Vehicle lane changing control method, device and equipment and computer readable storage medium
By obtaining the longitudinal boundary point of the target lane change gap and calculating the desired speed, the target vehicle is controlled to complete lane change, solving the problem of low lane change success rate and stability in the prior art, and achieving higher lane change success rate and safety.
Patent Information
- Application Number
- CN202411750576.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-02
- Publication Date
- 2025-03-21
- Estimated Expiration
- 2044-12-02
AI Technical Summary
The existing autonomous driving lane change control method focuses on the probability level, ignores the target lane change gap itself, resulting in a low lane change success rate and stability, and is prone to increase the probability of collision with surrounding vehicles.
By obtaining the longitudinal boundary point of the target lane change gap, the desired longitudinal speed of the target vehicle is calculated based on the preset acceleration, and the desired lateral speed is determined through the Bezier curve, so as to control the target vehicle to complete the lane change and enter the target lane change gap.
It effectively improves the success rate and stability of vehicle lane change, reduces the probability of collision with surrounding vehicles, and accurately grasps the lane change timing by considering the attributes of the target lane change gap.
Smart Images
Figure CN119659614A_ABST
Abstract
Description
Technical Field
[0001] The present invention application relates to the field of autonomous driving, and in particular to a vehicle lane change control method, device, equipment and computer-readable storage medium. Background Art
[0002] In the scenario of autonomous driving or assisted driving, some specific application scenarios often involve forced lane changes. For example, after passing a toll station, you need to merge from the auxiliary road to the main road. The auxiliary road is generally a vanishing section, so you need to change lanes to the main road. Commonly used lane change game algorithms include the leader-follower model and the POMDP model, but these methods focus on solving the interaction uncertainty caused by the different cooperation intentions of other vehicles, that is, they mainly improve the success rate of lane changes from a probabilistic level, but often ignore the properties of the target lane change gap itself. The target lane change gap is usually directly related to whether the vehicle changes lanes successfully. Therefore, there is an urgent need for a vehicle lane change control method that can solve the problem that the lane change gap itself is small and affects the lane change success rate. Summary of the invention
[0003] The present invention application provides a vehicle lane change control method, device, equipment and computer-readable storage medium, which can effectively improve the success rate and stability of vehicle lane changes and reduce the probability of collision.
[0004] In order to solve the above technical problems, the present invention provides a vehicle lane change control method, comprising:
[0005] Obtaining the longitudinal boundary point of the target lane change gap;
[0006] Calculating the desired longitudinal speed of the target vehicle according to the longitudinal boundary point and the preset acceleration; the preset acceleration is designed based on the time optimal principle; and determining the desired lateral speed through the Bezier curve;
[0007] Based on the expected longitudinal speed and the expected lateral speed, the target vehicle is controlled to complete the lane change so that the target vehicle enters the target lane change gap.
[0008] In the implementation of the present invention, based on the longitudinal boundary points of the target lane change gap and the preset acceleration, the expected longitudinal speed of the target vehicle is calculated, and the expected lateral speed is determined by the Bezier curve, so as to control the target vehicle to complete the lane change and merge into the target lane change gap. Compared with the existing technology of lane change control based on probability, by considering the properties of the target lane change gap itself to control the vehicle lane change, the timing of the lane change can be grasped, the success rate and stability of the lane change of the target vehicle are effectively improved, and the probability of collision with surrounding vehicles is reduced.
