Path planning method

Abstract

The invention discloses a path planning method, and relates to the field of auxiliary driving, and the method comprises the steps: planning an initial lane changing path for a to-be-changed lane when there are obstacles on the to-be-changed lane and an adjacent lane determined based on a lane changing instruction; the expected collision time between the current self-vehicle and the obstacle is determined; predicting a first collision danger degree coefficient of collision with an obstacle during lane changing based on the initial lane changing path; and judging whether to delay lane changing based on the instruction type of the lane changing instruction, the expected collision time and the first collision danger degree coefficient, and determining a target lane changing path based on a delayed lane changing judgment result, so as to execute corresponding lane changing operation according to the target lane changing path. Whether lane changing is delayed or not is judged according to the instruction type of the lane changing instruction, the expected collision time related to the obstacle and the first collision danger degree coefficient, a safer lane changing path is planned by adjusting the lane changing time, and therefore the risk of vehicle lane changing is reduced.

Description

Technical Field

[0001] The present invention relates to the field of assisted driving, and particularly to a path planning method. Background Art

[0002] At present, when a vehicle changes lanes during driving, it does not consider whether there are other vehicles around the lane to be changed. For example, when the host vehicle changes lanes to the right lane to be changed, if there is another vehicle on the right side of the lane to be changed, there is an easy sense of collision between the host vehicle and the other vehicle during the lane change, that is, since the distance from the other vehicle is relatively close when the host vehicle changes lanes, the danger of the lane change increases in this case, and it is easy to bring a sense of oppression to the driver. Therefore, when there are obstacles around the lane to be changed, how to plan a safer lane change path is a technical problem to be solved at present. Summary of the Invention

[0003] In view of this, the purpose of the present invention is to provide a path planning method, which can judge whether to delay the lane change according to the instruction type of the lane change instruction, the expected collision time related to the obstacle, and the first collision risk degree coefficient, and plan a safer lane change path by adjusting the timing of the lane change, so as to reduce the danger of the vehicle lane change. The specific scheme is as follows:

[0004] In a first aspect, the present application provides a path planning method, including:

[0005] When there are obstacles on the lane to be changed and the adjacent lane determined based on the lane change instruction, plan an initial lane change path for the lane to be changed;

[0006] Determine the expected collision time between the current host vehicle and the obstacle;

[0007] Predict the first collision risk degree coefficient when changing lanes based on the initial lane change path; the first collision risk degree coefficient represents the risk degree coefficient of collision with the obstacle;

[0008] Judge whether to delay the lane change based on the instruction type of the lane change instruction, the expected collision time, and the first collision risk degree coefficient, and determine the target lane change path based on the delay lane change judgment result, so as to perform corresponding lane change operations according to the target lane change path.

[0009] Optionally, the judging whether to delay the lane change based on the instruction type of the lane change instruction, the expected collision time, and the first collision risk degree coefficient includes:

[0010] If the instruction type of the lane change instruction is a lever-operated lane change instruction, or, the instruction type of the lane change instruction is an automatic lane change instruction and the expected collision time and the first collision risk degree coefficient do not meet the preset collision conditions, it is determined to change lanes immediately;

[0011] If the instruction type of the lane change instruction is an automatic lane change instruction and the expected collision time and the first collision risk coefficient meet the preset collision conditions, it is determined that the lane change is delayed;

[0012] Among them, the preset collision conditions include that the expected collision time is less than the preset time and the first collision risk coefficient is less than the first preset coefficient.

[0013] Optionally, determining the target lane change path based on the delayed lane change judgment result includes:

[0014] If the delayed lane change judgment result indicates a delayed lane change, determine the corresponding delayed lane change time, and re-plan the lane change path after the delayed lane change time to obtain the target lane change path;

[0015] If the delayed lane change judgment result indicates an immediate lane change, and the instruction type of the lane change instruction is a lever-operated lane change instruction, then determine whether to optimize the initial lane change path by judging whether the expected collision time and the first collision risk coefficient meet the preset collision conditions to obtain the target lane change path;

[0016] If the delayed lane change judgment result indicates an immediate lane change, and the instruction type of the lane change instruction is an automatic lane change instruction, then determine the initial lane change path as the target lane change path.

[0017] Optionally, determining whether to optimize the initial lane change path by judging whether the expected collision time and the first collision risk coefficient meet the preset collision conditions to obtain the target lane change path includes:

[0018] If the expected collision time and the first collision risk coefficient meet the preset collision conditions, optimize the initial lane change path based on the second collision risk coefficient and the vehicle lateral speed of each planned point on the initial lane change path to obtain the target lane change path; the second collision risk coefficient represents the risk coefficient of a collision between the host vehicle and the obstacle when the host vehicle is at the planned point;

[0019] If the expected collision time and the first collision risk coefficient do not meet the preset collision conditions, determine the initial lane change path as the target lane change path.

[0020] Optionally, before optimizing the initial lane change path based on the second collision risk coefficient and the vehicle lateral speed of each planned point on the initial lane change path, it further includes:

[0021] In a target coordinate system with any planned point on the initial lane-changing path as the origin, obtain the lateral distance from the any planned point to the obstacle, and determine the lateral vehicle speed of the any planned point based on the positions of the any planned point and the previous planned point;

[0022] Based on the lateral distance from the any planned point to the obstacle and the lateral vehicle speed of the any planned point, determine the second collision risk degree coefficient of the any planned point;

[0023] Wherein, the longitudinal axis direction of the target coordinate system is parallel to the tangent direction of the any planned point on the lane center line; the transverse axis direction of the target coordinate system is perpendicular to the tangent direction.

