Lane change trajectory quality assessment methods, devices and electronic equipment, and storage media

Abstract

This application discloses a method, device, electronic device, and storage medium for evaluating the quality of lane change trajectories. The method includes: acquiring a reference lane change trajectory of an autonomous vehicle at its current position; determining the lateral distance between trajectory points on the reference lane change trajectory and the center line of a target lane according to a preset evaluation dimension; determining the matching degree between the reference lane change trajectory and the target lane center line using a first evaluation strategy based on the lateral distance between the trajectory points and the target lane center line; determining the comfort level of the reference lane change trajectory using a second evaluation strategy based on the lateral distance between the trajectory points and the target lane center line; and determining the quality evaluation result of the reference lane change trajectory based on the matching degree between the reference lane change trajectory and the target lane center line and the comfort level of the reference lane change trajectory. This application designs evaluation strategies with different evaluation dimensions to evaluate the quality of lane change trajectories for lane change scenarios, making it more targeted and applicable to various scenarios, and the output results can provide a basis for guiding the vehicle's driving decisions.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a method, device, electronic device, and storage medium for evaluating lane change trajectory quality. Background Technology

[0002] Advanced Driver Assistance Systems (ADAS) utilize various onboard sensors and decision-making and control algorithms to enable vehicle behaviors such as lane changing, merging, overtaking, and following.

[0003] In lane-changing scenarios, evaluating the quality of the lane-changing trajectory is a crucial prerequisite for lane-changing decisions. Existing trajectory quality evaluation methods mainly score dimensions such as the fit and comfort of the reference trajectory, and finally give the final score through a weighted linear combination. However, this approach is mainly designed for general scenarios, not lane-changing scenarios, and the trajectory quality scores output by existing approaches cannot be used as a basis for guiding the driving decisions of autonomous vehicles. Summary of the Invention

[0004] This application provides a method, apparatus, electronic device, and storage medium for evaluating lane change trajectory quality, so as to achieve accurate evaluation of trajectory quality in lane change scenarios.

[0005] The embodiments of this application adopt the following technical solutions:

[0006] In a first aspect, embodiments of this application provide a method for evaluating the quality of lane change trajectories, wherein the method includes:

[0007] Obtain the reference lane-changing trajectory of the autonomous vehicle at its current location;

[0008] Based on the preset evaluation dimensions, determine the lateral distance between the trajectory point on the reference lane change trajectory and the center line of the target lane;

[0009] Based on the lateral distance between the trajectory points on the reference lane change trajectory and the center line of the target lane, the matching degree between the reference lane change trajectory and the center line of the target lane is determined using the first evaluation strategy.

[0010] The comfort level of the reference lane change trajectory is determined using a second evaluation strategy based on the lateral distance between the trajectory points on the reference lane change trajectory and the center line of the target lane.

[0011] The quality assessment result of the reference lane change trajectory is determined based on the matching degree between the reference lane change trajectory and the center line of the target lane and the comfort level of the reference lane change trajectory.

[0012] Optionally, determining the lateral distance between the trajectory point on the reference lane change trajectory and the centerline of the target lane according to a preset evaluation dimension includes:

[0013] If the preset evaluation dimension is the matching degree between the reference lane change trajectory and the center line of the target lane, then the lateral distance between each trajectory point on the reference lane change trajectory and the center line of the target lane is directly determined.

[0014] If the preset evaluation dimension is the comfort of the reference lane change trajectory, then the trajectory points on the reference lane change trajectory are traversed according to the preset lateral distance threshold, and the lateral distance between the traversed trajectory points and the center line of the target lane is determined.

[0015] Optionally, the step of traversing the trajectory points on the reference lane-changing trajectory according to a preset lateral distance threshold and determining the lateral distance between the traversed trajectory points and the centerline of the target lane includes:

[0016] Starting from the current position of the autonomous vehicle, the trajectory points on the reference lane change trajectory are traversed from near to far, and the lateral distance between the currently traversed trajectory point and the center line of the target lane is determined.

[0017] Based on the preset lateral distance threshold and the lateral distance between the currently traversed trajectory point and the center line of the target lane, determine whether to trigger the traversal termination condition.

[0018] If the traversal termination condition is triggered, the traversal stops and the traversed trajectory points are output.

[0019] Optionally, the matching degree includes distance matching degree, and determining the matching degree between the reference lane change trajectory and the target lane centerline using the first evaluation strategy based on the lateral distance between trajectory points on the reference lane change trajectory and the centerline of the target lane includes:

[0020] Determine the minimum lateral distance among the lateral distances between each trajectory point on the reference lane change trajectory and the centerline of the target lane;

[0021] Project the trajectory point of the minimum lateral distance onto the center line of the target lane to obtain the trajectory point information of the trajectory point of the minimum lateral distance on the center line of the target lane;

[0022] The perception data of the autonomous vehicle is acquired, and the distance matching degree between the reference lane change trajectory and the center line of the target lane is determined based on the perception data of the autonomous vehicle and the trajectory point information of the minimum lateral distance trajectory point on the center line of the target lane.

[0023] Optionally, the perception data includes the longitudinal distance between the current position of the autonomous vehicle and the obstacle, and the longitudinal distance between the current position of the autonomous vehicle and the destination. The trajectory point information of the minimum lateral distance trajectory point on the center line of the target lane includes the lateral displacement and longitudinal displacement of the minimum lateral distance trajectory point on the center line of the target lane.

[0024] The step of determining the distance matching degree between the reference lane change trajectory and the target lane centerline based on the perception data of the autonomous vehicle and the trajectory point information of the minimum lateral distance trajectory point on the target lane centerline includes:

[0025] Determine the minimum longitudinal distance between the current position of the autonomous vehicle and the longitudinal distance between the obstacle and the current position of the autonomous vehicle and the destination;

[0026] The distance matching degree between the reference lane change trajectory and the target lane centerline is determined based on the magnitude of the lateral displacement of the trajectory point with the minimum lateral distance on the centerline of the target lane, and the relative magnitude of the longitudinal displacement of the trajectory point with the minimum lateral distance on the centerline of the target lane with the minimum longitudinal distance.

