A road edge avoidance method and system in intelligent cruising

Abstract

The present invention provides a road edge avoidance method and system in intelligent cruise, the method comprising: when a vehicle is traveling on a specific road and the road curvature radius exceeds a predetermined threshold, the vehicle offset direction is calculated, and it is judged whether the road edge meets the offset condition; if the offset condition is met, the target vehicle information in the offset direction is obtained, and whether the target vehicle affects the offset of the vehicle is judged according to the position, relative distance and relative speed of the target vehicle; if the target vehicle does not affect the offset of the vehicle, the offset target of the vehicle in the current scene is calculated, the offset path is planned based on the offset target, and the offset driving of the vehicle is controlled; during the offset process or in the offset driving state, it is continuously judged whether the vehicle meets the return-to-center condition, and if the return-to-center condition is met, the vehicle is controlled to drive in the center of the lane. Through this solution, the vehicle can be controlled to appropriately offset to the opposite direction of the road edge in intelligent cruise, reduce the psychological pressure of the driver, improve the user experience, and increase the utilization rate of intelligent cruise.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent driving, and in particular relates to a road edge avoidance method and system in intelligent cruising. Background Art

[0002] With the rapid development of smart car technology, L2 intelligent driving systems have been widely used in mass-produced vehicles. Typical L2 lateral and longitudinal coupling control systems, such as TJA (traffic jam assist) and ICA (intelligent cruise assist), can well control the vehicle to drive in the center of the lane. However, in reality, because these functions are too mechanized, they are still rarely used by ordinary users. For example, when a vehicle is driving at high speed on a highway or urban expressway near the edge of the road or a lane of a guardrail, the intelligent cruise function still "mechanizes" the center of the lane, close to the edge of the road or the guardrail, which puts a lot of psychological pressure on the driver. The driver feels that he may hit the guardrail at any time, which causes users to exit the intelligent cruise in these scenarios. Summary of the invention

[0003] In view of this, an embodiment of the present invention provides a method and system for road edge avoidance in smart cruise, which is used to solve the problem that users rarely use smart cruise in specific scenarios.

[0004] In a first aspect of an embodiment of the present invention, a method for avoiding a road edge in intelligent cruising is provided, comprising:

[0005] When a vehicle is traveling on a specific road and the road curvature radius exceeds a predetermined threshold, the vehicle offset direction is calculated. If the vehicle offset direction is not 0, it is determined whether the road edge meets the offset condition.

[0006] If the road edge meets the offset condition, the target vehicle information in the offset direction is obtained, and according to the position of the target vehicle, the distance between the target vehicle and the ego vehicle, and the relative speed, it is determined whether the target vehicle affects the ego vehicle offset;

[0007] If the target vehicle does not affect the ego vehicle's offset, the offset target of the ego vehicle in the current scene is calculated, the offset path is planned based on the offset target, and the ego vehicle is controlled to offset.

[0008] During the deviation process or the deviation driving state, it is continuously determined whether the vehicle meets the return-to-center condition. If the return-to-center condition is met, the vehicle is controlled to drive in the center of the lane.

[0009] In a second aspect of an embodiment of the present invention, a system for road edge avoidance in intelligent cruising is provided, comprising:

[0010] A map positioning module is used to locate the vehicle and obtain the type of road the vehicle is on;

[0011] A fusion perception module is used to collect environmental perception information through sensors, wherein the environmental perception information includes at least the road curvature radius, the distance between the vehicle and the road edge, the vehicle information, the target vehicle information, and the distance between the vehicle and the lane lines on both sides;

[0012] The behavior decision module is used to determine whether to deviate or return to the center according to the environmental perception information, and calculate the corresponding deviation target or return target;

[0013] Among them, when the vehicle is traveling on a specific road and the road curvature radius exceeds a predetermined threshold, the vehicle offset direction is calculated. If the vehicle offset direction is not 0, it is determined whether the road edge meets the offset condition;

[0014] If the road edge meets the offset condition, the target vehicle information in the offset direction is obtained. According to the position of the target vehicle, the distance between the target vehicle and the ego vehicle, and the relative speed, it is determined whether the target vehicle affects the ego vehicle offset. If the target vehicle does not affect the ego vehicle offset, the offset target of the ego vehicle in the current scene is calculated.

[0015] During the deviation process or the deviation driving state, it is continuously determined whether the vehicle meets the return-to-center condition. If the return-to-center condition is met, the return-to-center target of the vehicle is calculated;

[0016] A path planning module is used to plan an offset path according to an offset target, or to plan a return path according to a return target;

[0017] A motion control module, used for controlling the vehicle to deviate or return to the center according to the deviation path or the return path;

[0018] In a third aspect of an embodiment of the present invention, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in the first aspect of the embodiment of the present invention when executing the computer program.

