory points, and facilitating the subsequent timely display of the simulated trajectory.

[0029] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The accompanying drawings herein are incorporated into and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and, together with the specification, are used to explain the technical solutions of the present disclosure.

[0031] Figure 1 An optional flowchart of a trajectory point screening method provided in an embodiment of the present disclosure;

[0032] Figure 2 An optional flowchart of a trajectory point screening method provided in an embodiment of the present disclosure;

[0033] Figure 3 An optional flowchart of a trajectory point screening method provided in an embodiment of the present disclosure;

[0034] Figure 4 An optional flowchart of a trajectory point screening method provided in an embodiment of the present disclosure;

[0035] Figure 5 An optional flowchart of a trajectory point screening method provided in an embodiment of the present disclosure;

[0036] Figure 6A A schematic diagram of an exemplary trajectory point screening principle provided by an embodiment of the present disclosure;

[0037] Figure 6B Another schematic diagram of an exemplary trajectory point screening principle provided by an embodiment of the present disclosure;

[0038] Figure 7 An optional flowchart of the trajectory generation method provided in an embodiment of the present disclosure;

[0039] Figure 8A A general schematic diagram of an exemplary real driving trajectory provided by an embodiment of the present disclosure;

[0040] Figure 8B A general schematic diagram of an exemplary simulation trajectory provided by an embodiment of the present disclosure;

[0041] Figure 9A A detailed schematic diagram of a partial trajectory of an exemplary real driving trajectory provided by an embodiment of the present disclosure;

[0042] Figure 9B A detailed schematic diagram of a portion of an exemplary simulated trajectory corresponding to a portion of an actual driving trajectory in an embodiment of the present disclosure;

[0043] Figure 10 A schematic structural diagram of a trajectory point screening device provided in an embodiment of the present disclosure;

[0044] Figure 11 A schematic structural diagram of a trajectory generating device provided in an embodiment of the present disclosure;

[0045] Figure 12A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solutions and advantages of the present disclosure clearer, the present disclosure will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limiting the present disclosure. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present disclosure.

[0047] The embodiments of the present disclosure provide a trajectory point screening method that can screen out important key trajectory points for generating accurate simulation trajectories, while reducing the amount of data transmitted to the cloud platform; the embodiments of the present disclosure also provide a trajectory generation method that can improve the efficiency of generating simulation trajectories. In some embodiments, the trajectory point screening method and trajectory generation method provided by the embodiments of the present disclosure can be applied to electronic devices. In the embodiments of the present disclosure, the electronic device for executing the trajectory point screening method and the trajectory generation method can be implemented as a vehicle (for example, a vehicle's onboard unit), and can also be implemented as various types of user terminals (terminal devices) such as AR glasses, laptops, tablet computers, desktop computers, set-top boxes, mobile devices (for example, mobile phones, portable music players, personal digital assistants, dedicated messaging devices, portable gaming devices). The following will take the electronic device that executes the trajectory point screening method and the trajectory generation method as an onboard unit of a vehicle as an example, and explain the trajectory point screening method and the trajectory generation method respectively.

[0048] Figure 1 This is an optional flow chart of the trajectory point screening method provided by the embodiment of the present disclosure, which will be combined with Figure 1 The steps shown are explained.

[0049] S101. Obtain M trajectory points of a real driving trajectory; M is an integer greater than 2.

[0050] S102 : Obtain a current key trajectory point from the M trajectory points, and determine a current basic slope based on the current key trajectory point.

[0051] When the vehicle is in motion or other states, the on-board unit can obtain the real trajectory data of the real driving trajectory (real trajectory) that the vehicle has traveled from the vehicle's built-in trajectory recording device (for example, a high-precision map device), or, when the real trajectory data of the real driving trajectory that the vehicle is about to travel is generated in the trajectory recording device, the on-board unit can obtain the real trajectory data of the real driving trajectory that the vehicle is about to travel from the vehicle's trajectory recording device, wherein the real trajectory data is composed of a series of trajectory points with longitude and latitude information arranged in chronological order (that is, position points with two-dimensional coordinates, for example, position points P(x, y)), for example, M trajectory points; after obtaining these M trajectory points, the on-board unit can first determine a current key trajectory point from these M trajectory points, and determine a current basic slope based on the current key trajectory point.

[0052] In some embodiments, as Figure 2 As shown, the above S102 can be realized by S1021. Figure 2 The steps shown are explained.

[0053] S1021. Obtain a current key trajectory point from the M trajectory points, and use the slope between the current key trajectory point and the next trajectory point of the current key trajectory point among the M trajectory points as the current basic slope; wherein the first trajectory point among the M trajectory points is the first key trajectory point.

[0054] In the disclosed embodiment, the onboard unit may use the first of the M trajectory points as the first key trajectory point to obtain the current key trajectory point. Thereafter, the onboard unit may determine the slope between the current key trajectory point and the next trajectory point of the current key trajectory point among the M trajectory points, that is, the second trajectory point, thereby obtaining the slope between the first and second trajectory points among the M trajectory points, and use the slope as the current basic slope L0. Here, the slope between the Pth trajectory point and the P+1th trajectory point refers to the slope of the line segment formed by the Pth trajectory point and the P+1th trajectory point; for example, the slope between the trajectory point P(x1, y1) and the trajectory point P+1(x2, y2) is: (y2-y1) / (x2-x1).

[0055] In the embodiment of the present disclosure, the first trajectory point among the M trajectory points is used as the current key trajectory point, and the slope between the first trajectory point and the second trajectory point among the M trajectory points is used as the current basic slope. On the one hand, the initial position point of the current driving trajectory line can be retained, and on the other hand, the initial slope of the current driving trajectory line can be obtained, which is conducive to the subsequent accurate screening of other key points.

