An intersection passing decision method, device, equipment and medium

Abstract

The application discloses a kind of intersection traffic decision method, device, equipment and medium, it is related to automatic driving technical field, including: when intersection position appears in front of ego car, target element is calculated according to the traffic light information, lane line information and intersection information obtained;Target element includes the angle between each traffic light and ego lane center line, the distance between each traffic light and ego car, the lateral distance between the projection point of each traffic light on stop line and ego lane center line, the front-back position relationship between each traffic light and ego car and the matching result between the type of each traffic light and ego lane driving direction;Each target element corresponding to each traffic light is weighted and averaged to calculate, to determine the target traffic light matched with ego lane according to the calculation result;When the current distance between ego car and intersection position satisfies preset threshold value, ego car is controlled to travel according to the current display state of target traffic light.Can more accurately carry out the matching of traffic light and lane.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, in particular to a method and device for intersection passing decision, equipment and medium. BACKGROUND

[0002] City roads include various traffic signs, traffic lights, ground markings, pedestrians and other variable traffic flows, which have high requirements for the perception, decision-making and control capabilities of ADAS (Advanced Driving Assistance System).

[0003] Intersection passing is a relatively complex scenario, which needs to consider traffic lights, ground signs, pedestrian crossings, surrounding vehicles and pedestrians and other factors. In intersection passing, traffic lights play an important role and can provide effective traffic control means to reduce congestion and delay through orderly traffic flow, which helps to improve traffic efficiency. In the intersection passing decision-making process, accurate matching of traffic lights and lanes is crucial to ensure the efficiency of intersection passing. Current technologies only consider the position and type of traffic lights to bind traffic lights and lanes, which is a single consideration and has low accuracy.

[0004] In summary, how to more accurately match traffic lights and lanes to improve the efficiency of intersection passing is a problem to be solved. SUMMARY

[0005] Therefore, the purpose of the present application is to provide a method and device for intersection passing decision, equipment and medium, which can more accurately match traffic lights and lanes to improve the efficiency of intersection passing. The specific scheme is as follows:

[0006] In a first aspect, the present application discloses a method for intersection passing decision, comprising:

[0007] When the intersection position in front of the ego vehicle appears, calculate the target elements according to the acquired traffic light information, lane line information and intersection information; wherein the target elements include the included angle between each traffic light and the center line of the ego lane, the distance between each traffic light and the ego vehicle, the lateral distance between the projection point of each traffic light on the stop line of the intersection and the center line of the ego lane, the front and rear position relationship between each traffic light and the ego vehicle, and the matching result between the type of each traffic light and the driving direction of the ego lane;

[0008] Weighted average calculation is performed on each target element corresponding to each traffic light to determine the target traffic light matched with the ego lane according to the calculation result;

[0009] When a current distance between the ego vehicle and the intersection position meets a preset threshold, the ego vehicle is controlled to travel according to a current display state of the target traffic light.

[0010] Optionally, an included angle between each traffic light and a center line of a lane of the ego vehicle is calculated according to the acquired traffic light information, lane line information and intersection information, including:

[0011] A first position coordinate corresponding to each traffic light is acquired in a vehicle body coordinate system, and a second position coordinate of a target point closest to the traffic light position in the center line of the lane of the ego vehicle is acquired;

[0012] A first vector is constructed based on the first position coordinate and the second position coordinate, and a second vector is constructed based on the second position coordinate and a position coordinate of an arbitrary point in the center line of the lane of the ego vehicle;

[0013] An included angle between the first vector and the second vector is taken as the included angle between each traffic light and the center line of the lane of the ego vehicle;

[0014] Correspondingly, a distance between each traffic light and the ego vehicle and a front-rear position relationship between each traffic light and the ego vehicle are calculated according to the acquired traffic light information, lane line information and intersection information, including:

[0015] An Euclidean distance between each traffic light and the ego vehicle is calculated based on an abscissa value and an ordinate value of the first position coordinate;

[0016] A front-rear position relationship between each traffic light and the ego vehicle is determined based on a positive or negative nature of the ordinate value in the first position coordinate.

[0017] Optionally, a transverse distance between a projection point of each traffic light on an intersection stop line and the center line of the lane of the ego vehicle is calculated according to the acquired traffic light information, lane line information and intersection information, including:

[0018] A third position coordinate and a fourth position coordinate corresponding to a start point and an end point of the intersection stop line are acquired, and a third vector is constructed based on the third position coordinate and the fourth position coordinate;

[0019] A fifth position coordinate of the projection point of each traffic light on the intersection stop line is calculated based on the first position coordinate and the third vector, and a straight line equation corresponding to the second vector is determined;

[0020] A transverse distance between the projection point of each traffic light on the intersection stop line and the center line of the lane of the ego vehicle is calculated based on the fifth position coordinate and the straight line equation.

[0021] Optionally, the types of traffic lights include straight, left turn, right turn and U-turn, and the driving directions of the self-lane include single driving direction and composite driving direction; wherein the single driving direction includes straight, left turn, right turn and U-turn, and the composite driving direction includes straight-left turn combination, straight-right turn combination, straight-left turn-right turn combination and straight-left turn-U-turn combination.