[0009] As a preferred solution, the step of obtaining the longitudinal boundary point of the target lane change gap includes:
[0010] Acquire the current longitudinal speed of the target vehicle, the longitudinal coordinate of the preceding vehicle of the target lane change gap, the current longitudinal speed of the preceding vehicle of the target lane change gap, the longitudinal coordinate of the following vehicle of the target lane change gap, and the current longitudinal speed of the following vehicle of the target lane change gap;
[0011] According to the preset vehicle length and the preset following time distance, in combination with the current longitudinal speed of the target vehicle, the longitudinal coordinate of the leading vehicle and the current longitudinal speed of the leading vehicle, a front boundary point of the target lane change gap is calculated; according to the vehicle length and the following time distance, in combination with the current longitudinal speed of the target vehicle, the longitudinal coordinate of the following vehicle and the current longitudinal speed of the following vehicle, a rear boundary point of the target lane change gap is calculated;
[0012] Based on the front boundary point and the rear boundary point, the longitudinal boundary point is obtained.
[0013] As a preferred solution, the preset acceleration includes a first acceleration and a second acceleration, the first acceleration is a positive value, and the second acceleration is a negative value;
[0014] The step of calculating the expected longitudinal speed of the target vehicle according to the longitudinal boundary point and the preset acceleration includes:
[0015] When the target lane change gap is located in front of the target vehicle, the expected longitudinal speed is calculated according to the following formula:
[0016]
[0017] When the target lane change gap is located behind the target vehicle, the expected longitudinal speed is calculated according to the following formula:
[0018]
[0019] Wherein, f1(x) is the expected longitudinal speed when the target lane change gap is located in front of the target vehicle, f2(x) is the expected longitudinal speed when the target lane change gap is located behind the target vehicle, k1 is the first acceleration, k2 is the second acceleration, x is the current longitudinal displacement of the target vehicle, X1 is the longitudinal coordinate of the front boundary point of the target lane change gap, X2 is the longitudinal coordinate of the rear boundary point of the target lane change gap, V2 is the speed of the target vehicle at the longitudinal coordinate of the front boundary point, V1 is the speed of the target vehicle at the longitudinal coordinate of the rear boundary point, and x m is the longitudinal displacement of the target vehicle when the acceleration is zero.
[0020] As a preferred solution, the controlling the target vehicle to complete the lane change so that the target vehicle enters the target lane change gap includes:
[0021] When the number of the target lane change gaps is greater than one, the costs of the target lane change gaps are calculated respectively by a preset cost function; and the target vehicle is controlled to complete the lane change so that the target vehicle enters the target lane change gap with the minimum cost.
[0022] As a preferred solution, the cost function includes:
[0023] F cost =w1×cost safe +w2×cost efficiency +w3×cost comfort ;
[0024] Among them, F cost is the cost function, cost safe Represents the security cost, cost efficiency Indicates the execution efficiency cost, cost comfort represents the comfort cost, w1, w2 and w3 are the weights of safety cost, execution efficiency cost and comfort cost respectively.
[0025] As a preferred solution, the safety cost is calculated based on the distance between the target vehicle and the vehicle in front of the target vehicle and the longitudinal length of the target lane change gap; the execution efficiency cost is calculated based on the position of the lane change starting point, the position of the lane change ending point, the speed of the target vehicle at the lane change starting point, the speed of the target vehicle at the lane change ending point and the speed of the target vehicle at the initial moment; the comfort cost is calculated based on the variance of the target vehicle, the vehicle in front of the target lane change gap and the vehicle behind the target lane change gap at the same time.
[0026] As a preferred solution, before obtaining the longitudinal boundary point of the target lane change gap, the vehicle lane change control method further includes:
[0027] Obtaining the initial lane change gap;
[0028] When the distance between the target vehicle and the vehicle ahead of the target vehicle, the longitudinal length of the initial lane change gap, the acceleration of the vehicle ahead of the initial lane change gap, and the acceleration of the vehicle behind the initial lane change gap meet preset conditions, the initial lane change gap is determined as the target lane change gap.