[0027] Optionally, the matching degree includes a stability matching degree, and determining the matching degree between the reference lane change trajectory and the target lane centerline using a first evaluation strategy based on the lateral distance between trajectory points on the reference lane change trajectory and the target lane centerline includes:

[0028] Determine the lane change type corresponding to the reference lane change trajectory;

[0029] Based on the lane change type corresponding to the reference lane change trajectory and the lateral distance between each trajectory point on the reference lane change trajectory and the center line of the target lane, the stability matching degree between the reference lane change trajectory and the center line of the target lane is determined.

[0030] Optionally, the lane change type includes left lane change and right lane change, and determining the stability matching degree between the reference lane change trajectory and the target lane centerline based on the lane change type corresponding to the reference lane change trajectory and the lateral distance between the trajectory points on the reference lane change trajectory and the target lane centerline includes:

[0031] If the lane change type is a left lane change, then determine the first trajectory point on the reference lane change trajectory whose lateral distance from the center line of the target lane is greater than zero, and determine the stability matching degree between the reference lane change trajectory and the center line of the target lane based on the maximum lateral distance of the trajectory points among the first trajectory points.

[0032] If the lane change type is a right lane change, then a second trajectory point on the reference lane change trajectory whose lateral distance from the center line of the target lane is less than zero is determined, and the stability matching degree between the reference lane change trajectory and the center line of the target lane is determined based on the minimum lateral distance of the trajectory points among the second trajectory points.

[0033] Optionally, the traversed trajectory points include multiple points, and determining the comfort level of the reference lane change trajectory using the second evaluation strategy based on the lateral distance between the trajectory points on the reference lane change trajectory and the centerline of the target lane includes:

[0034] Project each traversed trajectory point onto the center line of the target lane to obtain trajectory point information of each traversed trajectory point on the center line of the target lane. The trajectory point information of each traversed trajectory point on the center line of the target lane includes the lateral displacement and longitudinal displacement of each traversed trajectory point on the center line of the target lane.

[0035] Determine the first and second derivatives of the lateral displacement relative to the longitudinal displacement of each traversed trajectory point on the center line of the target lane;

[0036] Based on the first and second derivatives of the lateral displacement of each traversed trajectory point on the center line of the target lane relative to the longitudinal displacement, determine the mean of the first and second derivatives.

[0037] The comfort level of the reference lane change trajectory is determined based on the mean of the first derivative and the mean of the second derivative.

[0038] Secondly, embodiments of this application also provide a lane change trajectory quality assessment device, wherein the device includes:

[0039] The acquisition unit is used to acquire the reference lane-changing trajectory of the autonomous vehicle at its current position;

[0040] The first determining unit is used to determine the lateral distance between the trajectory point on the reference lane change trajectory and the center line of the target lane according to a preset evaluation dimension.

[0041] The first evaluation unit is used to determine the matching degree between the reference lane change trajectory and the center line of the target lane based on the lateral distance between the trajectory points on the reference lane change trajectory and the center line of the target lane using a first evaluation strategy.

[0042] The second evaluation unit is used to determine the comfort level of the reference lane change trajectory based on the lateral distance between the trajectory points on the reference lane change trajectory and the center line of the target lane using a second evaluation strategy.

[0043] The second determining unit is used to determine the quality assessment result of the reference lane change trajectory based on the matching degree between the reference lane change trajectory and the center line of the target lane and the comfort level of the reference lane change trajectory.

[0044] Thirdly, embodiments of this application also provide an electronic device, including:

[0045] Processor; and

[0046] A memory configured to store computer-executable instructions, which, when executed, cause the processor to perform any of the methods described above.

[0047] Fourthly, embodiments of this application also provide a computer-readable storage medium that stores one or more programs, which, when executed by an electronic device including multiple applications, cause the electronic device to perform any of the methods described above.

[0048] The at least one technical solution adopted in this application embodiment can achieve the following beneficial effects: The lane change trajectory quality assessment method of this application embodiment first obtains the reference lane change trajectory corresponding to the current position of the autonomous vehicle; then, according to a preset assessment dimension, determines the lateral distance between the trajectory points on the reference lane change trajectory and the center line of the target lane; then, based on the lateral distance between the trajectory points on the reference lane change trajectory and the center line of the target lane, a first assessment strategy is used to determine the matching degree between the reference lane change trajectory and the center line of the target lane; simultaneously, based on the lateral distance between the trajectory points on the reference lane change trajectory and the center line of the target lane, a second assessment strategy is used to determine the comfort level of the reference lane change trajectory; finally, based on the matching degree between the reference lane change trajectory and the center line of the target lane and the comfort level of the reference lane change trajectory, the quality assessment result of the reference lane change trajectory is determined. The lane change trajectory quality assessment method of this application embodiment designs assessment strategies with different assessment dimensions for lane change scenarios to conduct quality assessment of lane change trajectories, which is more targeted and applicable to different scenarios, and the output results can provide a basis for guiding the driving decisions of autonomous vehicles. Attached Figure Description

[0049] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0050] Figure 1 This is a flowchart illustrating a lane change trajectory quality assessment method according to an embodiment of this application.

[0051] Figure 2 This is a schematic diagram of the structure of a lane change trajectory quality assessment device according to an embodiment of this application;

[0052] Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0054] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0055] This application provides a method for evaluating the quality of lane change trajectories, such as... Figure 1 The diagram shows a flowchart of a lane change trajectory quality assessment method according to an embodiment of this application. The method includes at least the following steps S110 to S150:

[0056] Step S110: Obtain the reference lane change trajectory of the autonomous vehicle at its current location.

[0057] The lane change trajectory quality assessment method in this application is mainly used to evaluate the quality of the reference lane change trajectory planned by the trajectory planning module in an autonomous vehicle in a lane change scenario. Therefore, it is necessary to first obtain the reference lane change trajectory corresponding to the current position of the autonomous vehicle, such as the driving trajectory that the autonomous vehicle needs to refer to when changing lanes from lane A to lane B.

[0058] Step S120: Determine the lateral distance between the trajectory point on the reference lane change trajectory and the center line of the target lane according to the preset evaluation dimension.

[0059] The embodiments of this application predefine dimensions for evaluating the quality of a reference lane change trajectory. In autonomous driving scenarios, in order to ensure the safety, stability and controllability of vehicle driving, lane keeping is often required, that is, it is necessary to ensure that the vehicle travels along the center line of the lane as much as possible. Therefore, the planned trajectory also needs to match the center line of the lane as much as possible.