[0022] Correspondingly, the matching results between the type of each traffic light and the driving direction of the self-lane are calculated according to the acquired traffic light information, lane line information and intersection information, including:

[0023] If the driving direction of the self-lane is the single driving direction, it is determined whether the type of each traffic light is consistent with the single driving direction to obtain the matching result.

[0024] If the driving direction of the self-lane is the composite driving direction, the current driving direction is determined according to the navigation information, and then it is determined whether the type of each traffic light is consistent with the current driving direction to obtain the matching result.

[0025] Optionally, the control of the self-vehicle driving according to the current display state of the target traffic light includes:

[0026] If the current display state of the target traffic light is red light state, the distance between the current position of the self-vehicle and the stop line of the intersection is taken as the braking distance, so as to control the self-vehicle to perform the braking action based on the braking distance.

[0027] If the current display state of the target traffic light is green light state, the self-vehicle is controlled to normally drive based on the navigation information.

[0028] Optionally, the weighted average calculation is performed on each target element corresponding to each traffic light to determine the target traffic light matched with the self-lane according to the calculation result, including:

[0029] Each target element corresponding to each traffic light is scored according to a preset scoring rule to obtain a corresponding score value, and the score values are normalized to obtain processed score values.

[0030] All the processed score values corresponding to each traffic light are weighted and averaged according to a preset weight coefficient to obtain the calculation result of each traffic light.

[0031] The traffic light corresponding to the maximum value of the calculation result is taken as the target traffic light matched with the self-lane.

[0032] Optionally, the scoring of each target element corresponding to each traffic light according to the preset scoring rule to obtain a corresponding score value includes:

[0033] determining whether an absolute value of an included angle between the current traffic light and a lane center line of the ego vehicle is less than a preset included angle threshold, and if yes, setting a corresponding score value as a first preset score value, otherwise setting the corresponding score value as zero;

[0034] determining whether a distance between the current traffic light and the ego vehicle is less than a preset distance threshold, and if yes, setting a corresponding score value as a second preset score value, otherwise setting the corresponding score value as zero;

[0035] taking the lane center line of the ego vehicle as a boundary line, determining lane width sums on left and right sides of the lane center line respectively, and determining whether a distance between a projection point of the current traffic light on a stop line of the intersection and the lane center line is less than a corresponding lane width sum based on a transverse position relationship between the projection point and the lane center line, and if yes, setting a corresponding score value as a third preset score value, otherwise setting the corresponding score value as zero;

[0036] if the current traffic light is in front of the ego vehicle, setting a corresponding score value as a fourth preset score value, otherwise setting the corresponding score value as zero;

[0037] if a type of the current traffic light is consistent with a driving direction of the lane, setting a corresponding score value as a fifth preset score value, otherwise setting the corresponding score value as zero.

[0038] In a second aspect, the present application discloses a decision device for intersection passing, comprising:

[0039] a factor calculation module, configured to calculate target factors according to the acquired traffic light information, lane line information and intersection information when a position of an intersection appears in front of the ego vehicle, wherein the target factors include an included angle between each traffic light and a lane center line of the ego vehicle, a distance between each traffic light and the ego vehicle, a transverse distance between a projection point of each traffic light on a stop line of the intersection and the lane center line of the ego vehicle, a front-rear position relationship between each traffic light and the ego vehicle, and a matching result between a type of each traffic light and a driving direction of the lane;

[0040] a matching module, configured to perform weighted average calculation on each target factor corresponding to each traffic light, so as to determine a target traffic light matched with the lane according to a calculation result;

[0041] a control module, configured to control the ego vehicle to drive according to a current display state of the target traffic light when a current distance between the ego vehicle and the position of the intersection meets a preset threshold.

[0042] In a third aspect, the present application discloses an electronic device, comprising:

[0043] a memory, configured to save a computer program;

[0044] The processor is used to execute the computer program to implement the steps of the aforementioned intersection traffic decision-making method.

[0045] In a fourth aspect, the present application discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the steps of the aforementioned disclosed intersection traffic decision-making method are implemented.

[0046] It can be seen that when an intersection appears in front of the ego vehicle, the target elements are calculated based on the acquired traffic light information, lane line information and intersection information; wherein, the target elements include the angle between each traffic light and the center line of the ego lane, the distance between each traffic light and the ego vehicle, the lateral distance between the projection point of each traffic light on the stop line of the intersection and the center line of the ego lane, the front-to-back position relationship between each traffic light and the ego vehicle, and the matching result between the type of each traffic light and the driving direction of the ego lane; a weighted average calculation is performed on the target elements corresponding to each traffic light to determine the target traffic light that matches the ego lane based on the calculation results; when the current distance between the ego vehicle and the intersection position meets the preset threshold, the ego vehicle is controlled to travel according to the current display status of the target traffic light.

[0047] Beneficial effect: When an intersection appears in front of the vehicle, it is necessary to calculate the target elements based on the acquired traffic light information, lane line information, and intersection information, and then perform a weighted average calculation on the target elements corresponding to each traffic light to determine the target traffic light that matches the lane based on the calculation results; wherein, the target elements mainly include the angle between each traffic light and the center line of the lane, the distance between each traffic light and the vehicle, the lateral distance between the projection point of each traffic light on the stop line of the intersection and the center line of the lane, the front-to-back position relationship between each traffic light and the vehicle, and the matching result between the type of each traffic light and the driving direction of the lane. That is, the present application calculates the weighted score between each traffic light and the lane from multiple dimensions, thereby selecting the target traffic light that best matches the lane, improving the accuracy of the match, and thus improving the traffic efficiency at the intersection. Subsequently, when the current distance between the vehicle and the intersection position meets the preset threshold, the vehicle's travel can be controlled according to the current display status of the target traffic light. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without any creative work.