[0024] Optionally, the first collision risk degree coefficient when changing lanes based on the initial lane-changing path includes:

[0025] Determine the first average lateral speed based on the lateral vehicle speeds of the planned points within a preset time period on the initial lane-changing path; the preset time period is the time period adjacent to the current moment;

[0026] Determine the first collision risk degree coefficient according to the lateral distance from the first planned point on the initial lane-changing path to the obstacle and the first average lateral speed.

[0027] Optionally, optimizing the initial lane-changing path based on the second collision risk degree coefficient and the lateral vehicle speed of each planned point on the initial lane-changing path to obtain a target lane-changing path includes:

[0028] Determine the target planned points on the initial lane-changing path where the second collision risk degree coefficient is less than the second preset coefficient;

[0029] Determine the first-generation value of the target planned point based on the second collision risk degree coefficient of the target planned point;

[0030] Determine the second-generation value of the initial lane-changing path based on the lateral vehicle speeds of each planned point on the initial lane-changing path;

[0031] Optimize the initial lane-changing path by using the first-generation value and the second-generation value to obtain a target lane-changing path.

[0032] Optionally, determining the first-generation value of the target planned point based on the second collision risk degree coefficient of the target planned point includes:

[0033] Determine the first-generation value of the target planned point based on the difference between the second collision risk degree coefficient of the target planned point and the second preset coefficient.

[0034] Optionally, determining the second-generation value of the initial lane-changing path based on the lateral vehicle speed of each planned point on the initial lane-changing path includes:

[0035] Determining the maximum lateral speed from the lateral vehicle speeds of each planned point on the initial lane-changing path;

[0036] Determining a second average lateral speed based on the lateral vehicle speed of the target planned point;

[0037] Determining the second-generation value of the initial lane-changing path according to the maximum lateral speed and the second average lateral speed.

[0038] Optionally, determining the corresponding delayed lane-changing time includes:

[0039] Determining the maximum planned time from the planned times corresponding to the respective target planned points on the initial lane-changing path;

[0040] Determining the delayed lane-changing time based on the maximum planned time.

[0041] Optionally, determining the expected collision time between the current vehicle and the obstacle includes:

[0042] Determining the longitudinal distance from the front target to the rear target; the front target and the rear target are respectively the one with a forward position and the one with a rearward position among the current vehicle and the obstacle;

[0043] Determining the speed difference between the rear target and the front target;

[0044] Determining the expected collision time based on the ratio of the longitudinal distance and the speed difference and the positive or negative situation of the ratio.

[0045] In a second aspect, the present application provides a path planning device, including:

[0046] A path planning module, configured to plan an initial lane-changing path for the to-be-changed lane when there are obstacles in the to-be-changed lane and the adjacent lane determined based on a lane-changing instruction;

[0047] A time determination module, configured to determine the expected collision time between the current vehicle and the obstacle;

[0048] A coefficient prediction module, configured to predict a first collision risk degree coefficient when changing lanes based on the initial lane-changing path; the first collision risk degree coefficient represents the risk degree coefficient of a collision with the obstacle;

[0049] The lane change execution module is used to determine whether to delay the lane change based on the instruction type of the lane change instruction, the expected collision time, and the first collision risk coefficient, and determine the target lane change path based on the result of the delayed lane change judgment, so as to perform corresponding lane change operations according to the target lane change path.

[0050] In a third aspect, the present application provides an electronic device, including:

[0051] A memory for storing a computer program;

[0052] A processor for executing the computer program to implement the foregoing path planning method.

[0053] In a fourth aspect, the present application provides a computer-readable storage medium for storing a computer program, and when the computer program is executed by a processor, the foregoing path planning method is implemented.

[0054] In the present application, when there are obstacles in the to-be-changed lane and the adjacent lane determined based on the lane change instruction, an initial lane change path for the to-be-changed lane is planned; the expected collision time between the current vehicle and the obstacle is determined; the first collision risk coefficient when changing lanes based on the initial lane change path is predicted; the first collision risk coefficient represents the risk coefficient of a collision with the obstacle; it is determined whether to delay the lane change based on the instruction type of the lane change instruction, the expected collision time, and the first collision risk coefficient, and the target lane change path is determined based on the result of the delayed lane change judgment, so as to perform corresponding lane change operations according to the target lane change path. It can be seen that when there are obstacles in the to-be-changed lane and the adjacent lane, the present application determines whether to delay the lane change according to the instruction type of the lane change instruction, the expected collision time related to the obstacle, and the first collision risk coefficient, so as to plan a safer target lane change path by adjusting the timing of the lane change, thereby reducing the risk of collision between the vehicle and the obstacle when changing lanes along the target lane change path and improving the driving safety of the vehicle. Description of the Drawings

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0056] Figure 1 It is a flowchart of a path planning method disclosed in an embodiment of the present invention;

[0057] Figure 2A schematic diagram of a lane-changing path disclosed in an embodiment of the present invention;

[0058] Figure 3 A schematic diagram of the lateral distance from a planned point to an obstacle disclosed in an embodiment of the present invention;

[0059] Figure 4 A schematic diagram of the structure of a path planning device disclosed in an embodiment of the present invention;

[0060] Figure 5 A structural diagram of an electronic device disclosed in an embodiment of the present invention. Detailed implementation manners

[0061] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0062] At present, when a vehicle changes lanes during driving, it does not consider whether there are other vehicles around the lane to be changed. This makes it easy for the host vehicle to have a sense of collision with other vehicles when changing lanes, that is, when the host vehicle changes lanes, due to the close distance to other vehicles, the danger of changing lanes increases, and it is easy to bring a sense of oppression to the driver. For this reason, the present application provides a path planning method, which can judge whether to delay lane change according to the instruction type of the lane change instruction, the expected collision time related to the obstacle, and the first collision risk degree coefficient, and plan a safer lane-changing path by adjusting the timing of lane change, thereby reducing the danger of vehicle lane change.