[0060] Based on this, a preset evaluation dimension in this application embodiment can include the matching degree between the reference lane change trajectory and the center line of the target lane. Furthermore, during lane changes, changes in vehicle speed and acceleration can impact passenger comfort; therefore, the preset evaluation dimension in this application embodiment can also include passenger comfort during lane changes.

[0061] Different preset evaluation dimensions result in different trajectory points on the reference lane change trajectory that need to be processed. Therefore, this application can determine the trajectory points on the reference lane change trajectory that need to be processed based on different preset evaluation dimensions, and further determine the lateral distance between the trajectory points and the center line of the target lane, as the basis for subsequent evaluation of the quality of the reference lane change trajectory.

[0062] Step S130: Based on the lateral distance between the trajectory points on the reference lane change trajectory and the center line of the target lane, the matching degree between the reference lane change trajectory and the center line of the target lane is determined using the first evaluation strategy.

[0063] The first evaluation strategy in this application primarily measures the deviation between the trajectory points on the reference lane change trajectory and the target lane centerline, as well as the stability of the reference lane change trajectory relative to the target lane centerline, based on the lateral distance between the trajectory points on the reference lane change trajectory obtained in the aforementioned steps and the target lane centerline. A higher degree of matching between the reference lane change trajectory and the target lane centerline indicates a higher quality reference lane change trajectory.

[0064] Step S140: Based on the lateral distance between the trajectory points on the reference lane change trajectory and the center line of the target lane, the comfort level of the reference lane change trajectory is determined using a two-evaluation strategy.

[0065] The second evaluation strategy in this application embodiment mainly measures the passenger's comfort experience during the entire lane change process based on the lateral distance between the trajectory points on the reference lane change trajectory obtained in the aforementioned steps and the center line of the target lane. The higher the comfort of the reference lane change trajectory, the higher the quality of the reference lane change trajectory.

[0066] Step S150: Determine the quality assessment result of the reference lane change trajectory based on the matching degree between the reference lane change trajectory and the center line of the target lane and the comfort level of the reference lane change trajectory.

[0067] Based on the matching degree between the reference lane change trajectory and the target lane centerline obtained from the aforementioned steps, and the comfort level of the reference lane change trajectory, the quality assessment result of the reference lane change trajectory can be comprehensively determined, thereby realizing trajectory quality assessment in lane change scenarios. Furthermore, the quality assessment result of this embodiment can be represented as a multi-dimensional quality assessment vector based on the output results of the matching degree and comfort level. This multi-dimensional quality assessment vector can provide a basis for subsequent guidance of autonomous vehicle driving decisions.

[0068] The lane change trajectory quality assessment method of this application has designed assessment strategies with different assessment dimensions for lane change scenarios to assess the quality of lane change trajectories. It is more targeted and applicable to different scenarios, and the output results can provide a basis for guiding the driving decisions of autonomous vehicles.

[0069] In one embodiment of this application, determining the lateral distance between the trajectory points on the reference lane change trajectory and the center line of the target lane according to a preset evaluation dimension includes: if the preset evaluation dimension is the matching degree between the reference lane change trajectory and the center line of the target lane, then directly determining the lateral distance between each trajectory point on the reference lane change trajectory and the center line of the target lane; if the preset evaluation dimension is the comfort level of the reference lane change trajectory, then traversing the trajectory points on the reference lane change trajectory according to a preset lateral distance threshold and determining the lateral distance between the traversed trajectory points and the center line of the target lane.

[0070] As mentioned above, the preset evaluation dimensions of this application embodiment can be mainly divided into two dimensions: the matching degree between the reference lane change trajectory and the center line of the target lane, and the comfort of the reference lane change trajectory. For the matching degree between the reference lane change trajectory and the center line of the target lane, each trajectory point on the reference lane change trajectory can be directly used as the processing object to calculate the lateral distance between each trajectory point on the reference lane change trajectory and the center line of the target lane.

[0071] Regarding the comfort dimension of the reference lane change trajectory, the trajectory points on the reference lane change trajectory can be traversed according to a preset lateral distance threshold. The preset lateral distance threshold can be used to constrain when the traversal ends, so that the lateral distance between the traversed trajectory points and the center line of the target lane can be calculated based on the traversed trajectory points, instead of processing all trajectory points on the reference lane change trajectory.

[0072] In one embodiment of this application, the step of traversing the trajectory points on the reference lane change trajectory according to a preset lateral distance threshold and determining the lateral distance between the traversed trajectory points and the center line of the target lane includes: starting from the current position of the autonomous vehicle, traversing the trajectory points on the reference lane change trajectory from near to far and determining the lateral distance between the currently traversed trajectory point and the center line of the target lane; determining whether a traversal termination condition is triggered based on the preset lateral distance threshold and the lateral distance between the currently traversed trajectory point and the center line of the target lane; and stopping the traversal and outputting the traversed trajectory points if the traversal termination condition is triggered.

[0073] Since the comfort of the reference lane change trajectory in this application embodiment mainly addresses the impact of the lane change process on passengers, and the reference lane change trajectory is generally a driving process that gradually approaches the center line of the target lane from the current position of the autonomous vehicle, the current position of the autonomous vehicle can be used as the starting point to traverse the trajectory points on the reference lane change trajectory from near to far. For each trajectory point traversed, the lateral distance between the trajectory point and the center line of the target lane can be calculated. When the lateral distance between the currently traversed trajectory point and the center line of the target lane is small enough, for example, less than a preset lateral distance threshold e, it means that the position of the trajectory point is close enough to the center line of the target lane. Then, the trajectory points that have not yet been traversed will often be closer to the center line of the target lane or even already located on the center line of the lane. Therefore, the need for comfort evaluation for the trajectory points that have not yet been traversed has been greatly reduced. At this time, the traversal can be ended, and the lateral distance between the traversed trajectory points and the center line of the target lane can be calculated.

[0074] The above process effectively filters out some unnecessary trajectory points from participating in the comfort evaluation calculation, thus improving the accuracy of comfort assessment.

[0075] Additionally, it should be noted that a special case may occur in actual scenarios. For example, the reference lane change trajectory may be located on both sides of the target lane centerline. That is, some trajectory points on the reference lane change trajectory are located on the left side of the target lane centerline, and some trajectory points on the reference lane change trajectory are located on the right side of the target lane centerline. Therefore, if the above-mentioned traversal method from near to far is used, some trajectory points may be mistakenly filtered out. In other words, the lateral distance between these untraversed trajectory points and the target lane centerline may be greater than the preset lateral distance threshold e.

