Vehicle lane changing request verification method, device, equipment and medium

Abstract

The invention discloses a vehicle lane changing request verification method and device, equipment and a medium, and relates to the technical field of automatic driving, and the method comprises the steps: planning a lane changing track according to the current position of a vehicle and a target lane after a vehicle lane changing request is obtained; the lane changing track comprises an absolute lane changing track under a global coordinate system and a relative lane changing track relative to the current position of the vehicle; determining a detection area generated based on obstacles around the vehicle and the lane changing track, and performing collision detection verification on the vehicle lane changing request by using a verification algorithm set based on the detection area; the detection area comprises a detection area generated based on an absolute lane changing track and a static obstacle, a detection area generated based on a target lane and surrounding obstacles, a detection area generated based on a relative lane changing track and a rear obstacle, and a detection area generated based on a current lane of the vehicle and a front obstacle; and if the collision detection verification of each detection area is passed, allowing to respond to the vehicle lane changing request to execute the lane changing operation.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a vehicle lane change request verification method, device, equipment and medium. Background Art

[0002] In Advanced Driver Assistance Systems (ADAS), when a vehicle changes lanes autonomously or the driver changes lanes by levering the vehicle, it is necessary to perform safety checks on the obstacle information around the vehicle to ensure that the vehicle is safe during the lane change process. The obstacle information mainly refers to the location and speed information of obstacles such as vehicles and pedestrians.

[0003] Currently, the main method for safety verification of obstacles is to measure whether there is a collision risk by calculating the time to collision (TTC) between the ego vehicle and the target lane. However, the algorithm based on calculating the time to collision has the following problems: (1) When the speed of the obstacle is close to that of the ego vehicle, it is not very accurate to use TTC to make judgments; (2) When the obstacle is behind the ego vehicle and its speed is lower than that of the ego vehicle, it is difficult to use TTC to judge the risk; (3) TTC calculations are based on the assumption that the obstacle has a uniform speed, which is inconsistent with actual application situations; (4) TTC calculations do not take into account the interaction between the ego vehicle and the obstacle, while in actual situations, the interaction between the two is inevitable.

[0004] In summary, how to consider the interaction between the lane-changing trajectory of the vehicle and obstacles during the lane-changing process to better meet the actual vehicle lane-changing scenario and improve lane-changing safety is a problem that needs to be solved. Summary of the invention

[0005] In view of this, the purpose of the present invention is to provide a vehicle lane change request verification method, device, equipment and medium, which can take into account the interaction between the lane change trajectory of the vehicle and obstacles during the vehicle lane change process, so as to be more in line with the actual vehicle lane change scenario and improve the lane change safety. The specific scheme is as follows:

[0006] In a first aspect, the present application discloses a vehicle lane change request verification method, comprising:

[0007] After obtaining a lane change request from the vehicle, a lane change trajectory is planned according to the current position of the vehicle and the target lane; wherein the lane change trajectory includes an absolute lane change trajectory in a global coordinate system and a relative lane change trajectory relative to the current position of the vehicle;

[0008] Determine a detection area generated based on the obstacles around the ego vehicle and the lane change trajectory, and perform collision detection verification on the vehicle lane change request using a verification algorithm set based on the detection area; wherein the detection area includes a first detection area generated based on the absolute lane change trajectory and static obstacles, a second detection area generated based on the target lane and surrounding obstacles, a third detection area generated based on the relative lane change trajectory and rear obstacles, and a fourth detection area generated based on the ego vehicle's current lane and a front obstacle;

[0009] If the collision detection check of each of the detection areas passes, responding to the vehicle lane change request is allowed to perform a lane change operation.

[0010] Optionally, performing collision detection verification on the vehicle lane change request using a verification algorithm set based on the first detection area includes:

[0011] Sampling the absolute lane change trajectory according to a first preset sampling interval to obtain a plurality of sampling points, and generating a first vehicle profile at each sampling point according to first preset length and width information, so as to generate a first lane change trajectory profile based on a bounding box corresponding to each of the first vehicle profiles;

[0012] Determine whether a collision occurs based on a positional relationship between the first lane change trajectory profile and a static obstacle, and if no collision occurs, determine that the collision detection check of the first detection area passes.

[0013] Optionally, determining whether a collision occurs according to a positional relationship between the first lane change trajectory profile and a static obstacle includes:

[0014] If there is a collision, determining a target vehicle profile in the first lane change trajectory profile that collides with the static obstacle, and calculating a distance value between a center of a rear axle of the vehicle corresponding to the target vehicle profile and a lane centerline of the target lane;

[0015] Determining whether the distance value is less than a first preset distance threshold;

[0016] If the distance value is less than the first preset distance threshold, the corresponding static obstacle is ignored and it is determined that the collision detection check of the first detection area has passed; otherwise, it is determined that the collision detection check of the first detection area has failed.

[0017] Optionally, performing collision detection verification on the vehicle lane change request using a verification algorithm set based on the second detection area includes:

[0018] Constructing a target position area based on a first preset area in front of and a second preset area in the rear of the target lane relative to the current position of the vehicle;

[0019] It is determined whether surrounding obstacles exist in the target position area. If so, it is determined that the collision detection check of the second detection area fails. Otherwise, it is determined that the collision detection check of the second detection area passes.

[0020] Optionally, performing collision detection verification on the vehicle lane change request using a verification algorithm set based on the third detection area includes:

[0021] Sampling the relative lane-changing trajectory according to a second preset sampling interval to obtain a plurality of sampling points, and generating a second vehicle profile at each sampling point according to second preset length and width information, so as to generate a second lane-changing trajectory profile based on a bounding box corresponding to each of the second vehicle profiles;

[0022] Determining a first target obstacle in the target lane that is located behind an end point of the lane change trajectory;

[0023] constructing a first obstacle profile based on the lane change trajectory end point and the center point of the first target obstacle, and determining a first collision point according to a positional relationship between the first obstacle profile and the second lane change trajectory profile;

[0024] Calculating a longitudinal distance between the first target obstacle and the first collision point, and calculating a remaining distance value between the first target obstacle and the relative lane change trajectory based on the longitudinal distance, the current speed of the own vehicle, the speed of the first target obstacle, the driving reaction time of the first target obstacle, the target relative safety distance, and the target distance traveled by the first target obstacle relative to the own vehicle during the deceleration process;

[0025] It is determined whether the remaining distance value is greater than a second preset distance threshold value. If so, it is determined that the collision detection check of the third detection area has passed; otherwise, it is determined that the collision detection check of the third detection area has failed.