[0063] See Figure 1 As shown, an embodiment of the present invention discloses a path planning method, including:

[0064] Step S11: When there are obstacles in the lane to be changed and the adjacent lane determined based on the lane change instruction, plan an initial lane-changing path for the lane to be changed.

[0065] In an embodiment of the present invention, when obtaining a lane change instruction, the lane to be changed and the adjacent lane are determined based on the lane change instruction, where the adjacent lane is the lane adjacent to the lane to be changed, and it is judged whether there are obstacles on the lane to be changed and the adjacent lane that affect the lane change of the host vehicle; the obstacles include but are not limited to other vehicles, construction fences, pedestrians, etc.

[0066] If there are no obstacles on the lane to be changed and the adjacent lanes that affect the vehicle's lane change, an initial lane change path for the lane to be changed is planned, and the initial lane change path is determined as the target lane change path, so as to perform corresponding lane change operations according to the target lane change path.

[0067] If there are obstacles on the lane to be changed and the adjacent lanes that affect the vehicle's lane change, an initial lane change path for the lane to be changed is planned, and the first collision risk degree coefficient of the vehicle colliding with the obstacle when changing lanes based on the initial lane change path is predicted. Then, according to the instruction type of the lane change instruction, the expected collision time between the current vehicle and the obstacle, and the first collision risk degree coefficient, it is judged whether to delay the lane change, and the corresponding target lane change path is determined based on the delay lane change judgment result, so as to perform corresponding lane change operations according to the target lane change path.

[0068] It should be noted that for the instruction type of the lane change instruction, there are the following two types: one is the lever lane change instruction generated by the driver triggering the turn signal lever, that is, when the turn signal lever event is detected, the corresponding lever lane change instruction is generated based on the turn signal lever event. Since this lane change instruction is determined by the driver's lever, it has no delay and needs to be executed immediately. The other is the automatic lane change instruction actively triggered in the case of autonomous driving. This lane change instruction can come from overtaking lane change or merging lane change, etc., and has a certain delay. Therefore, when receiving the automatic lane change instruction, it can be executed immediately or delayed.

[0069] For the planning of the initial lane change path for the lane to be changed, it can be planned through existing path planning algorithms. The parameters considered include but are not limited to lane width, vehicle speed, current vehicle position, transverse and longitudinal distances from obstacles, distances from the lane lines of the lane to be changed, upper and lower limits of road driving speed, lane width, etc., which will not be elaborated here.

[0070] Step S12: Determine the expected collision time between the current vehicle and the obstacle.

[0071] In the embodiment of the present invention, after obtaining the speed of the current vehicle and the speed of the obstacle, the time required for the vehicle and the obstacle to maintain their current speeds until a collision occurs at the current moment is calculated to obtain the expected collision time (TTC, Time To Collision) between the current vehicle and the obstacle.

[0072] Specifically, the party with the forward position and the party with the rear position among the current vehicle and the obstacle are respectively recorded as the forward target and the rear target, the longitudinal distance from the forward target to the rear target is determined, and the speed difference between the rear target and the forward target is determined; based on the ratio of the longitudinal distance to the speed difference and the positive or negative situation of the ratio, the expected collision time is determined.

[0073] That is, determine the longitudinal distance from the front target to the rear target, where the longitudinal distance is a non - negative value, and subtract the speed of the front target from the speed of the rear target to obtain a speed difference, where the speed difference can be any value; calculate the ratio of the longitudinal distance to the speed difference, and when the ratio is non - negative, determine the ratio as the expected collision time, and when the ratio is negative or the speed difference is 0, determine a preset value approaching infinity as the expected collision time.

[0074] Step S13: Predict the first collision risk degree coefficient when changing lanes based on the initial lane - change path; the first collision risk degree coefficient characterizes the risk degree coefficient of a collision with the obstacle.

[0075] In the embodiment of the present invention, the risk degree coefficient of a collision between the vehicle itself and the obstacle when changing lanes based on the initial lane - change path is predicted to obtain the first collision risk degree coefficient. Among them, the first collision risk degree coefficient has a negative correlation with the collision risk degree, that is, the larger the first collision risk degree coefficient, the lower the collision risk degree; the smaller the first collision risk degree coefficient, the greater the collision risk degree.

[0076] Step S14: Based on the instruction type of the lane - change instruction, the expected collision time, and the first collision risk degree coefficient, determine whether to delay the lane - change, and determine the target lane - change path based on the result of the delay lane - change judgment, so as to perform the corresponding lane - change operation according to the target lane - change path.

[0077] In the embodiment of the present invention, after obtaining the expected collision time and the first collision risk degree coefficient, it is determined whether to delay the lane - change according to the instruction type of the lane - change instruction, the expected collision time, and the first collision risk degree coefficient. If changing lanes immediately, immediately determine the target lane - change path according to the initial lane - change path, so as to perform the corresponding lane - change operation according to the target lane - change path. If delaying the lane - change, determine the corresponding delay lane - change time, and re - plan the lane - change path after the delay lane - change time to obtain the target lane - change path, and then perform the corresponding lane - change operation according to the target lane - change path.

[0078] Specifically, for the judgment of whether to delay the lane - change, if the instruction type of the lane - change instruction is a lever - operated lane - change instruction, or, the instruction type of the lane - change instruction is an automatic lane - change instruction and the expected collision time and the first collision risk degree coefficient do not meet the preset collision conditions, it is determined to change lanes immediately; if the instruction type of the lane - change instruction is an automatic lane - change instruction and the expected collision time and the first collision risk degree coefficient meet the preset collision conditions, it is determined to delay the lane - change.