[0076] In this case, the embodiments of this application can replace the point-by-point traversal method by directly calculating the lateral distance between each trajectory point on the reference lane change trajectory and the center line of the target lane. The lateral distance between each trajectory point and the center line of the target lane is compared with a preset lateral distance threshold e, thereby filtering out trajectory points that are less than the preset lateral distance threshold e.

[0077] In one embodiment of this application, the matching degree includes a distance matching degree. The step of determining the matching degree between the reference lane change trajectory and the target lane centerline using a first evaluation strategy based on the lateral distance between trajectory points on the reference lane change trajectory and the target lane centerline includes: determining the minimum lateral distance among the lateral distances between each trajectory point on the reference lane change trajectory and the target lane centerline; projecting the trajectory point with the minimum lateral distance onto the target lane centerline to obtain trajectory point information of the trajectory point with the minimum lateral distance on the target lane centerline; acquiring the perception data of the autonomous vehicle, and determining the distance matching degree between the reference lane change trajectory and the target lane centerline based on the perception data of the autonomous vehicle and the trajectory point information of the trajectory point with the minimum lateral distance on the target lane centerline.

[0078] The matching degree between the reference lane change trajectory and the center line of the target lane in this application embodiment may specifically include the distance matching degree. The distance matching degree mainly measures the lateral distance matching degree and longitudinal distance matching degree between the trajectory points on the reference lane change trajectory and the center line of the target lane.

[0079] It should be noted that the lateral distance between the trajectory point on the reference lane change trajectory determined in the aforementioned embodiments and the center line of the target lane is mainly calculated based on the position coordinates of the trajectory point and the center line of the target lane in the Cartesian coordinate system. However, in trajectory planning scenarios, the coordinate points in the Cartesian coordinate system are often transformed into the Frenet coordinate system to simplify the difficulty of trajectory planning. The Frenet coordinate system describes the position of the autonomous vehicle relative to the center line of the lane, where the vertical coordinate S represents the travel distance along the center line of the lane, and the horizontal coordinate L represents the displacement relative to the vertical line, that is, the distance by which the autonomous vehicle deviates from the center line of the lane.

[0080] Based on this, the embodiments of this application can first find the minimum lateral distance and its corresponding trajectory point in the lateral distance between each trajectory point on the reference lane change trajectory and the center line of the target lane, and then project the trajectory point with the minimum lateral distance onto the center line of the target lane, that is, the Frenet coordinate system established with the center line of the target lane as the reference, so as to obtain the trajectory point information corresponding to the trajectory point with the minimum lateral distance on the center line of the target lane, including the horizontal and vertical coordinates of the trajectory point in the Frenet coordinate system. Since the lateral distance between the trajectory point and the center line of the target lane represents the magnitude of the lateral deviation, the smaller the minimum lateral distance during the entire lane change process, the higher the lateral distance matching degree.

[0081] However, in addition to considering lateral distance matching, vertical distance matching also needs to be considered, because in some cases, a high lateral distance matching does not necessarily mean a high vertical distance matching.

[0082] Based on this, this application can further obtain perception data provided by the perception module of the autonomous vehicle. The perception module can be, for example, a lidar, camera and other sensors installed on the autonomous vehicle. Based on these sensors, perception data related to trajectory planning can be collected. Finally, using these perception data and the horizontal and vertical coordinates of the trajectory point with the minimum lateral distance in the Frenet coordinate system, the longitudinal distance matching degree between the reference lane change trajectory and the center line of the target lane can be determined.

[0083] In one embodiment of this application, the perception data includes the longitudinal distance between the current position of the autonomous vehicle and the obstacle, and the longitudinal distance between the current position of the autonomous vehicle and the destination. The trajectory point information of the minimum lateral distance trajectory point on the center line of the target lane includes the lateral displacement and longitudinal displacement of the minimum lateral distance trajectory point on the center line of the target lane. Determining the distance matching degree between the reference lane change trajectory and the center line of the target lane based on the perception data of the autonomous vehicle and the trajectory point information of the minimum lateral distance trajectory point on the center line of the target lane includes: determining the minimum longitudinal distance between the current position of the autonomous vehicle and the obstacle, and the longitudinal distance between the current position of the autonomous vehicle and the destination; determining the distance matching degree between the reference lane change trajectory and the center line of the target lane based on the magnitude of the lateral displacement of the minimum lateral distance trajectory point on the center line of the target lane, and the relative magnitude of the longitudinal displacement of the minimum lateral distance trajectory point on the center line of the target lane and the minimum longitudinal distance.

[0084] In determining the lateral distance matching degree, this application embodiment mainly uses the horizontal coordinate Ps of the trajectory point with the minimum lateral distance in the Frenet coordinate system. The ideal state is Ps=0, which means that the lateral displacement of the trajectory point with the minimum lateral distance relative to the center line of the target lane is 0, that is, it is located on the center line of the target lane. Therefore, the lateral distance matching degree is the highest. However, in actual cases, there will often be a certain deviation. Therefore, the judgment condition "Ps=0" can be appropriately relaxed according to actual needs.

[0085] When determining the longitudinal distance matching degree, the main perception data used include the longitudinal distance D-obstacle between the current position of the autonomous vehicle and the obstacle, and the longitudinal distance D-end between the current position of the autonomous vehicle and the destination. It can be determined that the longitudinal displacement Do of the trajectory point on the reference lane change trajectory cannot be greater than D-obstacle or D-end. Otherwise, the trajectory point will pass through the position point of the obstacle or the position point of the destination. Therefore, the smaller value D-lane between D-obstacle and D-end can be taken as the basis for judging Do.

[0086] To facilitate the understanding of the above embodiments, based on the above two lateral distance matching degrees and longitudinal distance matching degrees, an evaluation strategy for the distance matching degree M in the following form can be constructed:

[0087] If P - s = 0 and D - o < D - lane, then M = 1, (1)

[0088] If P - s > 0 and D - o > D - lane, then M = -1, (2)

[0089] Otherwise, M ∈ {-1, 1}, (3)

[0090] Equation (1) above indicates that the trajectory point with the minimum lateral distance is located on the center line of the target lane, and at the same time, there is no conflict between the longitudinal displacement of this trajectory point and D - obstacle and D - end. This situation is the optimal distance matching degree, so the distance matching degree M can be assigned a value of 1. Equation (2) above indicates that the trajectory point with the minimum lateral distance is not located on the center line of the target lane, that is, there is a lateral displacement relative to the center line of the target lane, and there is a conflict between the longitudinal displacement of this trajectory point and D - obstacle or D - end. This situation is the worst distance matching degree, so the distance matching degree M can be assigned a value of -1. Of course, for other situations except these two, that is, the situation of Equation (3) above, it can be assigned a value between -1 and 1. The specific numerical value can be flexibly quantified by comprehensively considering the magnitudes of the lateral distance matching degree and the longitudinal distance matching degree, and no specific limitation is made here.