[0026] Optionally, the calculating of the remaining distance value between the first target obstacle and the relative lane change trajectory based on the longitudinal distance, the current speed of the own vehicle, the speed of the first target obstacle, the driving reaction time of the first target obstacle, the target relative safety distance, and the target distance traveled by the first target obstacle relative to the own vehicle during the deceleration process includes:

[0027] Determine the relative distance of the first target obstacle from the vehicle within the driving reaction time of the first target obstacle based on the current speed of the vehicle and the speed of the first target obstacle, and determine a target relative safety distance that matches the current speed of the vehicle;

[0028] Determine a lateral distance between the current position of the vehicle and the center line of the target lane, and determine a deceleration that matches the lateral distance, so as to use the deceleration to determine a first distance and time value that the first target obstacle needs to travel when decelerating to the current speed of the vehicle;

[0029] Calculating a second distance traveled by the vehicle based on the time value and the current speed of the vehicle, and calculating a target distance traveled by the vehicle relative to the first target obstacle during deceleration using the first distance and the second distance;

[0030] The difference between the longitudinal distance and the relative distance, the target relative safety distance and the target distance is determined as a remaining distance value between the first target obstacle and the relative lane change trajectory.

[0031] Optionally, performing collision detection verification on the vehicle lane change request using a verification algorithm set based on the fourth detection area includes:

[0032] Determine the first second target obstacle in front of the vehicle's current lane;

[0033] Taking the center point of the second target obstacle as the origin and constructing a second obstacle profile based on a safety distance corresponding to the vehicle speed of the second target obstacle;

[0034] Determine whether there is a collision based on the positional relationship between the second lane change trajectory profile and the second obstacle profile; if there is no collision, determine that the collision detection check of the fourth detection area has passed; otherwise, determine that the collision detection check of the fourth detection area has failed.

[0035] In a second aspect, the present application discloses a vehicle lane change request verification device, comprising:

[0036] A trajectory planning module is used to plan a lane-changing trajectory according to the current position of the vehicle and the target lane after obtaining a lane-changing request of the vehicle; wherein the lane-changing trajectory includes an absolute lane-changing trajectory in a global coordinate system and a relative lane-changing trajectory relative to the current position of the vehicle;

[0037] a collision detection module, configured to determine a detection area generated based on obstacles around the ego vehicle and the lane change trajectory, and perform collision detection verification on the vehicle lane change request using a verification algorithm set based on the detection area; wherein the detection area includes a first detection area generated based on the absolute lane change trajectory and static obstacles, a second detection area generated based on the target lane and surrounding obstacles, a third detection area generated based on the relative lane change trajectory and rear obstacles, and a fourth detection area generated based on the ego vehicle's current lane and a front obstacle;

[0038] The lane changing module is used to allow responding to the vehicle lane changing request to perform a lane changing operation if the collision detection verification of each detection area passes.

[0039] In a third aspect, the present application discloses an electronic device, comprising:

[0040] Memory, used to store computer programs;

[0041] The processor is used to execute the computer program to implement the steps of the vehicle lane change request verification method disclosed above.

[0042] 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 vehicle lane change request verification method disclosed above are implemented.

[0043] It can be seen that after obtaining the vehicle lane change request, the present application plans a lane change trajectory according to the current position of the vehicle and the target lane; wherein the lane change trajectory includes an absolute lane change trajectory in a global coordinate system and a relative lane change trajectory relative to the current position of the vehicle; a detection area generated based on the obstacles around the vehicle and the lane change trajectory is determined, and a collision detection verification is performed on the vehicle lane change request using a verification algorithm set based on the detection area; wherein the detection area includes a first detection area generated based on the absolute lane change trajectory and static obstacles, a second detection area generated based on the target lane and surrounding obstacles, a third detection area generated based on the relative lane change trajectory and rear obstacles, and a fourth detection area generated based on the current lane of the vehicle and the front obstacle; if the collision detection verification of each of the detection areas passes, it is allowed to respond to the vehicle lane change request to perform the lane change operation.

[0044] Beneficial effect: After obtaining the vehicle lane change request, the present application first plans a lane change trajectory according to the current position of the vehicle and the target lane. The lane change trajectory includes not only the absolute lane change trajectory in the global coordinate system, but also the relative lane change trajectory relative to the current position of the vehicle. Furthermore, the present application needs to generate a detection area based on the obstacles around the vehicle and the lane change trajectory, so as to perform collision detection verification on the vehicle lane change request using a verification algorithm set based on the detection area, so as to take into account the interaction between the lane change trajectory of the vehicle and the obstacle during the vehicle lane change process, so as to be more in line with the actual vehicle lane change scenario. The above-mentioned detection areas mainly include four types, namely, a first detection area generated based on the absolute lane change trajectory and static obstacles, a second detection area generated based on the target lane and surrounding obstacles, a third detection area generated based on the relative lane change trajectory and rear obstacles, and a fourth detection area generated based on the current lane of the vehicle and the front obstacle. That is, the present application constructs different detection areas with obstacles for collision detection using the absolute lane-changing trajectory and the relative lane-changing trajectory, and also constructs different detection areas with obstacles for collision detection using the vehicle's current lane and the target lane. Finally, only when the collision detection checks in each detection area are passed, is it allowed to respond to the vehicle's lane-changing request to execute the lane-changing operation. In this way, the lane-changing safety is also improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0046] Figure 1 A flow chart of a vehicle lane change request verification method disclosed in this application;

[0047] Figure 2 A schematic diagram of a safety verification process of a first detection area disclosed in the present application;

[0048] Figure 3 A schematic diagram of a safety verification process of a second detection area disclosed in the present application;

[0049] Figure 4 A schematic diagram of a safety verification process of a third detection area disclosed in the present application;

[0050] Figure 5 A schematic diagram of the relationship between a lateral distance and a deceleration disclosed in the present application;

