A vehicle driving assistance method and system for driving training
By calculating the minimum distance point and trajectory distance value between the vehicle's current trajectory and historical trajectories, the most similar trajectory is selected and auxiliary data is generated, which solves the problem of driver operation deviation in existing technologies and realizes real-time and accurate driving assistance.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- DUOLUN INTERNET TECH CO LTD
- Filing Date
- 2026-05-09
- Publication Date
- 2026-07-07
AI Technical Summary
Existing technologies cannot provide accurate and quantitative operational assistance suggestions in real time during vehicle driving, resulting in significant deviations in driver operation or inconsistencies with the expected driving trajectory, especially when driving on complex routes or at high speeds, making timely correction difficult.
By acquiring the vehicle's current trajectory and historical trajectory set, calculating the minimum distance point and trajectory distance value, filtering out the most similar trajectory, extracting reference data and generating auxiliary data, and providing quantitative driving suggestions in real time.
It enables real-time matching of historical and current trajectories during vehicle operation, providing quantifiable and actionable auxiliary information, improving the timeliness and accuracy of driving assistance, and reducing operational deviations.
Smart Images
Figure CN122347893A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of driver training technology, and more specifically, to a vehicle driving assistance method and system for driver training. Background Technology
[0002] In fixed or semi-fixed route driving scenarios, drivers need to follow certain operating procedures to complete the route, such as adjusting speed before curves, turning the steering wheel at specific positions, and maintaining a reasonable heading angle. Currently, common driver assistance methods mainly rely on the driver's own experience or voice prompts from others. However, different drivers have different driving habits, reaction speeds, and operational precision, which can easily lead to significant operational deviations or discrepancies between the actual driving trajectory and the intended trajectory during actual driving.
[0003] In related technologies, vehicle-mounted sensors are typically used to record driving trajectories. However, these methods cannot compare the differences between current operations and historical trajectories in real time during driving, nor can they provide quantitative operational assistance suggestions. Furthermore, because different drivers have different driving habits, the length and speed of the vehicle's trajectory also vary. Simply comparing the trajectory points in the current driving trajectory with those in the historical trajectory point by point cannot accurately measure the degree of similarity between these unequal-length trajectories.
[0004] As can be seen from the above, the relevant technologies do not provide any technical insights into how to provide timely and accurate assistance to the driver while the vehicle is in motion. Summary of the Invention
[0005] Therefore, it is necessary to provide a vehicle driving assistance method and system for driver training to address the above problems. This system can match the sub-trajectory corresponding to the current trajectory from the historical trajectory in real time during vehicle operation, and provide quantifiable and operable assistance information.
[0006] This application provides a vehicle driving assistance method for driver training, including: Obtain the vehicle's current trajectory, which includes multiple trajectory points arranged in chronological order; Obtain the vehicle's historical trajectory set, which includes multiple historical trajectories, each of which contains multiple trajectory points arranged in chronological order; Traverse the set of historical trajectories and obtain the minimum distance point between each historical trajectory and the current trajectory; the minimum distance point is the trajectory point on the historical trajectory that is closest to the last trajectory point of the current trajectory. For each historical trajectory, the sub-trajectory from the starting trajectory point to the minimum distance point on the historical trajectory is taken as the valid trajectory; Filter out the most similar trajectory to the current trajectory from the sub-trajectories of each historical trajectory; Extract reference data for the next trajectory point from the historical trajectory corresponding to the most similar trajectory; The running status data of the last trajectory point of the current trajectory is compared with the reference data to generate auxiliary data, which is used to assist vehicle driving.
[0007] In one optional implementation, the historical trajectory set is traversed to obtain the minimum distance point between each historical trajectory and the current trajectory, including: Calculate the Euclidean distance between the last trajectory point of the current trajectory and each trajectory point in the historical trajectory, and determine the point with the smallest Euclidean distance value as the minimum distance point.