[0079] Among them, the preset collision conditions include that the expected collision time is less than the preset time and the first collision risk coefficient is less than the first preset coefficient. That is, if the expected collision time is less than the preset time and the first collision risk coefficient is less than the first preset coefficient, it indicates that the probability of the host vehicle colliding with an obstacle when changing lanes based on the initial lane change path is relatively high; if the expected collision time is not less than the preset time, or the expected collision time is less than the preset time but the first collision risk coefficient is not less than the first preset coefficient, it indicates that the probability of the host vehicle colliding with an obstacle when changing lanes based on the initial lane change path is relatively low, or in other words, the host vehicle is almost unlikely to collide with an obstacle when changing lanes based on the initial lane change path.

[0080] Further, after obtaining the delayed lane change judgment result, if the delayed lane change judgment result indicates a delayed lane change, determine the corresponding delayed lane change time, and re-plan the lane change path after the corresponding delayed lane change time to obtain the target lane change path.

[0081] If the delayed lane change judgment result indicates an immediate lane change, and the instruction type of the lane change instruction is a lever-operated lane change instruction, determine whether to optimize the initial lane change path to obtain the target lane change path by judging whether the expected collision time and the first collision risk coefficient meet the preset collision conditions. If the delayed lane change judgment result indicates an immediate lane change, and the instruction type of the lane change instruction is an automatic lane change instruction, determine the initial lane change path as the target lane change path.

[0082] When the delayed lane change judgment result indicates an immediate lane change, and the instruction type of the lane change instruction is a lever-operated lane change instruction, if the expected collision time and the first collision risk coefficient meet the preset collision conditions, optimize the initial lane change path based on the second collision risk coefficient and the vehicle lateral speed of each planned point on the initial lane change path to obtain the target lane change path; if the expected collision time and the first collision risk coefficient do not meet the preset collision conditions, determine the initial lane change path as the target lane change path.

[0083] Among them, the second collision risk coefficient represents the risk coefficient of collision between the host vehicle and an obstacle when the host vehicle is at the planned point. Moreover, the second collision risk coefficient is negatively correlated with the collision risk, that is, the larger the second collision risk coefficient, the lower the collision risk; the smaller the second collision risk coefficient, the greater the collision risk.

[0084] For the determination of the second collision risk degree coefficient and the vehicle lateral speed of each planned point on the initial lane-changing path, it may specifically include: For any planned point on the initial lane-changing path, in the target coordinate system with any planned point as the origin, obtain the lateral distance from any planned point to the obstacle, and based on the positions of any planned point and the previous planned point, determine the vehicle lateral speed of any planned point; wherein, the longitudinal axis direction of the target coordinate system is parallel to the tangent direction of any planned point on the lane center line; the transverse axis direction of the target coordinate system is perpendicular to the tangent direction. Then, based on the lateral distance from any planned point to the obstacle and the vehicle lateral speed of any planned point, determine the second collision risk degree coefficient of any planned point, that is, the second collision risk degree coefficient = lateral distance / vehicle lateral speed.

[0085] It should be noted that for the vehicle lateral speed of any planned point, in the target coordinate system with any planned point as the origin, decompose the connection line between any planned point and the previous planned point into the movement amount in the longitudinal axis direction and the movement amount in the transverse axis direction, and then determine the vehicle lateral speed of any planned point based on the ratio of the movement amount in the transverse direction to the unit time (such as 0.1 s).

[0086] Furthermore, for the prediction of the first collision risk degree coefficient in step S13, it may specifically include: Determine the first average lateral speed based on the vehicle lateral speeds of the planned points within the preset time period on the initial lane-changing path; wherein, the preset time period is the time period adjacent to the current moment; then, based on the lateral distance from the first planned point on the initial lane-changing path to the obstacle and the first average lateral speed, determine the first collision risk degree coefficient, that is, the first collision risk degree coefficient = the lateral distance from the first planned point on the initial lane-changing path to the obstacle / the first average lateral speed.

[0087] According to one specific implementation manner, in the process of optimizing the initial lane-changing path to obtain the target lane-changing path based on the second collision risk degree coefficient and the vehicle lateral speed of each planned point on the initial lane-changing path, determine the target planned points with the second collision risk degree coefficient less than the second preset coefficient from the initial lane-changing path, and determine the first-generation value of the target planned points based on the second collision risk degree coefficient of the target planned points, and then determine the second-generation value of the initial lane-changing path based on the vehicle lateral speeds of each planned point on the initial lane-changing path; use the first-generation value and the second-generation value to optimize the initial lane-changing path to obtain the target lane-changing path. Wherein, the first preset coefficient and the second preset coefficient are selected with the same value.

[0088] In the process of determining the first-generation value of the target planned points based on the second collision risk degree coefficient of the target planned points, determine the first-generation value of the target planned points based on the difference between the second collision risk degree coefficient of the target planned points and the second preset coefficient.

[0089] Taking the second preset coefficient as 3 as an example, the calculation formula for the first-generation value is as follows:

[0090] ;

[0091] Among them, represents the second collision risk degree coefficient of the target planning point. Since the second collision risk degree coefficient of the target planning point is less than the second preset coefficient, therefore, is the second collision risk degree coefficient of the target planning point.

[0092] In the process of determining the second-generation value of the initial lane-changing path based on the lateral vehicle speed of each planning point on the initial lane-changing path, the maximum lateral speed is determined from the lateral vehicle speeds of each planning point on the initial lane-changing path; based on the lateral vehicle speed of the target planning point, the second average lateral speed is determined; according to the maximum lateral speed and the second average lateral speed, the second-generation value of the initial lane-changing path is determined. Among them, the calculation formula for the second-generation value is as follows:

[0093] ;

[0094] Among them, represents the lateral vehicle speed of the th planning point on the initial lane-changing path; represents the preset allowable overflow value, which allows the maximum lateral speed to overflow compared to the second average lateral speed; j represents the serial number of the first target planning point among each target planning point; k represents the serial number of the last target planning point among each target planning point.

