A method and terminal for generating smooth trajectory

Abstract

The present application provides a method and terminal for generating a smooth trajectory, which respectively obtains first driving data corresponding to a first moment and second driving data corresponding to a second moment in chronological order; divides the time interval from the first moment to the second moment into a first preset number of first sub-moments, and calculates position prediction data corresponding to each of the first sub-moments based on the first driving data and the second driving data; obtains a smooth trajectory from the first moment to the second moment based on the prediction data; the present application refines the line between two points into lines between multiple points, thereby achieving smoothing of the trajectory curve, and the prediction is based on the acquired driving data, thereby ensuring the accuracy of the trajectory prediction.

Description

Technical Field

[0001] The present invention relates to the field of data analysis, and in particular to a method and a terminal for generating a smooth trajectory. Background Art

[0002] The positioning data of the vehicle driving recorder equipment mostly comes from the signals of the Beidou system or the GPS system. Due to storage costs and communication costs, the longitude and latitude positioning data are usually recorded only once a minute. When driving on short-distance multi-road sections or curved sections, the positioning information collected by the driving recorder equipment for two consecutive minutes can only roughly determine that the vehicle's driving trajectory is a straight line, and it is impossible to locate the actual driving road of the vehicle during this time period; especially on curved roads, there is also a certain error in the accuracy of judging the vehicle passing the accident site, and the vehicle's driving trajectory cannot be intuitively obtained. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a method and a terminal for generating a smooth trajectory, so as to achieve high-precision restoration of the driving trajectory.

[0004] In order to solve the above technical problems, a technical solution adopted by the present invention is:

[0005] A method for generating a smooth trajectory, comprising the steps of:

[0006] Acquire first driving data corresponding to a first moment and second driving data corresponding to a second moment respectively in chronological order;

[0007] Divide the time interval from the first moment to the second moment into a first preset number of first sub-moments, and calculate the position prediction data corresponding to each of the first sub-moments according to the first driving data and the second driving data;

[0008] A smooth trajectory from the first moment to the second moment is obtained according to the prediction data.

[0009] In order to solve the above technical problems, another technical solution adopted by the present invention is:

[0010] A terminal for generating a smooth trajectory comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0011] Acquire first driving data corresponding to a first moment and second driving data corresponding to a second moment respectively in chronological order;

[0012] Divide the time interval from the first moment to the second moment into a first preset number of first sub-moments, and calculate the position prediction data corresponding to each of the first sub-moments according to the first driving data and the second driving data;

[0013] A smooth trajectory from the first moment to the second moment is obtained according to the prediction data.

[0014] The beneficial effects of the present invention are as follows: the moments of two known driving data and their corresponding driving data are obtained in chronological order, and the time interval between the two moments is segmented to obtain multiple sub-moments, and the position of each sub-moment is predicted according to the driving data, that is, the line between the two points is refined into the lines of multiple points, thereby achieving smooth trajectory curves, and the prediction is based on the acquired driving data, thereby ensuring the accuracy of trajectory prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A flow chart of steps of a method for generating a smooth trajectory according to an embodiment of the present invention;

[0016] Figure 2 A schematic diagram of the structure of a terminal for generating a smooth trajectory according to an embodiment of the present invention;

[0017] Figure 3 A schematic flow chart of a method for generating a smooth trajectory according to an embodiment of the present invention;

[0018] Figure 4 A speed-angle schematic diagram of an embodiment of the present invention;

[0019] Figure 5 A schematic diagram of generating a smooth trajectory according to an embodiment of the present invention;

[0020] Description of labels:

[0021] 1. A terminal for generating a smooth trajectory; 2. A processor; 3. A memory. DETAILED DESCRIPTION

[0022] In order to explain the technical content, achieved objectives and effects of the present invention in detail, the following is an explanation in combination with the implementation modes and the accompanying drawings.