[0008] In one alternative implementation, the most similar trajectory to the current trajectory is selected from the sub-trajectories of each historical trajectory, including: Calculate the trajectory distance between the valid trajectory and the current trajectory, and select the valid trajectory with the smallest trajectory distance as the most similar trajectory; The trajectory distance value between the valid trajectory and the current trajectory is used to indicate the degree of similarity between the valid trajectory and the current trajectory.
[0009] In one optional implementation, calculating the trajectory distance value between the valid trajectory and the current trajectory includes: Construct a cumulative distance matrix with the number of trajectory points in the current trajectory as the number of rows and the number of trajectory points in the valid trajectories as the number of columns; The cumulative distance is calculated cell by cell according to the recursive relationship, and the value in the lower right corner of the cumulative distance matrix is taken as the trajectory distance value.
[0010] In one optional implementation, reference data for the next trajectory point of the minimum distance point is extracted from the historical trajectories corresponding to the most similar trajectories, including: If the minimum distance point is not the last trajectory point in the historical trajectory corresponding to the most similar trajectory, then extract the reference data; If the minimum distance point is the last trajectory point in the historical trajectory corresponding to the most similar trajectory, then the process of assisting the vehicle to drive ends.
[0011] In one optional implementation, the reference data includes at least the vehicle's reference speed, reference heading angle, and reference steering wheel angle; the running status data of the last trajectory point of the current trajectory includes at least the vehicle's current driving speed, heading angle, and steering wheel angle. The running status data of the last trajectory point in the current trajectory is compared with the reference data to generate auxiliary data, including: After extracting the reference data, the speed difference between the vehicle's current speed and the reference speed, the heading angle difference between the vehicle's current heading angle and the reference heading angle, and the angle difference between the vehicle's current steering wheel angle and the reference steering wheel angle are calculated respectively. The speed difference, heading angle difference, and angle difference are output as auxiliary data.
[0012] In one alternative implementation, the method further includes: When the vehicle travels to the last trajectory point in the historical trajectory corresponding to the most similar trajectory, the current trajectory is added to the historical trajectory set; Record the number of times each historical trajectory is used in the historical trajectory set, and calculate the usage frequency of each historical trajectory based on the number of times it is used; When the usage frequency is lower than the preset frequency threshold, the corresponding historical trajectory will be removed from the historical trajectory set.
[0013] Furthermore, this application also provides a vehicle driving assistance system for driver training, used to implement the aforementioned vehicle driving assistance method for driver training, comprising: Data acquisition module: used to acquire the vehicle's current trajectory, which includes multiple trajectory points arranged in chronological order; Obtain the vehicle's historical trajectory set, which includes multiple historical trajectories, each of which contains multiple trajectory points arranged in chronological order; Trajectory calculation module: used to traverse the historical trajectory set and obtain the minimum distance point between each historical trajectory and the current trajectory; the minimum distance point is the trajectory point on the historical trajectory that is closest to the last trajectory point of the current trajectory; For each historical trajectory, the sub-trajectory from the starting trajectory point to the minimum distance point on the historical trajectory is taken as the valid trajectory; Track filtering module: Used to filter out the most similar track to the current track from the sub-tracks of each historical track; Data generation module: used to extract reference data for the next trajectory point of the minimum distance point from the historical trajectory corresponding to the most similar trajectory; The running status data of the last trajectory point of the current trajectory is compared with the reference data to generate auxiliary data, which is used to assist vehicle driving.
[0014] In another aspect, this application also provides an electronic device, comprising: The memory and processor are interconnected and communicate with each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the aforementioned vehicle driving assistance methods for driver training.
[0015] In another aspect, this application also provides a computer-readable storage medium storing computer instructions for causing a computer to perform the aforementioned vehicle driving assistance method for driver training.