[0095] Taking the example that there are a total of ten planning points on the initial lane-changing path, and the fifth to tenth planning points are target planning points, the maximum lateral speed is determined from the lateral vehicle speeds of the ten planning points on the initial lane-changing path; based on the lateral vehicle speeds of the fifth to tenth planning points, the second average lateral speed is determined, and at this time j = 5, k = 10; then, according to the maximum lateral speed, the second average lateral speed, and the preset allowable overflow value, the second-generation value of the initial lane-changing path is determined.

[0096] As Figure 2 shown, in the process of optimizing the initial lane-changing path by superimposing the first-generation value and the second-generation value, the initial lane-changing path is optimized to adjust both the first-generation value and the second-generation value towards zero, thereby obtaining the optimized target lane-changing path. It can be found that the target lane-changing path changes more slowly and evenly in terms of lateral speed compared to the initial lane-changing path, avoiding the safety problems caused by sudden changes in lateral speed.

[0097] When the delayed lane change judgment result indicates a delayed lane change, for the determination of the delayed lane change time, first, the maximum planned time is determined from the planned times corresponding to the respective target planned points on the initial lane change path, and then the delayed lane change time is determined based on the maximum planned time.

[0098] It should be noted that during the path planning process, a total planned time is generally set, such as 8 seconds, that is, a path of 8 seconds will be planned. When the delayed lane change judgment result indicates a delayed lane change, in order to enable the re-planning of the lane change path without considering the first-generation value and the second-generation value, combined with the condition that the second collision risk degree coefficient of the target planned point on the initial lane change path is less than the second preset coefficient, that is, the condition that the probability of collision between the host vehicle and the obstacle is relatively high when the host vehicle is at the target planned point, the present application adjusts the lane change timing to the end moment of the target planned point and then re-plans the lane change path, so as to obtain the target lane change path without considering the first-generation value and the second-generation value.

[0099] Specifically, when the delayed lane change judgment result indicates a delayed lane change, the maximum planned time is determined from the planned times corresponding to the respective target planned points on the initial lane change path. The maximum planned time is the planned time corresponding to the target planned point with the serial number k, and the delayed lane change time is determined based on the maximum planned time, so as to re-plan the lane change path after the delayed lane change time has passed to obtain the target lane change path, and perform the corresponding lane change operation according to the target lane change path.

[0100] Taking the example that there are a total of eight planned points on the initial lane change path of 8 seconds, and the fifth to eighth planned points are target planned points, the planned times corresponding to the respective target planned points on the initial lane change path are obtained. Assuming that the planned time corresponding to the fifth planned point is the 5th second, the planned time corresponding to the sixth planned point is the 6th second, the planned time corresponding to the seventh planned point is the 7th second, and the planned time corresponding to the eighth planned point is the 8th second. At this time, the maximum planned time is the 8th second. Correspondingly, the delayed lane change time is 8 seconds, that is, the lane change path is re-planned after 8 seconds to obtain the target lane change path.

[0101] It should be noted that when the present application performs a delayed lane change, due to the delay, a target lane change path with higher safety is planned by adjusting the lane change timing instead of suppressing the lateral speed of the lane change. That is, when the host vehicle changes lanes based on the target lane change path, the probability of collision with the obstacle is relatively low. When the present application performs an immediate lane change, due to the non-delay property, a target lane change path with higher safety is planned by suppressing the lateral speed of the lane change instead of adjusting the lane change timing. In this way, since the computing power resources required for path planning and optimization are relatively large, by using the two methods proposed by the present application to differentially plan the lane change path, the consumption of computing power resources can be reduced to a certain extent while better ensuring driving safety.

[0102] It can be seen that when there are obstacles in the lane to be changed and the adjacent lane, this application determines whether to delay the lane change according to the type of the lane change instruction, the expected collision time related to the obstacle, and the first collision risk degree coefficient, so as to plan a safer target lane change path by adjusting the timing of the lane change, thereby reducing the risk of collision with the obstacle when the host vehicle changes lanes along the target lane change path and improving the driving safety of the vehicle.

[0103] As Figure 3 shown, taking the obstacle as another vehicle, and the host vehicle and the other vehicle are driving on the straight lane line, and the lane change instruction is an instruction to change lanes to the right lane as an example, the specific calculation process of the lateral distance from any planned point on the initial lane change path to the obstacle is illustrated as follows:

[0104] Taking the center point O of the rear axle of the host vehicle at any planned point as the origin to establish a rectangular coordinate system. At this time, the longitudinal axis direction of the rectangular coordinate system is parallel to the front direction of the host vehicle, and the transverse axis direction of the rectangular coordinate system is perpendicular to the front direction of the host vehicle. In this coordinate system, the coordinates of the right front corner point A of the host vehicle (0.5We, Lc) can be obtained, where We represents the width of the host vehicle, and Lc represents the longitudinal distance from the center point of the rear axle of the host vehicle at any planned point to any planned point. And through the vision sensor / radar sensor, the center point coordinates of the other vehicle, that is, the coordinates of point B, can be obtained, and the included angle between the front direction of the host vehicle and the front direction of the other vehicle can be obtained , and the vehicle width of the other vehicle can also be obtained and the vehicle length . Correspondingly, the angles between the center point B of the other vehicle and the four corner points of the other vehicle are all , and at the same time, the distances from the center point B of the other vehicle to the four corner points of the other vehicle can also be calculated as . Based on this, taking the center point B of the other vehicle as the center of the circle and the distance from the center point B of the other vehicle to the four corner points of the other vehicle as the radius, a circle equation is constructed.