[0023] Please refer to Figure 1 , a method for generating a smooth trajectory, comprising the steps of:

[0024] Acquire first driving data corresponding to a first moment and second driving data corresponding to a second moment respectively in chronological order;

[0025] Divide the time interval from the first moment to the second moment into a first preset number of first sub-moments, and calculate the position prediction data corresponding to each of the first sub-moments according to the first driving data and the second driving data;

[0026] A smooth trajectory from the first moment to the second moment is obtained according to the prediction data.

[0027] From the above description, it can be seen that the beneficial effects of the present invention are: obtaining the moments of two known driving data and their corresponding driving data in chronological order, and segmenting the time interval between the two moments to obtain multiple sub-moments, and predicting the position of each sub-moment according to the driving data, that is, refining the line between the two points into the lines of multiple points, thereby achieving smoothing of the trajectory curve, and the prediction is based on the acquired driving data, which ensures the accuracy of the trajectory prediction.

[0028] Furthermore, the first driving data includes a vehicle speed set, positioning data and a turning angle set;

[0029] The obtaining of the first driving data corresponding to the first moment includes:

[0030] Divide the time interval from the moment before the first moment to the first moment into a second preset number of second sub-moments, obtain the vehicle speed and the turning angle corresponding to each of the second sub-moments, and obtain a vehicle speed set and a turning angle set;

[0031] Acquire the current position corresponding to the first moment to obtain the positioning data;

[0032] The second driving data has the same data structure as the first driving data.

[0033] From the above description, it can be seen that because the time interval between two positionings performed by the navigation device is usually long, driving data such as vehicle speed and turning angle can be obtained in real time. While obtaining the positioning data at a moment, all driving data from the previous moment to this moment are also obtained, which provides accurate reference data for trajectory prediction between two moments of known positioning data, thereby improving the accuracy of the final confirmed trajectory.

[0034] Further, the first preset number is equal to the second preset number;

[0035] The calculating of the position prediction data corresponding to each first sub-time according to the first driving data and the second driving data comprises:

[0036] Taking the positioning data corresponding to the first moment as the starting point and the positioning data corresponding to the second moment as the end point, obtaining the first position data corresponding to each of the first sub-moments according to the vehicle speed set and the turning angle set corresponding to the second moment;

[0037] Taking the positioning data corresponding to the first moment as the end point and the positioning data corresponding to the second moment as the starting point, obtaining the second position data corresponding to each of the first sub-moments according to the vehicle speed set and the turning angle set corresponding to the second moment;

[0038] The average of the first position data and the second position data is calculated to obtain the position prediction data.

[0039] From the above description, it can be seen that by making the first preset number equal to the second preset number, each first sub-moment will correspond to a set of known driving data, which can make predictions more convenient without the need for conversion. At the same time, the two time points of the known position data are used as starting points, and the predicted position corresponding to each first sub-moment is calculated according to the vehicle speed and the turning angle. Finally, the two predicted positions corresponding to each sub-moment are averaged, which improves the accuracy of the prediction results and ultimately achieves high-precision trajectory prediction.

[0040] Furthermore, the positioning data is longitude and latitude data.

[0041] From the above description, it can be seen that longitude and latitude data are used as positioning data. Since the known positioning data is usually longitude and latitude data, there is no need to convert coordinates. At the same time, positioning by longitude and latitude is a mature technology and is easy to use.

[0042] Further, taking the positioning data corresponding to the first moment as the starting point and the positioning data corresponding to the second moment as the end point, obtaining the first position data corresponding to each first sub-moment according to the vehicle speed set and the turning angle set corresponding to the second moment includes:

[0043] Taking the positioning data corresponding to the first moment as the starting point, traverse the first sub-moment, and when traversing to the target first sub-moment, obtain the time difference between the target first sub-moment and the previous first sub-moment, the first position data of the previous first sub-moment, and the vehicle speed and turning angle corresponding to the target first sub-moment, obtain the forward distance corresponding to the target first sub-moment according to the vehicle speed and the time difference, and obtain the first position data of the target first sub-moment according to the first position data of the previous first sub-moment, the forward distance and the turning angle.