[0051] Figure 6A distance relationship diagram between a vehicle and a rear obstacle disclosed in the present application;

[0052] Figure 7 A schematic diagram of a safety verification process of a fourth detection area disclosed in the present application;

[0053] Figure 8 A schematic diagram of a vehicle lane change in a specific scenario disclosed in this application;

[0054] Fig. 9 This is a structural schematic diagram of a vehicle lane change request verification device disclosed in this application;

[0055] Fig.10 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0057] At present, the method of safety verification of obstacles is mainly to measure whether there is a collision risk by calculating the collision time of the obstacle between the ego vehicle and the target lane. However, the algorithm based on calculating the collision time has the following problems: (1) When the speed of the obstacle is close to that of the ego vehicle, the judgment using TTC is not very accurate; (2) When the obstacle is behind the ego vehicle and the speed is lower than the speed of the ego vehicle, it is difficult to use TTC to judge the risk; (3) TTC calculations are all based on the assumption that the obstacle has a uniform speed, but this is inconsistent with the actual application situation; (4) TTC calculations do not consider the interaction between the ego vehicle and the obstacle, and in actual situations, the interaction between the two is inevitable. To this end, the embodiments of the present application disclose a vehicle lane change request verification method, device, equipment and medium, which can take into account the interaction between the lane change trajectory of the ego vehicle and the obstacle during the vehicle lane change process, so as to be more in line with the actual vehicle lane change scenario and improve the lane change safety.

[0058] See also Figure 1 As shown, the embodiment of the present application discloses a vehicle lane change request verification method, the method comprising:

[0059] Step S11: after obtaining a lane change request from the vehicle, a lane change trajectory is planned according to the current position of the vehicle and the target lane; wherein the lane change trajectory includes an absolute lane change trajectory in a global coordinate system and a relative lane change trajectory relative to the current position of the vehicle.

[0060] In this embodiment, after obtaining the vehicle lane change request, the lane change trajectory is first planned according to the current position of the vehicle and the target lane. It should be pointed out that the lane change trajectory includes not only the absolute lane change trajectory in the global coordinate system, but also the relative lane change trajectory relative to the current position of the vehicle.

[0061] In a specific implementation, the above-mentioned planning of the lane changing trajectory based on the current position of the vehicle and the target lane includes: planning an absolute lane changing trajectory based on the current position of the vehicle and the target lane in a global coordinate system; determining the relative position change amount of each trajectory point in the absolute lane changing trajectory relative to the current speed of the vehicle to generate a relative lane changing trajectory.

[0062] It is understandable that when a vehicle needs to change lanes, the vehicle's path planning system plans a smooth absolute lane change trajectory based on the positional relationship between the current vehicle position and the target lane, including when to start turning, the angle change of the turning, etc., to ensure that the vehicle can switch to the target lane safely and accurately. The absolute lane change trajectory refers to the motion trajectory of the vehicle in a global coordinate system (such as a geodetic coordinate system with the road as a reference). It describes the actual motion path of the vehicle in the actual road environment and does not depend on the position and motion state of other vehicles or objects. The calculation of the absolute lane change trajectory requires a comprehensive consideration of the vehicle's own motion state and road environment information. The vehicle's motion state includes parameters such as initial position, speed, acceleration, steering angle, etc., which can be obtained in real time through on-board sensors. At the same time, road environment information such as road curvature, slope, lane line position, etc. also affects the absolute lane change trajectory. For example, when changing lanes at a curve, the absolute lane change trajectory of the vehicle will bend accordingly according to the curvature of the curve to adapt to the shape of the road; if the road has a slope, the change in the speed of the vehicle during the lane change process will also affect its trajectory in the vertical direction. Based on the vehicle kinematic model, this information can be combined to calculate the position coordinates of the vehicle after each time step, thereby obtaining a continuous absolute lane change trajectory.

[0063] Furthermore, the present embodiment needs to determine the relative lane-changing trajectory relative to the current position of the vehicle. The relative lane-changing trajectory is a motion trajectory relative to a specific target, and its reference system depends on the selected reference object. The reference object selected in the present embodiment is the current speed of the vehicle. The starting point of the relative trajectory is usually the initial relative position of the vehicle relative to the reference object when the vehicle starts to calculate the relative trajectory, and the end point is the final relative position of the vehicle relative to the reference object at the end of the lane-changing process. The present embodiment generates the relative lane-changing trajectory of the vehicle relative to the reference object by determining the relative position change amount of each track point in the absolute lane-changing trajectory relative to the current speed of the vehicle. Specifically, it can be understood as determining the position deviation that needs to be adjusted relative to the uniform speed mode at the current vehicle speed. For example, when the vehicle changes lanes at a uniform speed, the displacement deviation generated is 0, and when the lane-changing is accelerated, the displacement deviation generated is positive, that is, in front of the vehicle. When the lane-changing is decelerated, the displacement deviation generated is negative, that is, behind the vehicle.

[0064] Step S12: Determine a detection area generated based on the obstacles around the ego vehicle and the lane change trajectory, and perform collision detection verification on the vehicle lane change request using a verification algorithm set based on the detection area; wherein the detection area includes a first detection area generated based on the absolute lane change trajectory and static obstacles, a second detection area generated based on the target lane and surrounding obstacles, a third detection area generated based on the relative lane change trajectory and rear obstacles, and a fourth detection area generated based on the ego vehicle's current lane and a front obstacle.

[0065] In this embodiment, it is necessary to generate a detection area based on the obstacles and lane change trajectory around the ego vehicle, so as to perform collision detection verification on the vehicle lane change request using a verification algorithm set based on the detection area, so as to take into account the interaction between the ego vehicle's lane change trajectory and obstacles during the vehicle lane change process, so as to be more in line with the actual vehicle lane change scenario. The above-mentioned detection areas mainly include four types, namely, a first detection area generated based on the absolute lane change trajectory and static obstacles, a second detection area generated based on the target lane and surrounding obstacles, a third detection area generated based on the relative lane change trajectory and rear obstacles, and a fourth detection area generated based on the current lane of the ego vehicle and the front obstacle. That is, this application needs to construct different detection areas with the absolute lane change trajectory and the relative lane change trajectory and obstacles for collision detection, and also construct different detection areas with the obstacles for collision detection for the ego vehicle's current lane and the target lane.