[0019] In a fourth aspect of an embodiment of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method provided in the first aspect of the embodiment of the present invention are implemented.

[0020] In the embodiment of the present invention, when the road and surrounding vehicles allow, the driver's psychological pressure can be reduced, the user experience of the smart cruise function can be improved, and the user utilization rate can be increased by appropriately offsetting the vehicle toward the edge of the road to avoid being too close to the edge of the road. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 A schematic flow chart of a method for avoiding a road edge in intelligent cruising provided by an embodiment of the present invention;

[0023] Figure 2 A schematic diagram of vehicle offset driving provided by an embodiment of the present invention;

[0024] Figure 3 A schematic diagram of vehicle driving state transition provided by an embodiment of the present invention;

[0025] Figure 4 A schematic diagram of the structure of a road edge avoidance system for intelligent cruising provided by one embodiment of the present invention;

[0026] Figure 5 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below 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 creative work are within the scope of protection of the present invention.

[0028] It should be understood that the term "including" and other similar expressions in the specification or claims of the present invention and the above-mentioned drawings are intended to cover non-exclusive inclusions, such as a process, method, system, or device including a series of steps or units is not limited to the listed steps or units. In addition, "first" and "second" are used to distinguish different objects, not to describe a specific order.

[0029] See also Figure 1 , a schematic flow chart of a method for avoiding road edges in intelligent cruising provided by an embodiment of the present invention includes:

[0030] S101, when a vehicle is traveling on a specific road and the road curvature radius exceeds a predetermined threshold, the vehicle offset direction is calculated, and if the vehicle offset direction is not 0, whether the road edge satisfies the offset condition is determined;

[0031] The specific road is generally a road that needs to be passed at high speed, such as a highway, a city expressway, etc. When the vehicle is traveling at high speed, approaching the edge of the road in the case of intelligent cruising will bring psychological pressure to the driver. The road curvature radius is used to measure the curvature of the road. Through on-board sensors, such as laser point clouds, cameras, etc., the road edge data can be collected and the road curvature radius can be calculated and determined, such as determining the road curvature radius based on guardrails, lane lines, etc. The predetermined threshold is a calibration quantity, which usually needs to be set in advance. Once the road curvature radius exceeds the threshold, it is determined that the current road curvature radius meets the offset condition.

[0032] Generally, when a vehicle approaches the edge of the road, it is necessary to perform an offset control on the vehicle to relieve the driver's psychological pressure. Therefore, it is first necessary to determine whether the vehicle is in a high-speed driving condition and whether the curvature of the road is within a certain range.

[0033] In some embodiments, the map positioning is used to determine whether the road on which the vehicle is currently traveling belongs to a highway or a city expressway. To prevent the vehicle from frequently switching between center driving and offset driving on a city road, it is set that the vehicle is allowed to offset driving only when the vehicle is traveling on a highway or a city expressway.

[0034] Specifically, the current road curvature radius R_Curvature is obtained. To avoid the safety risk caused by the vehicle deviating on a road with a curvature radius that is too small, the deviating condition is met only when R_Curvature>C_R_Curvature. Among them, C_R_Curvature is a calibration quantity, indicating the minimum curvature radius supported by the deviating.

[0035] The offset direction refers to the current driving direction of the vehicle, including rightward offset and leftward offset. Generally, the vehicle is controlled to drive in an offset manner only when the vehicle is offset to the left or to the right.

[0036] Specifically, when the distance between the vehicle and the left edge of the lane is less than the trigger threshold of the left edge distance, and the distance between the vehicle and the right edge of the lane is greater than the trigger threshold of the right edge distance, the deviation direction is the first set value, indicating that the vehicle is traveling on the left side of the road and deviating to the right;

[0037] When the distance between the vehicle and the left edge of the lane is greater than the trigger threshold of the left edge distance, and the distance between the vehicle and the right edge of the lane is less than the trigger threshold of the right edge distance, the deviation direction is the second set value, indicating that the vehicle is traveling on the right side of the road and deviating to the left;

[0038] When the distance between the vehicle and the left edge of the lane is less than the trigger threshold of the left edge distance, and the distance between the vehicle and the right edge of the lane is less than the trigger threshold of the right edge distance, or when the distance between the vehicle and the left edge of the lane is greater than the trigger threshold of the left edge distance, and the distance between the vehicle and the right edge of the lane is greater than the trigger threshold of the right edge distance, the offset direction is the third set value, indicating that no offset occurs.

[0039] The first, second and third setting values ​​all correspond to a specific value, such as 1, 2 and 0, where 1 and 2 represent offset, and 0 represents no offset. When the offset direction is the third setting value, it generally means that the road edges on both sides are too far or too close, and it is not suitable for offset driving.

