Yaw determination method and apparatus, computer device, and storage medium

Abstract

The application discloses a yaw determination method and device, computer equipment and a storage medium, the method comprises the following steps: when the target vehicle yaw, obtaining the original trajectory point information, the actual yaw time, the path information of the re-planned path and the time of the re-planned path of the target vehicle; based on the original trajectory point information, determining the actual driving path of the target vehicle; based on the actual yaw time, the time of the re-planned path and the actual driving path, determining the yaw trajectory; based on the yaw trajectory and the planned path before the target vehicle yaw, determining whether the target vehicle is in an error-prone scene; if the target vehicle is in an error-prone scene, determining whether the yaw misjudgment occurs. Not only can the driver's driving path be restored more accurately, but also the original trajectory point can be compatible with the complex scenes such as the road network equidistance deviation and the parallel road, so as to determine whether the current yaw determination of the navigation engine is wrong, thereby improving the accuracy and integrity of the yaw determination of the navigation engine.

Description

Yaw determination methods, apparatus, computer equipment and storage media Technical Field

[0001] This invention relates to the field of navigation technology, and in particular to a yaw determination method, apparatus, and storage medium. Background Technology

[0002] With the development of mobile internet and navigation technologies, people are increasingly reliant on map navigation applications for daily travel, and their demands for accuracy and sensitivity in navigation are also rising. Among these, the experience of deviation detection is crucial in navigation engine applications. Users expect deviation detection to be both accurate and sensitive. Incorrect deviation detection can lead to incorrect new routes and announcements, causing unnecessary detours and safety hazards. Conversely, slow deviation detection can result in delayed or lost guidance information and discrepancies with actual road information, both contributing to a poor user experience. Summary of the Invention

[0003] Therefore, it is necessary to provide a yaw determination method, apparatus, computer equipment, and storage medium to address the aforementioned technical problems and solve at least one of the problems existing in the prior art.

[0004] In a first aspect, embodiments of this application provide a yaw determination method, including:

[0005] When the target vehicle deviates from its course, obtain the target vehicle's original trajectory point information, actual deviation time, replanned path information, and replanning time.

[0006] Based on the original trajectory point information, the actual driving path of the target vehicle is determined;

[0007] Based on the actual yaw time, the time of replanning the route, and the actual driving route, the yaw trajectory is determined;

[0008] Based on the yaw trajectory and the planned path of the target vehicle before the yaw, determine whether the target vehicle is in a fault-prone scenario;

[0009] If the target vehicle is in a non-error-prone scenario, determine whether a yaw misjudgment has occurred.

[0010] In one embodiment, determining whether the target vehicle is in a fault-prone scenario based on the yaw trajectory and the planned path before the target vehicle veered off course includes:

[0011] Determine the first trajectory curve and yaw path corresponding to the yaw trajectory;

[0012] Based on the yaw path, determine the second trajectory curve;

[0013] Based on the map size of the first trajectory curve and the second trajectory curve, the corresponding third trajectory curve is extracted from the planned path before the target vehicle veers off course.

[0014] Compare the first trajectory curve, the second trajectory curve, and the third trajectory curve pairwise;

[0015] Based on the comparison results, it is determined whether the target vehicle is in a fault-prone scenario.

[0016] In one embodiment, determining whether the target vehicle is in a fault-prone scenario based on the comparison results includes:

[0017] If the second trajectory curve does not overlap with the third trajectory curve, the similarity between any two of the first, second, and third trajectory curves is greater than a preset similarity threshold, and the similarity between the first and second trajectory curves is greater than the similarity between the first and third trajectory curves, then the target vehicle is determined to be in a fault-prone scenario.

[0018] In one embodiment, determining whether a yaw misjudgment has occurred if the target vehicle is in an error-prone scenario includes:

[0019] If the target vehicle is in a fault-prone scenario, determine the comprehensive probability between different roads in the actual driving path;

[0020] Based on the product of the comprehensive probability and the preset penalty weight, the optimal matching path other than the actual driving path is determined from the candidate paths;

[0021] The optimal matching path is compared with the planned path before the target vehicle veered off course;

[0022] Based on the comparison results, it can be determined whether a yaw misjudgment has occurred.

[0023] In one embodiment, after determining whether the target vehicle is in a fault-prone scenario, the method further includes:

[0024] If the target vehicle is in a non-error-prone scenario, determine whether a yaw misjudgment has occurred.

[0025] In one embodiment, determining whether a yaw misjudgment has occurred includes:

[0026] Determine the yaw path corresponding to the yaw trajectory;

[0027] Compare the yaw path with the planned path of the target vehicle before it veered off course;

[0028] Based on the comparison results, determine whether a yaw misjudgment occurred.

[0029] In one embodiment, determining the yaw trajectory based on the actual yaw time, the time of replanning the route, and the actual travel path includes:

[0030] Based on the actual yaw time, determine the target yaw trajectory point;

[0031] Based on the target yaw trajectory point, the start trajectory point and end trajectory point are determined in the actual driving path;

[0032] The yaw trajectory is obtained based on the starting trajectory point and the ending trajectory point.

[0033] In one embodiment, after determining whether a yaw misjudgment has occurred, the method further includes:

[0034] When no yaw misjudgment occurs, determine the yaw error rate of the navigation engine;

[0035] Determine the yaw response duration in response to this navigation decision;

[0036] The yaw determination effect of the navigation engine is evaluated based on the yaw error rate and the yaw response time.