[0066] Step S13: If the collision detection check of each detection area passes, responding to the vehicle lane change request is allowed to perform the lane change operation.

[0067] In this embodiment, only when the collision detection check of each detection area is passed, the vehicle lane change request is responded to to perform the lane change operation. By setting the collision detection of multiple detection areas, the lane change safety is also improved.

[0068] It can be seen that after obtaining the vehicle lane change request, the present application first plans a lane change trajectory based on the current position of the vehicle and the target lane. The lane change trajectory includes not only the absolute lane change trajectory in the global coordinate system, but also the relative lane change trajectory relative to the current position of the vehicle. Furthermore, the present application needs to generate a detection area based on the obstacles around the vehicle and the lane change trajectory, so as to perform collision detection verification on the vehicle lane change request using a verification algorithm set based on the detection area, so as to take into account the interaction between the lane change trajectory of the vehicle and the obstacle during the vehicle lane change process, so as to be more in line with the actual vehicle lane change scenario. The above-mentioned detection areas mainly include four types, namely, a first detection area generated based on the absolute lane change trajectory and static obstacles, a second detection area generated based on the target lane and surrounding obstacles, a third detection area generated based on the relative lane change trajectory and rear obstacles, and a fourth detection area generated based on the current lane of the vehicle and the front obstacle. That is, the present application constructs different detection areas with obstacles for collision detection using the absolute lane-changing trajectory and the relative lane-changing trajectory, and also constructs different detection areas with obstacles for collision detection using the vehicle's current lane and the target lane. Finally, only when the collision detection checks in each detection area are passed, is it allowed to respond to the vehicle's lane-changing request to execute the lane-changing operation. In this way, the lane-changing safety is also improved.

[0069] It can be seen from the foregoing that the present application needs to detect four detection areas. The following is a detailed description of the process of performing collision detection verification on the vehicle lane change request using verification algorithms based on different detection area settings.

[0070] like Figure 2 As shown, in a specific embodiment, a collision detection check is performed on the vehicle lane change request using a verification algorithm set based on the first detection area, including: sampling the absolute lane change trajectory according to a first preset sampling interval to obtain a number of sampling points, and generating a first vehicle profile at each sampling point according to first preset length and width information, so as to generate a first lane change trajectory profile based on a bounding box corresponding to each of the first vehicle profiles; determining whether there is a collision based on a positional relationship between the first lane change trajectory profile and a static obstacle, and if there is no collision, determining that the collision detection check of the first detection area has passed.

[0071] In this embodiment, the first detection area is generated based on the absolute lane-changing trajectory and the static obstacle. In this case, the lane-changing trajectory profile of the vehicle is generated mainly based on the absolute lane-changing trajectory of the vehicle, and whether the obstacle collides with the lane-changing trajectory profile is detected.

[0072] Specifically, the absolute lane changing trajectory is first sampled according to a first preset sampling interval to obtain a number of sampling points. For example, in the longitudinal direction of the absolute lane changing trajectory, sampling can be performed at intervals of 3 meters to obtain a number of sampling points, and the heading angle and horizontal and vertical coordinate points of each sampling point are calculated.

[0073] Then, at each sampling point, a first vehicle profile is generated according to the first preset length and width information. Specifically, according to the heading angle and coordinate point of the sampling point, the sampling point is taken as the center point of the rear axle of the vehicle, the heading angle is taken as the vehicle orientation, and the first vehicle profile with a calculated width of 2 meters, a distance from the center point of the rear axle of the vehicle to the front of the vehicle of 4 meters, and a distance from the center point of the rear axle of the vehicle to the rear of the vehicle of 1 meter.

[0074] Further, the boundBox of the first vehicle contour is calculated, such as Figure 2 As shown in the yellow rectangular box in , this is mainly to simplify the collision algorithm, and then the first lane change trajectory profile is generated based on the bounding box corresponding to each first vehicle profile.

[0075] Finally, this embodiment determines whether there is a collision based on the positional relationship between the first lane change trajectory profile and the static obstacle, that is, whether the obstacle position intersects with the first lane change trajectory profile. If there is no collision, it is determined that the collision detection check of the first detection area has passed.

[0076] Among them, it should be pointed out that the above-mentioned determining whether there is a collision based on the positional relationship between the first lane change trajectory profile and the static obstacle includes: if there is a collision, determining the target vehicle profile that collides with the static obstacle in the first lane change trajectory profile, and calculating the distance value between the corresponding vehicle rear axle center in the target vehicle profile and the lane centerline of the target lane; judging whether the distance value is less than a first preset distance threshold; if the distance value is less than the first preset distance threshold, ignoring the corresponding static obstacle, and judging that the collision detection check of the first detection area passes, otherwise judging that the collision detection check of the first detection area fails.

[0077] That is, if there is a collision between the obstacle and the first lane change trajectory profile, it is necessary to specifically determine the target vehicle profile that collides with the static obstacle in the first lane change trajectory profile, and calculate the distance value between the corresponding vehicle rear axle center in the target vehicle profile and the lane centerline of the target lane. If the distance value is less than the first preset distance threshold, it means that the collision occurred near the end of the lane change, and it is considered that the static obstacle collision has little effect on the lane change behavior, so the collision point can be ignored, that is, in this case, it is still considered that the collision detection check of the first detection area has passed. If the distance value is not less than the first preset distance threshold, it is determined that the collision detection check of the first detection area has failed. The first preset distance threshold can be calibrated according to actual conditions, for example, it can be set to 0.5 meters.

[0078] The safety verification process of the first detection area not only outputs the collision result, but also outputs the collision point position, so as to evaluate whether it affects the safety of the lane change.

[0079] like Figure 3 As shown, in a specific embodiment, a collision detection check is performed on the vehicle lane change request using a verification algorithm based on the second detection area setting, including: constructing a target position area based on a first preset area in front and a second preset area in the rear of the target lane relative to the current position of the vehicle; determining whether surrounding obstacles exist in the target position area, and if so, determining that the collision detection check of the second detection area fails, otherwise determining that the collision detection check of the second detection area passes.