[0044] Further, taking the positioning data corresponding to the first moment as the end point and the positioning data corresponding to the second moment as the starting point, obtaining the second position data corresponding to each first sub-moment according to the vehicle speed set and the turning angle set corresponding to the second moment includes:

[0045] Taking the positioning data corresponding to the second moment as the starting point, traverse the first sub-moment, and when traversing to the target first sub-moment, obtain the time difference between the target first sub-moment and the subsequent first sub-moment, the first position data of the subsequent first sub-moment, and the vehicle speed and turning angle corresponding to the target first sub-moment, obtain the forward distance corresponding to the target first sub-moment according to the vehicle speed and the time difference, and obtain the second position data of the target first sub-moment according to the first position data of the subsequent first sub-moment, the forward distance and the turning angle.

[0046] From the above description, it can be seen that if the positioning data at a moment, the time difference between it and the next moment, and the vehicle speed and turning angle at the next moment are known, the distance traveled by a vehicle in the time difference, that is, the forward distance, can be obtained. The positioning data at the next moment can be determined based on the forward distance, the turning angle, and the positioning data at a moment. In this way, by traversing the first sub-moment, the first position data corresponding to each first sub-moment can be obtained, thereby refining two known trajectory points into multiple trajectory points. In addition, since the data of the next first sub-moment is calculated based on the data of the previous first sub-moment, it may cause the accumulation of errors. Calculating the data in two directions from the first moment to the second moment and from the second moment to the first moment can eliminate the cumulative errors to a certain extent, making the results more accurate.

[0047] Further, obtaining the forward distance corresponding to the target first sub-time according to the vehicle speed and the time difference includes:

[0048] L i =v i ×t;

[0049] Wherein, Li represents the forward distance corresponding to the first sub-moment of the target; vi represents the vehicle speed corresponding to the first sub-moment of the target; and t represents the time difference.

[0050] From the above description, it can be seen that the advance distance is calculated by using the vehicle speed corresponding to the target first sub-moment and the time difference between the vehicle speed and the previous first sub-moment or the next first sub-moment, thereby realizing the prediction of the advance distance.

[0051] Further, obtaining the first position data of the target at the first sub-moment according to the first position data of the previous first sub-moment, the forward distance and the turning angle includes:

[0052]

[0053]

[0054] Among them, (Lat i+1 , Lon i+1) represents the first position data of the target at the first sub-time; (Lat i , Lon i ) represents the first position data of the previous first sub-moment; θ (i+1) represents the turning angle; L (i+1) Indicates the distance advanced.

[0055] Further, the obtaining of the second position data of the target first sub-moment according to the first position data of the subsequent first sub-moment, the forward distance and the turning angle comprises:

[0056]

[0057]

[0058] Among them, (Lat i-1 , Lon i-1 ) represents the second position data of the target at the first sub-time; (Lat i , Lon i ) represents the first position data of the next first sub-moment; θ (i-1) represents the turning angle; L (i-1) Indicates the distance advanced.

[0059] From the above description, it can be seen that the calculation of the first position data and the second position data is converted into longitude and latitude calculation to realize the longitude and latitude representation of the first position data and the second position data, which is convenient for direct comparison and overlap with known maps and convenient for using the smoothed trajectory.

[0060] Please refer to Figure 2 A terminal for generating a smooth trajectory comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps in the above-mentioned method for generating a smooth trajectory when executing the computer program.

[0061] The above-mentioned method for generating a smooth trajectory of the present invention can be applied to generating a smooth driving trajectory, which is described below through a specific implementation method.