[0016] Compared to existing technologies, the advantages of this application are: (1) This application obtains the current trajectory and historical trajectory set of the vehicle, traverses each historical trajectory to find the minimum distance point closest to the last trajectory point of the current trajectory, and takes the sub-trajectory from the starting point of the historical trajectory to the minimum distance point as the valid trajectory. Then, it calculates the trajectory distance value between the valid trajectory and the current trajectory to filter the most similar trajectory, and extracts the reference data of the next trajectory point in the historical trajectory corresponding to the most similar trajectory. It can accurately locate the reference object closest to the current driving performance from the historical trajectory set. Subsequently, the reference data is compared with the running status data of the last trajectory point of the current trajectory to generate auxiliary data, thereby predicting the ideal operating state at the next moment. Thus, this application can match the sub-trajectory corresponding to the current trajectory in the historical trajectory in real time during vehicle driving, and provide quantitative and operable auxiliary information, overcoming the problems of related technologies relying on subjective experience, feedback lag and lack of quantitative standards, and improving the timeliness and accuracy of driving assistance.
[0017] (2) This application calculates the Euclidean distance between the last trajectory point of the current trajectory and each trajectory point of the historical trajectory, and determines the trajectory point with the smallest distance as the minimum distance point. This can quickly and accurately locate the closest corresponding position of two trajectories in space, providing a reliable basis for extracting effective trajectories. Attached Figure Description
[0018] Figure 1 A flowchart of a vehicle driving assistance method for driver training provided in an embodiment of this application; Figure 2 A schematic diagram illustrating the matching of the current trajectory with multiple historical trajectories provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation
[0019] To make the above-mentioned objectives, features, and advantages of this application more apparent and understandable, the specific embodiments of this application are described in detail below with reference to the accompanying drawings. Many specific details are set forth in the following description to provide a thorough understanding of this application. However, this application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar modifications without departing from the spirit of this application. Therefore, this application is not limited to the specific embodiments disclosed below.
[0020] During driver training, trainees are required to complete a route within a fixed area according to specific operating procedures, such as adjusting speed before curves, turning the steering wheel at specific points, and maintaining a reasonable heading angle. Currently, common assistance methods mainly rely on the instructor's manual observation and voice prompts, which suffer from strong subjectivity, delayed feedback, and a lack of quantifiable standards. Different trainees have different driving habits, reaction speeds, and operational precision, leading to significant operational deviations or discrepancies from the expected driving trajectory during actual driving. This is especially true when the vehicle is traveling at high speeds or the route is complex, making it difficult for trainees to promptly perceive the degree of deviation between their own trajectory and the ideal trajectory.
[0021] Therefore, in order to solve the above problems, this application provides a method for assisting vehicle driving. Figure 1 A flowchart of a method for assisted vehicle driving according to an embodiment of this application is shown, with reference to... Figure 1 As shown, the method includes the following steps: S1. Obtain the vehicle's current trajectory and historical trajectory set.
[0022] Specifically, the current trajectory includes multiple trajectory points arranged in chronological order; the historical trajectory set includes multiple historical trajectories of the vehicle traveling within the target area, with multiple historical trajectories having the same starting and ending positions, and each historical trajectory including multiple trajectory points arranged in chronological order.
[0023] In this embodiment, the vehicle is equipped with a data acquisition system, which includes a Global Navigation Satellite System (GNSS) positioning module, wheel speed sensors, an Inertial Measurement Unit (IMU), and a steering wheel angle sensor. During vehicle operation, the data acquisition system continuously collects the vehicle's operating status data at a preset frequency, generating a trajectory point each time. All collected trajectory points are arranged in chronological order to form the current trajectory.
[0024] In this embodiment, the historical trajectory set is pre-stored in the vehicle's onboard storage or a cloud server. Each historical trajectory originates from a past driving process characterized by no violations and smooth driving, or a trajectory deemed acceptable based on indicators such as trajectory smoothness and deviation from the standard path. Each historical trajectory consists of multiple trajectory points arranged in chronological order. Specifically, each trajectory point includes at least the following information: the vehicle's current position coordinates, including the x and y coordinates; the driving speed; the heading angle; and the steering wheel angle. All trajectory points use the same coordinate system and units, and undergo preprocessing such as noise reduction and interpolation after acquisition.