[0037] Secondly, a yaw determination device is provided, comprising:

[0038] The yaw information acquisition unit is used to acquire the original trajectory point information, actual yaw time, replanned path information, and replanned path time of the target vehicle when the target vehicle veers off course.

[0039] The actual driving path determination unit is used to determine the actual driving path of the target vehicle based on the original trajectory point information.

[0040] A yaw trajectory determination unit is used to determine the yaw trajectory based on the actual yaw time, the time of replanning the route, and the actual driving route;

[0041] The error-prone scenario determination unit is used to determine whether the target vehicle is in an error-prone scenario based on the yaw trajectory and the planned path before the target vehicle veers off course.

[0042] The yaw determination unit is used to determine whether a yaw misjudgment has occurred if the target vehicle is in an error-prone scenario.

[0043] Thirdly, a readable storage medium is provided, on which computer-readable instructions are stored, characterized in that the computer-readable instructions, when executed by a processor, implement the yaw determination method as described above.

[0044] The aforementioned yaw determination method, apparatus, computer equipment, and storage medium are implemented as follows: when a target vehicle veers off course, acquiring the target vehicle's original trajectory point information, actual yaw time, replanned path information, and replanned path time; determining the target vehicle's actual driving path based on the original trajectory point information; determining the yaw trajectory based on the actual yaw time, the replanned path time, and the actual driving path; determining whether the target vehicle is in an error-prone scenario based on the yaw trajectory and the planned path before the yaw; and determining whether a yaw misjudgment has occurred if the target vehicle is in an error-prone scenario. In this embodiment, when the navigation engine detects that the vehicle has deviated from its course, it can obtain the vehicle's trajectory points, deviation time, re-planning path, and the time of re-planning path to determine the vehicle's actual driving path and deviation trajectory. Based on the current scenario of the vehicle, it can determine whether a deviation misjudgment has occurred. This not only more accurately restores the driver's driving path but also accommodates complex scenarios such as original trajectory point drift, road network equidistant deviation, and parallel roads. This helps determine whether the navigation engine's deviation judgment is incorrect, thereby improving the accuracy and completeness of the navigation engine's deviation judgment. Attached Figure Description

[0045] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 is a flowchart illustrating a yaw determination method according to an embodiment of the present invention;

[0047] Figure 2 is a schematic diagram of an application environment of the yaw determination method according to an embodiment of the present invention;

[0048] Figure 3 is a schematic diagram of an application environment of the road network matching method in a fault-prone scenario according to an embodiment of the present invention;

[0049] Figure 4 is a structural schematic diagram of a yaw determination device according to an embodiment of the present invention;

[0050] Figure 5 is a schematic diagram of a computer device according to an embodiment of the present invention. Detailed Implementation

[0051] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0052] In one embodiment, as shown in FIG1, a yaw determination method is provided, comprising the following steps:

[0053] In step S110, when the target vehicle deviates from its course, the original trajectory point information, actual deviation time, replanned path information, and replanned path time of the target vehicle are obtained.

[0054] Optionally, referring to Figure 2, a navigation application can be pre-installed on a front-end device, such as a mobile phone or in-vehicle system. During vehicle operation or when navigation begins, the navigation application collects the target vehicle's location information in real time and reports it to the cloud, where it is stored in a database. When the navigation engine detects that the target vehicle's path does not match the original planned path and there is a deviation, it can initiate a deviation detection request. When the cloud receives the deviation detection request, it records the actual deviation timestamp and sends the replanned path information, such as the path ID and path shape point string, to the front-end device. Simultaneously, the cloud stores the path information (path ID, path information (including LinkID and driving direction LinkDir), and path shape point string) offline in a designated database. When the front-end navigation application receives the replanned path, it also records the time of the replanned path, i.e., the timestamp of the front-end displaying the replanned path, and records and reports it in real time. This allows the acquisition of the target vehicle's original trajectory point information, actual deviation time, replanned path information, and the time of replanning the path.

[0055] This location information may include the timestamp, speed, direction, latitude and longitude, and positioning accuracy of the original trajectory points. Understandably, this trajectory point information can be collected through a positioning system, specifically the Global Positioning System (GPS) or Global Navigation Satellite System (GNSS).

[0056] In step S120, the actual driving path of the target vehicle is determined based on the original trajectory point information;

[0057] Optionally, the pre-stored complete original trajectory points can be sorted according to preset rules, such as chronological order or positional order. Then, the complete trajectory point information of the target vehicle can be extracted from the database, and a preset path planning algorithm, such as Hidden Markov Model (HMM), geometric matching algorithm, or Naive Bayes map matching algorithm, can be used to match the trajectory points to the corresponding road network to obtain a matched path. This matched path is then used as the actual driving path, i.e., the optimal path M. total The above-described process of matching actual driving routes can be understood as a path matching method in an offline matching scenario.

[0058] Among them, M total The actual travel path of the target vehicle can consist of multiple road network links, which are sequentially ordered according to time or travel location. Then M... total Link1→Link2→...→Link n .

[0059] Taking the Hidden Markov Model (HMM) algorithm as an example, it features high noise tolerance and high signal sparsity tolerance. In road network matching, the original trajectory points can be regarded as an observation sequence, and the road states in the road network can be regarded as hidden states. By defining the state transition probability (the probability of a vehicle moving from one road to another), the observation probability (the probability of generating a certain observation trajectory point on a certain road), and the initial state probability, the most likely hidden state sequence can be found using methods such as the Viterbi algorithm. This allows the trajectory points to be accurately mapped onto the road network, thus accurately mapping the vehicle trajectory onto the road network data and reconstructing the actual driving path of the target vehicle.