[0062] Please refer to Figure 1 , Embodiment 1 of the present invention is:

[0063] A method for generating a smooth trajectory, comprising the steps of:

[0064] S1. Acquire first driving data corresponding to a first moment and second driving data corresponding to a second moment respectively in chronological order;

[0065] The first driving data includes a vehicle speed set, positioning data and a turning angle set;

[0066] The obtaining of the first driving data corresponding to the first moment includes:

[0067] Divide the time interval from the moment before the first moment to the first moment into a second preset number of second sub-moments, obtain the vehicle speed and the turning angle corresponding to each of the second sub-moments, and obtain a vehicle speed set and a turning angle set; obtain the current position corresponding to the first moment, and obtain the positioning data;

[0068] The data structure of the second driving data is the same as that of the first driving data, specifically:

[0069] The obtaining of the second driving data corresponding to the second moment includes:

[0070] Divide the time interval from the moment before the second moment to the second moment into a second preset number of second sub-moments, obtain the vehicle speed and the turning angle corresponding to each of the second sub-moments, and obtain a vehicle speed set and a turning angle set; obtain the current position corresponding to the second moment, and obtain the positioning data;

[0071] In an optional implementation, the positioning data is latitude and longitude data;

[0072] S2, dividing the time interval from the first moment to the second moment into a first preset number of first sub-moments, and calculating the position prediction data corresponding to each of the sub-moments according to the first driving data and the second driving data;

[0073] In an optional implementation, if the first preset number is equal to the second preset number, there is no need to perform calculation again to make the first sub-moment correspond to the second sub-moment, and the second sub-moment overlaps with the first sub-moment; if the first preset number is not equal to the second preset number, the vehicle speed and turning angle of the first sub-moment are estimated based on the vehicle speed and turning angle corresponding to the second sub-moment;

[0074] When the first preset number is equal to the second preset number, calculating the position prediction data corresponding to each of the sub-times according to the first driving data and the second driving data in S2 includes:

[0075] S21, taking the positioning data corresponding to the first moment as a starting point and the positioning data corresponding to the second moment as an end point, obtaining the first position data corresponding to each of the first sub-moments according to the vehicle speed set and the turning angle set corresponding to the second moment, including:

[0076] Taking the positioning data corresponding to the first moment as a starting point, traversing the first sub-moments, when traversing to a target first sub-moment, obtaining a time difference between the target first sub-moment and a previous first sub-moment, the first position data of the previous first sub-moment, and a vehicle speed and a turning angle corresponding to the target first sub-moment, obtaining an advance distance corresponding to the target first sub-moment according to the vehicle speed and the time difference, and obtaining the first position data of the target first sub-moment according to the first position data of the previous first sub-moment, the advance distance, and the turning angle;

[0077] S22, taking the positioning data corresponding to the first moment as the end point and the positioning data corresponding to the second moment as the starting point, obtaining the second position data corresponding to each of the first sub-moments according to the vehicle speed set and the turning angle set corresponding to the second moment, including:

[0078] Taking the positioning data corresponding to the second moment as a starting point, traversing the first sub-moments, when traversing to a target first sub-moment, obtaining a time difference between the target first sub-moment and a subsequent first sub-moment, the first position data of the subsequent first sub-moment, and a vehicle speed and a turning angle corresponding to the target first sub-moment, obtaining an advance distance corresponding to the target first sub-moment according to the vehicle speed and the time difference, and obtaining a second position data of the target first sub-moment according to the first position data of the subsequent first sub-moment, the advance distance, and the turning angle;

[0079] In S21 and S22, the first sub-moments are sorted in time order. When the target first sub-moment is represented by i+1, the previous first sub-moment is represented by i; when the target first sub-moment is represented by i-1, the next first sub-moment is represented by i. It can be seen that i is just a subscript representation for conveniently distinguishing the order relationship during the traversal process. The target first sub-moment can also be i, the previous first sub-moment is i-1, and the next first sub-moment is i+1. No restriction is made here.

[0080] Then the forward distance corresponding to the first sub-moment of the target includes:

[0081] L i =v i ×t;

[0082] Wherein, Li represents the forward distance corresponding to the first sub-time of the target; vi represents the vehicle speed corresponding to the first sub-time of the target; t represents the time difference;

[0083] In an optional implementation, the forward distance may also be calculated using the average of the vehicle speeds at the first sub-moment and the previous first sub-moment or the next first sub-moment. Then, in S21, L i+1 =(v i+1 +v i ) / 2×t, in S22, Li-1 =(v i-1 +v i ) / 2×t;