[0040] Exemplarily, the distance between the vehicle and the left road edge is Dy_edge_left, and the distance between the vehicle and the right road edge is Dy_edge_right;

[0041] When Dy_edge_left≤C_edge_left and Dy_edge_right>C_edge_right, the vehicle is traveling on the left side of the road and offset to the right, Offset_Direction=1;

[0042] Among them, C_edge_left is a calibration quantity, which indicates the trigger threshold of the distance between the vehicle and the left edge of the road when the vehicle is traveling on the leftmost side in a highway or urban expressway scenario; C_edge_right is a calibration quantity, which indicates the trigger threshold of the distance between the vehicle and the right edge of the road when the vehicle is traveling on the rightmost side in a highway or urban expressway scenario.

[0043] When Dy_edge_left>C_edge_left and Dy_edge_right≤C_edge_right, the vehicle is traveling on the right side of the road and offset to the left, Offset_Direction=2;

[0044] When Dy_edge_left≤C_edge_left and Dy_edge_right≤C_edge_right, both sides are close to the road edge, and no offset occurs, Offset_Direction=0;

[0045] When Dy_edge_left>C_edge_left and Dy_edge_right>C_edge_right, both sides are far away from the edge of the road, and no offset occurs, and Offset_Direction=0.

[0046] The road edge generally refers to the specific boundaries on both sides of the road, usually guardrails, etc. The road edge curve is a curve constructed based on the road edge (such as guardrails). Since the road edge curve may be discontinuous and the curve segment may be short, certain processing is required.

[0047] Optionally, obtain the curve equation of the road edge and the starting point and end point of the curve; merge acceptable discontinuous road edge curve segments within a preset range; filter curve segments whose distance between the starting point and the end point is less than a predetermined value; if the longitudinal distance between the coordinates of the starting point of the merged curve segment and the vehicle is less than a preset threshold, determine that the road edge meets the offset condition.

[0048] For example, the road edge curve equation corresponding to the offset direction Offset_Direction and its starting point and end point are obtained. If there is a short discontinuity at the road edge and its curve trend can be maintained, the perception fusion outputs a curve equation corresponding to multiple curve segments, so there are multiple starting points and end points. The starting points and end points of the curve are (Dx_start_p1, Dx_stop_p1), (Dx_start_p2, Dx_stop_p2), (Dx_start_p3, Dx_stop_p3)... from near to far.

[0049] Merge discontinuous road edge curve segments within the acceptable range. If the distance between the end point of the current curve segment and the start point of the next curve segment is less than a certain threshold, that is, |Dx_start_p(n+1)–Dx_stop_p(n)|<C_Dx_edge_intermittent, then the intermittent distance between curve segment n and curve segment n+1 is considered to be within the acceptable range, then curve segment n and curve segment n+1 are merged into one road edge curve, and so on. Among them, C_Dx_edge_intermittent is a calibration quantity, which represents the acceptable road edge intermittent distance.

[0050] After the merging is completed, the merged road edge start and end are obtained. Further, the shorter road edge curve segments are filtered. If the distance between the start and end of the curve segment is less than a certain threshold, that is, |Dx_start_p(n+1)–Dx_stop_p(n)|<C_Dx_edge_Length, then this road edge curve segment is filtered. Among them, C_Dx_edge_Length is the longitudinal distance filtering threshold between the start and end of the road edge curve.

[0051] If there are still unfiltered road edge curve segments, further determine the distance between the starting point of the road edge curve and the vehicle

[0052] If the starting coordinate of the road edge curve is less than C_Dx_start, the offset condition is met. C_Dx_start is the trigger threshold of the longitudinal distance between the starting point of the road edge curve and the vehicle. That is, after merging, when the starting coordinate of the road edge curve segment and the longitudinal distance between the vehicle are less than a certain value, the road edge is judged to meet the offset condition.

[0053] S102, if the road edge meets the offset condition, then obtain the target vehicle information in the offset direction, and determine whether the target vehicle affects the offset of the own vehicle according to the position of the target vehicle, the distance between the target vehicle and the own vehicle, and the relative speed;

[0054] After completing the judgment of the driving environment of the self-vehicle, that is, whether the self-vehicle meets the offset conditions, it is also necessary to judge whether other vehicles will affect the offset of the self-vehicle to avoid safety accidents caused by offset.

[0055] The target vehicle is another vehicle relative to the own vehicle. The target vehicle information can be detected by a vehicle-mounted camera, a laser radar, etc., including the position and distance of the target vehicle, and the speed of the target vehicle can be calculated.