[0049] Figure 1A flow chart of a method for intersection passing decision disclosed in the present application;

[0050] Figure 2 A schematic diagram of a framework structure of an ADAS system disclosed in the present application;

[0051] Figure 3 A schematic diagram of an angle between a traffic light and a lane center line disclosed in the present application;

[0052] Figure 4 A schematic diagram of a Euclidean distance between a traffic light and a vehicle disclosed in the present application;

[0053] Figure 5 A schematic diagram of a lateral distance between a projection point of a traffic light on a stop line at an intersection and a lane center line disclosed in the present application;

[0054] Figure 6 A flow chart of a specific method for intersection passing decision disclosed in the present application;

[0055] Figure 7 A schematic diagram of a structure of an intersection passing decision device disclosed in the present application;

[0056] Figure 8 A structure diagram of an electronic device disclosed in the present application. DETAILED DESCRIPTION

[0057] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0058] In the intersection passing decision process, if the start-stop passing before the intersection is to be realized, it is crucial to accurately match the traffic light and the lane, which can ensure the efficiency of the intersection passing. At present, most technologies only consider the position and type of the traffic light to bind the traffic light and the lane, and the considered factors are relatively single, and the accuracy is low. Therefore, the embodiments of the present application disclose a method, device, equipment and medium for intersection passing decision, which can more accurately match the traffic light and the lane, so as to improve the efficiency of the intersection passing.

[0059] Referring to Figure 1 The embodiments of the present application disclose a method for intersection passing decision, which comprises the following steps:

[0060] Step S11: When an intersection appears in front of the vehicle, target elements are calculated based on the acquired traffic light information, lane line information, and intersection information; wherein the target elements include the angle between each traffic light and the centerline of the lane, the distance between each traffic light and the vehicle, the lateral distance between the projection point of each traffic light on the stop line of the intersection and the centerline of the lane, the front-to-back positional relationship between each traffic light and the vehicle, and the matching result between the type of each traffic light and the driving direction of the lane.

[0061] In this embodiment, the framework structure of the ADAS system is first introduced. Figure 2 As shown in the figure, it mainly includes a perception module, a vehicle information module, a map module, a positioning module, a navigation module, a decision-making and planning module, and a control module. Among them: the perception module mainly outputs real-time lane line information, traffic light information, intersection information, ground sign information, etc.; the navigation module mainly outputs navigation turn information at intersections, including turn type and distance, etc.; the map module mainly receives the perception data from the perception module and the positioning information from the positioning module to construct a lane topology map, outputs lane line information, lane information, intersection information, etc., receives navigation data and combines it with positioning information to output turn information such as turn direction and turn distance, etc.; the decision-making and planning module mainly combines perception data, map data and navigation information to make lane change decisions and output planned trajectories; the control module mainly uses the planned trajectory output by the decision-making and planning module and vehicle information to calculate the steering wheel angle and acceleration to achieve vehicle control.

[0062] In this application, when an intersection appears in front of the vehicle, it is first necessary to calculate the target elements based on the traffic light information, lane line information and intersection information obtained from the perception module and the map module. Among them, the target elements mainly include the following five types: the angle between each traffic light and the center line of the lane, the distance between each traffic light and the vehicle, the lateral distance between the projection point of each traffic light on the stop line of the intersection and the center line of the lane, the front and rear position relationship between each traffic light and the vehicle, and the matching result between the type of each traffic light and the driving direction of the lane.

[0063] In a specific embodiment, the angle between each traffic light and the center line of the self-lane is calculated based on the acquired traffic light information, lane line information and intersection information, including: obtaining the first position coordinates corresponding to each traffic light in the vehicle body coordinate system, and obtaining the second position coordinates of the target point on the center line of the self-lane that is closest to the traffic light position; constructing a first vector based on the first position coordinates and the second position coordinates, and constructing a second vector based on the second position coordinates and the position coordinates of any point on the center line of the self-lane; and using the angle between the first vector and the second vector as the angle between each traffic light and the center line of the self-lane.

[0064] That is, first, the first position coordinate corresponding to each traffic light in the vehicle body coordinate system is obtained from the perception module, denoted as , and a set of coordinate points from the lane center line of the ego vehicle is obtained from the map module . The second position coordinate of the target point closest to the traffic light position in the lane center line is taken as , and the first vector is constructed based on the first position coordinate and the second position coordinate . Then, the second vector is constructed based on the second position coordinate and the position coordinate of any point in the lane center line of the ego vehicle. In order to improve the accuracy of the calculation, considering the case of a curved road, the two points closest to the traffic light position in the lane center line are usually selected, i.e. and to construct the second vector .

[0065] The angle between the first vector and the second vector is calculated by the following formula:

[0066] ;

[0067] Then is taken as the angle between each traffic light and the lane center line of the ego vehicle, as shown in Figure 3 .