[0105] Furthermore, for the first straight line passing through the left front corner point of the other vehicle and point B, it is determined that the included angle between the first straight line and the transverse axis direction of the rectangular coordinate system is , and according to this included angle, the slope of the first straight line can be obtained as . Combining the coordinates of point B, the equation of the first straight line can be obtained. According to the equation of the first straight line and the circle equation, the coordinates of the left front corner point of the other vehicle can be obtained.

[0106] Similarly, for the second straight line passing through the left rear corner point of the other vehicle and point B, it is determined that the included angle between the second straight line and the transverse axis direction of the rectangular coordinate system is , and according to this included angle, the slope of the second straight line can be obtained as , the equation of the second straight line can be obtained by combining the coordinates of point B. Based on the equation of the second straight line and the equation of the circle, the coordinates of the left rear corner point of the other vehicle can be obtained.

[0107] After obtaining the coordinates of the left front corner point and the left rear corner point of the other vehicle, construct the equation of the third straight line passing through the left front corner point and the left rear corner point of the other vehicle, and then determine the slope of the fourth straight line perpendicular to the third straight line according to the slope of the third straight line. Combine the coordinates of the right front corner point A of the own vehicle to obtain the equation of the fourth straight line passing through the right front corner point A of the own vehicle and perpendicular to the third straight line. Determine the coordinates of the intersection point of the third straight line and the fourth straight line according to the equations of the third straight line and the fourth straight line, and determine the distance dl from the right front corner point A of the own vehicle to the intersection point according to the coordinates of the right front corner point A of the own vehicle and the coordinates of the intersection point. At this time, approximately determine the distance dl from the right front corner point A of the own vehicle to the intersection point as the lateral distance from any planned point to the other vehicle.

[0108] See Figure 4 As shown, an embodiment of the present invention discloses a path planning device, including:

[0109] A path planning module 11, configured to plan an initial lane change path for the to-be-changed lane when there are obstacles in the to-be-changed lane determined based on a lane change instruction and an adjacent lane;

[0110] A time determination module 12, configured to determine an expected collision time between the current own vehicle and the obstacle;

[0111] A coefficient prediction module 13, configured to predict a first collision risk degree coefficient when changing lanes based on the initial lane change path; the first collision risk degree coefficient characterizes the risk degree coefficient of a collision with the obstacle;

[0112] A lane change execution module 14, configured to determine whether to delay the lane change based on the instruction type of the lane change instruction, the expected collision time, and the first collision risk degree coefficient, and determine a target lane change path based on the delay lane change determination result, so as to perform a corresponding lane change operation according to the target lane change path.

[0113] It can be seen that when there are obstacles in the to-be-changed lane and the adjacent lane, this application determines whether to delay the lane change according to the instruction type of the lane change instruction, the expected collision time related to the obstacle, and the first collision risk degree coefficient, so as to plan a safer target lane change path by adjusting the timing of the lane change, thereby reducing the risk of collision with the obstacle when the own vehicle changes lanes along the target lane change path and improving the driving safety of the vehicle.

[0114] In some specific embodiments, the lane change execution module 14 includes:

[0115] An immediate lane change determination unit, configured to determine an immediate lane change if the instruction type of the lane change instruction is a lever-operated lane change instruction, or, if the instruction type of the lane change instruction is an automatic lane change instruction and the expected time to collision and the first collision risk coefficient do not meet a preset collision condition;

[0116] A delayed lane change determination unit, configured to determine a delayed lane change if the instruction type of the lane change instruction is an automatic lane change instruction and the expected time to collision and the first collision risk coefficient meet a preset collision condition;

[0117] Wherein, the preset collision condition includes that the expected time to collision is less than a preset time and the first collision risk coefficient is less than a first preset coefficient.

[0118] In some specific embodiments, the lane change execution module 14 includes:

[0119] A replanning sub-module, configured to determine a corresponding delayed lane change time if the delayed lane change determination result indicates a delayed lane change, and replan a lane change path after the delayed lane change time has elapsed to obtain a target lane change path.

[0120] In some specific embodiments, the lane change execution module 14 includes:

[0121] A path optimization sub-module, configured to determine whether to optimize the initial lane change path to obtain a target lane change path by determining whether the expected time to collision and the first collision risk coefficient meet a preset collision condition if the delayed lane change determination result indicates an immediate lane change and the instruction type of the lane change instruction is a lever-operated lane change instruction;

[0122] A path determination sub-module, configured to determine the initial lane change path as the target lane change path if the delayed lane change determination result indicates an immediate lane change and the instruction type of the lane change instruction is an automatic lane change instruction.

[0123] In some specific embodiments, the path optimization sub-module includes:

[0124] A lane change path optimization unit, configured to optimize the initial lane change path based on the second collision risk coefficient and the vehicle lateral speed of each planning point on the initial lane change path to obtain a target lane change path if the expected time to collision and the first collision risk coefficient meet a preset collision condition; the second collision risk coefficient represents the risk coefficient of a collision between the host vehicle and the obstacle when the host vehicle is at the planning point;

[0125] The first path determination unit is configured to determine the initial lane-changing path as the target lane-changing path if the expected collision time and the first collision risk degree coefficient do not meet the preset collision conditions.