[0056] Specifically, if the lateral distance or longitudinal distance between the ego vehicle and the target vehicle is greater than a set value, it is determined that the target vehicle does not affect the deviation of the ego vehicle;

[0057] If the target vehicle is in front of the ego vehicle and the speed of the target vehicle is greater than the speed of the ego vehicle, it is determined that the target vehicle does not affect the deviation of the ego vehicle;

[0058] If the target vehicle is in front of the ego vehicle and the speed of the target vehicle is less than that of the ego vehicle, the time when the target vehicle will affect the offset of the ego vehicle is calculated. If the time when the target vehicle will affect the offset of the ego vehicle is greater than the preset time threshold, the target vehicle does not affect the offset of the ego vehicle. Otherwise, the target vehicle affects the offset of the ego vehicle.

[0059] If the target vehicle is behind the ego vehicle and its speed is lower than that of the ego vehicle, it is determined that the target vehicle does not affect the deviation of the ego vehicle.

[0060] If the target vehicle is behind the ego vehicle and its speed is greater than that of the ego vehicle, the time that the target vehicle will affect the ego vehicle's offset is calculated. If the time that the target vehicle will affect the ego vehicle's offset is greater than the preset time threshold, the target vehicle does not affect the ego vehicle's offset. Otherwise, the target vehicle affects the ego vehicle's offset.

[0061] Exemplarily, the lateral distance of the target vehicle is set to Dy_target, the longitudinal distance is set to Dx_target, the relative longitudinal speed is set to Vx_target, and the relative longitudinal acceleration is set to Ax_target.

[0062] When Dy_target>C_Dy_target, it is considered that the target does not affect the deviation of the vehicle. C_Dy_target is a calibration quantity, which indicates the lateral distance threshold for judging whether the target vehicle affects the deviation of the vehicle.

[0063] If the above conditions are met, further judgment can be made. If |Dx_target|>C_Dx_target, it is considered that the longitudinal distance of the vehicle is far. C_Dy_target is a calibration quantity, which indicates the longitudinal distance threshold for judging whether the target vehicle affects the deviation of the vehicle.

[0064] When Dx_target>0, the target vehicle is in front of the vehicle, and the speed of the target vehicle is further determined.

[0065] If Vx_target>0, the target vehicle is faster than the ego vehicle and does not affect the ego vehicle offset;

[0066] If Vx_target<0, the target vehicle is slower than the ego vehicle, and TTC_target is further calculated. When TTC_target>C_TTC_target, it does not affect the ego vehicle offset.

[0067] Among them, TTC_target is solved according to the equation to obtain |Vx_target|*TTC_target+1 / 2*|Ax_target|*(TTC_target)^2=|Dx_target|, and C_TTC_target is a calibration quantity used to indicate the time threshold for judging that the target vehicle is about to affect the deviation of the ego vehicle.

[0068] When Dx_target<0, the target vehicle is behind the vehicle, and the speed of the target vehicle is further determined.

[0069] If Vx_target>0, the target vehicle is faster than the ego vehicle, and the longitudinal TTC_target is further calculated. When TTC_target>C_TTC_target, it does not affect the ego vehicle offset.

[0070] If Vx_target<0, the target vehicle is slower than the ego vehicle and does not affect the ego vehicle offset.

[0071] S103: If the target vehicle does not affect the offset of the ego vehicle, then the offset target of the ego vehicle in the current scene is calculated, an offset path is planned based on the offset target, and the ego vehicle is controlled to offset and travel;

[0072] The offset target is the target position of the vehicle offset, which can generally be determined according to the vehicle speed and the distance between the lane line and the lane edge.

[0073] Specifically, the corresponding offset target is obtained according to the current speed of the ego vehicle, the distance between the ego vehicle and the lane line, and the driving behavior map; the offset target is set as the lateral offset distance of the ego vehicle, and the PID control parameters of the offset process are solved to control the offset driving of the ego vehicle.

[0074] Exemplarily, the distance Dy_line_left between the vehicle and the left lane line is obtained, and the distance Dy_edge_line between the current road edge and the lane edge is calculated, Dy_edge_line=|Dy_edge_left-Dy_line_left|.

[0075] Calculate the offset target of the current scene, specifically according to the current vehicle speed V, Dy_edge_line and MAP_left, calculate the offset target offset_distance of the current scene. Among them, MAP_left is the MAP calibration quantity, which is the driving behavior map of the offset target of the vehicle driving on the left side of the main road of the highway or urban expressway. In this map, the corresponding offset_distance can be queried according to V and Dy_edge_line.

[0076] The path is planned according to the offset target, and then the lane is controlled according to the planned path to change from driving in the center of the lane to driving according to the offset target.