[0056] S103. When the current trajectory point is not the Mth trajectory point, based on the current basic slope, the slope between the previous trajectory point and the current trajectory point among the M trajectory points, and the slope between the current key trajectory point and the current trajectory point, determine the next key trajectory point and the next basic slope from the M trajectory points, until all the trajectory points to be screened among the M trajectory points are traversed, and N-1 key trajectory points are obtained; N is an integer less than M; and the N-1 key trajectory points are combined with the Mth trajectory point to generate a simulated trajectory corresponding to the actual driving trajectory.

[0057] In the embodiment of the present disclosure, after obtaining the current basic slope, the on-board unit can determine a current trajectory point from the M trajectory points, and determine whether the current trajectory point is the M-th trajectory point. If the current trajectory point is not the M-th trajectory point, the on-board unit can continue to determine the next key trajectory point and the next basic slope from the M trajectory points based on the slope between the current trajectory point and the previous trajectory point of the current trajectory point, and the slope between the current key point and the current trajectory point. This cycle is iterated until all the trajectory points to be screened in the M trajectory points are exhausted, and N-1 key trajectory points can be obtained, where N is an integer less than M. Moreover, these N-1 key trajectory points and the M-th trajectory point are used to generate a simulated trajectory corresponding to the actual driving trajectory of the vehicle.

[0058] In the embodiment of the present disclosure, since the trajectory points are screened out from the original trajectory points corresponding to the real trajectory, the data volume of the screened trajectory points is smaller than the data volume of the original trajectory points, thereby reducing the efficiency of transmitting or processing the trajectory points compared to transmitting or processing the original trajectory points; at the same time, since the key trajectory points are screened out from the original trajectory points based on the slopes between the trajectory points, the screened key trajectory points are all important trajectory points in the original trajectory points, so that the simulated trajectory subsequently generated based on the screened trajectory points is also accurate compared to the real trajectory.

[0059] In some embodiments, after the above S103, the method further includes: sending N-1 key trajectory points and the Mth trajectory point to the cloud platform, and the cloud platform is used to generate a simulated trajectory corresponding to the real driving trajectory based on the N-1 key trajectory points and the Mth trajectory point.

[0060] After the on-board unit has screened out all the key trajectory points from the M trajectory points, it can send all of these key trajectory points to the cloud platform. Based on these key trajectory points, the cloud platform can generate a simulated trajectory corresponding to the actual driving trajectory formed by these M trajectory points for display, thereby knowing the vehicle's driving trajectory.

[0061] Here, the trajectory points to be screened among the M trajectory points are all trajectory points after the next key trajectory point among the M trajectory points.

[0062] For example, when the first key trajectory point is the first trajectory point among the M trajectory points, and the first basic slope L0 is the slope between the first trajectory point and the second trajectory point, the current trajectory point among the M trajectory points is the third trajectory point among the M trajectory points, and the trajectory point before the current trajectory point is the second trajectory point. Thus, the on-board unit can calculate the slope L0 between the first trajectory point and the second trajectory point, the slope L1 between the second trajectory point and the third trajectory point, and the slope L2 between the first trajectory point and the third trajectory point. The slope L2 between the two points is used to determine whether the second trajectory point is the next key trajectory point. If not, the next current trajectory point is selected and the previous trajectory of the next current trajectory point is determined to be the next key trajectory point, until the next key trajectory point is determined from the M trajectory points, and the next basic slope is determined according to the next key trajectory point. After that, the loop iteration is continued until the trajectory points after the next key trajectory point in the M trajectory points are traversed, and N-1 key trajectory points are obtained.

[0063] In some embodiments, as Figure 3 As shown, the above S103 can be implemented through S1031-S1033. Figure 3 The steps shown are described as an example.

[0064] S1031. Based on the i-th basic slope, the slope between the j-1th trajectory point and the j-th trajectory point, and the slope between the i-th key trajectory point and the j-th trajectory point, determine whether the j-1th trajectory point is the i+1th key trajectory point; the current basic slope is the i-th basic slope, and the next basic slope is the i+1th basic slope; the current key trajectory point is the i-th key trajectory point, and the next key trajectory point is the i+1th key trajectory point; the previous trajectory point is the j-1th trajectory point, and the current trajectory point is the j-th trajectory point; i is an integer from 1 to N-1; j is an integer from 3 to M-1.

[0065] S1032. When the j-1th trajectory point is not the i+1th key trajectory point, based on the i-th basic slope, the j+1th trajectory point is used as the current trajectory point to continue to determine whether the jth trajectory point is the i+1th key trajectory point, until the j+Hth trajectory point is determined to be the i+1th key trajectory point; wherein j+H is an integer less than M and greater than or equal to j.

[0066] The on-board unit can calculate the slope L1 between the j-1th trajectory point and the jth trajectory point, and calculate the slope L2 between the i-th key trajectory point and the j-th trajectory point, and determine whether the j-1th trajectory point is the i+1th key trajectory point based on the slope L1 and the slope L2, as well as the i-th basic slope L0; and if the j-1th trajectory point is not the i+1th key trajectory point, continue to use the j+1th trajectory point as the current trajectory point and the j-th trajectory point as the current trajectory point The previous trajectory point is taken as the loop, and the slope between the j-th trajectory point and the j+1-th trajectory point is calculated as the new L1, and the slope between the i-th key trajectory point and the j+1-th trajectory point is calculated as the new L2. According to the new slope L1 and the new slope L2, as well as the i-th basic slope L0, it is determined whether the j-th trajectory point is the i+1-th key trajectory point. This cycle is iterated until the j+H-th trajectory point is determined to be the i+1-th key trajectory point, thereby obtaining the i+1-th key point.