[0060] Optionally, a backtracking algorithm based on connectivity constraints can be used to select the optimal possible connected path to obtain the actual driving path. Each link (road segment) has a start point, an end point, and direction information. For any trajectory point, during the forward process, the connectivity between the trajectory point and the previous trajectory point can be checked according to the path planning algorithm and the road network topology. If a connection exists, i.e., there is a valid path from the trajectory point to the previous trajectory point, it is added to the connectivity list N. The objective function in the backtracking can be as follows:

[0061] Given the model θ and the observation sequence (trajectory point string) Z = (Z1, Z2, ..., Zn) n Given a set of connected lists N, find the optimal sequence of hidden states X = (X1, X2, ..., X...). n ), that is, the most likely candidate road segment.

[0062]

[0063] That is, only when no candidate matching point can be found in the connectivity list N is the selection based on the principle of maximizing the probability of the candidate matching point chosen. Because existing HMM model road network matching algorithms set the transition probability of disconnected paths to a minimum value during the forward process, continuous trajectory drift can still maximize the overall probability of disconnection, leading to matching errors. Therefore, the backtracking algorithm based on connectivity constraints avoids trajectory drift and matching disconnected paths, thereby reducing matching errors.

[0064] It should be noted that the specific implementation process of the backtracking algorithm based on connectivity constraints to obtain the optimal actual driving path is as follows: Based on the original trajectory point information, feature information of the trajectory points, such as speed and direction, is extracted. Based on this feature information, road segment selection begins, including setting a candidate range, i.e., delineating the possible road segment range in the road network based on the trajectory point features; then, candidate road segments are selected from these defined ranges, and the number of candidate road segments is determined. Next, the observation probability is calculated, evaluating the likelihood of a trajectory point appearing on each candidate road segment based on the previously extracted trajectory point features and the selected candidate road segments. Then, the state transition probability is calculated, which determines the probability of transitioning from one road segment to another based on road network data and the order of trajectory points. After obtaining the observation probability and state transition probability, a comprehensive probability is further calculated, comprehensively considering the above two probabilities to evaluate the overall trajectory matching probability. Subsequently, the Viterbi algorithm is used to solve for the comprehensive probability, finding the most likely matching path. Road segment matching is performed based on the Viterbi algorithm solution to determine the final matching road segment. Finally, a backtracking operation is performed to check and optimize the matching results, ultimately outputting an accurate matching result, which is the actual driving trajectory of the target vehicle in the road network. The backtracking algorithm based on connectivity constraints described above can more accurately reconstruct the driver's driving trajectory, with a matching accuracy rate greater than 98%.

[0065] In step S130, the yaw trajectory is determined based on the actual yaw time, the time of replanning the route, and the actual driving route;

[0066] Optionally, the target vehicle's trajectory can be segmented based on the obtained rerouting time; that is, the timestamp T of the rerouting route after deviation can be obtained. B Find the timestamp T corresponding to the frontend initiating the deviation request. A Based on timestamp T A Find the trajectory point P of the target vehicle, and take a 100m segment forward from P as the starting trajectory point S1. The ending trajectory point is less than or equal to the timestamp T. BThe last trajectory point S2 is extracted and used as the standard trajectory [S1->S2] during this yaw period. This standard trajectory [S1->S2] can be used as the yaw trajectory during this yaw period.

[0067] Understandably, the location of trajectory point P corresponds to a timestamp T. B The time point it represents reflects the specific geographical location of the vehicle when it veered off course.

[0068] In step S140, based on the yaw trajectory and the planned path before the target vehicle veered off course, it is determined whether the target vehicle is in a fault-prone scenario.

[0069] It's important to note that error-prone scenarios refer to situations where the original trajectory point drifts into a path that connects to other routes, or where there is an equidistant deviation between the road network data and the target vehicle's trajectory point, or parallel roads (including main and auxiliary roads / elevated bridges, etc.), leading to potential errors in offline matching. As shown in Figure 3, there is a partial mismatch between the target vehicle's original trajectory point A and the road network mapping point B obtained through the offline matching algorithm. Specifically, in the middle of Figure 3, there is a section where the matched route mapping point B is on an auxiliary road, but the target vehicle is actually traveling on the main road. The trajectory point drifts closer to the auxiliary road, causing a matching error, and thus the resulting driving path is incorrect. In this scenario, the original route plan is for the target vehicle to travel along the main road, and the target vehicle is indeed traveling on the main road. However, the navigation engine, based on the offline matching results, judges that the target vehicle has deviated from its course, which is an incorrect judgment and constitutes a false deviation. However, as shown in Figure 2, the matching result will still consider the trajectory to be traveling on the auxiliary road, indicating a deviation. In this case, the navigation engine's deviation judgment will be considered correct. Since one erroneous deviation is not identified, it is not conducive to the subsequent evaluation of the navigation engine's deviation judgment effect, which can easily lead to an increase in the navigation engine's misjudgment rate and a decrease in the accuracy of deviation judgment.