[0077] At the initial moment of the migration process, the lateral migration distance is 0 and the lateral velocity is 0, that is,

[0078] At the end of the offset process, the lateral offset distance is offset_distance, the lateral speed is 0, and the longitudinal distance traveled is x 1 ,but

[0079] The longitudinal distance traveled during the excursion process can be approximately calculated based on the current vehicle speed and the time constant of the excursion process: 1 =V·C_τ 1 .

[0080] According to the above conditions, solve the cubic equation y=a 0 +a 1 x+a 2 x 2 +a 3 x 3 ;

[0081] In the formula, x represents the longitudinal distance, y represents the lateral distance, V is the current vehicle speed, C_τ 1 is a calibration quantity, which represents the time constant of the offset process.

[0082] The solution is:

[0083]

[0084] The PID control algorithm is used to control the vehicle to deviate according to the above planned path.

[0085] S104: During the deviation process or the deviation driving state, it is continuously determined whether the vehicle meets the return-to-center condition. If the return-to-center condition is met, the vehicle is controlled to drive in the center of the lane.

[0086] like Figure 2 and 3 As shown, during the vehicle deviation process or the deviation driving state, it is possible to determine whether the return-to-center condition is met based on real-time environmental perception. If the return-to-center condition is met, the vehicle is controlled to turn to center driving.

[0087] The return-to-center condition includes the road type, the road curvature radius, or the influence of the target vehicle, etc.

[0088] Specifically, if the current road type is about to change, or the road curvature radius does not exceed a predetermined threshold, or the target vehicle is about to affect the deviation of the vehicle, the vehicle is controlled to travel in the center.

[0089] In one embodiment, the distance between the vehicle and the lane lines on both sides of the lane is obtained, and according to the distance between the vehicle and the lane lines on both sides of the lane, it is determined whether the vehicle should return to the right side or to the left side;

[0090] The return distance is calculated and the return path is planned. By solving the PID control parameters of the return process, the vehicle is controlled to stay in the center of the lane.

[0091] Exemplarily, the distance Dy_line_left between the vehicle and the left lane line and the distance Dy_line_right between the vehicle and the right lane line are obtained;

[0092] Determine the vehicle's return direction. If Dy_line_left<Dy_line_right, return to the right side; if Dy_line_left>Dy_line_right, return to the left side.

[0093] Calculate the distance back to the center:

[0094] Replace offset_distance with offset_back, C_τ 1 Replace with C_τ 2 The method of the embodiment in step S103 is used to calculate the return path, and the vehicle is controlled to change from driving according to the offset target to driving in the center of the lane.

[0095] In this embodiment, by simulating the driver's driving habits, when conditions such as the road, road edge, and surrounding vehicles permit, the vehicle no longer maintains complete centering, but instead appropriately deviates in the opposite direction of the road edge, thereby reducing the driver's psychological pressure, improving the user experience of the intelligent cruise function, and being more humanized.

[0096] It should be understood that the serial numbers of the steps in the above embodiments do not imply a sequence of execution, and the execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0097] Figure 4 A schematic diagram of a system for road edge avoidance in intelligent cruising provided in an embodiment of the present invention, the system comprising:

[0098] A map positioning module 410 is used to locate the vehicle and obtain the type of road the vehicle is on;

[0099] The fusion perception module 420 is used to collect environmental perception information through sensors, wherein the environmental perception information at least includes the road curvature radius, the distance between the vehicle and the road edge, the vehicle information, the target vehicle information, and the distance between the vehicle and the lane lines on both sides;

[0100] The behavior decision module 430 is used to determine whether to deviate or return to the center according to the environmental perception information, and calculate the corresponding deviate target or return to the center target;

[0101] Among them, when the vehicle is traveling on a specific road and the road curvature radius exceeds a predetermined threshold, the vehicle offset direction is calculated. If the vehicle offset direction is not 0, it is determined whether the road edge meets the offset condition;

[0102] If the road edge meets the offset condition, the target vehicle information in the offset direction is obtained. According to the position of the target vehicle, the distance between the target vehicle and the ego vehicle, and the relative speed, it is determined whether the target vehicle affects the ego vehicle offset. If the target vehicle does not affect the ego vehicle offset, the offset target of the ego vehicle in the current scene is calculated.

[0103] During the deviation process or the deviation driving state, it is continuously determined whether the vehicle meets the return-to-center condition. If the return-to-center condition is met, the return-to-center target of the vehicle is calculated;

[0104] A path planning module 440 is used to plan a deviation path according to a deviation target, or to plan a return path according to a return target;

[0105] The motion control module 450 is used to control the vehicle to deviate or return to the center according to the deviation path or the return path.