[0080] In this embodiment, the second detection area is generated based on the target lane and surrounding obstacles. In this case, it is necessary to construct the target position area based on the first preset area in front of the target lane and the second preset area behind the current position of the vehicle. In this embodiment, the center position of the rear axle of the vehicle is used to represent the current position of the vehicle. Figure 3 As shown in FIG. 1 , according to the lane-changing direction of the vehicle, the 10-meter area in front of the target lane and the 5-meter area in the rear of the target lane relative to the center of the rear axle of the vehicle can be used as the target position area. Among them, the specific area range of the first preset area in front and the second preset area in the rear can be calibrated, not limited to Figure 3 Then, the present application determines whether surrounding obstacles exist in the target location area. If so, it determines that the collision detection check of the second detection area fails, that is, there is a collision risk. Otherwise, it determines that the collision detection check of the second detection area passes.

[0081] The safety verification process of the second detection area can solve the problem of inaccurate TTC calculation caused by a relatively low vehicle speed by performing a safety verification on obstacles around the vehicle.

[0082] like Figure 4As shown, in a specific embodiment, the collision detection verification of the vehicle lane change request is performed using a verification algorithm set based on the third detection area, including: sampling the relative lane change trajectory according to a second preset sampling interval to obtain a number of sampling points, and generating a second vehicle profile at each sampling point according to second preset length and width information, so as to generate a second lane change trajectory profile based on a bounding box corresponding to each second vehicle profile; determining the first first target obstacle in the target lane that is located behind the end point of the lane change trajectory; constructing a first obstacle profile based on the end point of the lane change trajectory and the center point of the first target obstacle, and generating a second lane change trajectory profile based on the first obstacle profile and the second lane change trajectory; The method comprises the steps of: determining a first collision point based on a positional relationship between the first target obstacle and the relative lane change trajectory contours; calculating a longitudinal distance between the first target obstacle and the first collision point, and calculating a remaining distance value between the first target obstacle and the relative lane change trajectory based on the longitudinal distance, the current speed of the own vehicle, the speed of the first target obstacle, the driving reaction time of the first target obstacle, the target relative safety distance, and the target distance of the first target obstacle relative to the own vehicle during the deceleration process; judging whether the remaining distance value is greater than a second preset distance threshold, and if so, judging that the collision detection check of the third detection area has passed, otherwise judging that the collision detection check of the third detection area has failed.

[0083] In this embodiment, the third detection area is generated based on the relative lane change trajectory and the rear obstacle. First, the relative lane change trajectory is sampled according to the second preset sampling interval to obtain a number of sampling points, for example, on the relative trajectory, sampling is performed at a sampling interval of 3 meters to obtain a number of sampling points, and the coordinates of the sampling points are calculated.

[0084] Then, at each sampling point, a second vehicle profile is generated according to the second preset length and width information. Specifically, the heading angle is 0, the sampling point is the center point of the rear axle of the vehicle, the width is calculated to be 2 meters, the distance from the center point of the rear axle of the vehicle to the front of the vehicle is 4 meters, and the distance from the center point of the rear axle of the vehicle to the rear of the vehicle is 1 meter. The second lane change trajectory profile is generated based on the bounding box corresponding to each second vehicle profile, such as Figure 4 shown.

[0085] Next, it is necessary to determine the first target obstacle in the target lane behind the end point of the lane change trajectory, and then construct a first obstacle profile based on the end point of the lane change trajectory and the center point of the first target obstacle, as shown in the following figure: Figure 4 As shown, the end point of the lane-changing trajectory is offset 1 meter in the opposite direction of the lane-changing direction as a vertex, and the center point of the obstacle is offset 1 meter in the lane-changing direction of the vehicle as another vertex, so as to output the first obstacle contour. Then, the first collision point is determined according to the positional relationship between the first obstacle contour and the second lane-changing trajectory contour, that is, the first collision point where the vehicle intersects with the first obstacle contour during the lane-changing process is determined according to the second lane-changing trajectory contour.

[0086] After obtaining the first collision point, the longitudinal distance between the first target obstacle and the first collision point is calculated, and the remaining distance value between the first target obstacle and the relative lane change trajectory is calculated based on the longitudinal distance, the current speed of the own vehicle, the speed of the first target obstacle, the driving reaction time of the first target obstacle, the target relative safety distance, and the target distance traveled by the own vehicle during the deceleration of the first target obstacle.

[0087] Finally, it is determined whether the remaining distance value is greater than the second preset distance threshold. If so, it is determined that the collision detection check of the third detection area has passed, otherwise it is determined that the collision detection check of the third detection area has failed.

[0088] In a specific embodiment, the above-mentioned calculation of the remaining distance value between the first target obstacle and the relative lane change trajectory based on the longitudinal distance, the current speed of the own vehicle, the speed of the first target obstacle, the driving reaction time of the first target obstacle, the target relative safety distance, and the target distance of the first target obstacle relative to the own vehicle during the deceleration process includes: determining the relative distance of the first target obstacle relative to the own vehicle within the driving reaction time of the first target obstacle based on the current speed of the own vehicle and the speed of the first target obstacle, and determining the target relative safety distance matching the current speed of the own vehicle; determining the relative distance between the current position of the own vehicle and the speed of the first target obstacle; The method comprises the steps of: calculating a lateral distance between the center lines of the target lanes and the lane center lines of the target lanes, and determining a deceleration matching the lateral distance, so as to use the deceleration to determine a first distance and time value that the first target obstacle needs to travel when decelerating to the current speed of the own vehicle; calculating a second distance traveled by the own vehicle based on the time value and the current speed of the own vehicle, and using the first distance and the second distance to calculate a target distance traveled by the first target obstacle relative to the own vehicle during the deceleration process; and determining the difference between the longitudinal distance and the relative distance, the target relative safety distance and the target distance as the remaining distance value between the first target obstacle and the relative lane change trajectory.

[0089] That is, in this embodiment, it is first necessary to determine the relative distance d_r traveled by the first target obstacle relative to the ego vehicle within the driving reaction time t_r of the first target obstacle based on the current vehicle speed v_ego and the speed v_obs of the first target obstacle, and determine the target relative safety distance that matches the current vehicle speed of the ego vehicle.