[0068] In the specific embodiment, the distance between each traffic light and the ego vehicle and the front-back position relationship between each traffic light and the ego vehicle are calculated according to the obtained traffic light information, lane line information and intersection information, including: calculating the Euclidean distance between each traffic light and the ego vehicle based on the horizontal coordinate value and the vertical coordinate value of the first position coordinate; determining the front-back position relationship between each traffic light and the ego vehicle based on the positive or negative nature of the vertical coordinate value in the first position coordinate.

[0069] It can be understood that since the first position coordinate corresponding to each traffic light is obtained in the vehicle body coordinate system , the Euclidean distance d0 between each traffic light and the ego vehicle can be calculated by the horizontal coordinate value and the vertical coordinate value of the first position coordinate, and the schematic diagram of the Euclidean distance is shown in Figure 4 , and the calculation formula of the Euclidean distance is as follows:

[0070] .

[0071] In addition, it is also necessary to determine the front-back position relationship between the traffic light and the ego vehicle, i.e. whether the traffic light is in front of or behind the vehicle body, which can be determined according to the positive or negative nature of the vertical coordinate value t x in the first position coordinate, i.e. if t x ​≥ 0, it means that the traffic light is in front of the vehicle body, if t x < 0, it means that the traffic light is behind the vehicle body.

[0072] In the specific embodiment, the lateral distance between the projection point of each traffic light on the stop line of the intersection and the lane center line is calculated according to the acquired traffic light information, lane line information and intersection information, including: acquiring third position coordinates and fourth position coordinates corresponding to the start point and end point of the stop line of the intersection respectively, and constructing a third vector based on the third position coordinates and the fourth position coordinates; calculating a fifth position coordinate of the projection point of each traffic light on the stop line of the intersection based on the first position coordinate and the third vector, and determining a straight line equation corresponding to the second vector; calculating the lateral distance between the projection point of each traffic light on the stop line of the intersection and the lane center line based on the fifth position coordinate and the straight line equation.

[0073] That is, the present application needs to acquire third position coordinates and fourth position coordinates corresponding to the start point and end point of the stop line of the intersection respectively, and construct a third vector based on the third position coordinates and the fourth position coordinates and the third vector to calculate the fifth position coordinate of the projection point of each traffic light on the stop line of the intersection , and the calculation formula is as follows:

[0074] ;

[0075] Then, the straight line equation corresponding to the second vector is determined, that is, the two points closest to the traffic light position from the lane center line and are fitted into a straight line equation, assuming that the straight line equation is y=kx+b, where k represents the slope and b is the constant term, then the lateral distance d between the projection point and the lane center line is calculated using the following formula:

[0076] .

[0077] As shown in Figure 5 , dist1 and dist2 in the figure are examples of the lateral distance between the projection point of different traffic lights on the stop line of the intersection and the lane center line given by the embodiments of the present application.

[0078] It should be noted that the types of traffic lights include straight, left turn, right turn and U-turn, and the driving directions of the lane include single driving direction and composite driving direction; wherein the single driving direction includes straight, left turn, right turn and U-turn, and the composite driving direction includes straight-left turn, straight-right turn, straight-left turn-right turn and straight-left turn-U-turn; accordingly, the matching result between the type of each traffic light and the driving direction of the lane is calculated according to the acquired traffic light information, lane line information and intersection information, including: if the driving direction of the lane is the single driving direction, it is judged whether the type of each traffic light is consistent with the single driving direction and the matching result is obtained; if the driving direction of the lane is the composite driving direction, the current driving direction is determined according to the navigation information, and then it is judged whether the type of each traffic light is consistent with the current driving direction and the matching result is obtained.

[0079] In the embodiment, the type of traffic light and the driving direction of the lane can be acquired from the map module. The type of traffic light can include but is not limited to straight, left turn, right turn, U-turn, etc., and the driving direction of the lane includes but is not limited to single driving direction and composite driving direction, and the single driving direction includes straight, left turn, right turn, U-turn, etc., and the composite driving direction includes but is not limited to straight-left turn, straight-right turn, straight-left turn-right turn, straight-left turn-U-turn, etc. If the driving direction of the lane is the single driving direction, it is judged whether the type of each traffic light is consistent with the single driving direction, and the corresponding matching result is obtained, and if the driving direction of the lane is the composite driving direction, the current driving direction needs to be determined according to the navigation information, for example, the driving direction of the lane is straight-left turn, and the navigation information indicates that the left turn is needed at present, so the actual current driving direction of the lane is left turn, and then it is judged whether the type of each traffic light is consistent with the current driving direction, and the corresponding matching result is obtained.

[0080] Step S12: weighted average calculation is performed on each target element corresponding to each traffic light to determine the target traffic light matched with the lane according to the calculation result.

[0081] In the embodiment, after the target elements are calculated according to the foregoing method, weighted average calculation is performed on each target element corresponding to each traffic light to determine the target traffic light matched with the lane according to the calculation result, so as to establish the binding relationship between the target traffic light and the lane. That is, the target traffic light most matched with the lane can be selected by calculating multiple target elements to calculate the weighted score between each traffic light and the lane from multiple dimensions, the accuracy of matching is improved, and the intersection passing efficiency is improved.

[0082] Step S13: when the current distance between the vehicle and the intersection position meets the preset threshold, the vehicle is controlled to drive according to the current display state of the target traffic light.