[0106] Optionally, the calculating the vehicle offset direction includes:

[0107] When the distance between the vehicle and the left edge of the lane is less than the trigger threshold of the left edge distance, and the distance between the vehicle and the right edge of the lane is greater than the trigger threshold of the right edge distance, the deviation direction is the first set value, indicating that the vehicle is traveling on the left side of the road and deviating to the right;

[0108] When the distance between the vehicle and the left edge of the lane is greater than the trigger threshold of the left edge distance, and the distance between the vehicle and the right edge of the lane is less than the trigger threshold of the right edge distance, the deviation direction is the second set value, indicating that the vehicle is traveling on the right side of the road and deviating to the left;

[0109] When the distance between the vehicle and the left edge of the lane is less than the trigger threshold of the left edge distance, and the distance between the vehicle and the right edge of the lane is less than the trigger threshold of the right edge distance, or when the distance between the vehicle and the left edge of the lane is greater than the trigger threshold of the left edge distance, and the distance between the vehicle and the right edge of the lane is greater than the trigger threshold of the right edge distance, the offset direction is the third set value, indicating that no offset occurs.

[0110] Optionally, the determining whether the road edge satisfies the offset condition includes:

[0111] Obtain the curve equation of the road edge and the starting point and end point of the curve;

[0112] Merge acceptable discontinuous road edge curve segments within a preset range;

[0113] Filter the curve segments whose distance between the starting point and the end point is less than a predetermined value;

[0114] If the longitudinal distance between the coordinates of the starting point of the merged road edge curve segment and the vehicle is less than a preset threshold, it is determined that the road edge meets the offset condition.

[0115] Specifically, the step of acquiring target vehicle information in the offset direction and judging whether the target vehicle affects the offset of the own vehicle according to the position of the target vehicle, the distance between the target vehicle and the own vehicle, and the relative speed includes:

[0116] If the lateral distance or longitudinal distance between the ego vehicle and the target vehicle is greater than the set value, it is determined that the target vehicle does not affect the deviation of the ego vehicle;

[0117] If the target vehicle is in front of the ego vehicle and the speed of the target vehicle is greater than the speed of the ego vehicle, it is determined that the target vehicle does not affect the deviation of the ego vehicle;

[0118] If the target vehicle is in front of the ego vehicle and the speed of the target vehicle is less than the speed of the ego vehicle, the time when the target vehicle will affect the offset of the ego vehicle is calculated. If the time when the target vehicle will affect the offset of the ego vehicle is greater than the preset time threshold, the target vehicle does not affect the offset of the ego vehicle. Otherwise, it is determined that the target vehicle affects the offset of the ego vehicle.

[0119] If the target vehicle is behind the ego vehicle and its speed is lower than that of the ego vehicle, it is determined that the target vehicle does not affect the deviation of the ego vehicle.

[0120] If the target vehicle is behind the ego vehicle and its speed is greater than that of the ego vehicle, the time it will take for the target vehicle to affect the ego vehicle's offset is calculated. If the time it will take for the target vehicle to affect the ego vehicle's offset is greater than a preset time threshold, the target vehicle does not affect the ego vehicle's offset. Otherwise, it is determined that the target vehicle affects the ego vehicle's offset.

[0121] Wherein, the path planning module 440 includes:

[0122] An offset target acquisition unit is used to acquire a corresponding offset target according to the current speed of the vehicle, the distance between the vehicle and the lane line, and the driving behavior map;

[0123] The control parameter calculation unit is used to set the offset target as the lateral offset distance of the vehicle, and solve the PID control parameters of the offset process to control the offset driving of the vehicle.

[0124] Wherein, during the deviation process or the deviation driving state, continuously determining whether the vehicle meets the return-to-center condition includes:

[0125] If the current road type is about to change, or the road curvature radius does not exceed the preset threshold, or the target vehicle is about to affect the deviation of the vehicle, the vehicle is controlled to drive in the center.

[0126] The path planning module 440 further includes:

[0127] A return-to-center direction judgment unit is used to obtain the distance between the vehicle and the lane lines on both sides of the lane, and judge whether the vehicle should return to the right or left side according to the distance between the vehicle and the lane lines on both sides of the lane;

[0128] The centering path planning unit is used to calculate the centering distance and plan the centering path. By solving the PID control parameters of the centering process, the vehicle is controlled to keep driving in the center of the lane.

[0129] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0130] Figure 5 1 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. The electronic device is used for road edge avoidance in intelligent cruising. Figure 5 As shown, the electronic device 5 of this embodiment includes: a memory 510, a processor 520 and a system bus 530, wherein the memory 510 includes an executable program 5101 stored thereon, and those skilled in the art can understand that Figure 5The electronic device structure shown in the figure does not constitute a limitation of the electronic device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0131] Combine the following Figure 5 A detailed introduction to the various components of electronic equipment:

[0132] The memory 510 can be used to store software programs and modules, and the processor 520 executes various functional applications and data processing of the electronic device by running the software programs and modules stored in the memory 510. The memory 510 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device (such as cache data), etc. In addition, the memory 510 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0133] The memory 510 includes an executable program 5101 of a network request method, and the executable program 5101 can be divided into one or more modules / units, which are stored in the memory 510 and executed by the processor 520 to realize vehicle offset driving, etc. The one or more modules / units can be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the computer program 5101 in the electronic device 5. For example, the computer program 5101 can be divided into a map positioning module, a fusion perception module, a behavior decision module, a path planning module, and a motion control module.