[0067] Exemplarily, when i=1, j=3, the first key trajectory point is the first trajectory point among the M trajectory points, and the first basic slope L0 is the slope between the first trajectory point and the second trajectory point, the current trajectory point among the M trajectory points is the third trajectory point among the M trajectory points, and the trajectory point before the current trajectory point is the second trajectory point, thus, the on-board unit can determine whether the second trajectory point is the second key trajectory point based on the slope L0 between the first trajectory point and the second trajectory point, the slope L1 between the second trajectory point and the third trajectory point, and the slope L2 between the first trajectory point and the third trajectory point; And when the second trajectory point is not the second key trajectory point, continue to use the fourth trajectory point as the current trajectory point, use the third trajectory point as the previous trajectory point of the current trajectory point, and calculate the slope between the third trajectory point and the fourth trajectory point as the new L1, and calculate the slope between the first key trajectory point and the fourth trajectory point as the new L2, and determine whether the third trajectory point is the second key trajectory point based on the new slope L1 and the new slope L2, as well as the first basic slope L0. Repeat this cycle until it is determined that the 3+Hth trajectory point is the second key trajectory point, thereby obtaining the second key point.

[0068] In some embodiments, as Figure 4 As shown, the above S1031 can be implemented through S201-S203. Figure 4 The steps shown are described as an example.

[0069] S201: Determine a first slope between the i-th key trajectory point and the j-th trajectory point, and a second slope between the j-1-th trajectory point and the j-th trajectory point.

[0070] S202 : Determine a first threshold range and a second threshold range according to the i-th basic slope and a preset threshold.

[0071] The on-board unit can calculate the slope of the line segment formed by the ith key trajectory point and the jth trajectory point based on the coordinate points of the ith key trajectory point and the jth trajectory point to obtain a first slope; and calculate the slope of the line segment formed by the j-1th trajectory point and the jth trajectory point based on the coordinate points of the j-1th trajectory point and the jth trajectory point to obtain a second slope; and also determine the first threshold range and the second threshold range based on the ith basic slope and the preset threshold.

[0072] Here, the preset threshold can be set according to actual needs, and the embodiments of the present disclosure do not limit this.

[0073] In some embodiments, as Figure 5 As shown, the above S202 can be realized by S2021-S2023. Figure 5 The steps shown are described as an example.

[0074] S2021. Determine a first boundary threshold and a second boundary threshold based on the i-th basic slope, the first weight, and the first threshold; the preset thresholds include: the first weight, the second weight, the first threshold, and the second threshold.

[0075] S2022: Determine a third boundary threshold and a fourth boundary threshold according to the i-th basic slope, the second weight, and the second threshold.

[0076] S2023: The first boundary threshold and the second boundary threshold form a first threshold range, and the third boundary threshold and the fourth boundary threshold form a second threshold range.

[0077] When the preset thresholds include: a first weight w1, a second weight w2, a first threshold Y1 and a second threshold Y2, the on-board unit can determine the first boundary threshold B1 and the second boundary threshold B2 based on the i-th basic slope L0, the first weight w1 and the first threshold Y1; and determine the third boundary threshold B3 and the fourth boundary threshold B4 based on the i-th basic slope L0, the second weight w2 and the second threshold Y2; wherein the first boundary threshold B1 is less than the second boundary threshold B2, and the third boundary threshold B3 is less than the fourth boundary threshold B4; then, the first boundary threshold B1 and the second boundary threshold B2 are combined into a first threshold range, and the third boundary threshold B3 and the fourth boundary threshold B4 are combined into a second threshold range.

[0078] In some embodiments, the on-board unit can determine the difference between the i-th basic slope L0 and the first threshold value Y1, and use the product of the difference between the i-th basic slope L0 and the first threshold value Y1 and the first weight w1 as the first boundary threshold value B1; and determine the sum of the i-th basic slope L0 and the first threshold value Y1, and use the product of the sum of the i-th basic slope L0 and the first threshold value Y1 and the first weight w1 as the second boundary threshold value B2. Similarly, the on-board unit can also determine the difference between the i-th basic slope L0 and the second threshold value Y2, and use the product of the difference between the i-th basic slope L0 and the second threshold value Y2 and the second weight w2 as the third boundary threshold value B3; and determine the sum of the i-th basic slope L0 and the second threshold value Y2, and use the product of the sum of the i-th basic slope L0 and the second threshold value Y2 and the second weight w2 as the fourth boundary threshold value B4, where B1 is shown in the following formula (1), B2 is shown in the following formula (2), B3 is shown in the following formula (3), and B4 is shown in the following formula (4):

[0079] B1=w1×(L0-Y1) (1)

[0080] B2=w1×(L0+Y1) (2)

[0081] B3=w2×(L0-Y2) (3)

[0082] B4=w2×(L0+Y2) (4)

[0083] On this basis, the first threshold range is (w1×(L0−Y1), w1×(L0+Y1)), and the second threshold range is (w2×(L0−Y2), w2×(L0+Y2)).

[0084] In some embodiments, the first weight w1, the second weight w2, the first threshold Y1, and the second threshold Y2 used to determine whether a trajectory point is a key trajectory point may have at least one identical value or at least one different value from the first weight w1, the second weight w2, the first threshold Y1, and the second threshold Y2 used to determine whether the next trajectory point is a key trajectory point, and the embodiments of the present disclosure do not limit this.

[0085] S203 : Determine whether the j-1th trajectory point is the i+1th key trajectory point based on the subordination relationship between the first slope and the first threshold range, and the subordination relationship between the second slope and the second threshold range.

[0086] When the on-board unit obtains the first slope, the first threshold range, the second slope, and the second threshold range, it can determine whether the first slope belongs to the first threshold range, and whether the second slope belongs to the second threshold range, and determine whether the j-1th trajectory point is the i+1th key trajectory point based on the judgment results.