[0070] Based on the above reasons, it can be determined whether the target vehicle is in a fault-prone scenario by comparing the obtained yaw trajectory with the planned path before the target vehicle veered off course. Optionally, a first trajectory curve (curve_1) can be obtained based on the yaw trajectory [S1->S2]. The yaw path can be obtained based on the yaw trajectory. Based on the matching latitude and longitude points and link point strings of the yaw path, the corresponding second trajectory curve (curve_2) can be obtained. At the same time, the latitude and longitude of the current route point string can be extracted from the planned path before the target vehicle veered off course using the map size of the first trajectory curve and the second trajectory curve to generate a third trajectory curve (curve_3).

[0071] Then, the similarity between each pair of curve_1, curve_2, and curve_3 is calculated using a similarity algorithm. If curve_3 and curve_2 do not overlap, but are similar to each other and satisfy Similar(curve_1, curve_3) > Similar(curve_1, curve_2), it is identified as an error-prone scenario. The main reasons for error-prone scenarios are that the original trajectory point of the target vehicle drifts to a path that can connect to other paths, there is an equidistant deviation between the road network data and the driver's trajectory point, or the scenario is on a parallel road (such as a main road, auxiliary road, or overpass), which can easily lead to matching errors.

[0072] Understandably, based on the timestamps corresponding to the starting and ending points of the yaw trajectory, the corresponding path can be extracted from the actual driving path. This path is the yaw path, which refers to the path traveled by the target vehicle when it veers off course.

[0073] In step S150, if the target vehicle is in an error-prone scenario, it is determined whether a yaw misjudgment has occurred.

[0074] Understandably, different methods can be used to determine whether the navigation engine has made a erroneous deviation in different scenarios. For example, if the target vehicle is in a non-error-prone scenario, the path M matching the deviation trajectory [S1->S2] and the planned route R of the target vehicle before the deviation can be used for judgment. That is, the path M and R can be compared. If the comparison results are different, it can be considered that the target vehicle has actually deviated, that is, the navigation engine's judgment is correct; if the comparison results are the same, it can be considered that the target vehicle has not deviated, and therefore the navigation engine has made a deviation judgment error.

[0075] The aforementioned deviation determination method includes: when the target vehicle deviates, acquiring the target vehicle's original trajectory point information, actual deviation time, replanned path information, and replanned path time; determining the target vehicle's actual driving path based on the original trajectory point information; determining the deviation trajectory based on the actual deviation time, the replanned path time, and the actual driving path; determining whether the target vehicle is in an error-prone scenario based on the deviation trajectory and the planned path before the deviation; and determining whether a deviation misjudgment has occurred if the target vehicle is in a non-error-prone scenario. In this embodiment, when the navigation engine detects that the vehicle has deviated, it can acquire the vehicle's trajectory points, deviation time, replanned path, and replanned path time to determine the vehicle's actual driving path and deviation trajectory. Based on the vehicle's current scenario, it can determine whether a deviation misjudgment has occurred. This not only more accurately reconstructs the driver's driving path but also accommodates complex scenarios such as original trajectory point drift, road network equidistant deviations, and parallel roads, thereby determining whether the navigation engine's deviation judgment is incorrect and improving the accuracy and completeness of the navigation engine's deviation judgment.

[0076] In one embodiment of this application, determining the yaw trajectory based on the actual yaw time, the time of replanning the route, and the actual travel path includes:

[0077] Based on the actual yaw time, determine the target yaw trajectory point;

[0078] Based on the target yaw trajectory point, the start trajectory point and end trajectory point are determined in the actual driving path;

[0079] The yaw trajectory is obtained based on the starting trajectory point and the ending trajectory point.

[0080] Optionally, the optimal path M can be obtained through a first-round offline matching process based on the acquired original trajectory points. total M total For the driver's driving path M total :Link1:→Link2→...→Link n It consists of multiple road network links. Then, based on the obtained rerouting time, the target vehicle's trajectory can be segmented, that is, the timestamp T of the rerouting route after deviation can be obtained. B Find the timestamp T corresponding to the frontend initiating the deviation request. A Based on timestamp T A Find the trajectory point P of the target vehicle, and take a 100m segment forward from P as the starting trajectory point S1. The ending trajectory point is less than or equal to the timestamp T. BThe last trajectory point S2 is extracted and used as the standard trajectory [S1->S2] during this yaw period. This standard trajectory [S1->S2] can be used as the yaw trajectory during this yaw period.

[0081] The location of the trajectory point P corresponds to the timestamp T. B The time point it represents reflects the specific geographical location of the vehicle when it veered off course.

[0082] In one embodiment of this application, determining whether the target vehicle is in a fault-prone scenario based on the yaw trajectory and the planned path before the target vehicle veers off includes:

[0083] Determine the first trajectory curve and yaw path corresponding to the yaw trajectory;

[0084] Based on the yaw path, determine the second trajectory curve;

[0085] Based on the map size of the first trajectory curve and the second trajectory curve, the corresponding third trajectory curve is extracted from the planned path before the target vehicle veers off course.

[0086] Compare the first trajectory curve, the second trajectory curve, and the third trajectory curve pairwise;

[0087] Based on the comparison results, it is determined whether the target vehicle is in a fault-prone scenario.

[0088] It should be noted that error-prone scenarios refer to scenarios where the original trajectory point happens to drift into other paths that can be connected, where there is an equidistant deviation between the road network data and the trajectory point of the target vehicle, or where there are parallel roads (including main and auxiliary roads / elevated bridges, etc.), which can lead to errors in offline matching.