[0091] Of course, it should be noted that the above - listed quantization strategy is only an exemplary description. Those skilled in the art can flexibly define other forms of quantization strategies to quantify the distance matching degree according to actual needs, and no specific limitation is made here.

[0092] In an embodiment of the present application, the matching degree includes a stability matching degree. The method for determining the matching degree between the reference lane - changing trajectory and the center line of the target lane based on the lateral distance between the trajectory points on the reference lane - changing trajectory and the center line of the target lane using the first evaluation strategy includes: determining the lane - changing type corresponding to the reference lane - changing trajectory; and determining the stability matching degree between the reference lane - changing trajectory and the center line of the target lane according to the lane - changing type corresponding to the reference lane - changing trajectory and the lateral distance between each trajectory point on the reference lane - changing trajectory and the center line of the target lane.

[0093] The matching degree in the embodiments of this application may also include the stability matching degree. The stability matching degree is mainly used to measure whether the reference lane change trajectory is excessive. Excessive lane change can be understood as the reference lane change trajectory crossing the center line of the target lane, that is, there is an intersection with the center line of the target lane. If excessive lane change occurs, in order to maintain the lane, it is often necessary to control the autonomous vehicle to return to the position of the center line of the lane. This may cause the autonomous vehicle to sway left and right on both sides of the center line of the target lane. Therefore, the stability of the reference lane change trajectory can be considered to be poor.

[0094] Furthermore, different lane change types, i.e. different lane change directions, will also affect the calculation of stability matching degree. Therefore, in this embodiment, the lane change type corresponding to the current reference lane change trajectory is first determined, and then the stability matching degree between the reference lane change trajectory and the target lane centerline is calculated based on the lane change type and the lateral distance between each trajectory point on the reference lane change trajectory and the target lane centerline.

[0095] In one embodiment of this application, the lane change type includes left lane change and right lane change. Determining the stability matching degree between the reference lane change trajectory and the target lane centerline based on the lane change type corresponding to the reference lane change trajectory and the lateral distance between the trajectory points on the reference lane change trajectory and the target lane centerline includes: if the lane change type is a left lane change, identifying a first trajectory point on the reference lane change trajectory with a lateral distance greater than zero from the target lane centerline, and determining the stability matching degree between the reference lane change trajectory and the target lane centerline based on the maximum lateral distance among the trajectory points in the first trajectory point; if the lane change type is a right lane change, identifying a second trajectory point on the reference lane change trajectory with a lateral distance less than zero from the target lane centerline, and determining the stability matching degree between the reference lane change trajectory and the target lane centerline based on the minimum lateral distance among the trajectory points in the second trajectory point.

[0096] The lane change types in this application embodiment are mainly divided into two types: left lane change, which is changing lanes from the current lane to the left lane of the target lane, and right lane change, which is changing lanes from the current lane to the right lane of the target lane. In this application embodiment, it is necessary to first determine which trajectory points are the transition points for lane changes. If the lane change type is left lane change, then it is necessary to find the trajectory points located to the left of the center line of the target lane; if the lane change type is right lane change, then it is necessary to find the trajectory points located to the right of the center line of the target lane.

[0097] In the Frenet coordinate system established with the target lane centerline as the reference, the left side of the target lane centerline represents a positive x-axis value, and the right side represents a negative x-axis value. Therefore, for a left lane change, the first trajectory point on the reference lane change trajectory with a lateral distance greater than zero (positive value) from the target lane centerline can be used as the lane change transition point. Then, the stability matching degree between the reference lane change trajectory and the target lane centerline is determined based on the maximum lateral distance among the trajectory points in the first trajectory point. For a right lane change, the second trajectory point on the reference lane change trajectory with a lateral distance less than zero (negative value) from the target lane centerline can be used as the lane change transition point. Then, the stability matching degree between the reference lane change trajectory and the target lane centerline is determined based on the minimum lateral distance among the trajectory points in the second trajectory point.

[0098] In this embodiment, the selected lane change trajectory points can be maintained as a set. For example, the set E is initialized and is empty. If it is a left lane change, the lateral distance L between each trajectory point and the center line of the target lane is calculated in the Frenet coordinate system. If L is greater than 0, the trajectory point is stored in set E. Conversely, if it is a right lane change, if L is less than 0, the trajectory point is stored in set E.

[0099] After obtaining the trajectory points corresponding to different lane change types, for left-side lane changes, since the lateral distances corresponding to the trajectory points of lane change overshoot are positive, the maximum lateral distance L between each trajectory point in the set and the center line of the target lane can be used as the stability matching degree S. The larger L is, the greater the degree of lane change overshoot, and the lower the stability matching degree S. For right-side lane changes, since the lateral distances corresponding to the trajectory points of lane change overshoot are negative, the minimum lateral distance L between each trajectory point in the set and the center line of the target lane can be used as the stability matching degree S. The smaller L is, the greater the degree of lane change overshoot, and the lower the stability matching degree S.

[0100] In one embodiment of this application, the traversed trajectory points include multiple points. The step of determining the comfort level of the reference lane change trajectory using a second evaluation strategy based on the lateral distance between the trajectory points on the reference lane change trajectory and the centerline of the target lane includes: projecting each traversed trajectory point onto the centerline of the target lane to obtain trajectory point information of each traversed trajectory point on the centerline of the target lane, wherein the trajectory point information of each traversed trajectory point on the centerline of the target lane includes the lateral displacement and longitudinal displacement of each traversed trajectory point on the centerline of the target lane; determining the first and second derivatives of the lateral displacement of each traversed trajectory point on the centerline of the target lane relative to the longitudinal displacement; determining the mean of the first derivative and the mean of the second derivative based on the first and second derivatives of the lateral displacement of each traversed trajectory point on the centerline of the target lane relative to the longitudinal displacement; and determining the comfort level of the reference lane change trajectory based on the mean of the first derivative and the mean of the second derivative.