[0090] Among them, the calculation formula of relative distance d_r is as follows:

[0091] d_r = (v_obs - v_ego) × t_r;

[0092] The calculation formula of the target relative safety distance is d_s=safeDis×k; where safeDis is the default safety distance, and k is the speed gain coefficient, which increases with the increase of speed. The specific value of k can be obtained by table lookup, that is, the corresponding relationship between different speeds and different k values ​​is established in advance, and then the corresponding k value is found from the table according to the current speed of the vehicle to calculate the target relative safety distance.

[0093] Furthermore, this embodiment determines the lateral distance between the current position of the vehicle and the center line of the target lane, and determines the deceleration that matches the lateral distance, so as to use the deceleration to determine the first distance and time value that the first target obstacle needs to travel when decelerating to the current speed of the vehicle. It can be understood that in the actual environment, when the rear obstacle finds that a vehicle in front cuts into the lane, if the distance is close, the rear obstacle vehicle will slow down, so it is necessary to calculate the deceleration of the rear obstacle. At present, different decelerations are set according to different vehicle speeds. However, as the distance between the position of the vehicle and the center line of the target lane gradually decreases during the lane change process, the attention to the collision risk of the rear obstacle is gradually reduced. Therefore, at the same speed, different decelerations should be used to evaluate according to the different lateral distances between the current position of the vehicle and the center line of the target lane, so as to take into account the interaction between the vehicle and the obstacle.

[0094] Therefore, in this embodiment, the lateral distance between the vehicle and the center line of the target lane is normalized to 3.5 meters, and the deceleration is divided into comfortable deceleration and dangerous deceleration. According to the coefficient of the lateral distance, the theoretical deceleration d_calc is continuously adjusted. The specific adjustment method is as follows: Figure 5 as shown in .

[0095] After determining the deceleration that matches the lateral distance, the first distance obs_dis that the first target obstacle needs to travel when decelerating to the current speed of the vehicle is calculated. The calculation formula of the first distance obs_dis is:

[0096] obs_dis= (v_obs×v_obs - v_ego×v_ego) / (2×d_calc);

[0097] The time t_dec required for the first target obstacle to decelerate to the current speed of the vehicle is:

[0098] t_dec=(v_obs-v_ego) / d_calc;

[0099] Then, the second distance d_ego traveled by the ego vehicle is calculated based on the time value and the current speed of the ego vehicle:

[0100] d_ego=v_ego×t_dec;

[0101] Then, the first distance obs_dis and the second distance d_ego can be used to calculate the target distance d_dis of the first target obstacle relative to the ego vehicle during the deceleration process:

[0102] d_dis = obs_dis – d_ego;

[0103] Finally, if Figure 6 As shown, the difference between the longitudinal distance d_t and the relative distance d_r, the target relative safety distance d_s and the target distance d_dis is determined as the remaining distance value d_remaining between the first target obstacle and the relative lane change trajectory:

[0104] That is, d_remaining=d_t-d_r-d_s-d_dis;

[0105] If d_remaining is greater than the second preset distance threshold 0, it is considered safe and there is no collision risk; otherwise, it is considered that there is a collision risk.

[0106] The safety verification process of the third detection area above shows that in the process of lane changing of the ego vehicle, this application needs to consider factors such as the driver's reaction time of the obstacle vehicle, the distance between the collision point of the obstacle and the lane changing trajectory, the braking distance of the obstacle vehicle, and the safety distance. It also considers the interaction of the obstacle vehicle, which is more in line with the actual vehicle lane changing situation. In addition, this solution proposes an algorithm based on the correlation between the lateral distance between the ego vehicle and the center line of the target lane and the collision concern of the rear obstacle, which is more in line with the collision risk judgment logic of human drivers.

[0107] like Figure 7 As shown, in a specific embodiment, a collision detection check is performed on the vehicle lane change request using a verification algorithm set based on the fourth detection area, including: determining the first second target obstacle in front of the current lane of the vehicle; taking the center point of the second target obstacle as the origin, and constructing a second obstacle contour based on a safety distance corresponding to the vehicle speed of the second target obstacle; determining whether there is a collision based on the positional relationship between the second lane change trajectory contour and the second obstacle contour, and if there is no collision, determining that the collision detection check of the fourth detection area has passed, otherwise determining that the collision detection check of the fourth detection area has failed.

[0108] In this embodiment, the fourth detection area is generated based on the current lane of the vehicle and the obstacle in front. Therefore, the first second target obstacle in front of the current lane of the vehicle is determined first, and the center point of the second target obstacle is used as the origin, and the second obstacle contour is constructed based on the safety distance corresponding to the vehicle speed of the second target obstacle. Figure 7As shown, firstly, the outline of the obstacle itself is obtained, and then the outline is expanded backward by a safety distance related to the speed of the second target obstacle to obtain the second obstacle outline, that is, the obstacle expansion outline represented by the green dotted box in the figure. It can be understood that as the speed of the obstacle is different, the obstacle has different safety distance requirements. Then, according to the positional relationship between the second lane change trajectory outline and the second obstacle outline, it is determined whether there is a collision between the two, that is, whether there is an intersecting part. If there is no collision, it is determined that the collision detection check of the fourth detection area has passed, otherwise it is determined that the collision detection check of the fourth detection area has failed.

[0109] The safety verification process of the fourth detection area can solve the problem of collision caused by being too close to the vehicle in front during lane change.

[0110] See also Figure 8 As shown, Figure 8 This is a schematic diagram of a vehicle lane change in a specific scenario disclosed in this application. Figure 8 The current position of the vehicle and the position of the end point of the lane change trajectory in the target lane are shown in FIG. , and the black dotted line between the two is the approximate lane change trajectory line.

[0111] This application needs to perform collision detection verification on the first detection area generated based on the absolute lane changing trajectory and the static obstacle. First, it is necessary to generate a corresponding first lane changing trajectory profile based on the absolute lane changing trajectory, and detect whether a collision occurs between the static obstacle and the first lane changing trajectory profile. Since the first lane changing trajectory profile runs through the entire lane changing process, Figure 8 It is not convenient to give a complete trajectory outline diagram. The specific collision detection and verification process can be found in Figure 2 as shown in .