[0089] Optionally, if the target vehicle is in an error-prone scenario, when the yaw trajectory of the target vehicle is obtained, the yaw trajectory may include multiple trajectory points, each of which may correspond to specific latitude and longitude values. The latitude and longitude values ​​are arranged according to the order of time or position of the target vehicle, etc., to obtain a series of latitude and longitude points. Connecting the latitude and longitude points in sequence will yield a yaw curve that can represent the actual driving trajectory of the target vehicle during the yaw period, namely the first trajectory curve curve_1.

[0090] Based on the timestamps corresponding to the starting and ending points of the yaw trajectory, the corresponding path is extracted from the actual driving route. This path is the yaw path, which refers to the path the target vehicle traveled when it veered off course. Based on this yaw path, the set of nodes contained in each segment of the yaw path, i.e., the link string, can be obtained. Each link corresponds to a latitude and longitude number, thus obtaining a series of matching latitude and longitude points. Connecting these points sequentially yields the second trajectory curve, curve_2.

[0091] Using the map size of the first trajectory curve curve_1 and the second trajectory curve curve_2, i.e. the area range of the first trajectory curve and the second trajectory curve, the corresponding road segment within the area is extracted from the planned path before the target vehicle deviates. By obtaining the latitude and longitude values ​​of all trajectory points corresponding to the road segment, and connecting the latitude and longitude points in sequence, the third trajectory curve curve_3 can be obtained.

[0092] Then, the similarity of the first trajectory curve (curve_1), the second trajectory curve (curve_2), and the third trajectory curve (curve_3) can be calculated pairwise. For example, similarity algorithms based on curvature or Dynamic Time Warping (DTW) algorithms can be used to calculate the similarity, resulting in a similarity value (Similar) between each pair of trajectory curves. These Similar values ​​are then compared with a pre-set similarity threshold. If all Similar values ​​are greater than the threshold, they are considered similar. Based on this comparison, it can be determined whether the target vehicle is in a fault-prone scenario.

[0093] In one embodiment of this application, determining whether the target vehicle is in a fault-prone scenario based on the comparison results includes:

[0094] If the second trajectory curve does not overlap with the third trajectory curve, the similarity between any two of the first, second, and third trajectory curves is greater than a preset similarity threshold, and the similarity between the first and second trajectory curves is greater than the similarity between the first and third trajectory curves, then the target vehicle is determined to be in a fault-prone scenario.

[0095] Optionally, if the third trajectory curve curve_3 does not coincide with the second trajectory curve curve_2, the similarity value can be calculated to determine that the pairwise trajectory curves are similar and

[0096] If Similar(curve_1,curve_3) > Similar(curve_1,curve_2), then it is an error-prone scenario. This could be due to the target vehicle's original trajectory point drifting into another connectable path, an equidistant deviation between the road network data and the target vehicle's trajectory point, or parallel roads (including main and auxiliary roads / elevated bridges, etc.) causing matching errors.

[0097] In one embodiment of this application, determining whether a yaw misjudgment has occurred if the target vehicle is in an error-prone scenario includes:

[0098] If the target vehicle is in a fault-prone scenario, determine the comprehensive probability between different roads in the actual driving path;

[0099] Based on the product of the comprehensive probability and the preset penalty weight, the optimal matching path other than the actual driving path is determined from the candidate paths;

[0100] The optimal matching path is compared with the planned path before the target vehicle veered off course;

[0101] Based on the comparison results, it can be determined whether a yaw misjudgment has occurred.

[0102] It should be noted that when the target vehicle is in an error-prone scenario, the actual driving path obtained by the offline matching method may be inaccurate. Therefore, it is necessary to optimize the forward process and perform a second round of matching to obtain a second matching result. For example, if the first round matching result is M, that is, the actual driving path obtained by offline matching is M, in the forward process, the comprehensive probability between links in the matching result M is multiplied by a penalty weight, such as 0.3, to preferentially avoid matching result M. Finally, an optimal matching path solution M other than matching result M will be obtained. opt As a second matching result, it is used for determining erroneous course in error-prone scenarios.

[0103] It should be noted that the matching result M can consist of multiple links. When performing offline route matching using an offline algorithm, such as the HMM algorithm, each link can be considered as a state. For the starting point of the matching result M, its initial probability can be determined first, based on prior knowledge or historical data. For each state, the observation probability can be calculated based on its associated observation data, such as location and speed. Taking location as an example, the observation probability can be determined based on the degree of matching between the current link and the observed location. Then, the probability of moving from one link to the next, i.e., the transition probability, can be calculated based on the road network topology, traffic rules, historical driving data, etc. Finally, the comprehensive probability can be calculated based on the initial probability, the transition probability, and the observation probability.

[0104] The optimal matching path solution M obtained during the second round of matching is... opt After that, the M opt It can consist of multiple links, and the planned path before the target vehicle deviates can also consist of multiple links. By comparing M opt The similarity between the link and the link of the planned path before the target vehicle deviated is used. If the similarity is greater than the preset similarity threshold, it can be considered that the comparison is consistent. In this case, it can be considered that a deviation misjudgment has occurred. Otherwise, it is considered that the target vehicle has deviated, that is, the deviation judgment result of the navigation engine is correct.

[0105] In one embodiment of this application, after determining whether the target vehicle is in a fault-prone scenario, the method further includes:

[0106] If the target vehicle is in a non-error-prone scenario, determine whether a yaw misjudgment has occurred.