[0087] In some embodiments, the above S203 may be implemented through S2031 or S2032:

[0088] S2031: When the first slope is within a first threshold range and the second slope is within a second threshold range, determine that the j-1th trajectory point is not the i+1th key trajectory point.

[0089] S2032: When the first slope does not fall within the first threshold range and / or the second slope does not fall within the second threshold range, determine that the j-1th trajectory point is the i+1th key trajectory point.

[0090] The on-board unit can determine that the j-1th trajectory point is not the i+1th key trajectory point when the first slope is within the first threshold range and the second slope is also within the second threshold range; and can determine that the j-1th trajectory point is the i+1th key trajectory point in any of the following three situations. The three situations include: (1) the first slope is not within the first threshold range and the second slope is not within the second threshold range; (2) the first slope is not within the first threshold range and the second slope is within the second threshold range; (3) the first slope is within the first threshold range and the second slope is not within the second threshold range.

[0091] Here, if the first slope is greater than the first boundary threshold and less than the second boundary threshold, it is indicated that the first slope belongs to the first threshold range; or, if the first slope is equal to the first boundary threshold or equal to the second boundary threshold, it is indicated that the first slope belongs to the first threshold range. Similarly, if the second slope is greater than the third boundary threshold and less than the fourth boundary threshold, it is indicated that the second slope belongs to the second threshold range; or, if the second slope is equal to the third boundary threshold or equal to the fourth boundary threshold, it is indicated that the second slope belongs to the second threshold range.

[0092] Regarding the principle of determining whether a trajectory point is a key trajectory point through the relationship between the slope and the threshold range, the following will be Figure 6A and Figure 6B For explanation. Figure 6AAs shown in the figure, P0, P1 and P2 are three sequentially distributed trajectory points that make up a real trajectory. L11 represents the slope of P0 and P1, L12 represents the slope of P0 and P2, and L10 can be regarded as the basic slope. If the difference between the angles of L11 and L10 is within the threshold range, then it can be considered that P0 and P1 are likely to be on the same straight line segment. Similarly, on this basis, if the difference between the angles of L12 and L10 is also within the threshold range, it can also be considered that P2 and P1 are likely to be on the same straight line segment. Therefore, it can be determined that P1 is not a key trajectory point. Figure 6B As shown, P0, P1, and P2 are three sequentially distributed trajectory points that make up another trajectory line; L20 represents the slope between P0 and P1, and L21 represents the slope between P1 and P2. If the slope between L21 and L20 exceeds a threshold, P1 can be considered an inflection point and can be determined to be a key trajectory point. Based on the above, it can be seen that the trajectory point screening method provided by the embodiment of the present disclosure can solve both non-mutation situations over long distances and mutation situations over short distances, so that the selected trajectory points are all important trajectory points, and the simulated trajectory ultimately generated based on the obtained trajectory points can accurately depict the real trajectory.

[0093] S1033. Determine the i+1th basic slope based on the i+1th key trajectory point and the j+H+1th trajectory point, and continue to judge the key trajectory point of the j+H+1th trajectory point until all trajectory points after the i+1th key trajectory point are traversed, and N-1 key trajectory points are obtained; the trajectory points to be screened among the M trajectory points are the trajectory points after the i+1th key trajectory point among the M trajectory points.

[0094] In some embodiments, the above-mentioned S1033 can be implemented in the following manner: taking the slope between the i+1th key trajectory point and the j+H+1th trajectory point as the i+1th basic slope; based on the i+1th basic slope, the slope between the j+H+1th trajectory point and the j+H+2th trajectory point, and the slope between the i+1th key trajectory point and the j+H+2th trajectory point, determining the i+2th key trajectory point and the i+2th basic slope from the trajectory points after the i+1th key trajectory point, until all the trajectory points after the i+1th key trajectory point are traversed, and N-1 key trajectory points are obtained.

[0095] In the embodiment of the present disclosure, when the on-board unit determines that the j+Hth trajectory point is the i+1th key trajectory point, it can determine the slope between the i+1th key trajectory point and the j+H+1th trajectory point, and use the slope as the i+1th basic slope L0, and can continue to use the next trajectory point of the j+H+1th trajectory point, that is, the j+H+2th trajectory point, as the current trajectory point, and use the j+H+1th trajectory point as the previous trajectory point, and calculate the j+H+1th trajectory point. The slope between the j+H+2th trajectory point and the j+H+2th trajectory point is taken as the new slope L1, and the slope between the i+1th key trajectory point and the j+H+2th trajectory point is calculated as the new slope L2. According to the i+1th basic slope L0, the new slope L1 and the new slope L2, it is determined whether the j+H+1th trajectory point is the i+2th key trajectory point. This cycle is iterated until all the trajectory points after the i+1th key trajectory point are traversed, and N-1 key trajectory points are obtained.

[0096] Here, the principle of determining whether the j+H+1th trajectory point is the i+2th key trajectory point based on the i+1th basic slope L0, the new slope L1 and the new slope L2 is the same as the principles of S201-S203, s2021-S2023 and S201-S2032 above, and the embodiments of the present disclosure are not repeated here.

[0097] The present disclosure also provides a trajectory generation method, such as Figure 7 As shown, it will be Figure 7 The steps shown in are explained.

[0098] S301: Obtain original data corresponding to the actual driving trajectory.

[0099] In an embodiment of the present disclosure, when the vehicle is in driving or other states, the on-board unit can obtain the original data of the actual driving trajectory that the vehicle has traveled from the vehicle's trajectory recording device, or, when the real trajectory data of the actual driving trajectory that the vehicle is about to travel is generated in the trajectory recording device, the on-board unit can obtain the original data of the actual driving trajectory that the vehicle is about to travel from the vehicle's trajectory recording device.