[0101] In calculating the comfort of the reference lane change trajectory, the embodiments of this application mainly consider the magnitude of the impact of the lane change trajectory on passengers. For example, during the lane change process, the speed and acceleration of an autonomous vehicle will change significantly. If the speed and acceleration of the lane change are too large, the passenger's comfort experience will be poor.

[0102] Based on this, the embodiments of this application can also evaluate comfort in the Frenet coordinate system established with the center line of the target lane as the reference. Based on the aforementioned embodiments, the evaluation of comfort is mainly based on the traversed trajectory points. Therefore, each traversed trajectory point can be projected onto the center line of the target lane to obtain the trajectory point information of each traversed trajectory point on the center line of the target lane. Specifically, this can include the lateral displacement and longitudinal displacement of the traversed trajectory points in the Frenet coordinate system.

[0103] Then, the first and second derivatives of the lateral displacement with respect to the longitudinal displacement of each traversed trajectory point in the Frenet coordinate system are calculated, which describe the changing trends of the geometric shape. Specifically, the first derivative of the lateral displacement with respect to the longitudinal displacement characterizes the trend of velocity change, while the second derivative characterizes the trend of acceleration change.

[0104] To improve the accuracy of comfort assessment, we can further calculate the average of the first and second derivatives corresponding to each traversed trajectory point to obtain the average first derivative D' and the average second derivative D”. The larger the average first derivative D' and the average second derivative D”, the lower the comfort level. Therefore, the average first derivative D' and the average second derivative D” can be used as the final comfort evaluation result.

[0105] Additionally, it should be noted that since the comfort assessment stage uses the mean method, if trajectory points that are very close to the center line of the target lane are also included in the calculation of the mean of the first derivative D' and the mean of the second derivative D”, it will affect the accuracy of the final calculated comfort and its assessment significance. Therefore, this is the main reason why this application did not use all trajectory points on the reference lane change trajectory as the basis for calculating comfort in the aforementioned embodiments.

[0106] Based on the foregoing embodiments, the quality assessment result of a lane change trajectory output by the embodiments of this application can be characterized as a multi-dimensional quality assessment vector {M,S,D',D”}. Since each assessment dimension in the vector has its own numerical value and corresponding physical meaning, each dimension in the vector can be used to guide the driving decisions of subsequent autonomous vehicles to a certain extent. Compared with the scheme of directly using a unified scoring method to evaluate the quality of lane change trajectories, it has more practical application value and guidance value.

[0107] This application embodiment also provides a lane change trajectory quality assessment device 200, such as... Figure 2 The diagram shows a schematic representation of a lane change trajectory quality assessment device according to an embodiment of this application. The device 200 includes: an acquisition unit 210, a first determination unit 220, a first evaluation unit 230, a second evaluation unit 240, and a second determination unit 250, wherein:

[0108] Acquisition unit 210 is used to acquire the reference lane change trajectory of the autonomous vehicle at its current position;

[0109] The first determining unit 220 is used to determine the lateral distance between the trajectory point on the reference lane change trajectory and the center line of the target lane according to a preset evaluation dimension.

[0110] The first evaluation unit 230 is used to determine the matching degree between the reference lane change trajectory and the center line of the target lane based on the lateral distance between the trajectory points on the reference lane change trajectory and the center line of the target lane using a first evaluation strategy.

[0111] The second evaluation unit 240 is used to determine the comfort level of the reference lane change trajectory based on the lateral distance between the trajectory points on the reference lane change trajectory and the center line of the target lane using a second evaluation strategy.

[0112] The second determining unit 250 is used to determine the quality assessment result of the reference lane change trajectory based on the matching degree between the reference lane change trajectory and the center line of the target lane and the comfort level of the reference lane change trajectory.

[0113] In one embodiment of this application, the first determining unit 220 is specifically used to: if the preset evaluation dimension is the matching degree between the reference lane change trajectory and the center line of the target lane, then directly determine the lateral distance between each trajectory point on the reference lane change trajectory and the center line of the target lane; if the preset evaluation dimension is the comfort level of the reference lane change trajectory, then traverse the trajectory points on the reference lane change trajectory according to the preset lateral distance threshold and determine the lateral distance between the traversed trajectory points and the center line of the target lane.

[0114] In one embodiment of this application, the first determining unit 220 is specifically used to: take the current position of the autonomous vehicle as the starting point, traverse the trajectory points on the reference lane change trajectory from near to far and determine the lateral distance between the currently traversed trajectory point and the center line of the target lane; determine whether a traversal termination condition is triggered based on a preset lateral distance threshold and the lateral distance between the currently traversed trajectory point and the center line of the target lane; if the traversal termination condition is triggered, stop the traversal and output the traversed trajectory points.

[0115] In one embodiment of this application, the matching degree includes a distance matching degree, and the first evaluation unit 230 is specifically used to: determine the minimum lateral distance among the lateral distances between each trajectory point on the reference lane change trajectory and the center line of the target lane; project the trajectory point with the minimum lateral distance onto the center line of the target lane to obtain the trajectory point information of the trajectory point with the minimum lateral distance on the center line of the target lane; acquire the perception data of the autonomous vehicle, and determine the distance matching degree between the reference lane change trajectory and the center line of the target lane based on the perception data of the autonomous vehicle and the trajectory point information of the trajectory point with the minimum lateral distance on the center line of the target lane.

[0116] In one embodiment of this application, the perception data includes the longitudinal distance between the current position of the autonomous vehicle and the obstacle, and the longitudinal distance between the current position of the autonomous vehicle and the destination. The trajectory point information of the minimum lateral distance trajectory point on the center line of the target lane includes the lateral displacement and longitudinal displacement of the minimum lateral distance trajectory point on the center line of the target lane. The first evaluation unit 230 is specifically used to: determine the minimum longitudinal distance between the current position of the autonomous vehicle and the obstacle and the longitudinal distance between the current position of the autonomous vehicle and the destination; and determine the distance matching degree between the reference lane change trajectory and the center line of the target lane based on the magnitude of the lateral displacement of the minimum lateral distance trajectory point on the center line of the target lane and the relative magnitude of the longitudinal displacement of the minimum lateral distance trajectory point on the center line of the target lane and the minimum longitudinal distance.