[0025] In one specific embodiment, the current trajectory is the trajectory data collected by the trainee during driving training while driving in a designated area (e.g., right-angle turn, reversing into a parking space, or curved driving). Each trajectory point includes at least the following information: the vehicle's current position coordinates, driving speed, heading angle, and steering wheel angle. The position coordinates are established with a preset reference point within the area as the origin; the heading angle represents the angle between the vehicle's front direction and the area's markings; and the steering wheel angle reflects the trainee's steering intention during operation.
[0026] In a specific embodiment, the trajectory points in the current trajectory and the historical trajectory can be defined using the following mathematical form: Let the current trajectory be... ,in The vehicle's current position coordinates, For driving speed, For heading angle, For steering wheel angle, This represents the total number of trajectory points. The historical trajectory set is defined as follows: ,in For the first The number of trajectory points in a historical trajectory. This represents the total number of historical trajectories.
[0027] S2. Traverse the set of historical trajectories and obtain the minimum distance point between each historical trajectory and the current trajectory; for each historical trajectory, take the sub-trajectory from the starting trajectory point to the minimum distance point as the valid trajectory.
[0028] Specifically, the minimum distance point is the trajectory point on the historical trajectory that is closest to the last trajectory point of the current trajectory.
[0029] Specifically, iterate through the set of historical trajectories to obtain the minimum distance point between each historical trajectory and the current trajectory, including: Calculate the Euclidean distance between the last trajectory point of the current trajectory and each trajectory point in the historical trajectory, and determine the point with the smallest Euclidean distance value as the minimum distance point.
[0030] In this embodiment, the current trajectory is recorded as The last trajectory point of the current trajectory is recorded as .in: This represents the total number of data collection points for the current trajectory.
[0031] Let the set of historical trajectories be denoted as .in: This represents the total number of historical trajectories.
[0032] For the Historical trajectory It contains Let there be a trajectory point, denoted as... Traversing the first Historical trajectory All trajectory points ( ), calculate the last trajectory point of the current trajectory respectively. With each Euclidean distance between After traversing the entire process, the historical trajectory will be recorded. The point on the trajectory that minimizes the Euclidean distance is determined as the minimum distance point. Its index is denoted as The corresponding minimum distance value is denoted as The process is as follows: ; ; For each historical trajectory In determining the minimum distance point Then, the historical trajectory is traced from the starting point. to the minimum distance point Extract all trajectory points between (including the given point) in their original order to form the valid trajectory corresponding to this historical trajectory, denoted as . The length of the effective trajectory is .
[0033] Specifically, in the historical trajectory set, all valid trajectories corresponding to historical trajectories together form the valid trajectory set, denoted as . This is used for subsequent similarity calculations.
[0034] In a specific embodiment, for a right-angle turn, the effective trajectory refers to the sub-trajectory from the deceleration point before the student enters the turn to the point where the steering wheel begins to straighten. This sub-trajectory contains the most critical speed control and steering coordination information during the turn, and is the core area for measuring whether the student's operation is standardized.
[0035] S3. Filter out the most similar trajectory to the current trajectory from the sub-trajectories of each historical trajectory.
[0036] Specifically, the trajectory distance value between the valid trajectory and the current trajectory is calculated to indicate the similarity between them. The valid trajectory with the smallest trajectory distance value is selected as the most similar trajectory.
[0037] Specifically, the trajectory distance value between the valid trajectory and the current trajectory is calculated, including: Construct a cumulative distance matrix with the number of trajectory points in the current trajectory as the number of rows and the number of trajectory points in the valid trajectory as the number of columns; calculate the cumulative distance cell by cell according to the recursive relationship, and take the value of the lower right corner of the cumulative distance matrix as the trajectory distance value.
[0038] In this embodiment, for the current trajectory (length is) (trajectories of individual points) and the set of valid trajectories Each valid trajectory (length is) (Each trajectory point) uses the Dynamic Time Warping (DTW) algorithm to calculate the trajectory distance between the two, thereby quantifying the similarity between the current trajectory and each valid trajectory.