[0112] This application also needs to perform collision detection verification on the second detection area generated by the target lane and surrounding obstacles, as follows Figure 8 As shown in the red dotted box, the second detection area can be specifically composed of the 10-meter area in front and the 5-meter area behind the target lane relative to the center position of the rear axle of the vehicle, and then determine whether there are obstacles in this area, such as Figure 8 In the scene shown, there are no obstacles in the area, so it can be determined that the collision detection check for this part has passed.

[0113] This application also needs to perform collision detection verification on the third detection area generated by the relative lane change trajectory and the rear obstacle. First, it is also necessary to generate a corresponding second lane change trajectory profile for the relative lane change trajectory, and detect whether there is a collision risk between the first obstacle located behind the end point of the lane change trajectory in the target lane and the second lane change trajectory profile. The approximate detection area is as follows: Figure 8 As shown in the blue dotted box in the figure, the specific collision detection and verification process can be found in Figure 4 and Figure 6 as shown in .

[0114] This application also needs to perform collision detection verification on the fourth detection area generated based on the current lane of the vehicle and the obstacle in front. First, the first obstacle in front of the current lane of the vehicle is determined, and then the outline of the obstacle itself is obtained, and then the outline is expanded backward by a safety distance related to the speed of the obstacle to obtain the corresponding obstacle outline. Specifically, Figure 8 As shown in the green dotted box, it is then determined whether there is a collision between the second lane changing trajectory contour corresponding to the relative lane changing trajectory and the obstacle contour. The specific collision detection and verification process can be found in Figure 7 as shown in .

[0115] Finally, only when the collision detection checks of the above detection areas have passed, is it allowed to respond to the vehicle's lane change request and perform the lane change operation.

[0116] See also Fig. 9 As shown, the embodiment of the present application discloses a vehicle lane change request verification device, the device comprising:

[0117] The trajectory planning module 11 is used to plan a lane-changing trajectory according to the current position of the vehicle and the target lane after obtaining the lane-changing request of the vehicle; wherein the lane-changing trajectory includes an absolute lane-changing trajectory in a global coordinate system and a relative lane-changing trajectory relative to the current position of the vehicle;

[0118] A collision detection module 12, used to determine a detection area generated based on the obstacles around the ego vehicle and the lane change trajectory, and perform a collision detection check on the vehicle lane change request using a verification algorithm set based on the detection area; wherein the detection area includes a first detection area generated based on the absolute lane change trajectory and static obstacles, a second detection area generated based on the target lane and surrounding obstacles, a third detection area generated based on the relative lane change trajectory and rear obstacles, and a fourth detection area generated based on the ego vehicle's current lane and a front obstacle;

[0119] The lane changing module 13 is configured to allow responding to the vehicle lane changing request to perform a lane changing operation if the collision detection checks of the detection areas are all passed.

[0120] It can be seen that after obtaining the vehicle lane change request, the present application first plans a lane change trajectory based on the current position of the vehicle and the target lane. The lane change trajectory includes not only the absolute lane change trajectory in the global coordinate system, but also the relative lane change trajectory relative to the current position of the vehicle. Furthermore, the present application needs to generate a detection area based on the obstacles around the vehicle and the lane change trajectory, so as to perform collision detection verification on the vehicle lane change request using a verification algorithm set based on the detection area, so as to take into account the interaction between the lane change trajectory of the vehicle and the obstacle during the vehicle lane change process, so as to be more in line with the actual vehicle lane change scenario. The above-mentioned detection areas mainly include four types, namely, a first detection area generated based on the absolute lane change trajectory and static obstacles, a second detection area generated based on the target lane and surrounding obstacles, a third detection area generated based on the relative lane change trajectory and rear obstacles, and a fourth detection area generated based on the current lane of the vehicle and the front obstacle. That is, the present application constructs different detection areas with obstacles for collision detection using the absolute lane-changing trajectory and the relative lane-changing trajectory, and also constructs different detection areas with obstacles for collision detection using the vehicle's current lane and the target lane. Finally, only when the collision detection checks in each detection area are passed, is it allowed to respond to the vehicle's lane-changing request to execute the lane-changing operation. In this way, the lane-changing safety is also improved.

[0121] Since the embodiments of the device part correspond to the embodiments of the method part, the embodiments of the device part refer to the description of the embodiments of the method part, which will not be described here. In addition, the invention has the same beneficial effects as the above-mentioned vehicle lane change request verification method.

[0122] Fig.10 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Specifically, it may 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 used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the vehicle lane change request verification method performed by the electronic device disclosed in any of the aforementioned embodiments.

[0123] 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 the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0124] Among them, the processor 21 may 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 hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 21 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0125] In addition, the memory 22, as a carrier for storing resources, can be a read-only memory, a random access memory, a 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 method can be temporary storage or permanent storage.

[0126] Among them, the operating system 221 is used to manage and control the hardware devices and computer programs 222 on the electronic device 20, so as to realize the operation and processing of the massive data 223 in the memory 22 by the processor 21, which can be Windows, Unix, Linux, etc. In addition to including a computer program that can be used to complete the vehicle lane change request verification method performed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 222 can further include a computer program that can be used to complete other specific tasks. In addition to data received by the electronic device and transmitted from an external device, the data 223 can also include data collected by its own input and output interface 25, etc.

[0127] 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 vehicle lane change request verification method steps disclosed in any of the aforementioned embodiments are implemented.

[0128] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0129] 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 with electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. 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.

[0130] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, 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.

[0131] Finally, it should be noted that, in this article, relational terms such as first and second, etc. 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 these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0132] The above is a detailed introduction to a vehicle lane change request verification method, device, equipment and storage medium provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for a person skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A vehicle lane change request verification method, characterized in that: include: After obtaining a lane change request from the vehicle, a lane change trajectory is planned according to the current position of the vehicle and the target lane; wherein the lane change trajectory includes an absolute lane change trajectory in a global coordinate system and a relative lane change trajectory relative to the current position of the vehicle; Determine a detection area generated based on the obstacles around the ego vehicle and the lane change trajectory, and perform collision detection verification on the vehicle lane change request using a verification algorithm set based on the detection area; wherein the detection area includes a first detection area generated based on the absolute lane change trajectory and static obstacles, a second detection area generated based on the target lane and surrounding obstacles, a third detection area generated based on the relative lane change trajectory and rear obstacles, and a fourth detection area generated based on the ego vehicle's current lane and a front obstacle; If the collision detection check of each of the detection areas passes, responding to the vehicle lane change request is allowed to perform a lane change operation.