[0084] Then, the step of obtaining the first position data of the target at the first sub-moment according to the first position data at the previous first sub-moment, the forward distance and the turning angle in S21 includes:

[0085]

[0086]

[0087] Among them, (Lat i+1 , Lon i+1 ) represents the first position data of the target at the first sub-time; (Lat i , Lon i ) represents the first position data of the previous first sub-moment; θ (i+1) represents the turning angle; L (i+1) represents the distance advanced;

[0088] S21 and S22 also include: when traversing to the first sub-moment of determination that is the same moment as the first moment or the second moment, calculating the difference between the first position data / second position data corresponding to the first sub-moment of determination and the positioning data corresponding to the first moment / second moment, and if the difference exceeds a threshold, adjusting the data value in the forward distance; in an optional implementation, when traversing to the first sub-moment of determination that is the same moment as the first moment or the second moment, the first position data / second position data takes the positioning data corresponding to the first moment / second moment;

[0089] The step of obtaining the second position data of the target at the first sub-moment according to the first position data of the subsequent first sub-moment, the forward distance and the turning angle in S22 includes:

[0090]

[0091]

[0092] Among them, (Lat i-1 , Lon i-1 ) represents the second position data of the target at the first sub-time; (Lat i , Lon i ) represents the first position data of the next first sub-moment; θ (i-1) represents the turning angle; L (i-1) represents the distance advanced;

[0093] When calculating the first position data of the first target at the first sub-moment, it is necessary to obtain the positioning data of the first moment or the second moment. Specifically, in S21, the first sub-moment before the first target at the first sub-moment does not belong to the first sub-moment corresponding to the second moment, so its related data is not in the second driving data at the second moment. At this time, it is necessary to obtain the positioning data of the first sub-moment for calculation, and the same is true for the next first sub-moment in S22.

[0094] S23, calculating the mean of the first position data and the second position data to obtain the position prediction data;

[0095] S3. Obtaining a smooth trajectory from the first moment to the second moment according to the predicted data;

[0096] In an optional implementation, longitude and latitude points corresponding to the position prediction data are obtained according to the position prediction data, and the longitude and latitude points are connected to obtain a smooth trajectory.

[0097] Embodiment 2

[0098] Embodiment 2 of the present application is:

[0099] A method for generating a smooth trajectory, which is different from embodiment 1 in that it also includes:

[0100] S01, obtaining driving data and positioning data of a vehicle to be predicted within a preset time period, and associating the driving data and the positioning data through time information;

[0101] In an optional implementation, the driving data and positioning data of the vehicle to be predicted within one day are obtained. Specifically, the driving data is obtained through a driving recorder, a driving sensor, etc., and the vehicle position data is obtained through a device that records the latitude and longitude of the vehicle, such as a GPS recorder;

[0102] At this time, because the frequency of acquiring driving data is greater than the frequency of acquiring positioning data, the time of acquiring positioning data is used as the dividing point to divide the driving data into different sets; that is, assuming that the positioning data is acquired at the first moment, the driving data corresponding to the first moment is the driving data from the moment before the first moment to the first moment.

[0103] S02, traversing the moment information, when traversing to the first moment, obtaining the next moment after the first moment, that is, the second moment, and executing each step in S1-S3 until all moments in the preset time period are traversed, and obtaining a smooth trajectory prediction of the vehicle in the preset time period.

[0104] Please refer to Figure 3-Figure 5 , Embodiment 3 of the present invention is:

[0105] Apply the above method of generating a smooth trajectory to a practical scenario:

[0106] A1. Collect the vehicle's driving data for the day, including time, speed, positioning data, and turning angle;

[0107] In an optional embodiment, the turning angle is a heading angle, which can be calculated by a steering wheel angle;

[0108] The position at the 0th minute is recorded as (Lat, Lon), and a rectangular coordinate system is established with the origin, due north and due east as follows: Figure 4 ;