[0083] In the embodiment, when the current distance between the ego vehicle and the intersection position meets a preset threshold, the ego vehicle is controlled to travel according to the current display state of the target traffic light.

[0084] In the specific embodiment, the control of the ego vehicle to travel according to the current display state of the target traffic light includes: if the current display state of the target traffic light is a red light state, the distance between the current position of the ego vehicle and the stop line of the intersection is taken as a braking distance, and the ego vehicle is controlled to perform a stop action based on the braking distance; and if the current display state of the target traffic light is a green light state, the ego vehicle is controlled to travel normally based on navigation information. That is, when the ego vehicle travels to a certain threshold before the intersection, the current display state of the target traffic light is determined in real time, and if the current display state is a red light, a decision of deceleration and stop is made, the longitudinal distance of the stop is the distance from the current position of the ego vehicle to the stop line of the intersection, specifically, a center point closest to the distance in the center line of the ego lane is found as a planning endpoint, and a stop trajectory is planned based on the point and output to a control module to realize the stop action. On the contrary, if the traffic light of the lane before the intersection is always green, the ego vehicle is controlled to travel normally based on the navigation information, for example, a decision of straight passing through the intersection is made, and a normal centering trajectory is planned and output to the control module.

[0085] It can be seen that when the intersection position appears in front of the ego vehicle, the target elements are calculated according to the acquired traffic light information, lane line information and intersection information, and each target element corresponding to each traffic light is weighted and averaged to determine the target traffic light matched with the ego lane according to the calculation result; wherein the target elements mainly include the included angle between each traffic light and the center line of the ego lane, the distance between each traffic light and the ego vehicle, the lateral distance between the projection point of each traffic light on the stop line of the intersection and the center line of the ego lane, the front and rear position relationship between each traffic light and the ego vehicle, and the matching result between the type of each traffic light and the driving direction of the ego lane. That is, the weighted score between each traffic light and the ego lane is calculated from multiple dimensions in the application, so as to select the target traffic light most matched with the ego lane, improve the matching accuracy, and improve the intersection passing efficiency. When the current distance between the ego vehicle and the intersection position meets a preset threshold, the ego vehicle is controlled to travel according to the current display state of the target traffic light.

[0086] Referring to Figure 6 The embodiment of the application discloses a specific intersection passing decision method, and compared with the previous embodiment, the technical solution is further described and optimized. Specifically, it includes:

[0087] Step S21: When a road intersection position appears in front of the ego vehicle, a target element is calculated according to the acquired traffic light information, lane line information and intersection information; wherein the target element includes an included angle between each traffic light and a lane center line of the ego vehicle, a distance between each traffic light and the ego vehicle, a lateral distance between a projection point of each traffic light on a stop line of the intersection and the lane center line of the ego vehicle, a front-rear position relationship between each traffic light and the ego vehicle, and a matching result between a type of each traffic light and a driving direction of the lane of the ego vehicle.

[0088] Step S22: Each target element corresponding to each traffic light is scored according to a preset scoring rule to obtain a corresponding score value, and each score value is normalized to obtain a processed score value.

[0089] In the embodiment, after each target element is calculated, each target element corresponding to each traffic light is scored according to a preset scoring rule to obtain a corresponding score value, and in order to ensure the comparability of the scores, the score values of each factor also need to be normalized to obtain a processed score value.

[0090] In the specific embodiment, the scoring of each target element corresponding to each traffic light according to the preset scoring rule to obtain a corresponding score value includes: judging whether an absolute value of an included angle between a current traffic light and a lane center line of the ego vehicle is less than a preset included angle threshold value, if yes, setting the corresponding score value as a first preset score value, otherwise setting the corresponding score value as zero; judging whether a distance between the current traffic light and the ego vehicle is less than a preset distance threshold value, if yes, setting the corresponding score value as a second preset score value, otherwise setting the corresponding score value as zero; determining a total lane width on a left side and a right side of the lane center line of the ego vehicle respectively, and judging whether a distance between a projection point of the current traffic light on a stop line of the intersection and the lane center line of the ego vehicle is less than a corresponding total lane width based on a lateral position relationship between the projection point and the lane center line, if yes, setting the corresponding score value as a third preset score value, otherwise setting the corresponding score value as zero; if the current traffic light is in front of the ego vehicle, setting the corresponding score value as a fourth preset score value, otherwise setting the corresponding score value as zero; if a type of the current traffic light is consistent with a driving direction of the lane of the ego vehicle, setting the corresponding score value as a fifth preset score value, otherwise setting the corresponding score value as zero.

[0091] Specifically, when scoring the included angle between each traffic light and the lane center line of the ego vehicle, the preset included angle threshold value is set in the embodiment , and if an absolute value of the included angle between the current traffic light and the lane center line of the ego vehicle is less than the preset included angle threshold value If yes, the corresponding score value f1 is set as a first preset score value; otherwise, the corresponding score value is set as f1=0.

[0092] In scoring the distance between each traffic light and the ego vehicle, the embodiment of the present application sets a preset distance threshold If the distance between the current traffic light and the ego vehicle is less than the preset distance threshold , the corresponding score value f2 is set as a second preset score value; otherwise, the corresponding score value is set as f2=0.