[0107] Understandably, different methods can be used to determine whether the navigation engine has made a erroneous deviation in different scenarios. For example, if the target vehicle is in a non-error-prone scenario, the path M matching the deviation trajectory [S1->S2] and the planned route R of the target vehicle before the deviation can be used for judgment. That is, the path M and R can be compared. If the comparison results are different, it can be considered that the target vehicle has actually deviated, that is, the navigation engine's judgment is correct; if the comparison results are the same, it can be considered that the target vehicle has not deviated, and therefore the navigation engine has made a deviation judgment error.

[0108] In one embodiment of this application, determining whether a yaw misjudgment has occurred includes:

[0109] Determine the yaw path corresponding to the yaw trajectory;

[0110] Compare the yaw path with the planned path of the target vehicle before it veered off course;

[0111] Based on the comparison results, determine whether a yaw misjudgment occurred.

[0112] Optionally, based on the timestamps corresponding to the starting trajectory point S1 and the ending trajectory point S2 of the yaw trajectory, a corresponding path can be extracted from the actual driving path. This path is the yaw path M, which refers to the path traveled by the target vehicle when it veers off course. The yaw path M can consist of multiple links, which can be combined into a link string according to time or position order. For example, M: Link m-2 →Link m-1 →Link mThe planned path R before the target vehicle veers off course can also consist of multiple links, for example, R: Link1→Link2→...→Link k The similarity of the deviated path M and the planned path R before the target vehicle deviated is compared. If the similarity is greater than the preset similarity threshold, it means that the target vehicle has not deviated and the navigation engine's deviation judgment is wrong. Otherwise, it means that the target vehicle has deviated and the navigation engine's deviation judgment is accurate.

[0113] In one embodiment of this application, after determining whether a yaw misjudgment has occurred, the method further includes:

[0114] When no yaw misjudgment occurs, determine the yaw error rate of the navigation engine;

[0115] Determine the yaw response duration in response to this navigation decision;

[0116] The yaw determination effect of the navigation engine is evaluated based on the yaw error rate and the yaw response time.

[0117] Wherein, the deviation rate = the total number of deviations / the total number of deviations;

[0118] Yaw response time = timestamp of front-end obtaining yaw and replanning route - timestamp of driver's actual yaw point;

[0119] Optionally, if no misjudgment of deviation occurs, meaning the navigation engine's deviation judgment is correct, the navigation engine's misjudgment rate and deviation response time can be calculated. In non-error-prone scenarios, if the Link strings of the actual driving path M and the planned route R before the target vehicle's deviation are different, then the navigation engine's deviation is a correct deviation, and the actual driving path M is still selected for deviation point determination.

[0120] Based on the yaw trajectory information [S1->S2] during the yaw period, and the corresponding matching path result M (i.e., using the timestamps corresponding to trajectory points S1 and S2 to match the actual driving path M), total (To be intercepted), let M:Link m-2 →Link m-1 →Link m Compare the link strings of M and R, and find the link in M ​​whose earliest time differs from R. yaw Simultaneously, the yaw trajectory segment [S1->S2] was found to match Link. yaw The earliest trajectory point S yaw The timestamp T of the trajectory point yaw This represents the actual moment the driver deviated from the course. Therefore, the yawing response time = the timestamp T of the replanned route after the yawing. B - Driver's actual deviation timestamp Tyaw It should be noted that yaw response time is an important indicator for measuring the yaw sensitivity of a navigation engine, and yaw response time calculation is only performed on correct yaw determinations.

[0121] For the erroneous deviation rate, the total number of erroneous deviations by the navigation engine and the total number of deviations can be counted. If this is an erroneous deviation, the total number of erroneous deviations is incremented by 1; otherwise, it remains unchanged.

[0122] Once the yaw error rate and yaw response time are obtained, if the yaw response time is less than a preset time threshold, the navigation engine is considered to have high sensitivity; if there is no yaw error rate, the navigation engine is considered to have high accuracy. This allows for the evaluation of the navigation engine's yaw detection performance, and adjustments can be made based on the evaluation results to improve the accuracy of yaw detection. Furthermore, the aforementioned automated yaw response time calculation method can replace the existing manual road test marking calculation method, saving labor costs and improving efficiency.

[0123] In this embodiment, when the navigation engine detects that the vehicle has deviated from its course, it can obtain the vehicle's trajectory points, deviation time, re-planning path, and the time of re-planning path to determine the vehicle's actual driving path and deviation trajectory. Based on the current scenario of the vehicle, it can determine whether a deviation misjudgment has occurred. This not only more accurately restores the driver's driving path but also accommodates complex scenarios such as original trajectory point drift, road network equidistant deviation, and parallel roads. This helps determine whether the navigation engine's deviation judgment is incorrect, thereby improving the accuracy and completeness of the navigation engine's deviation judgment.

[0124] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0125] In one embodiment, a yaw determination device is provided, which corresponds one-to-one with the yaw determination method in the above embodiments. As shown in Figure 4, the yaw determination device includes a yaw information acquisition unit 10, an actual driving path determination unit 20, a yaw trajectory determination unit 30, an error-prone scenario judgment unit 40, and a yaw determination unit 50. Detailed descriptions of each functional module are as follows:

[0126] The yaw information acquisition unit 10 is used to acquire the original trajectory point information, actual yaw time, replanned path information, and replanned path time of the target vehicle when the target vehicle veers off course.