[0039] Specifically, construct a Cumulative distance matrix row index The trajectory point number corresponding to the current trajectory (from 1 to ...) ), column index The trajectory point number corresponding to the valid trajectory (from 1 to ...) Each element in the cumulative distance matrix. Indicates the current trajectory before Before each point and the effective trajectory The cumulative distance between points.
[0040] First, calculate the distance at the starting point of the cumulative distance matrix. That is, it is equal to the distance between the first trajectory point of the current trajectory and the first trajectory point of the valid trajectory (the starting point of the cumulative distance matrix corresponds to the matching cost of the starting points of the two sequences).
[0041] Then, fill in the first row (only following the valid trajectory) and the first column (only following the current trajectory). Following only the valid trajectory is equivalent to the current trajectory stopping at the first point, with the valid trajectory gradually increasing in points.
[0042] Specifically, for , Equal to the first trajectory point of the current trajectory and the valid trajectory point The distance between each trajectory point, plus the cumulative distance from the previous column. ;for , Equal to the current trajectory number The distance between each trajectory point and the first trajectory point of the valid trajectory, plus the cumulative distance of the previous row. The calculation process is as follows: ; ; ; Finally, for each cell in the remaining positions of the cumulative distance matrix ( and Its value is determined by the minimum of the distance between the current two points plus the distance between the three adjacent left, top, and top-left cells. The calculation process is as follows: ; In the formula: For the current trajectory The trajectory point and the valid trajectory Distance values between trajectory points; This indicates that the current trajectory has moved forward one point, while the valid trajectory remains stationary; This indicates that the valid trajectory advances one point, while the current trajectory remains stationary. This means that the current trajectory and the valid trajectory advance one point simultaneously, and the minimum value among the three is the destination. The cumulative cost of the optimal alignment path.
[0043] After calculating the entire matrix, the bottom right element of the cumulative distance matrix is... That is, the current trajectory With valid trajectory The original trajectory distance between the two points. Since the original trajectory distance increases with trajectory length, to eliminate the influence of different trajectory lengths on the distance value, it is normalized. The normalized trajectory distance is obtained by dividing the original trajectory distance by the sum of the current trajectory length and the effective trajectory length. The calculation process is as follows: ; This is the normalized trajectory distance; the smaller the value, the more similar the two trajectories are.
[0044] Iterate through the set of valid trajectories, calculate the normalized trajectory distance for each valid trajectory, and select the valid trajectory with the smallest normalized distance as the most similar trajectory. The process is as follows: ; ; Through the above process, the most similar trajectory was obtained. This is used to indicate the sub-track that is most similar to the current track among all historical tracks.
[0045] Reference Figure 2 As shown, Figure 2The diagram illustrates the matching relationship between the current trajectory and multiple historical trajectories. Curve a represents the current driving trajectory, while curves b and c represent two different historical trajectories. At the trajectory comparison starting point O, the distance between curve a and curve b is less than the distance between curve a and curve c. Therefore, the historical trajectory corresponding to curve b is determined as the most similar trajectory, and auxiliary prompts are generated after point O based on the characteristics of curve b.
[0046] S4. Extract reference data for the next trajectory point of the minimum distance point from the historical trajectory corresponding to the most similar trajectory; compare the running status data of the last trajectory point of the current trajectory with the reference data and generate auxiliary data to assist vehicle driving.
[0047] Specifically, the reference data includes at least the vehicle's reference speed, reference heading angle, and reference steering wheel angle; the operating status data of the last trajectory point of the current trajectory includes at least the vehicle's current driving speed, heading angle, and steering wheel angle.
[0048] Specifically, from the historical trajectories corresponding to the most similar trajectory, reference data for the next trajectory point of the minimum distance point is extracted, including: if the minimum distance point is not the last trajectory point in the historical trajectory corresponding to the most similar trajectory, then reference data is extracted; if the minimum distance point is the last trajectory point in the historical trajectory corresponding to the most similar trajectory, then the process of assisted vehicle driving ends.