[0100] In the embodiment of the present disclosure, the original data of the real driving trajectory is the real trajectory data of the real driving trajectory mentioned above.

[0101] S302: Filter the original data for key trajectory points to obtain filtered data.

[0102] The on-board unit can filter the key trajectory points of the original data when the original data is obtained, thereby obtaining filtered data; wherein the amount of the filtered data is smaller than the amount of the original data.

[0103] In some embodiments, the filtered data is a portion of the original data.

[0104] In some embodiments, the original data includes: multiple track points; the filtered data includes: multiple key track points; the onboard unit can use the track point filtering method in the above embodiment, for example, Figure 1-Figure 5 The method shown in FIG1 is to screen multiple trajectory points for key trajectory points, thereby obtaining multiple key trajectory points.

[0105] S303: Send the filtered data to the cloud platform; the cloud platform is used to perform trajectory simulation on the filtered data to obtain a simulated trajectory.

[0106] After the on-board unit has filtered out the filtered data from the original data, it can send all the filtered data to the cloud platform so that the cloud platform can simulate the trajectory based on the filtered data, thereby obtaining a simulated trajectory corresponding to the real driving trajectory.

[0107] In some embodiments, the simulated trajectory corresponds to simulated data, and the simulated data includes filtered data; alternatively, the simulated data may be generated by connecting adjacent trajectory points in the filtered data. Here, after obtaining the filtered data, the cloud platform may connect adjacent trajectory points in the filtered data, thereby using the resulting trajectory line data as the simulated data corresponding to the simulated trajectory.

[0108] In some embodiments, the size of the simulated data corresponding to the simulated trajectory is smaller than the size of the original data corresponding to the real driving trajectory.

[0109] In some embodiments, the lane change trajectory (for example, changing from the left lane to the right lane), the straight trajectory and the turning trajectory in the simulated trajectory are the same as the actual driving trajectory; and for some minor trajectory changes in the actual driving trajectory, for example, the shaking trajectory caused by the vehicle suddenly moving to the left or right and then suddenly returning to the original driving direction, the simulated trajectory will not be displayed.

[0110] In some embodiments, the simulated trajectory is consistent in shape with the actual driving trajectory. Figure 8A It is a general schematic diagram of a real driving trajectory provided by an embodiment of the present disclosure; Figure 8B It is an overall schematic diagram of the simulation trajectory provided by the embodiment of the present disclosure. Figure 9A It is a detailed schematic diagram of a portion of a real driving trajectory provided by an embodiment of the present disclosure; Figure 9B This is a detailed schematic diagram of the portion of the simulated trajectory provided by the embodiment of the present disclosure that corresponds to the portion of the actual driving trajectory. By comparing 8A and 8B, and comparing 9A and 9B, it can be seen that the simulated trajectory is consistent in shape with the actual driving trajectory, achieving an accurate reproduction of the actual driving trajectory.

[0111] In some embodiments, the simulated trajectory can be displayed through the display device of the terminal device. For example, after the cloud platform generates the simulated trajectory, the simulation data corresponding to the simulated trajectory can be returned to the on-board unit so that the simulated trajectory can be displayed through the display device of the vehicle where the on-board unit is located; in some embodiments, the simulated trajectory can also be displayed by the administrator terminal, for example, by the display device connected to the cloud platform, or by the central console, etc.

[0112] In some embodiments of the present disclosure, the above-mentioned trajectory point screening method can also be executed by a cloud platform, and a trajectory generation method is also provided, which is applied to the cloud platform, and the method includes: obtaining the original data corresponding to the actual driving trajectory of the terminal device; screening the original data for key trajectory points to obtain screened data; performing trajectory simulation on the screened data to obtain simulation data corresponding to the simulated trajectory of the terminal device, and sending the simulation data to the terminal device. For example, the cloud platform can obtain the original data corresponding to the actual driving trajectory of the vehicle corresponding to the on-board unit, and screen the original data for key trajectory points to obtain screened data, and then perform trajectory simulation on the screened data to obtain simulation data corresponding to the simulated trajectory of the vehicle, and send the simulation data to the vehicle so that the vehicle's display device can display the simulated trajectory. It should be noted that the principle of the trajectory generation method applied to the cloud platform is the same as the principle of the trajectory generation method applied to the terminal device, and will not be repeated here.

[0113] The present disclosure also provides a trajectory point screening device, which can be included in a terminal device. Figure 10 A schematic diagram of the structure of the trajectory point screening device provided in an embodiment of the present disclosure; Figure 10 As shown, the trajectory point screening device 1 includes: a first acquisition unit 11, used to obtain M trajectory points of the real driving trajectory; M is an integer greater than 2; a first determination unit 12, used to obtain the current key trajectory point from the M trajectory points, and determine the current basic slope based on the current key trajectory point; a first screening unit 13, used to determine the next key trajectory point and the next basic slope from the M trajectory points based on the current basic slope, the slope between the previous trajectory point and the current trajectory point in the M trajectory points, and the slope between the key trajectory point and the current trajectory point, when the current trajectory point is not the Mth trajectory point, until the trajectory points to be screened in the M trajectory points are traversed, and N-1 key trajectory points are obtained; N is an integer less than M; the N-1 key trajectory points are combined with the Mth trajectory point to generate a simulated trajectory corresponding to the real driving trajectory.

[0114] In some embodiments of the present disclosure, the first acquisition unit 11 is further used to obtain the current key trajectory point from the M trajectory points, and use the slope between the current key trajectory point and the next trajectory point of the current key trajectory point in the M trajectory points as the current basic slope; wherein the first trajectory point in the M trajectory points is the first key trajectory point.