[0127] The actual driving path determination unit 20 is used to determine the actual driving path of the target vehicle based on the original trajectory point information.

[0128] The yaw trajectory determination unit 30 is used to determine the yaw trajectory based on the actual yaw time, the time of replanning the route, and the actual driving route;

[0129] The error-prone scenario judgment unit 40 is used to determine whether the target vehicle is in an error-prone scenario based on the yaw trajectory and the planned path before the target vehicle veers off course.

[0130] Yaw determination unit 50 is used to determine whether a yaw misjudgment has occurred if the target vehicle is in an error-prone scenario.

[0131] In one embodiment of this application, the error-prone scenario determination unit 40 is further configured to:

[0132] Determine the first trajectory curve and yaw path corresponding to the yaw trajectory;

[0133] Based on the yaw path, determine the second trajectory curve;

[0134] Based on the map size of the first trajectory curve and the second trajectory curve, the corresponding third trajectory curve is extracted from the planned path before the target vehicle veers off course.

[0135] Compare the first trajectory curve, the second trajectory curve, and the third trajectory curve pairwise;

[0136] Based on the comparison results, it is determined whether the target vehicle is in a fault-prone scenario.

[0137] In one embodiment of this application, the error-prone scenario determination unit 40 is further configured to:

[0138] If the second trajectory curve does not overlap with the third trajectory curve, the similarity between any two of the first, second, and third trajectory curves is greater than a preset similarity threshold, and the similarity between the first and second trajectory curves is greater than the similarity between the first and third trajectory curves, then the target vehicle is determined to be in a fault-prone scenario.

[0139] In one embodiment of this application, the yaw determination unit 50 is further configured to:

[0140] If the target vehicle is in a fault-prone scenario, determine the comprehensive probability between different roads in the actual driving path;

[0141] Based on the product of the comprehensive probability and the preset penalty weight, the optimal matching path other than the actual driving path is determined from the candidate paths;

[0142] The optimal matching path is compared with the planned path before the target vehicle veered off course;

[0143] Based on the comparison results, it can be determined whether a yaw misjudgment has occurred.

[0144] In one embodiment of this application, the yaw determination unit 50 is further configured to:

[0145] If the target vehicle is in a non-error-prone scenario, determine whether a yaw misjudgment has occurred.

[0146] In one embodiment of this application, the yaw determination unit 50 is further configured to:

[0147] Determine the yaw path corresponding to the yaw trajectory;

[0148] Compare the yaw path with the planned path of the target vehicle before it veered off course;

[0149] Based on the comparison results, determine whether a yaw misjudgment occurred.

[0150] In one embodiment of this application, the yaw trajectory determination unit 30 is further configured to:

[0151] Based on the actual yaw time, determine the target yaw trajectory point;

[0152] Based on the target yaw trajectory point, the start trajectory point and end trajectory point are determined in the actual driving path;

[0153] The yaw trajectory is obtained based on the starting trajectory point and the ending trajectory point.

[0154] In one embodiment of this application, the device further includes a navigation engine evaluation unit, used for:

[0155] When no yaw misjudgment occurs, determine the yaw error rate of the navigation engine;

[0156] Determine the yaw response duration in response to this navigation decision;

[0157] The yaw determination effect of the navigation engine is evaluated based on the yaw error rate and the yaw response time.

[0158] In this embodiment, when the navigation engine detects that the vehicle has deviated from its course, it can obtain the vehicle's trajectory points, deviation time, re-planning path, and the time of re-planning path to determine the vehicle's actual driving path and deviation trajectory. Based on the current scenario of the vehicle, it can determine whether a deviation misjudgment has occurred. This not only more accurately restores the driver's driving path but also accommodates complex scenarios such as original trajectory point drift, road network equidistant deviation, and parallel roads. This helps determine whether the navigation engine's deviation judgment is incorrect, thereby improving the accuracy and completeness of the navigation engine's deviation judgment.

[0159] Specific limitations regarding the yaw determination device can be found in the limitations of the yaw determination method above, and will not be repeated here. Each module in the aforementioned yaw determination device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0160] In one embodiment, a computer device is provided, which may be a terminal device, and its internal structure diagram is shown in Figure 5. The computer device includes a processor, memory, and a network interface connected via a system bus. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a readable storage medium. The readable storage medium stores computer-readable instructions. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer-readable instructions are executed by the processor, they implement a yaw determination method. The readable storage medium provided in this embodiment includes both non-volatile readable storage media and volatile readable storage media.

[0161] In this application embodiment, a computer device is provided, including a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor. When the processor executes the computer-readable instructions, it implements the steps of the yaw determination method described above.

[0162] In one embodiment of the application, a readable storage medium is provided, which stores computer-readable instructions. When the computer-readable instructions are executed by a processor, they implement the steps of the yaw determination method described above.