[0117] In one embodiment of this application, the matching degree includes a stability matching degree, and the first evaluation unit 230 is specifically used to: determine the lane change type corresponding to the reference lane change trajectory; and determine the stability matching degree between the reference lane change trajectory and the target lane centerline based on the lane change type corresponding to the reference lane change trajectory and the lateral distance between each trajectory point on the reference lane change trajectory and the centerline of the target lane.

[0118] In one embodiment of this application, the lane change type includes left lane change and right lane change. The first evaluation unit 230 is specifically used to: if the lane change type is left lane change, determine a first trajectory point on the reference lane change trajectory whose lateral distance from the center line of the target lane is greater than zero, and determine the stability matching degree between the reference lane change trajectory and the center line of the target lane based on the maximum lateral distance of the trajectory points among the first trajectory points; if the lane change type is right lane change, determine a second trajectory point on the reference lane change trajectory whose lateral distance from the center line of the target lane is less than zero, and determine the stability matching degree between the reference lane change trajectory and the center line of the target lane based on the minimum lateral distance of the trajectory points among the second trajectory points.

[0119] In one embodiment of this application, the traversed trajectory points include multiple points, and the second evaluation unit 240 is specifically used to: project each traversed trajectory point onto the center line of the target lane to obtain trajectory point information of each traversed trajectory point on the center line of the target lane, wherein the trajectory point information of each traversed trajectory point on the center line of the target lane includes the lateral displacement and longitudinal displacement of each traversed trajectory point on the center line of the target lane; determine the first and second derivatives of the lateral displacement of each traversed trajectory point on the center line of the target lane relative to the longitudinal displacement; determine the mean of the first derivative and the mean of the second derivative based on the first and second derivatives of the lateral displacement of each traversed trajectory point on the center line of the target lane relative to the longitudinal displacement; and determine the comfort level of the reference lane change trajectory based on the mean of the first derivative and the mean of the second derivative.

[0120] It is understood that the above-mentioned lane change trajectory quality assessment device can realize each step of the lane change trajectory quality assessment method provided in the foregoing embodiments. The relevant explanations of the lane change trajectory quality assessment method are applicable to the lane change trajectory quality assessment device, and will not be repeated here.

[0121] Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Please refer to it. Figure 3At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and memory. The memory may include main memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for other business operations.

[0122] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0123] Memory is used to store programs. Specifically, programs may include program code, which includes computer operation instructions. Memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0124] The processor reads the corresponding computer program from non-volatile memory into main memory and then executes it, forming a lane change trajectory quality assessment device at the logical level. The processor executes the program stored in memory and specifically performs the following operations:

[0125] Obtain the reference lane-changing trajectory of the autonomous vehicle at its current location;

[0126] Based on the preset evaluation dimensions, determine the lateral distance between the trajectory point on the reference lane change trajectory and the center line of the target lane;

[0127] Based on the lateral distance between the trajectory points on the reference lane change trajectory and the center line of the target lane, the matching degree between the reference lane change trajectory and the center line of the target lane is determined using the first evaluation strategy.

[0128] The comfort level of the reference lane change trajectory is determined using a second evaluation strategy based on the lateral distance between the trajectory points on the reference lane change trajectory and the center line of the target lane.

[0129] The quality assessment result of the reference lane change trajectory is determined based on the matching degree between the reference lane change trajectory and the center line of the target lane and the comfort level of the reference lane change trajectory.

[0130] The above is as stated in this application. Figure 1 The method executed by the lane change trajectory quality assessment device disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0131] The electronic device can also perform Figure 1 The method for implementing the lane change trajectory quality assessment device, and the realization of the lane change trajectory quality assessment device in... Figure 1 The functions of the embodiments shown are not described in detail here.

[0132] This application also proposes a computer-readable storage medium that stores one or more programs, the programs including instructions that, when executed by an electronic device including multiple applications, enable the electronic device to perform... Figure 1 The method executed by the lane change trajectory quality assessment device in the illustrated embodiment is specifically used to perform:

[0133] Obtain the reference lane-changing trajectory of the autonomous vehicle at its current location;

[0134] Based on the preset evaluation dimensions, determine the lateral distance between the trajectory point on the reference lane change trajectory and the center line of the target lane;

[0135] Based on the lateral distance between the trajectory points on the reference lane change trajectory and the center line of the target lane, the matching degree between the reference lane change trajectory and the center line of the target lane is determined using the first evaluation strategy.

[0136] The comfort level of the reference lane change trajectory is determined using a second evaluation strategy based on the lateral distance between the trajectory points on the reference lane change trajectory and the center line of the target lane.

[0137] The quality assessment result of the reference lane change trajectory is determined based on the matching degree between the reference lane change trajectory and the center line of the target lane and the comfort level of the reference lane change trajectory.

[0138] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0139] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0140] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0141] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0142] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0143] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0144] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0145] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0146] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0147] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method of evaluating lane change trajectory quality, wherein, The method includes: Obtain the reference lane-changing trajectory of the autonomous vehicle at its current location; Based on the preset evaluation dimensions, determine the lateral distance between the trajectory point on the reference lane change trajectory and the center line of the target lane; Based on the lateral distance between the trajectory points on the reference lane change trajectory and the center line of the target lane, the matching degree between the reference lane change trajectory and the center line of the target lane is determined using the first evaluation strategy. The comfort level of the reference lane change trajectory is determined using a second evaluation strategy based on the lateral distance between the trajectory points on the reference lane change trajectory and the center line of the target lane. The quality assessment result of the reference lane change trajectory is determined based on the matching degree between the reference lane change trajectory and the center line of the target lane and the comfort level of the reference lane change trajectory. The matching degree includes distance matching degree. Determining the matching degree between the reference lane change trajectory and the target lane centerline using a first evaluation strategy, based on the lateral distance between trajectory points on the reference lane change trajectory and the centerline of the target lane, includes: Determine the minimum lateral distance among the lateral distances between each trajectory point on the reference lane change trajectory and the centerline of the target lane; Project the trajectory point of the minimum lateral distance onto the center line of the target lane to obtain the trajectory point information of the trajectory point of the minimum lateral distance on the center line of the target lane; The perception data of the autonomous vehicle is acquired, and the distance matching degree between the reference lane change trajectory and the center line of the target lane is determined based on the perception data of the autonomous vehicle and the trajectory point information of the minimum lateral distance trajectory point on the center line of the target lane.