[0115] In some embodiments of the present disclosure, the current basic slope is the i-th basic slope, and the next basic slope is the i+1-th basic slope; the current key trajectory point is the i-th key trajectory point, and the next key trajectory point is the i+1-th key trajectory point; the previous trajectory point is the j-1-th trajectory point, and the current trajectory point is the j-th trajectory point; the trajectory point to be filtered among the M trajectory points is the trajectory point after the i+1-th key trajectory point among the M trajectory points; i is an integer from 1 to N-1; j is an integer from 3 to M-1; the first screening unit 13 is further used to determine based on the i-th basic slope, the slope between the j-1-th trajectory point and the j-th trajectory point, and the slope between the i-th key trajectory point and the j-th trajectory point Whether the j-1th trajectory point is the i+1th key trajectory point; if the j-1th trajectory point is not the i+1th key trajectory point, based on the i-th basic slope, take the j+1th trajectory point as the current trajectory point to continue to judge whether the j-th trajectory point is the i+1th key trajectory point, until it is judged that the j+H-th trajectory point is the i+1th key trajectory point; wherein j+H is an integer less than M and greater than or equal to j; determine the i+1th basic slope based on the i+1th key trajectory point and the j+H+1th trajectory point, continue to judge the key trajectory point of the j+H+1th trajectory point, until the trajectory points after the i+1th key trajectory point are traversed, and the N-1 key trajectory points are obtained.

[0116] In some embodiments of the present disclosure, the first screening unit 13 is further used to determine a first slope between the i-th key trajectory point and the j-th trajectory point, and a second slope between the j-1-th trajectory point and the j-th trajectory point; determine a first threshold range and a second threshold range based on the i-th basic slope and a preset threshold; and determine whether the j-1-th trajectory point is the i+1-th key trajectory point based on a subordinate relationship between the first slope and the first threshold range, and a subordinate relationship between the second slope and the second threshold range.

[0117] In some embodiments of the present disclosure, the first screening unit 13 is further used to determine that the j-1th trajectory point is not the i+1th key trajectory point when the first slope falls within the first threshold range and the second slope falls within the second threshold range; and to determine that the j-1th trajectory point is the i+1th key trajectory point when the first slope does not fall within the first threshold range and / or the second slope does not fall within the second threshold range.

[0118] In some embodiments of the present disclosure, the preset threshold includes: a first weight, a second weight, a first threshold and a second threshold; the first screening unit 13 is also used to determine the first boundary threshold and the second boundary threshold based on the i-th basic slope, the first weight and the first threshold; determine the third boundary threshold and the fourth boundary threshold based on the i-th basic slope, the second weight and the second threshold; the first boundary threshold and the second boundary threshold are combined into the first threshold range, and the third boundary threshold and the fourth boundary threshold are combined into the second threshold range.

[0119] In some embodiments of the present disclosure, the first screening unit 13 is further configured to use the slope between the i+1th key trajectory point and the j+H+1th trajectory point as the i+1th basic slope; based on the i+1th basic slope, the slope between the j+H+1th trajectory point and the j+H+2th trajectory point, and the slope between the i+1th key trajectory point and the j+H+2th trajectory point, determine the i+2th key trajectory point and the i+2th basic slope from the trajectory points after the i+1th key trajectory point, until the N-1 key trajectory points are obtained after traversing all the trajectory points after the i+1th key trajectory point.

[0120] In some embodiments of the present disclosure, the trajectory point screening device also includes: a first sending unit, used to send the N-1 key trajectory points and the Mth trajectory point to a cloud platform, and the cloud platform is used to generate a simulated trajectory corresponding to the real driving trajectory based on the N-1 key trajectory points and the Mth trajectory point.

[0121] The present disclosure also provides a trajectory generating device, which can be included in a terminal device. Figure 11 A schematic diagram of the structure of a trajectory generating device provided in an embodiment of the present disclosure; Figure 11As shown, the trajectory generation device 2 includes: a second acquisition unit 21, which is used to obtain raw data corresponding to the real driving trajectory; a second screening unit 22, which is used to screen the key trajectory points of the raw data to obtain screened data; a second sending unit 23, which is used to send the screened data to the cloud platform; the cloud platform is used to perform trajectory simulation on the screened data to obtain a simulated trajectory.

[0122] In some embodiments of the present disclosure, the screening data is a portion of the original data.

[0123] In some embodiments of the present disclosure, the simulation data corresponding to the simulation trajectory includes the filtered data; or, the simulation data corresponding to the simulation trajectory is generated by connecting adjacent trajectory points in the filtered data.

[0124] In some embodiments of the present disclosure, the size of the simulated data corresponding to the simulated trajectory is smaller than the size of the original data corresponding to the real driving trajectory.

[0125] In some embodiments of the present disclosure, the simulated trajectory is consistent with the actual driving trajectory in shape.

[0126] In some embodiments of the present disclosure, the lane change trajectory, the straight trajectory, and the turning trajectory in the simulated trajectory are the same as the real driving trajectory.

[0127] In some embodiments of the present disclosure, the original data includes: multiple trajectory points; the filtered data includes: multiple key trajectory points; the second filtering unit 22 is further used to use the above-mentioned trajectory point filtering method to perform key trajectory point filtering on the multiple trajectory points to obtain the multiple key trajectory points.

[0128] The present disclosure also provides an electronic device, Figure 12 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure, such as Figure 12 As shown, the electronic device 3 includes: a memory 32 and a processor 33, wherein the memory 32 and the processor 33 are connected via a communication bus 31; the memory 32 is used to store an executable computer program; the processor 33 is used to implement the trajectory point screening method provided by the embodiment of the present disclosure when executing the executable computer program stored in the memory 32.