[0049] Specifically, the state data of the last trajectory point of the current trajectory is compared with the reference data to generate auxiliary data, including: after extracting the reference data, calculating the speed difference between the vehicle's current driving speed and the reference speed, the heading angle difference between the vehicle's current heading angle and the reference heading angle, and the angle difference between the vehicle's current steering wheel angle and the reference steering wheel angle, and outputting the speed difference, heading angle difference, and angle difference as auxiliary data.
[0050] In this embodiment, let's assume that the most similar trajectory selected in step S3 is... Derived from historical trajectory And the index of the minimum distance point on the historical trajectory determined in step S2 is .
[0051] judge With historical trajectory Total points Size relationship: like This indicates that the point with the minimum distance is not the last point in the historical trajectory. Therefore, the point from the historical trajectory is extracted as follows: trajectory points And obtain the following three parameters as reference data: reference speed Reference heading angle Reference steering wheel angle .
[0052] like This indicates that the minimum distance point has aligned with the last point of the historical trajectory, meaning the current vehicle position has reached the end of the historical trajectory, thus ending the current assisted vehicle driving process.
[0053] After obtaining the reference data, obtain the last trajectory point of the current trajectory. Operating status data: Current vehicle speed The vehicle's current heading angle The current steering wheel angle of the vehicle Calculate the speed difference between the vehicle's current speed and the reference speed. The difference between the vehicle's current heading angle and the reference heading angle. The angle difference between the current steering wheel angle and the reference steering wheel angle. The calculation process is as follows: ; ; ; like A positive value indicates that the current speed is too fast; if A negative value indicates that the current speed is too slow; if A positive value indicates oversteering; if... A negative value indicates insufficient steering wheel steering.
[0054] The three differences calculated above are output as auxiliary data, which can be displayed on a vehicle screen or announced via voice.
[0055] In a specific embodiment, taking a right-angle turn in driving training as an example, suppose the reference point after the minimum distance point of a certain historical trajectory is: steering wheel angle 180 degrees to the right, speed 10 km / h. If the current trainee's actual steering wheel angle is 150 degrees to the right (angle difference - 30 degrees) and the actual speed is 15 km / h (speed difference + 5 km / h), then the output auxiliary data can be used to generate operation prompts for this project, such as prompting the trainee to increase the steering wheel angle or decrease the vehicle speed. The calculated difference is converted into information directly related to specific driving actions, helping trainees to correct operational deviations in real time during actual driving.
[0056] In this embodiment, the most similar trajectory Derived from historical trajectory Its length is the index of the minimum distance point, denoted as . The endpoint of the most similar trajectory (i.e., the point with the minimum distance) is defined as... ,in Here are the position coordinates. The next trajectory point is defined as... .
[0057] S5. When the vehicle travels to the last trajectory point in the historical trajectory corresponding to the most similar trajectory, add the current trajectory to the historical trajectory set; record the number of times each historical trajectory in the historical trajectory set is used, and calculate the usage frequency of each historical trajectory based on the number of times it is used; when the usage frequency is lower than the preset frequency threshold, remove the corresponding historical trajectory from the historical trajectory set.
[0058] Specifically, when the vehicle reaches the last trajectory point in the historical trajectory corresponding to the most similar trajectory, the current trajectory is added to the historical trajectory set as a new historical trajectory. In addition, the number of times each historical trajectory in the historical trajectory set is selected as the most similar trajectory is recorded. Each time step S3 is executed and the most similar trajectory is successfully selected, the usage count of the corresponding historical trajectory is incremented by 1.
[0059] In this embodiment, after every 100 matches or after each addition of a new historical trajectory, historical trajectories with a usage frequency below a preset frequency threshold are removed from the historical trajectory set. The usage frequency is the proportion of the number of times a historical trajectory is used relative to the total number of times all historical trajectories are used; in this embodiment, it is 1%. This step ensures the timeliness and effectiveness of the historical trajectory set.