2. The method of claim 1, wherein, The step of determining the lateral distance between the trajectory point on the reference lane change trajectory and the centerline of the target lane according to the preset evaluation dimension includes: If the preset evaluation dimension is the matching degree between the reference lane change trajectory and the center line of the target lane, then the lateral distance between each trajectory point on the reference lane change trajectory and the center line of the target lane is directly determined. If the preset evaluation dimension is the comfort of the reference lane change trajectory, then the trajectory points on the reference lane change trajectory are traversed according to the preset lateral distance threshold, and the lateral distance between the traversed trajectory points and the center line of the target lane is determined.

3. The method of claim 2, wherein, The step of traversing the trajectory points on the reference lane change trajectory according to a preset lateral distance threshold and determining the lateral distance between the traversed trajectory points and the centerline of the target lane includes: Starting from the current position of the autonomous vehicle, the trajectory points on the reference lane change trajectory are traversed from near to far, and the lateral distance between the currently traversed trajectory point and the center line of the target lane is determined. Based on the preset lateral distance threshold and the lateral distance between the currently traversed trajectory point and the center line of the target lane, determine whether to trigger the traversal termination condition. If the traversal termination condition is triggered, the traversal stops and the traversed trajectory points are output.

4. The method of claim 1, wherein, The perception data includes the longitudinal distance between the current position of the autonomous vehicle and the obstacle, and the longitudinal distance between the current position of the autonomous vehicle and the destination. The trajectory point information of the minimum lateral distance trajectory point on the center line of the target lane includes the lateral displacement and longitudinal displacement of the minimum lateral distance trajectory point on the center line of the target lane. The step of determining the distance matching degree between the reference lane change trajectory and the target lane centerline based on the perception data of the autonomous vehicle and the trajectory point information of the minimum lateral distance trajectory point on the target lane centerline includes: Determine the minimum longitudinal distance between the current position of the autonomous vehicle and the longitudinal distance between the obstacle and the current position of the autonomous vehicle and the destination; The distance matching degree between the reference lane change trajectory and the target lane centerline is determined based on the magnitude of the lateral displacement of the trajectory point with the minimum lateral distance on the centerline of the target lane, and the relative magnitude of the longitudinal displacement of the trajectory point with the minimum lateral distance on the centerline of the target lane with the minimum longitudinal distance.

5. The method of claim 1, wherein, The matching degree includes a stability matching degree. Determining the matching degree between the reference lane change trajectory and the target lane centerline using a first evaluation strategy, based on the lateral distance between trajectory points on the reference lane change trajectory and the centerline of the target lane, includes: Determine the lane change type corresponding to the reference lane change trajectory; Based on the lane change type corresponding to the reference lane change trajectory and the lateral distance between each trajectory point on the reference lane change trajectory and the center line of the target lane, the stability matching degree between the reference lane change trajectory and the center line of the target lane is determined.

6. The method of claim 5, wherein, The lane change types include left-side lane changes and right-side lane changes. Determining the stability matching degree between the reference lane change trajectory and the target lane centerline based on the lane change type corresponding to the reference lane change trajectory and the lateral distance between the trajectory points on the reference lane change trajectory and the target lane centerline includes: If the lane change type is a left lane change, then determine the first trajectory point on the reference lane change trajectory whose lateral distance from the center line of the target lane is greater than zero, and determine the stability matching degree between the reference lane change trajectory and the center line of the target lane based on the maximum lateral distance of the trajectory points among the first trajectory points. If the lane change type is a right lane change, then a second trajectory point on the reference lane change trajectory whose lateral distance from the center line of the target lane is less than zero is determined, and the stability matching degree between the reference lane change trajectory and the center line of the target lane is determined based on the minimum lateral distance of the trajectory points among the second trajectory points.

7. The method of claim 2, wherein, The traversed trajectory points include multiple points. The determination of the comfort level of the reference lane change trajectory using a second evaluation strategy, based on the lateral distance between the trajectory points on the reference lane change trajectory and the centerline of the target lane, includes: Project each traversed trajectory point onto the center line of the target lane to obtain trajectory point information of each traversed trajectory point on the center line of the target lane. The trajectory point information of each traversed trajectory point on the center line of the target lane includes the lateral displacement and longitudinal displacement of each traversed trajectory point on the center line of the target lane. Determine the first and second derivatives of the lateral displacement relative to the longitudinal displacement of each traversed trajectory point on the center line of the target lane; Based on the first and second derivatives of the lateral displacement of each traversed trajectory point on the center line of the target lane relative to the longitudinal displacement, determine the mean of the first and second derivatives. The comfort level of the reference lane change trajectory is determined based on the mean of the first derivative and the mean of the second derivative.

8. A lane change trajectory quality assessment apparatus, wherein, The device includes: The acquisition unit is used to acquire the reference lane-changing trajectory of the autonomous vehicle at its current position; The first determining unit is used to determine the lateral distance between the trajectory point on the reference lane change trajectory and the center line of the target lane according to a preset evaluation dimension. The first evaluation unit is used to determine the matching degree between the reference lane change trajectory and the center line of the target lane based on the lateral distance between the trajectory points on the reference lane change trajectory and the center line of the target lane using a first evaluation strategy. The second evaluation unit is used to determine the comfort level of the reference lane change trajectory based on the lateral distance between the trajectory points on the reference lane change trajectory and the center line of the target lane using a second evaluation strategy. The second determining unit is used to determine the quality assessment result of the reference lane change trajectory based on the matching degree between the reference lane change trajectory and the center line of the target lane and the comfort level of the reference lane change trajectory. The matching degree includes a distance matching degree, and the first evaluation unit is specifically used for: Determine the minimum lateral distance among the lateral distances between each trajectory point on the reference lane change trajectory and the centerline of the target lane; Project the trajectory point of the minimum lateral distance onto the center line of the target lane to obtain the trajectory point information of the trajectory point of the minimum lateral distance on the center line of the target lane; The perception data of the autonomous vehicle is acquired, and the distance matching degree between the reference lane change trajectory and the center line of the target lane is determined based on the perception data of the autonomous vehicle and the trajectory point information of the minimum lateral distance trajectory point on the center line of the target lane.

9. An electronic device, comprising: processor; as well as A memory configured to store computer-executable instructions, which, when executed, cause the processor to perform the method of any one of claims 1 to 7.

10. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of applications, cause the electronic device to perform the method of any one of claims 1 to 7.

Images