[0029] Correspondingly, the present invention also provides a vehicle lane change control device, which includes an acquisition module, a speed determination module and a control module; wherein:
[0030] The acquisition module is used to acquire the longitudinal boundary point of the target lane change gap;
[0031] The speed determination module is used to calculate the expected longitudinal speed of the target vehicle according to the longitudinal boundary point and the preset acceleration; the preset acceleration is designed based on the time optimal principle; and the expected lateral speed is determined by the Bezier curve;
[0032] The control module is used for controlling the target vehicle to complete lane change based on the expected longitudinal speed and the expected lateral speed, so that the target vehicle enters the target lane change gap.
[0033] As a preferred solution, the acquisition module acquires the longitudinal boundary point of the target lane change gap, including:
[0034] The acquisition module acquires the current longitudinal speed of the target vehicle, the longitudinal coordinate of the preceding vehicle of the target lane change gap, the current longitudinal speed of the preceding vehicle of the target lane change gap, the longitudinal coordinate of the following vehicle of the target lane change gap, and the current longitudinal speed of the following vehicle of the target lane change gap;
[0035] According to the preset vehicle length and the preset following time distance, in combination with the current longitudinal speed of the target vehicle, the longitudinal coordinate of the leading vehicle and the current longitudinal speed of the leading vehicle, a front boundary point of the target lane change gap is calculated; according to the vehicle length and the following time distance, in combination with the current longitudinal speed of the target vehicle, the longitudinal coordinate of the following vehicle and the current longitudinal speed of the following vehicle, a rear boundary point of the target lane change gap is calculated;
[0036] Based on the front boundary point and the rear boundary point, the longitudinal boundary point is obtained.
[0037] As a preferred solution, the preset acceleration includes a first acceleration and a second acceleration, the first acceleration is a positive value, and the second acceleration is a negative value;
[0038] The speed determination module calculates the expected longitudinal speed of the target vehicle according to the longitudinal boundary point and the preset acceleration, including:
[0039] When the target lane change gap is located in front of the target vehicle, the speed determination module calculates the expected longitudinal speed according to the following formula:
[0040]
[0041] When the target lane change gap is located behind the target vehicle, the speed determination module calculates the expected longitudinal speed according to the following formula:
[0042]
[0043] Wherein, f1(x) is the expected longitudinal speed when the target lane change gap is located in front of the target vehicle, f2(x) is the expected longitudinal speed when the target lane change gap is located behind the target vehicle, k1 is the first acceleration, k2 is the second acceleration, x is the current longitudinal displacement of the target vehicle, X1 is the longitudinal coordinate of the front boundary point of the target lane change gap, X2 is the longitudinal coordinate of the rear boundary point of the target lane change gap, V2 is the speed of the target vehicle at the longitudinal coordinate of the front boundary point, V1 is the speed of the target vehicle at the longitudinal coordinate of the rear boundary point, and x m is the longitudinal displacement of the target vehicle when the acceleration is zero.
[0044] As a preferred solution, the control module controls the target vehicle to complete the lane change so that the target vehicle enters the target lane change gap, including:
[0045] When the number of the target lane change gaps is greater than one, the control module calculates the cost of each of the target lane change gaps using a preset cost function; and controls the target vehicle to complete the lane change so that the target vehicle enters the target lane change gap with the minimum cost.
[0046] As a preferred solution, the cost function includes:
[0047] F cost =w1×cost safe +w2×cost efficiency +w3×cost comfort ;
[0048] Among them, F cost is the cost function, cost safe Represents the security cost, cost efficiency Indicates the execution efficiency cost, cost comfort represents the comfort cost, w1, w2 and w3 are the weights of safety cost, execution efficiency cost and comfort cost respectively.
[0049] As a preferred solution, the safety cost is calculated based on the distance between the target vehicle and the vehicle in front of the target vehicle and the longitudinal length of the target lane change gap; the execution efficiency cost is calculated based on the position of the lane change starting point, the position of the lane change ending point, the speed of the target vehicle at the lane change starting point, the speed of the target vehicle at the lane change ending point and the speed of the target vehicle at the initial moment; the comfort cost is calculated based on the variance of the target vehicle, the vehicle in front of the target lane change gap and the vehicle behind the target lane change gap at the same time.