[0134] The processor 520 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire electronic device. By running or executing software programs and / or modules stored in the memory 510, and calling data stored in the memory 510, it performs various functions of the electronic device and processes data, thereby monitoring the overall status of the electronic device. Optionally, the processor 520 may include one or more processing units; preferably, the processor 520 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, application programs, etc., and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 520.

[0135] The system bus 530 is used to connect the various functional components inside the computer, and can transmit data information, address information, and control information. Its types can be, for example, PCI bus, ISA bus, CAN bus, etc. The instructions of the processor 520 are transmitted to the memory 510 through the bus, and the memory 510 feeds back data to the processor 520. The system bus 530 is responsible for the data and instruction exchange between the processor 520 and the memory 510. Of course, the system bus 530 can also be connected to other devices, such as network interfaces, display devices, etc.

[0136] In the embodiment of the present invention, the executable program executed by the processor 520 included in the electronic device includes:

[0137] When a vehicle is traveling on a specific road and the road curvature radius exceeds a predetermined threshold, the vehicle offset direction is calculated. If the vehicle offset direction is not 0, it is determined whether the road edge meets the offset condition.

[0138] If the road edge meets the offset condition, the target vehicle information in the offset direction is obtained, and according to the position of the target vehicle, the distance between the target vehicle and the ego vehicle, and the relative speed, it is determined whether the target vehicle affects the ego vehicle offset;

[0139] If the target vehicle does not affect the ego vehicle's offset, the offset target of the ego vehicle in the current scene is calculated, the offset path is planned based on the offset target, and the ego vehicle is controlled to offset.

[0140] During the deviation process or the deviation driving state, it is continuously determined whether the vehicle meets the return-to-center condition. If the return-to-center condition is met, the vehicle is controlled to drive in the center of the lane.

[0141] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0142] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0143] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A road edge avoidance method in intelligent cruising, It is characterized in that include: When a vehicle is traveling on a specific road and the road curvature radius exceeds a predetermined threshold, the vehicle offset direction is calculated. If the vehicle offset direction is not 0, it is determined whether the road edge meets the offset condition. If the road edge meets the offset condition, the target vehicle information in the offset direction is obtained, and according to the position of the target vehicle, the distance between the target vehicle and the ego vehicle, and the relative speed, it is determined whether the target vehicle affects the ego vehicle offset; If the target vehicle does not affect the ego vehicle's offset, the offset target of the ego vehicle in the current scene is calculated, the offset path is planned based on the offset target, and the ego vehicle is controlled to offset. The step of calculating the offset target of the vehicle in the current scene, planning the offset path based on the offset target, and controlling the offset driving of the vehicle includes: Obtain the corresponding offset target according to the current speed of the vehicle, the distance between the vehicle and the lane line, and the driving behavior map; The offset target is set as the lateral offset distance of the vehicle, and the PID control parameters of the offset process are solved to control the offset driving of the vehicle; During the deviation process or the deviation driving state, it is continuously determined whether the vehicle meets the return-to-center condition. If the return-to-center condition is met, the vehicle is controlled to drive in the center of the lane.

2. The method according to claim 1, It is characterized in that The calculating of the vehicle offset direction comprises: When the distance between the vehicle and the left edge of the lane is less than the trigger threshold of the left edge distance, and the distance between the vehicle and the right edge of the lane is greater than the trigger threshold of the right edge distance, the deviation direction is the first set value, indicating that the vehicle is traveling on the left side of the road and deviating to the right; When the distance between the vehicle and the left edge of the lane is greater than the trigger threshold of the left edge distance, and the distance between the vehicle and the right edge of the lane is less than the trigger threshold of the right edge distance, the deviation direction is the second set value, indicating that the vehicle is traveling on the right side of the road and deviating to the left; When the distance between the vehicle and the left edge of the lane is less than the trigger threshold of the left edge distance, and the distance between the vehicle and the right edge of the lane is less than the trigger threshold of the right edge distance, or when the distance between the vehicle and the left edge of the lane is greater than the trigger threshold of the left edge distance, and the distance between the vehicle and the right edge of the lane is greater than the trigger threshold of the right edge distance, the offset direction is the third set value, indicating that no offset occurs.