[0126] In some specific embodiments, the path planning device further includes:

[0127] The lateral parameter determination unit is configured to obtain the lateral distance from any planning point on the initial lane-changing path to the obstacle in a target coordinate system with the any planning point as the origin, and determine the lateral vehicle speed of the any planning point based on the positions of the any planning point and the previous planning point;

[0128] The second coefficient determination unit is configured to determine the second collision risk degree coefficient of the any planning point based on the lateral distance from the any planning point to the obstacle and the lateral vehicle speed of the any planning point;

[0129] Wherein, the longitudinal axis direction of the target coordinate system is parallel to the tangent direction of the any planning point on the lane center line; the transverse axis direction of the target coordinate system is perpendicular to the tangent direction.

[0130] In some specific embodiments, the coefficient prediction module 13 includes:

[0131] The first average speed determination unit is configured to determine the first average lateral speed based on the lateral vehicle speeds of the planning points within a preset time period on the initial lane-changing path; the preset time period is a time period adjacent to the current moment;

[0132] The first coefficient determination unit is configured to determine the first collision risk degree coefficient according to the lateral distance from the first planning point on the initial lane-changing path to the obstacle and the first average lateral speed.

[0133] In some specific embodiments, the lane-changing path optimization unit includes:

[0134] The target planning point determination unit is configured to determine a target planning point from the initial lane-changing path whose second collision risk degree coefficient is less than a second preset coefficient;

[0135] The first-generation value determination unit is configured to determine the first-generation value of the target planning point based on the second collision risk degree coefficient of the target planning point;

[0136] The second-generation value determination unit is configured to determine the second-generation value of the initial lane-changing path based on the lateral vehicle speeds of each planning point on the initial lane-changing path;

[0137] The second path determination unit is configured to optimize the initial lane-changing path by using the first-generation value and the second-generation value to obtain a target lane-changing path.

[0138] In some specific embodiments, the first-generation value determination unit includes:

[0139] The first determination unit is configured to determine the first-generation value of the target planning point based on the difference between the second collision risk degree coefficient of the target planning point and the second preset coefficient.

[0140] In some specific embodiments, the second-generation value determination unit includes:

[0141] The maximum speed determination unit is configured to determine the maximum lateral speed from the vehicle lateral speeds of each planning point on the initial lane-changing path;

[0142] The second average speed determination unit is configured to determine the second average lateral speed based on the vehicle lateral speed of the target planning point;

[0143] The second determination unit is configured to determine the second-generation value of the initial lane-changing path according to the maximum lateral speed and the second average lateral speed.

[0144] In some specific embodiments, the replanning sub-module includes:

[0145] The maximum time determination unit is configured to determine the maximum planning time from the planning times corresponding to the respective target planning points on the initial lane-changing path;

[0146] The delay time determination unit is configured to determine the delayed lane-changing time based on the maximum planning time.

[0147] In some specific embodiments, the time determination module 12 includes:

[0148] The longitudinal distance determination unit is configured to determine the longitudinal distance from the front target to the rear target; the front target and the rear target are respectively the one with a forward position and the one with a rearward position among the current vehicle and the obstacle;

[0149] The speed difference determination unit is configured to determine the speed difference between the rear target and the front target;

[0150] The collision time determination unit is configured to determine the expected collision time based on the ratio of the longitudinal distance to the speed difference and the positive or negative situation of the ratio.

[0151] Furthermore, an embodiment of the present application also discloses an electronic device, Figure 5It is a structural diagram of an electronic device 20 shown according to an exemplary embodiment. The content in the figure should not be regarded as any limitation on the scope of use of this application.

[0152] Figure 5 This is a schematic structural diagram of an electronic device 20 provided by an embodiment of this application. The electronic device 20 may specifically 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. Among them, the memory 22 is used to store a computer program, and the computer program is loaded and executed by the processor 21 to implement the relevant steps in the path planning method disclosed in any of the foregoing embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0153] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows is any communication protocol applicable to the technical solution of this application, and no specific limitation is imposed on it here; the input / output interface 25 is used to obtain external input data or output data to the outside, and its specific interface type can be selected according to specific application needs, and no specific limitation is made here.

[0154] In addition, as a carrier for resource storage, the memory 22 may be a read-only memory, a random access memory, a magnetic disk, or an optical disc, etc. The resources stored thereon may include an operating system 221, a computer program 222, etc., and the storage method may be temporary storage or permanent storage.

[0155] Among them, the operating system 221 is used to manage and control each hardware device on the electronic device 20 and the computer program 222, and it may be Windows Server, Netware, Unix, Linux, etc. In addition to the computer program that can be used to complete the path planning method executed by the electronic device 20 disclosed in any of the foregoing embodiments, the computer program 222 may further include computer programs that can be used to complete other specific tasks.

[0156] Furthermore, this application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the path planning method disclosed above. For the specific steps of this method, reference may be made to the corresponding content disclosed in the foregoing embodiments, and details are not repeated here.

[0157] In this specification, the various embodiments are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. For the same or similar parts among the embodiments, reference can be made to each other. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple. For the relevant parts, reference can be made to the description in the method section.

[0158] Those skilled in the art can further realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the composition and steps of the examples have been generally described according to functions in the above description. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0159] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be directly implemented by hardware, software modules executed by a processor, or a combination of both. The software modules can be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium well-known in the technical field.

[0160] Finally, it should also be noted that in this article, relational 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 actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including the said element.

[0161] The technical solutions provided in this application have been introduced in detail above. Specific examples have been used herein to elaborate on the principles and implementation manners of this application. The description of the above embodiments is only used to help understand the method and its core idea of this application. At the same time, for those of ordinary skill in the art, according to the idea of this application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to this application.

Claims

1. A path planning method, characterized in that, Including: When there are obstacles in the to-be-changed lane determined based on the lane change instruction and the adjacent lane, planning an initial lane change path for the to-be-changed lane; Determining the expected time to collision between the current vehicle and the obstacle; Predicting a first collision risk coefficient when changing lanes based on the initial lane change path; the first collision risk coefficient characterizes the risk coefficient of a collision with the obstacle; Judging whether to delay the lane change based on the instruction type of the lane change instruction, the expected time to collision, and the first collision risk coefficient, and determining a target lane change path based on the result of the delay lane change judgment, so as to perform a corresponding lane change operation according to the target lane change path.