[0050] As a preferred solution, the vehicle lane change control device further includes a target lane change gap determination module, and the target lane change gap determination module is used to, before the acquisition module acquires the longitudinal boundary point of the target lane change gap:
[0051] Obtaining the initial lane change gap;
[0052] When the distance between the target vehicle and the vehicle ahead of the target vehicle, the longitudinal length of the initial lane change gap, the acceleration of the vehicle ahead of the initial lane change gap, and the acceleration of the vehicle behind the initial lane change gap meet preset conditions, the initial lane change gap is determined as the target lane change gap.
[0053] Correspondingly, the present application also provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and the processor implements the vehicle lane change control method when executing the computer program.
[0054] Correspondingly, the present application also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the vehicle lane change control method. BRIEF DESCRIPTION OF THE DRAWINGS
[0055] Figure 1 : A flow chart of an embodiment of a vehicle lane change control method provided in the present application.
[0056] Figure 2 : A schematic diagram of a scenario of an embodiment of the vehicle lane change control method provided in the present application.
[0057] Figure 3 : A schematic diagram of a scenario of another embodiment of the vehicle lane change control method provided in the present application.
[0058] Figure 4 : A schematic diagram of an expected longitudinal speed curve of an embodiment of a target lane change gap between car E and car F provided in the present application.
[0059] Figure 5 : A schematic diagram of an expected longitudinal speed curve of an embodiment of a target lane change gap between car E and car D provided in the present application.
[0060] Figure 6 : A schematic diagram of a lane change route of an embodiment of a target lane change gap between car E and car F provided in the present application.
[0061] Figure 7 ; A schematic diagram of a lane change route of an embodiment of a target lane change gap between vehicle E and vehicle D provided in the present application.
[0062] Figure 8 ; A structural schematic diagram of an embodiment of a vehicle lane change control device provided in the present application. DETAILED DESCRIPTION
[0063] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.
[0064] Embodiment 1
[0065] Please refer to Figure 1 , Figure 1 A vehicle lane change control method provided by the present invention includes steps S101 to S103; wherein:
[0066] Step S101, obtaining the longitudinal boundary point of the target lane change gap.
[0067] In this step, the target lane change gap of the lane adjacent to the target vehicle can be determined, and its longitudinal boundary point can be obtained. The target lane change gap refers to the gap available for lane change in the adjacent lane. The longitudinal boundary point refers to the rear position of the vehicle in front of the target lane change gap (front boundary point) and the front position of the vehicle behind the target lane change gap (rear boundary point).
[0068] By determining the front boundary point and the rear boundary point, the longitudinal reachable area of the target lane change gap can be obtained.
[0069] For example, Figure 2 As shown in the figure, A is the target vehicle, or the ego vehicle, and there is a construction section in front of vehicle C. The target lane change gap behind the target vehicle is between vehicle D and vehicle E, and the target lane change gap in front of the target vehicle is between vehicle E and vehicle F. In order to pass normally, vehicle A needs to change lanes to the target lane change gap in front of vehicle E or the target lane change gap behind vehicle E.
[0070] like Figure 3 The figure shows a schematic diagram of a lane change scenario, where A is the target vehicle, the target lane change gap slot1 is the gap between vehicles E and F, and the target lane change gap slot2 is the gap between vehicles E and D. The FLU coordinate system is constructed with the center of the target vehicle A as the origin coordinate. Assume that the length of all vehicles is l obs , with a width of w obs , the longitudinal coordinate of the center of the target vehicle A is x obsA , the horizontal coordinate is y obsA, the longitudinal velocity is v xobsA , the lateral velocity is v yobsA , the longitudinal acceleration is a xobsA , the lateral acceleration is a yobsA .