[0129] An embodiment of the present disclosure provides a computer-readable storage medium storing a computer program for causing the processor 33 to execute the trajectory point screening method provided by the embodiment of the present disclosure.

[0130] In some embodiments of the present disclosure, the storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or various devices including one or any combination of the above memories.

[0131] In some embodiments of the present disclosure, executable instructions may be in the form of a program, software, software module, script, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.

[0132] As an example, executable instructions may, but need not, correspond to a file in a file system, may be stored as part of a file that stores other programs or data, such as in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinating files (e.g., files storing one or more modules, subroutines, or code portions).

[0133] By way of example, executable instructions may be deployed to be executed on one computing device, or on multiple computing devices at one site, or on multiple computing devices distributed across multiple sites and interconnected by a communication network.

[0134] In summary, the present technical implementation scheme, because the track points are screened from the original track points corresponding to the real track, the data volume of the screened track points is smaller than that of the original track points, thereby reducing the efficiency of transmitting or processing the track points compared to transmitting or processing the original track points. Furthermore, because the key track points are screened from the original track points based on the slopes between the track points, the screened key track points are all important track points in the original track points, and the subsequent simulated track generated based on the screened track points is also accurate compared to the real track. Furthermore, because the key track points are determined from the original data corresponding to the real driving track and transmitted to the cloud platform for trajectory simulation to generate the simulated track, the amount of data transmitted to the cloud platform is reduced, the efficiency of data transmission to the cloud platform is improved, and the efficiency of generating the simulated track based on the key track points is improved, which facilitates the subsequent timely display of the simulated track.

[0135] The above description is merely an embodiment of the present disclosure and is not intended to limit the scope of protection of the present disclosure. Any modifications, equivalent replacements, and improvements made within the spirit and scope of the present disclosure are included in the scope of protection of the present disclosure.

Claims

1. A trajectory point screening method, characterized in that: include: Get M trajectory points of the actual driving trajectory; M is an integer greater than 2; Obtaining a current key trajectory point from the M trajectory points, and determining a current basic slope based on the current key trajectory point; If the current trajectory point is not the Mth trajectory point, based on the current basic slope, the slope between the previous trajectory point and the current trajectory point among the M trajectory points, and the slope between the key trajectory point and the current trajectory point, determine the next key trajectory point and the next basic slope from the M trajectory points, until all the trajectory points to be screened among the M trajectory points are traversed, thereby obtaining N-1 key trajectory points; N is an integer less than M; the N-1 key trajectory points are combined with the Mth trajectory point to generate a simulated trajectory corresponding to the real driving trajectory; The current basic slope is the i-th basic slope, and the next basic slope is the i+1-th basic slope; the current key trajectory point is the i-th key trajectory point, and the next key trajectory point is the i+1-th key trajectory point; the previous trajectory point is the j-1-th trajectory point, and the current trajectory point is the j-th trajectory point; the trajectory point to be screened among the M trajectory points is the trajectory point after the i+1-th key trajectory point among the M trajectory points; i is an integer from 1 to N-1; j is an integer from 3 to M-1; The method further comprises determining a next key trajectory point and a next basic slope from the M trajectory points based on the current basic slope, the slope between the previous trajectory point and the current trajectory point, and the slope between the key trajectory point and the current trajectory point, until all the trajectory points to be screened in the M trajectory points are traversed, thereby obtaining N-1 key trajectory points, including: Determine a first slope between the i-th key trajectory point and the j-th trajectory point, and a second slope between the j-1-th trajectory point and the j-th trajectory point; determine a first threshold range and a second threshold range based on the i-th basic slope and a preset threshold; and determine whether the j-1-th trajectory point is the i+1-th key trajectory point based on a subordinate relationship between the first slope and the first threshold range, and a subordinate relationship between the second slope and the second threshold range.

2. The method according to claim 1, characterized in that The acquiring a current key trajectory point from the M trajectory points and determining a current basic slope based on the current key trajectory point includes: The current key trajectory point is obtained from the M trajectory points, and the slope between the current key trajectory point and the next trajectory point of the current key trajectory point in the M trajectory points is used as the current basic slope; wherein the first trajectory point in the M trajectory points is the first key trajectory point.

3. The method according to claim 1, characterized in that The method further includes determining a next key trajectory point and a next basic slope from the M trajectory points based on the current basic slope, the slope between a previous trajectory point in the M trajectory points and the current trajectory point, and the slope between the key trajectory point and the current trajectory point, until all the trajectory points to be screened in the M trajectory points are traversed to obtain N-1 key trajectory points. If the j-1th trajectory point is not the i+1th key trajectory point, based on the i-th basic slope, the j+1th trajectory point is used as the current trajectory point to continue determining whether the jth trajectory point is the i+1th key trajectory point, until the j+Hth trajectory point is determined to be the i+1th key trajectory point; where j+H is an integer less than M and greater than or equal to j; The i+1th basic slope is determined based on the i+1th key trajectory point and the j+H+1th trajectory point, and the key trajectory point judgment of the j+H+1th trajectory point is continued until the trajectory points after the i+1th key trajectory point are traversed, and the N-1 key trajectory points are obtained.

4. The method according to claim 1, wherein The determining, based on the subordination relationship between the first slope and the first threshold range, and the subordination relationship between the second slope and the second threshold range, whether the j-1th trajectory point is the i+1th key trajectory point includes: When the first slope is within the first threshold range and the second slope is within the second threshold range, determining that the j-1th trajectory point is not the i+1th key trajectory point; When the first slope does not fall within the first threshold range and / or the second slope does not fall within the second threshold range, it is determined that the j-1th trajectory point is the i+1th key trajectory point.