[0093] In scoring the lateral distance between the projection point of each traffic light on the stop line at the intersection and the center line of the ego lane, first, the total width of the lanes on the left and right sides of the center line of the ego lane is determined, that is, the lane widths of the ego lane, the lane on the left side of the ego lane, and the lane on the right side of the ego lane are obtained from the map module, and the width of half of the ego lane and the total width of the lane widths of all the lanes on the right side of the ego lane are set as width right , that is, the lane width of all the lanes on the right side of the center line of the ego lane is obtained, and the width of half of the ego lane and the total width of the lane widths of all the lanes on the left side of the ego lane are set as width left , that is, the lane width of all the lanes on the left side of the center line of the ego lane is obtained. Then, based on the lateral positional relationship between the projection point of the current traffic light on the stop line at the intersection and the center line of the ego lane, it is determined whether the distance between the projection point and the center line of the ego lane is less than the corresponding total width of the lanes, if yes, the corresponding score value f3 is set as a third preset score value, otherwise, the corresponding score value is set as f3=0. For example, if the projection point of the traffic light on the stop line at the intersection is on the right side of the center line of the ego lane, if the vertical distance from the projection point to the center line of the ego lane is less than width right , the score is set as the third preset score value, otherwise, no score is obtained, that is, f3=0.

[0094] In scoring the front-back positional relationship between each traffic light and the ego vehicle, if the current traffic light is in front of the ego vehicle, the corresponding score value f4 is set as a fourth preset score value, otherwise, the corresponding score value is set as f4=0.

[0095] In scoring the matching result between the type of each traffic light and the driving direction of the ego lane, if the type of the current traffic light is consistent with the driving direction of the ego lane, the corresponding score value f5 is set as a fifth preset score value, otherwise, the corresponding score value is set as f5=0.

[0096] Further, for the scoring of the same target factor, the following formula is used for the normalization processing of the score value:

[0097] ;

[0098] wherein f min is the minimum value of the score of the target factor of this type, f max is the maximum value of the score of the target factor of this type.

[0099] Step S23: The calculation result of each traffic light is obtained by performing weighted average calculation on all the processed score values corresponding to each traffic light according to the preset weight coefficients, and the traffic light corresponding to the maximum value of the calculation result is taken as the target traffic light matched with the lane of the ego vehicle.

[0100] In this embodiment, the preset weight coefficients w1, w2, w3, w4 and w5 are obtained, and the calculation result s of each traffic light is obtained by performing weighted average calculation on all the processed score values corresponding to each traffic light using the preset weight coefficients, and the calculation formula of s is as follows:

[0101] ;

[0102] It should be noted that, in order to avoid that some factors dominate the final score due to too large weight, and to avoid being ignored due to too small weight, the weight is normalized in this embodiment, that is, when calculating the weighted score, the set weight needs to meet two conditions:

[0103] ;

[0104] .

[0105] Step S24: When the current distance between the ego vehicle and the intersection position meets the preset threshold, the ego vehicle is controlled to travel according to the current display state of the target traffic light.

[0106] It should be noted that the more specific processing process of the above steps S21 and S24 can refer to the corresponding content disclosed in the foregoing embodiments, and will not be described here in detail.

[0107] It can be seen that the present application considers the binding of traffic lights and lanes in multiple dimensions, including the angle between the traffic light and the lane center line, the Euclidean distance from the traffic light to the ego vehicle, the transverse distance from the projection point of the traffic light on the stop line of the intersection to the lane center line of the ego vehicle, the front-back relationship between the traffic light and the ego vehicle, the type of the traffic light and whether the driving direction of the lane matches, wherein the lane is processed in combination with the navigation turning information to handle the scene of the composite driving direction, which can ensure the accuracy of the lane-level traffic light matching to improve the efficiency of intersection passing. Moreover, when performing weighted average calculation on each target factor corresponding to each traffic light, the score value of each factor needs to be calculated according to the preset scoring rule, and the score value also needs to be normalized, and then the preset weight coefficient is used to perform weighted average calculation to obtain the final calculation result, so as to ensure the accuracy and authenticity of the calculation result.

[0108] Referring to Figure 7 The embodiment of the present application discloses a kind of intersection passing decision device, the device includes:

[0109] Element calculation module 11, for when the intersection position appears in front of ego vehicle, target element is calculated according to the traffic light information, lane line information and intersection information obtained;Wherein, the target element includes the included angle between each traffic light and the center line of ego lane, the distance between each traffic light and ego vehicle, the lateral distance between the projection point of each traffic light on intersection stop line and the center line of ego lane, the front-back position relationship between each traffic light and ego vehicle and the matching result between the type of each traffic light and the driving direction of ego lane;

[0110] Matching module 12, for each target element corresponding to each traffic light is weighted average calculation, to determine the target traffic light matched with ego lane according to the calculation result;

[0111] Control module 13, for when the current distance between ego vehicle and the intersection position satisfies preset threshold, ego vehicle is controlled to travel according to the current display state of the target traffic light.