2. The vehicle lane change request verification method according to claim 1, characterized in that: Performing collision detection verification on the vehicle lane change request using a verification algorithm set based on the first detection area includes: Sampling the absolute lane change trajectory according to a first preset sampling interval to obtain a plurality of sampling points, and generating a first vehicle profile at each sampling point according to first preset length and width information, so as to generate a first lane change trajectory profile based on a bounding box corresponding to each of the first vehicle profiles; Determine whether a collision occurs based on a positional relationship between the first lane change trajectory profile and a static obstacle, and if no collision occurs, determine that the collision detection check of the first detection area passes.

3. The vehicle lane change request verification method according to claim 2, characterized in that: The determining whether there is a collision according to the positional relationship between the first lane change trajectory profile and the static obstacle includes: If there is a collision, determining a target vehicle profile in the first lane change trajectory profile that collides with the static obstacle, and calculating a distance value between a center of a rear axle of the vehicle corresponding to the target vehicle profile and a lane centerline of the target lane; Determining whether the distance value is less than a first preset distance threshold; If the distance value is less than the first preset distance threshold, the corresponding static obstacle is ignored and it is determined that the collision detection check of the first detection area has passed; otherwise, it is determined that the collision detection check of the first detection area has failed.

4. The vehicle lane change request verification method according to claim 1, characterized in that: Performing a collision detection check on the vehicle lane change request using a verification algorithm set based on the second detection area includes: Constructing a target position area based on a first preset area in front of and a second preset area in the rear of the target lane relative to the current position of the vehicle; It is determined whether surrounding obstacles exist in the target position area. If so, it is determined that the collision detection check of the second detection area fails. Otherwise, it is determined that the collision detection check of the second detection area passes.

5. The vehicle lane change request verification method according to any one of claims 1 to 4, characterized in that: Performing a collision detection check on the lane change request of the vehicle using a verification algorithm set based on the third detection area includes: Sampling the relative lane-changing trajectory according to a second preset sampling interval to obtain a plurality of sampling points, and generating a second vehicle profile at each sampling point according to second preset length and width information, so as to generate a second lane-changing trajectory profile based on a bounding box corresponding to each of the second vehicle profiles; Determining a first target obstacle in the target lane that is located behind an end point of the lane change trajectory; constructing a first obstacle profile based on the lane change trajectory end point and the center point of the first target obstacle, and determining a first collision point according to a positional relationship between the first obstacle profile and the second lane change trajectory profile; Calculating a longitudinal distance between the first target obstacle and the first collision point, and calculating a remaining distance value between the first target obstacle and the relative lane change trajectory based on the longitudinal distance, the current speed of the own vehicle, the speed of the first target obstacle, the driving reaction time of the first target obstacle, the target relative safety distance, and the target distance traveled by the first target obstacle relative to the own vehicle during the deceleration process; It is determined whether the remaining distance value is greater than a second preset distance threshold value. If so, it is determined that the collision detection check of the third detection area has passed; otherwise, it is determined that the collision detection check of the third detection area has failed.

6. The vehicle lane change request verification method according to claim 5, characterized in that: The calculating of the remaining distance value between the first target obstacle and the relative lane change trajectory based on the longitudinal distance, the current speed of the vehicle, the speed of the first target obstacle, the driving reaction time of the first target obstacle, the target relative safety distance, and the target distance traveled by the vehicle during the deceleration of the first target obstacle includes: Determine the relative distance of the first target obstacle from the vehicle within the driving reaction time of the first target obstacle based on the current speed of the vehicle and the speed of the first target obstacle, and determine a target relative safety distance that matches the current speed of the vehicle; Determine a lateral distance between the current position of the vehicle and the center line of the target lane, and determine a deceleration that matches the lateral distance, so as to use the deceleration to determine a first distance and time value that the first target obstacle needs to travel when decelerating to the current speed of the vehicle; Calculating a second distance traveled by the vehicle based on the time value and the current speed of the vehicle, and calculating a target distance traveled by the vehicle relative to the first target obstacle during deceleration using the first distance and the second distance; The difference between the longitudinal distance and the relative distance, the target relative safety distance and the target distance is determined as a remaining distance value between the first target obstacle and the relative lane change trajectory.

7. The vehicle lane change request verification method according to claim 5, characterized in that: Performing a collision detection check on the vehicle lane change request using a verification algorithm set based on the fourth detection area includes: Determine the first second target obstacle in front of the vehicle's current lane; Taking the center point of the second target obstacle as the origin and constructing a second obstacle profile based on a safety distance corresponding to the vehicle speed of the second target obstacle; Determine whether there is a collision based on the positional relationship between the second lane change trajectory profile and the second obstacle profile; if there is no collision, determine that the collision detection check of the fourth detection area has passed; otherwise, determine that the collision detection check of the fourth detection area has failed.

8. A vehicle lane change request verification device, characterized in that: include: A trajectory planning module is used to plan a lane-changing trajectory according to the current position of the vehicle and the target lane after obtaining a lane-changing request of the vehicle; wherein the lane-changing trajectory includes an absolute lane-changing trajectory in a global coordinate system and a relative lane-changing trajectory relative to the current position of the vehicle; a collision detection module, configured to determine a detection area generated based on obstacles around the ego vehicle and the lane change trajectory, and perform collision detection verification on the vehicle lane change request using a verification algorithm set based on the detection area; wherein the detection area includes a first detection area generated based on the absolute lane change trajectory and static obstacles, a second detection area generated based on the target lane and surrounding obstacles, a third detection area generated based on the relative lane change trajectory and rear obstacles, and a fourth detection area generated based on the ego vehicle's current lane and a front obstacle; The lane changing module is used to allow responding to the vehicle lane changing request to perform a lane changing operation if the collision detection verification of each detection area passes.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the steps of the vehicle lane change request verification method as described in 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 vehicle lane change request verification method as described in any one of claims 1 to 7 are implemented.

Images