2. The path planning method according to claim 1, characterized in that The judging whether to delay the lane change based on the instruction type of the lane change instruction, the expected time to collision, and the first collision risk coefficient includes: If the instruction type of the lane change instruction is a lever-operated lane change instruction, or, the instruction type of the lane change instruction is an automatic lane change instruction and the expected time to collision and the first collision risk coefficient do not meet the preset collision conditions, it is determined to change lanes immediately; If the instruction type of the lane change instruction is an automatic lane change instruction and the expected time to collision and the first collision risk coefficient meet the preset collision conditions, it is determined to delay the lane change; Wherein, the preset collision conditions include that the expected time to collision is less than a preset time and the first collision risk coefficient is less than a first preset coefficient.

3. The path planning method according to claim 2, wherein The determining the target lane change path based on the result of the delay lane change judgment includes: If the result of the delay lane change judgment indicates a delayed lane change, determining a corresponding delay lane change time, and re-planning the lane change path after the delay lane change time has passed to obtain the target lane change path; If the result of the delay lane change judgment indicates an immediate lane change and the instruction type of the lane change instruction is a lever-operated lane change instruction, then by judging whether the expected time to collision and the first collision risk coefficient meet the preset collision conditions, to determine whether to optimize the initial lane change path to obtain the target lane change path; If the result of the delay lane change judgment indicates an immediate lane change and the instruction type of the lane change instruction is an automatic lane change instruction, then the initial lane change path is determined as the target lane change path.

4. The path planning method according to claim 3, wherein The determining whether to optimize the initial lane change path to obtain the target lane change path by judging whether the expected time to collision and the first collision risk coefficient meet the preset collision conditions includes: If the expected time to collision and the first collision risk coefficient meet the preset collision conditions, then based on the second collision risk coefficient and the vehicle lateral speed of each planned point on the initial lane change path, optimizing the initial lane change path to obtain the target lane change path; the second collision risk coefficient characterizes the risk coefficient of a collision with the obstacle when the vehicle is at the planned point; If the expected time to collision and the first collision risk coefficient do not meet the preset collision conditions, then the initial lane change path is determined as the target lane change path.

5. The path planning method according to claim 4, wherein Before optimizing the initial lane-changing path based on the second collision risk degree coefficient and the vehicle lateral speed of each planned point on the initial lane-changing path, it further includes: In a target coordinate system with any planned point on the initial lane-changing path as the origin, obtain the lateral distance from the any planned point to the obstacle, and determine the vehicle lateral speed of the any planned point based on the positions of the any planned point and the previous planned point; Determine the second collision risk degree coefficient of the any planned point based on the lateral distance from the any planned point to the obstacle and the vehicle lateral speed of the any planned point; Wherein, the longitudinal axis direction of the target coordinate system is parallel to the tangent direction of the any planned point on the lane center line; the transverse axis direction of the target coordinate system is perpendicular to the tangent direction.

6. The path planning method according to claim 5, wherein The prediction of the first collision risk degree coefficient when changing lanes based on the initial lane-changing path includes: Determine the first average lateral speed based on the vehicle lateral speeds of the planned points within a preset time period on the initial lane-changing path; the preset time period is the time period adjacent to the current moment; Determine the first collision risk degree coefficient according to the lateral distance from the first planned point on the initial lane-changing path to the obstacle and the first average lateral speed.

7. The path planning method according to claim 4, characterized in that Optimizing the initial lane-changing path based on the second collision risk degree coefficient and the vehicle lateral speed of each planned point on the initial lane-changing path to obtain a target lane-changing path includes: Determine the target planned points on the initial lane-changing path whose second collision risk degree coefficients are less than the second preset coefficient; Determine the first-generation value of the target planned point based on the second collision risk degree coefficient of the target planned point; Determine the second-generation value of the initial lane-changing path based on the vehicle lateral speeds of each planned point on the initial lane-changing path; Use the first-generation value and the second-generation value to optimize the initial lane-changing path to obtain a target lane-changing path.

8. The path planning method according to claim 7, wherein The determination of the first-generation value of the target planned point based on the second collision risk degree coefficient of the target planned point includes: Determine the first-generation value of the target planned point based on the difference between the second collision risk degree coefficient of the target planned point and the second preset coefficient.

9. The path planning method according to claim 7, wherein The determination of the second-generation value of the initial lane-changing path based on the vehicle lateral speeds of each planned point on the initial lane-changing path includes: Determine the maximum lateral speed from the vehicle lateral speeds of each planned point on the initial lane-changing path; Determine the second average lateral speed based on the vehicle lateral speed of the target planned point; Determine the second-generation value of the initial lane-changing path according to the maximum lateral speed and the second average lateral speed.

10. The path planning method according to claim 7, characterized in that, The determination of the corresponding delayed lane-changing time includes: Determine the maximum planned time from the planned times corresponding to the respective target planned points on the initial lane-changing path; Determine the delayed lane-changing time based on the maximum planned time.

11. The path planning method according to any one of claims 1 to 10, characterized in that The determination of the expected collision time between the current vehicle and the obstacle includes: Determine the longitudinal distance from the front target to the rear target; the front target and the rear target are respectively the one with a forward position and the one with a rearward position among the current vehicle and the obstacle. Determine the speed difference between the rear target and the front target. Based on the ratio of the longitudinal distance to the speed difference and the positive or negative situation of the ratio, determine the expected time to collision.

Images