[0109] The position at the 1st minute is P 1 (Lat', Lon'), the acquisition speed from the 0th minute to the 1st minute is recorded as: v i =[v 1 ,v 2 , ..., v 58 ], the steering wheel angle is collected from the 0th minute to the 1st minute and the heading angle is calculated as: θ i =[θ 1 ,θ 2 , ..., θ 58 ];

[0110] Then the distance traveled per second from minute 0 to minute 1 is L i =[L 1 , L 2 , ..., L 58 ], the distance traveled per second from the 1st minute to the 0th minute is L' i =[L' 1 ,L' 2 , ..., L' 58 ]; (Since the position information at the 0th minute and the 1st minute is known, no calculation is performed in this embodiment)

[0111] A2, according to P 0 (Lat, Lon) calculates the driving distance L at 1s, 2s, ... 58s in sequence i and the longitude and latitude of the first location data (Lat i , Lon i );

[0112] Reference for calculating the driving distance in the i-th second:

[0113] L i =v i *t;

[0114] The latitude and longitude calculation refers to the following formula:

[0115]

[0116]

[0117] where θ i is the vehicle direction angle, R is the radius of the earth;

[0118] The longitude and latitude position at the i-th second is: (Lat i , Lon i )

[0119] According to P 1 (Lat', Lon') reversely deduce the driving distance L' at 59s, 58s, ... 1s i and the latitude and longitude data of the second location data (Lat' i , Lon' i ):

[0120] Reference for calculating the driving distance in the (i-1)th second:

[0121] L (i-1) =v (i-1) *t

[0122] The latitude and longitude calculation refers to the following formula:

[0123]

[0124]

[0125] When the 0-minute position is inferred from the 1-minute position, the steering wheel angle from the 1-minute to the 0-minute position is recorded as: θ' i =[(θ 1 +180°),(θ 2 +180°),……(θ 59 +180°)];

[0126] A3. Calculate the mean of the first position data and the second position data to obtain the predicted data, and the longitude and latitude data of the predicted data at the i-th second:

[0127] A4. After calculating all minute curves of the day, the smooth trajectory of the day is obtained.

[0128] Please refer to Figure 2 , Embodiment 4 of the present invention is:

[0129] A terminal 1 for generating a smooth trajectory includes a processor 2, a memory 3, and a computer program stored in the memory 3 and executable on the processor 2. When the processor 2 executes the computer program, each step in Embodiment 1, Embodiment 2, or Embodiment 3 is implemented.

[0130] In summary, the present invention provides a method and terminal for generating a smooth trajectory, by recording the driving data of the vehicle while recording the vehicle positioning data, the driving data including speed and turning angle, dividing the time interval for obtaining the positioning data into multiple sub-time intervals to obtain multiple sub-moments, predicting the position data corresponding to each sub-moment according to the known positioning data, speed and turning angle, and refining the points corresponding to two positioning data that are far apart into a combination of multiple points through the driving data, so that the connection line of the driving trajectory is smoother; at the same time, when calculating the point prediction between the two positioning data, the two positioning data are respectively used as starting points for calculation, because the calculation process is based on the position data of the previous point to obtain the position data of the next point, which will cause the accumulation of errors, and calculating and predicting separately from two directions will reduce the impact of the accumulated errors, so that the final smooth trajectory is closer to the actual trajectory of the vehicle, thereby providing reliable reference data for scenarios such as vehicle accident assessment.