[0163] Those skilled in the art will understand that implementing all or part of the processes in the methods of the above embodiments can be accomplished by instructing related hardware with computer-readable instructions. These computer-readable instructions can be stored in a non-volatile readable storage medium or a volatile readable storage medium. When executed, these computer-readable instructions can include the processes of the embodiments of the methods described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0164] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0165] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A yaw determination method, characterized in that, The method includes: when a target vehicle veers off course, acquiring the target vehicle's original trajectory point information, actual veergence time, replanned path information, and replanned path time, wherein the original trajectory point information includes the trajectory point's timestamp, speed, direction, latitude and longitude, and positioning accuracy; based on the original trajectory point information, fusing multi-dimensional trajectory information and using a backtracking algorithm with connectivity constraints to filter legally connected paths to determine the target vehicle's actual driving path, excluding disconnected matching results caused by trajectory drift; based on the actual veergence time, the replanned path time, and the actual driving path, defining a veergence trajectory interval within the actual driving path to obtain the veergence trajectory; and based on the veergence trajectory and the planned path before the target vehicle veers off course, determining the target... Whether the vehicle is in an error-prone scenario, where the original trajectory point drift, road network data deviation, or parallel roads cause path matching errors; if the target vehicle is in an error-prone scenario, a scenario-adaptive path matching optimization strategy is used to determine whether a veergence misjudgment has occurred, including: determining the comprehensive probability between different roads in the actual driving path; determining the optimal matching path other than the actual driving path from the candidate paths based on the product of the comprehensive probability and the preset penalty weight; comparing the optimal matching path with the planned path before the target vehicle veered off course; and determining whether a veergence misjudgment has occurred based on the comparison result; if the target vehicle is in a non-error-prone scenario, a direct comparison between the veergence trajectory and the planned path before veergence is used to determine whether a veergence misjudgment has occurred.

2. The yaw determination method as described in claim 1, characterized in that, The step of determining whether the target vehicle is in a fault-prone scenario based on the yaw trajectory and the planned path before the target vehicle veers off includes: determining a first trajectory curve and a yaw path corresponding to the yaw trajectory; determining a second trajectory curve based on the yaw path; extracting a corresponding third trajectory curve from the planned path before the target vehicle veers off based on the size of the first and second trajectory curves; comparing the first, second, and third trajectory curves pairwise; and determining whether the target vehicle is in a fault-prone scenario based on the comparison results.

3. The yaw determination method as described in claim 2, characterized in that, The step of determining whether the target vehicle is in an error-prone scenario based on the comparison results includes: if the second trajectory curve and the third trajectory curve do not overlap, the similarity between any two of the first trajectory curve, the second trajectory curve and the third trajectory curve is greater than a preset similarity threshold, and the similarity between the first trajectory curve and the second trajectory curve is greater than the similarity between the first trajectory curve and the third trajectory curve, then the target vehicle is determined to be in an error-prone scenario.

4. The yaw determination method as described in claim 1, characterized in that, The step of determining whether a velocity misjudgment has occurred by directly comparing the velocity trajectory with the planned path before the velocity deviation includes: determining the velocity path corresponding to the velocity trajectory; comparing the velocity path with the planned path of the target vehicle before the velocity deviation; and determining whether a velocity misjudgment has occurred based on the comparison result.

5. The yaw determination method as described in claim 1, characterized in that, Determining the yaw trajectory based on the actual yaw time, the replanning time, and the actual driving path includes: determining a target yaw trajectory point based on the actual yaw time; determining a start trajectory point and an end trajectory point in the actual driving path based on the target yaw trajectory point; and obtaining the yaw trajectory based on the start trajectory point and the end trajectory point.

6. The yaw determination method according to any one of claims 1-5, characterized in that, After determining whether a yaw error has occurred, the method further includes: when no yaw error has occurred, determining the yaw error rate of the navigation engine; determining the yaw response time for the current navigation determination result; and evaluating the yaw determination effect of the navigation engine based on the yaw error rate and the yaw response time.

7. A yaw determination device, characterized in that, The device includes: a yaw information acquisition unit, used to acquire the original trajectory point information, actual yaw time, replanned path information, and replanned path time of the target vehicle when the target vehicle veers off course, wherein the original trajectory point information includes the timestamp, speed, direction, latitude and longitude, and positioning accuracy of the trajectory point; an actual driving path determination unit, used to determine the actual driving path of the target vehicle by fusing multi-dimensional trajectory information and using a backtracking algorithm with connectivity constraints based on the original trajectory point information, and excluding disconnected matching results caused by trajectory drift; a yaw trajectory determination unit, used to delineate a yaw trajectory interval in the actual driving path based on the actual yaw time, the replanned path time, and the actual driving path, to obtain the yaw trajectory; and an error-prone scenario judgment unit, used to determine the yaw trajectory based on the yaw trajectory and the target vehicle's position. The system describes the planned path of the target vehicle before deviation and determines whether the target vehicle is in an error-prone scenario. An error-prone scenario refers to a scenario where path matching is prone to errors due to drift of the original trajectory points, deviation of road network data, or parallel roads. A deviation determination unit is used to determine whether a deviation misjudgment has occurred if the target vehicle is in an error-prone scenario, employing a scenario-adaptive path matching optimization strategy. This includes: determining the comprehensive probability between different roads in the actual driving path; determining the optimal matching path other than the actual driving path from candidate paths based on the product of the comprehensive probability and a preset penalty weight; comparing the optimal matching path with the planned path of the target vehicle before deviation; and determining whether a deviation misjudgment has occurred based on the comparison result. If the target vehicle is in a non-error-prone scenario, a direct comparison between the deviation trajectory and the planned path before deviation determines whether a deviation misjudgment has occurred.

8. A readable storage medium having computer-readable instructions stored thereon, characterized in that, When the computer-readable instructions are executed by a processor, they implement the yaw determination method as described in any one of claims 1 to 6.

Images