3. The method according to claim 1, It is characterized in that The determining whether the road edge satisfies the offset condition comprises: Obtain the curve equation of the road edge and the starting point and end point of the curve; Merge acceptable discontinuous road edge curve segments within a preset range; Filter the curve segments whose distance between the starting point and the end point is less than a predetermined value; If the longitudinal distance between the coordinates of the starting point of the merged road edge curve segment and the vehicle is less than a preset threshold, it is determined that the road edge meets the offset condition.

4. The method according to claim 1, It is characterized in that The step of obtaining target vehicle information in the offset direction and judging whether the target vehicle affects the offset of the vehicle according to the position of the target vehicle, the distance between the target vehicle and the vehicle, and the relative speed includes: If the lateral distance or longitudinal distance between the ego vehicle and the target vehicle is greater than the set value, it is determined that the target vehicle does not affect the deviation of the ego vehicle; If the target vehicle is in front of the ego vehicle and the speed of the target vehicle is greater than the speed of the ego vehicle, it is determined that the target vehicle does not affect the deviation of the ego vehicle; If the target vehicle is in front of the ego vehicle and the speed of the target vehicle is less than the speed of the ego vehicle, the time when the target vehicle will affect the offset of the ego vehicle is calculated. If the time when the target vehicle will affect the offset of the ego vehicle is greater than the preset time threshold, the target vehicle does not affect the offset of the ego vehicle. Otherwise, it is determined that the target vehicle affects the offset of the ego vehicle. If the target vehicle is behind the ego vehicle and its speed is lower than that of the ego vehicle, it is determined that the target vehicle does not affect the deviation of the ego vehicle. If the target vehicle is behind the ego vehicle and its speed is greater than that of the ego vehicle, the time it will take for the target vehicle to affect the ego vehicle's offset is calculated. If the time it will take for the target vehicle to affect the ego vehicle's offset is greater than a preset time threshold, the target vehicle does not affect the ego vehicle's offset. Otherwise, it is determined that the target vehicle affects the ego vehicle's offset.

5. The method according to claim 1, It is characterized in that During the deviation process or the deviation driving state, continuously determining whether the vehicle meets the return-to-center condition includes: If the current road type is about to change, or the road curvature radius does not exceed the preset threshold, or the target vehicle is about to affect the deviation of the vehicle, the vehicle is controlled to drive in the center.

6. The method according to claim 5, It is characterized in that The controlling the vehicle to travel in the center comprises: Obtain the distance between the vehicle and the lane lines on both sides of the lane, and determine whether the vehicle should return to the right or left center based on the distance between the vehicle and the lane lines on both sides of the lane; The return distance is calculated and the return path is planned. By solving the PID control parameters of the return process, the vehicle is controlled to stay in the center of the lane.

7. A system for road edge avoidance in intelligent cruising, It is characterized in that include: A map positioning module is used to locate the vehicle and obtain the type of road the vehicle is on; A fusion perception module is used to collect environmental perception information through sensors, wherein the environmental perception information includes at least the road curvature radius, the distance between the vehicle and the road edge, the vehicle information, the target vehicle information, and the distance between the vehicle and the lane lines on both sides; The behavior decision module is used to determine whether to deviate or return to the center according to the environmental perception information, and calculate the corresponding deviation target or return target; Among them, when the vehicle is traveling on a specific road and the road curvature radius exceeds a predetermined threshold, the vehicle offset direction is calculated. If the vehicle offset direction is not 0, it is determined whether the road edge meets the offset condition; If the road edge meets the offset condition, the target vehicle information in the offset direction is obtained. According to the position of the target vehicle, the distance between the target vehicle and the ego vehicle, and the relative speed, it is determined whether the target vehicle affects the ego vehicle offset. If the target vehicle does not affect the ego vehicle offset, the offset target of the ego vehicle in the current scene is calculated. During the deviation process or the deviation driving state, it is continuously determined whether the vehicle meets the return-to-center condition. If the return-to-center condition is met, the return-to-center target of the vehicle is calculated; A path planning module is used to plan an offset path according to an offset target, or to plan a return path according to a return target; Wherein, the path planning module includes: An offset target acquisition unit is used to acquire a corresponding offset target according to the current speed of the vehicle, the distance between the vehicle and the lane line, and the driving behavior map; A control parameter calculation unit is used to set the offset target as the lateral offset distance of the vehicle, and solve the PID control parameters of the offset process to control the offset driving of the vehicle; The motion control module is used to control the vehicle to deviate or return to the center according to the deviation path or the return path.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, the steps of the method for avoiding the road edge in intelligent cruising according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium storing a computer program. It is characterized in that When the computer program is executed, the steps of a method for avoiding a road edge in intelligent cruising as described in any one of claims 1 to 6 are implemented.

Images