[0060] This application also provides a vehicle driving assistance system for driver training, which implements the above embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.
[0061] This application provides a vehicle driving assistance system for driver training, including: Data acquisition module: used to acquire the current trajectory of the vehicle, the current trajectory including multiple trajectory points arranged in chronological order; Obtain a set of historical trajectories for the vehicle, wherein the set of historical trajectories includes multiple historical trajectories, and each historical trajectory includes multiple trajectory points arranged in chronological order; Trajectory calculation module: used to traverse the set of historical trajectories and obtain the minimum distance point between each historical trajectory and the current trajectory; the minimum distance point is the trajectory point on the historical trajectory that is closest to the last trajectory point of the current trajectory; For each historical trajectory, the sub-trajectory from the starting trajectory point to the minimum distance point on the historical trajectory is taken as the valid trajectory; Trajectory filtering module: used to filter out the most similar trajectory to the current trajectory from the sub-trajectories of each historical trajectory; Data generation module: used to extract reference data of the next trajectory point of the minimum distance point from the historical trajectory corresponding to the most similar trajectory; The running status data of the last trajectory point of the current trajectory is compared with the reference data to generate auxiliary data, which is used to assist vehicle driving.
[0062] Reference Figure 3 As shown, Figure 3 This is a schematic diagram of the structure of an electronic device provided in an optional embodiment of the present invention. This electronic device can be a computer device used to execute the above-described method. Figure 3 As shown, the electronic device includes one or more processors 10, a memory 20, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processor can process instructions executed within the electronic device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces).
[0063] The processor 10 may further include a hardware chip. This hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.
[0064] The memory 20 stores instructions executable by at least one processor 10 to cause the at least one processor 10 to perform the method shown in the above embodiments.
[0065] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created by the use of the electronic device based on the display of a mini-program landing page. Furthermore, the memory 20 may include high-speed random access memory (RAM), and may also include non-transient memory, such as at least one disk storage device, flash memory device, or other non-transient solid-state storage device. The memory 20 may include volatile memory, such as RAM; the memory may also include non-volatile memory, such as flash memory, hard disk, or solid-state drive; the memory 20 may also include combinations of the above types of memory.
[0066] The electronic device also includes a communication interface 30 for communicating with other devices or communication networks.
[0067] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.
[0068] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0069] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this invention patent should be determined by the appended claims.
Claims
1. A vehicle driving assistance method for driver training, characterized in that, The method includes: Obtain the current trajectory of the vehicle, which includes multiple trajectory points arranged in chronological order; Obtain a set of historical trajectories for the vehicle, wherein the set of historical trajectories includes multiple historical trajectories, and each historical trajectory includes multiple trajectory points arranged in chronological order; Traverse the set of historical trajectories and obtain the minimum distance point between each historical trajectory and the current trajectory; the minimum distance point is the trajectory point on the historical trajectory that is closest to the last trajectory point of the current trajectory. For each historical trajectory, the sub-trajectory from the starting trajectory point to the minimum distance point on the historical trajectory is taken as the valid trajectory; The most similar trajectory to the current trajectory is selected from the sub-trajectories of each historical trajectory. Extract reference data for the next trajectory point of the minimum distance point from the historical trajectories corresponding to the most similar trajectories; The running status data of the last trajectory point of the current trajectory is compared with the reference data to generate auxiliary data, which is used to assist vehicle driving in driver training.
2. The vehicle driving assistance method for driver training according to claim 1, characterized in that, The process of traversing the historical trajectory set and obtaining the minimum distance point between each historical trajectory and the current trajectory includes: Calculate the Euclidean distance between the last trajectory point of the current trajectory and each trajectory point in the historical trajectory, and determine the point with the smallest Euclidean distance value as the minimum distance point.