[0131] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent transformations made using the contents of the present invention's specification and drawings, or directly or indirectly applied in related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for generating a smooth trajectory, characterized in that: Includes steps: Acquire first driving data corresponding to a first moment and second driving data corresponding to a second moment respectively in chronological order; Divide the time interval from the first moment to the second moment into a first preset number of first sub-moments, and calculate the position prediction data corresponding to each of the first sub-moments according to the first driving data and the second driving data; Obtaining a smooth trajectory from the first moment to the second moment according to the predicted data; The first driving data includes a vehicle speed set, positioning data and a turning angle set, and the obtaining of the first driving data corresponding to the first moment includes: dividing a time interval from a moment before the first moment to the first moment into a second preset number of second sub-moments, obtaining a vehicle speed and a turning angle corresponding to each of the second sub-moments, obtaining a vehicle speed set and a turning angle set, obtaining a current position corresponding to the first moment, and obtaining the positioning data; The method of calculating the position prediction data corresponding to each first sub-moment based on the first driving data and the second driving data includes: taking the positioning data corresponding to the first moment as the starting point, the positioning data corresponding to the second moment as the end point, and obtaining the first position data corresponding to each first sub-moment based on the vehicle speed set and the turning angle set corresponding to the second moment, specifically including: taking the positioning data corresponding to the first moment as the starting point, traversing the first sub-moments, and when traversing to the target first sub-moment, obtaining the time difference between the target first sub-moment and the previous first sub-moment, the first position data of the previous first sub-moment, and the vehicle speed and turning angle corresponding to the target first sub-moment, obtaining the forward distance corresponding to the target first sub-moment based on the vehicle speed and the time difference, and obtaining the first position data of the target first sub-moment based on the first position data of the previous first sub-moment, the forward distance and the turning angle.

2. A method for generating a smooth trajectory according to claim 1, characterized in that: The second driving data has the same data structure as the first driving data.

3. A method for generating a smooth trajectory according to claim 2, characterized in that: The first preset number is equal to the second preset number; The calculating of the position prediction data corresponding to each first sub-time according to the first driving data and the second driving data further includes: Taking the positioning data corresponding to the first moment as the end point and the positioning data corresponding to the second moment as the starting point, obtaining the second position data corresponding to each of the first sub-moments according to the vehicle speed set and the turning angle set corresponding to the second moment; The average of the first position data and the second position data is calculated to obtain the position prediction data.

4. A method for generating a smooth trajectory according to claim 1, characterized in that: The positioning data is longitude and latitude data.

5. A method for generating a smooth trajectory according to claim 3, characterized in that: The method of taking the positioning data corresponding to the first moment as the end point and the positioning data corresponding to the second moment as the starting point, and obtaining the second position data corresponding to each first sub-moment according to the vehicle speed set and the turning angle set corresponding to the second moment comprises: Taking the positioning data corresponding to the second moment as the starting point, traverse the first sub-moment, and when traversing to the target first sub-moment, obtain the time difference between the target first sub-moment and the subsequent first sub-moment, the first position data of the subsequent first sub-moment, and the vehicle speed and turning angle corresponding to the target first sub-moment, obtain the forward distance corresponding to the target first sub-moment according to the vehicle speed and the time difference, and obtain the second position data of the target first sub-moment according to the first position data of the subsequent first sub-moment, the forward distance and the turning angle.

6. A method for generating a smooth trajectory according to claim 1 or 5, characterized in that: The step of obtaining the advance distance corresponding to the target first sub-time according to the vehicle speed and the time difference comprises: L i =v i ×t; Wherein, Li represents the forward distance corresponding to the first sub-moment of the target; vi represents the vehicle speed corresponding to the first sub-moment of the target; and t represents the time difference.

7. A method for generating a smooth trajectory according to claim 1, characterized in that: The obtaining of the first position data of the target at the first sub-moment according to the first position data of the previous first sub-moment, the forward distance and the turning angle comprises: Among them, (Lat i+1 ,Lon i+1 ) represents the first position data of the target at the first sub-time; (Lat i ,Lon i ) represents the first position data of the previous first sub-moment; θ (i+1) represents the turning angle; L (i+1) Indicates the distance advanced.

8. A method for generating a smooth trajectory according to claim 5, characterized in that: The obtaining of the second position data of the target first sub-time according to the first position data of the subsequent first sub-time, the forward distance and the turning angle comprises: Among them, (Lat i-1 ,Lon i-1 ) represents the second position data of the target at the first sub-time; (Lat i ,Lon i ) represents the first position data of the next first sub-moment; θ (i-1) represents the turning angle; L (i-1) Indicates the distance advanced.

9. A terminal for generating a smooth trajectory, 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, the steps in the method for generating a smooth trajectory described in any one of claims 1 to 8 are implemented.

Images