[0112] It can be seen that when the intersection position appears in front of ego vehicle, then target element is calculated according to the traffic light information, lane line information and intersection information obtained, and each target element corresponding to each traffic light is weighted average calculation, to determine the target traffic light matched with ego lane according to the calculation result;Wherein, target element mainly includes the included angle between each traffic light and the center line of ego lane, the distance between each traffic light and ego vehicle, the lateral distance between the projection point of each traffic light on intersection stop line and the center line of ego lane, the front-back position relationship between each traffic light and ego vehicle and the matching result between the type of each traffic light and the driving direction of ego lane. That is, the weighted score between each traffic light and ego lane is calculated from multiple dimensions in the present application, so that the target traffic light most matched with ego lane is selected, the accuracy of matching is improved, and the intersection passing efficiency is improved. When the current distance between ego vehicle and intersection position satisfies preset threshold subsequently, ego vehicle can be controlled to travel according to the current display state of the target traffic light.

[0113] Since the embodiments of the device part correspond to the embodiments of the method part, the embodiments of the device part will be described with reference to the embodiments of the method part, which will not be described here. Moreover, it has the same beneficial effects as the intersection passing decision method mentioned above.

[0114] Figure 8A structural schematic diagram of an electronic device is provided in the embodiments of the present application. Specifically, it can include at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is configured to store a computer program, which is loaded and executed by the processor 21 to implement the related steps in the intersection passing decision method performed by the electronic device disclosed in any of the preceding embodiments.

[0115] In the embodiments, the power supply 23 is configured to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 is capable of creating a data transmission channel between the electronic device 20 and external devices, and the communication protocol followed by the communication interface 24 can be any communication protocol applicable to the technical solution of the present application, which is not limited specifically herein; the input / output interface 25 is configured to obtain external input data or output data to the outside world, and the specific interface type can be selected according to the specific application needs, which is not limited specifically herein.

[0116] The processor 21 can include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 can be implemented in at least one of a hardware form of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), and a PLA (Programmable Logic Array). The processor 21 can also include a main processor and a coprocessor. The main processor is a processor for processing data in a wake-up state, also known as a CPU (Central Processing Unit). The coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor 21 can be integrated with a GPU (Graphics Processing Unit) that is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 21 can also include an AI (Artificial Intelligence) processor for processing machine learning-related computing operations.

[0117] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, a random access memory, a magnetic disk, or an optical disk, etc. The resources stored thereon include an operating system 221, a computer program 222, and data 223, etc. The storage mode can be temporary storage or permanent storage.

[0118] The operating system 221 is used to manage and control the hardware devices and computer programs 222 on the electronic device 20, enabling the processor 21 to calculate and process the massive amount of data 223 in the memory 22. It can be run under Windows, Unix, Linux, or other operating systems. In addition to computer programs capable of implementing the intersection traffic decision-making method disclosed in any of the aforementioned embodiments and executed by the electronic device 20, the computer programs 222 may further include computer programs capable of performing other specific tasks. Data 223 may include data received by the electronic device from external devices, as well as data collected by its own input / output interface 25.

[0119] Furthermore, an embodiment of the present application also discloses a computer-readable storage medium, in which a computer program is stored. When the computer program is loaded and executed by a processor, the steps of the intersection traffic decision method disclosed in any of the aforementioned embodiments are implemented.

[0120] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from the other embodiments. Reference can be made to the descriptions of the identical or similar parts between the various embodiments. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple, and the relevant parts can be referred to the descriptions of the methods.

[0121] Those skilled in the art may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the composition and steps of each example according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0122] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module can be placed in random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, a hard disk, a removable disk, a compact disc read-only memory (CD-ROM), or any other form of storage medium known in the art.

[0123] Finally, it needs to be pointed out that in this paper, the relationship terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between the entities or operations. Moreover, the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or device. Without more limitations, the element defined by the statement "including a" does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0124] The intersection passing decision method, device, equipment and storage medium provided by the application are described in detail above, the principle and implementation manner of the application are described in this paper by applying specific examples, and the above example description is only used to help understand the method and core idea of the application; meanwhile, for those skilled in the art, according to the idea of the application, the specific implementation manner and application range will be changed, and the above description should not be understood as a limitation on the application.

Claims

1. A method for making decisions about traffic flow at an intersection, characterized in that: include: When an intersection appears in front of the vehicle, target elements are calculated based on the acquired traffic light information, lane line information, and intersection information. These target elements include the angle between each traffic light and the centerline of the vehicle's lane, the distance between each traffic light and the vehicle, the lateral distance between the projection of each traffic light on the intersection's stop line and the centerline of the vehicle's lane, the fore-and-aft positional relationship between each traffic light and the vehicle, and the matching result between each traffic light type and the direction of travel in the vehicle's lane. Perform weighted average calculation on each target element corresponding to each traffic light, and determine the target traffic light that matches the lane based on the calculation result; When the current distance between the vehicle and the intersection location meets a preset threshold, the vehicle is controlled to travel according to the current display state of the target traffic light.

2. The intersection traffic decision method according to claim 1, characterized in that: Calculate the angle between each traffic light and the centerline of the lane based on the acquired traffic light information, lane line information, and intersection information, including: Obtaining the first position coordinates corresponding to each traffic light in the vehicle coordinate system, and obtaining the second position coordinates of the target point closest to the traffic light position on the center line of the lane; Constructing a first vector based on the first position coordinates and the second position coordinates, and constructing a second vector based on the second position coordinates and the position coordinates of any point on the centerline of the lane; The angle between the first vector and the second vector is used as the angle between each traffic light and the center line of the lane; Accordingly, the distance between each traffic light and the vehicle, as well as the front-to-rear position relationship between each traffic light and the vehicle, is calculated based on the acquired traffic light information, lane line information, and intersection information, including: Calculate the Euclidean distance between each traffic light and the vehicle based on the abscissa value and the ordinate value of the first position coordinate; The front-to-rear positional relationship between each traffic light and the vehicle is determined based on the positive or negative value of the vertical coordinate in the first position coordinate.