3. The vehicle driving assistance method for driver training according to claim 1, characterized in that, The step of selecting the most similar trajectory to the current trajectory from the sub-trajectories of each historical trajectory includes: Calculate the trajectory distance value between the valid trajectory and the current trajectory, and select the valid trajectory with the smallest trajectory distance value as the most similar trajectory; The trajectory distance value between the valid trajectory and the current trajectory is used to indicate the degree of similarity between the valid trajectory and the current trajectory.
4. The vehicle driving assistance method for driver training according to claim 3, characterized in that, Calculating the trajectory distance between the valid trajectory and the current trajectory includes: Construct a cumulative distance matrix with the number of trajectory points of the current trajectory as the number of rows and the number of trajectory points of the valid trajectory as the number of columns; The cumulative distance is calculated cell by cell according to the recursive relationship, and the value of the lower right corner of the cumulative distance matrix is taken as the trajectory distance value.
5. The vehicle driving assistance method for driver training according to claim 1, characterized in that, The step of extracting reference data for the next trajectory point of the minimum distance point from the historical trajectory corresponding to the most similar trajectory includes: If the minimum distance point is not the last trajectory point in the historical trajectory corresponding to the most similar trajectory, then extract reference data; If the minimum distance point is the last trajectory point in the historical trajectory corresponding to the most similar trajectory, then the assisted vehicle driving process ends.
6. The vehicle driving assistance method for driver training according to claim 5, characterized in that, The reference data includes at least the vehicle's reference speed, reference heading angle, and reference steering wheel angle; the running status data of the last trajectory point of the current trajectory includes at least the vehicle's current driving speed, heading angle, and steering wheel angle. The step of comparing the running status data of the last trajectory point of the current trajectory with the reference data and generating auxiliary data includes: After extracting the reference data, the speed difference between the vehicle's current speed and the reference speed, the heading angle difference between the vehicle's current heading angle and the reference heading angle, and the angle difference between the vehicle's current steering wheel angle and the reference steering wheel angle are calculated respectively. The speed difference, heading angle difference, and angle difference are output as auxiliary data.
7. The vehicle driving assistance method for driver training according to claim 1, characterized in that, The method further includes: When the vehicle travels to the last trajectory point in the historical trajectory corresponding to the most similar trajectory, the current trajectory is added to the historical trajectory set; Record the number of times each historical trajectory is used in the historical trajectory set, and calculate the usage frequency of each historical trajectory based on the number of times it is used; When the usage frequency is lower than a preset frequency threshold, the corresponding historical trajectory is removed from the historical trajectory set.
8. A vehicle driving assistance system for driver training, used to implement the vehicle driving assistance method for driver training as described in any one of claims 1 to 7, characterized in that, The system includes: Data acquisition module: used to acquire the current trajectory of the vehicle, the current trajectory including multiple trajectory points arranged in chronological order; Obtain a set of historical trajectories for the vehicle, wherein the set of historical trajectories includes multiple historical trajectories, and each historical trajectory includes multiple trajectory points arranged in chronological order; Trajectory calculation module: used to traverse the set of historical trajectories and obtain the minimum distance point between each historical trajectory and the current trajectory; the minimum distance point is the trajectory point on the historical trajectory that is closest to the last trajectory point of the current trajectory; For each historical trajectory, the sub-trajectory from the starting trajectory point to the minimum distance point on the historical trajectory is taken as the valid trajectory; Trajectory filtering module: used to filter out the most similar trajectory to the current trajectory from the sub-trajectories of each historical trajectory; Data generation module: used to extract reference data of the next trajectory point of the minimum distance point from the historical trajectory corresponding to the most similar trajectory; The running status data of the last trajectory point of the current trajectory is compared with the reference data to generate auxiliary data, which is used to assist vehicle driving.
9. An electronic device, characterized in that, include: A memory and a processor are communicatively connected, the memory storing computer instructions, and the processor executing the computer instructions to perform the vehicle driving assistance method for driving training as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the vehicle driving assistance method for driver training as described in any one of claims 1 to 7.