5. The method according to claim 1, wherein The preset threshold value includes: a first weight, a second weight, a first threshold value, and a second threshold value; and determining the first threshold value range and the second threshold value range according to the i-th basic slope and the preset threshold value includes: Determining a first boundary threshold and a second boundary threshold according to the i-th basic slope, the first weight and the first threshold; Determining a third boundary threshold and a fourth boundary threshold according to the i-th basic slope, the second weight and the second threshold; The first boundary threshold and the second boundary threshold are combined into the first threshold range, and the third boundary threshold and the fourth boundary threshold are combined into the second threshold range.

6. The method according to claim 3, characterized in that The determining of the i+1th basic slope based on the i+1th key trajectory point and the j+H+1th trajectory point, and continuing to determine the key trajectory point for the j+H+1th trajectory point until all trajectory points after the i+1th key trajectory point are traversed, thereby obtaining the N-1 key trajectory points, includes: The slope between the i+1th key trajectory point and the j+H+1th trajectory point is used as the i+1th basic slope; Based on the i+1th basic slope, the slope between the j+H+1th trajectory point and the j+H+2th trajectory point, and the slope between the i+1th key trajectory point and the j+H+2th trajectory point, the i+2th key trajectory point and the i+2th basic slope are determined from the trajectory points after the i+1th key trajectory point, until the trajectory points after the i+1th key trajectory point are traversed, and the N-1 key trajectory points are obtained.

7. The method according to claim 1, characterized in that The method further comprises: The N-1 key trajectory points and the M-th trajectory point are sent to a cloud platform, and the cloud platform is used to generate a simulated trajectory corresponding to the real driving trajectory based on the N-1 key trajectory points and the M-th trajectory point.

8. A trajectory generation method, characterized in that: include: Obtain the original data corresponding to the actual driving trajectory; Performing key trajectory point screening on the original data to obtain screened data; Sending the screening data to a cloud platform; The cloud platform is used to perform trajectory simulation on the screened data to obtain a simulated trajectory; The original data includes: a plurality of trajectory points; the filtered data includes: a plurality of key trajectory points; The step of screening the original data for key trajectory points to obtain screened data includes: The method according to any one of claims 1 to 7 is adopted to perform key trajectory point screening on the multiple trajectory points to obtain the multiple key trajectory points.

9. The method according to claim 8, characterized in that The filtered data is a portion of the original data.

10. The method according to claim 8, characterized in that The simulation data corresponding to the simulation trajectory includes the filtered data; or, the simulation data corresponding to the simulation trajectory is generated by connecting adjacent trajectory points in the filtered data.

11. The method according to claim 8, characterized in that The size of the simulated data corresponding to the simulated trajectory is smaller than the size of the original data corresponding to the real driving trajectory.

12. The method according to any one of claims 8 to 11, characterized in that The simulated trajectory is consistent with the actual driving trajectory in shape.

13. The method according to any one of claims 8 to 11, characterized in that: The lane change trajectory, straight-moving trajectory, and turning trajectory in the simulated trajectory are the same as the real driving trajectory.

14. A trajectory point screening device, characterized in that: include: A first acquisition unit is used to acquire M trajectory points of the real driving trajectory; M is an integer greater than 2; a first determining unit, configured to obtain a current key trajectory point from the M trajectory points, and determine a current basic slope based on the current key trajectory point; a first screening unit configured to, if the current trajectory point is not the Mth trajectory point, determine a next key trajectory point and a next basic slope from the M trajectory points based on the current basic slope, the slope between a previous trajectory point and the current trajectory point among the M trajectory points, and the slope between the key trajectory point and the current trajectory point, until all trajectory points to be screened among the M trajectory points are traversed, thereby obtaining N-1 key trajectory points; N is an integer less than M; and the N-1 key trajectory points are combined with the Mth trajectory point to generate a simulated trajectory corresponding to the actual driving trajectory; The current basic slope is the i-th basic slope, and the next basic slope is the i+1-th basic slope; the current key trajectory point is the i-th key trajectory point, and the next key trajectory point is the i+1-th key trajectory point; the previous trajectory point is the j-1-th trajectory point, and the current trajectory point is the j-th trajectory point; the trajectory point to be screened among the M trajectory points is the trajectory point after the i+1-th key trajectory point among the M trajectory points; i is an integer from 1 to N-1; j is an integer from 3 to M-1; The first screening unit is further used to determine a first slope between the i-th key trajectory point and the j-th trajectory point, and a second slope between the j-1-th trajectory point and the j-th trajectory point; determine a first threshold range and a second threshold range based on the i-th basic slope and a preset threshold; and determine whether the j-1-th trajectory point is the i+1-th key trajectory based on a subordinate relationship between the first slope and the first threshold range, and a subordinate relationship between the second slope and the second threshold range.

15. A trajectory generating device, characterized in that: include: A second acquisition unit is used to acquire raw data corresponding to the actual driving trajectory; A second screening unit is used to screen the original data for key trajectory points to obtain screened data; A second sending unit, configured to send the screening data to a cloud platform; The cloud platform is used to perform trajectory simulation on the screened data to obtain a simulated trajectory; The original data includes: a plurality of trajectory points; the filtered data includes: a plurality of key trajectory points; The second screening unit is further configured to use the method according to any one of claims 1 to 7 to screen the multiple track points for key track points, thereby obtaining the multiple key track points.

16. An electronic device, characterized in that: include: a memory for storing executable computer programs; A processor, configured to implement the method according to any one of claims 1 to 13 when executing the executable computer program stored in the memory.

17. A computer-readable storage medium, characterized in that A computer program is stored, which is used to cause a processor to implement the method according to any one of claims 1 to 13 when the program is executed.

Images