3. The intersection traffic decision method according to claim 2, characterized in that: Calculate the lateral distance between the projection point of each traffic light on the stop line of the intersection and the center line of the lane based on the acquired traffic light information, lane line information, and intersection information, including: Obtaining third position coordinates and fourth position coordinates corresponding to the start point and the end point of the stop line at the intersection, respectively, and constructing a third vector based on the third position coordinates and the fourth position coordinates; Calculating the fifth position coordinates of the projection point of each traffic light on the stop line of the intersection based on the first position coordinates and the third vector, and determining the equation of the straight line corresponding to the second vector; The lateral distance between the projection point of each traffic light on the stop line of the intersection and the center line of the lane is calculated based on the fifth position coordinate and the straight line equation.

4. The intersection traffic decision-making method according to claim 1, characterized in that: Traffic light types include straight ahead, left turn, right turn, and U-turn; and lane driving directions include single driving directions and combined driving directions; wherein the single driving directions include straight ahead, left turn, right turn, and U-turn; and the combined driving directions include straight ahead and left turn, straight ahead and right turn, straight ahead and left turn and right turn, and straight ahead and left turn and U-turn; Accordingly, the matching result between each traffic light type and the driving direction of the own lane is calculated based on the acquired traffic light information, lane line information, and intersection information, including: If the driving direction of the lane is the single driving direction, determining whether the type of each traffic light is consistent with the single driving direction and obtaining a matching result; If the driving direction of the lane is the composite driving direction, the current driving direction is determined according to the navigation information, and then it is determined whether the type of each traffic light is consistent with the current driving direction and a matching result is obtained.

5. The intersection traffic decision method according to claim 1, characterized in that: The controlling the vehicle to travel according to the current display state of the target traffic light includes: If the current display state of the target traffic light is a red light state, the distance between the current position of the vehicle and the stop line of the intersection is used as the braking distance, so as to control the vehicle to perform a braking action based on the braking distance; If the current display state of the target traffic light is a green light state, the vehicle is controlled to travel normally based on the navigation information.

6. The intersection traffic decision-making method according to any one of claims 1 to 5, characterized in that: The weighted average calculation of each target element corresponding to each traffic light to determine the target traffic light matching the own lane according to the calculation result includes: Scoring each target element corresponding to each traffic light according to a preset scoring rule to obtain a corresponding scoring value, and normalizing each scoring value to obtain a processed scoring value; Performing a weighted average calculation on all the processed score values ​​corresponding to each traffic light according to a preset weight coefficient to obtain a calculation result for each traffic light; The traffic light corresponding to the maximum value of the calculation result is used as the target traffic light matching the ego lane.

7. The intersection traffic decision method according to claim 6, characterized in that: Scoring each target element corresponding to each traffic light according to a preset scoring rule to obtain a corresponding scoring value includes: Determine whether the absolute value of the angle between the current traffic light and the center line of the lane is less than a preset angle threshold; if so, set the corresponding score value to a first preset score; otherwise, set the corresponding score value to zero; Determine whether the distance between the current traffic light and the vehicle is less than a preset distance threshold, and if so, set the corresponding score value to a second preset score value; otherwise, set the corresponding score value to zero; Using the centerline of the lane as the dividing line, determine the sum of the lane widths to the left and right of the centerline of the lane, and determine, based on the lateral positional relationship between the projection point of the current traffic light on the stop line at the intersection and the centerline of the lane, whether the distance between the projection point and the centerline of the lane is less than the corresponding sum of the lane widths. If so, set the corresponding score value to a third preset score; otherwise, set the corresponding score value to zero. If the current traffic light is in front of the vehicle, the corresponding score value is set to the fourth preset score value; otherwise, the corresponding score value is set to zero; If the type of the current traffic light is consistent with the driving direction of the lane, the corresponding score value is set to the fifth preset score value; otherwise, the corresponding score value is set to zero.

8. A road intersection traffic decision-making device, characterized in that: include: an element calculation module, configured to calculate target elements based on acquired traffic light information, lane line information, and intersection information when an intersection appears ahead of the ego vehicle; wherein the target elements include the angle between each traffic light and the centerline of the ego vehicle's lane, the distance between each traffic light and the ego vehicle, the lateral distance between the projection of each traffic light on the intersection stop line and the centerline of the ego vehicle's lane, the fore-aft positional relationship between each traffic light and the ego vehicle, and the matching result between the type of each traffic light and the driving direction of the ego vehicle's lane; A matching module is used to perform weighted average calculation on each target element corresponding to each traffic light, so as to determine the target traffic light that matches the lane based on the calculation result; The control module is used to control the vehicle to travel according to the current display state of the target traffic light when the current distance between the vehicle and the intersection position meets a preset threshold.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor is used to execute the computer program to implement the steps of the intersection traffic decision-making method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that Used to store computer programs; wherein, when the computer program is executed by a processor, the steps of the intersection traffic decision-making method according to any one of claims 1 to 7 are implemented.

Images