[0071] The vehicle state parameters of the target vehicle, such as speed and acceleration, can be obtained through the body sensors, and the vehicle state parameters of the remaining vehicles can be obtained through the perception system of the target vehicle. The physical position and safety distance of the vehicle must be considered during the lane change process. The actual accessible space of the target vehicle is the yellow area, and the red dot indicates the center point of the longitudinal boundary of the accessible space.
[0072] In some preferred embodiments, the step of obtaining the longitudinal boundary point of the target lane change gap includes:
[0073] Acquire the current longitudinal speed of the target vehicle, the longitudinal coordinate of the preceding vehicle of the target lane change gap, the current longitudinal speed of the preceding vehicle of the target lane change gap, the longitudinal coordinate of the following vehicle of the target lane change gap, and the current longitudinal speed of the following vehicle of the target lane change gap;
[0074] According to the preset vehicle length and the preset following time distance, in combination with the current longitudinal speed of the target vehicle, the longitudinal coordinate of the leading vehicle and the current longitudinal speed of the leading vehicle, a front boundary point of the target lane change gap is calculated; according to the vehicle length and the following time distance, in combination with the current longitudinal speed of the target vehicle, the longitudinal coordinate of the following vehicle and the current longitudinal speed of the following vehicle, a rear boundary point of the target lane change gap is calculated;
[0075] Based on the front boundary point and the rear boundary point, the longitudinal boundary point is obtained.
[0076] Exemplarily, the longitudinal coordinates of each boundary point include:
[0077] X FE1 =x obsF -l obs -max((v xobsA -v xobsF )×ttc slot , 0);
[0078] X FE2 =x obsE +l obs +max((v xobsE -v xobsA )×ttc slot , 0);
[0079] X ED1 =x obsE -l obs -max((v xobsA-v xobsE )×ttc slot , 0);
[0080] X ED2 =x obsD +l obs +max((v xobsD -v xobsA )×ttc slot , 0);
[0081] X CA =x obsC -l obs -max((v xobsA -v xobsC )×ttc slot , 0);
[0082] X AB =x obsB +l obs +max((v xobsB -v xobsA )×ttc slot , 0);
[0083] Among them, ttc slot Refers to the time to collision (calculated as relative distance divided by relative speed, in seconds), which can be 2; X FE1 , X FE2 , X ED1 , X ED2 , X CA and X AB are the longitudinal coordinates of point FE1, point FE2, point ED1, point ED2, point CA and point AB respectively; xobsF 、v xobsE 、v xobsD 、v xobsC and v xobsB They are the longitudinal velocities of cars F, E, D, C and B respectively.
[0084] In this way, the longitudinal coordinates of the front boundary point and the rear boundary point of the target lane change gap can be calculated, laying the foundation for calculating the expected longitudinal speed of the target vehicle in the subsequent steps.
[0085] Step S102, calculating the expected longitudinal speed of the target vehicle according to the longitudinal boundary point and the preset acceleration; the preset acceleration is designed based on the time optimal principle; and determining the expected lateral speed through the Bezier curve.
[0086] In some embodiments, the preset acceleration includes a first acceleration and a second acceleration, the first acceleration is a positive value, and the second acceleration is a negative value.
[0087] The step of calculating the expected longitudinal speed of the target vehicle according to the longitudinal boundary point and the preset acceleration includes:
[0088] When the target lane change gap is located in front of the target vehicle, the expected longitudinal speed is calculated according to the following formula:
[0089]
[0090] When the target lane change gap is located behind the target vehicle, the expected longitudinal speed is calculated according to the following formula:
[0091]
[0092] Wherein, f1(x) is the expected longitudinal speed when the target lane change gap is located in front of the target vehicle, f2(x) is the expected longitudinal speed when the target lane change gap is located behind the target vehicle, k1 is the first acceleration, k2 is the second acceleration, x is the current longitudinal displacement of the target vehicle, X1 is the longitudinal coordinate of the front boundary point of the target lane change gap, X2 is the longitudinal coordinate of the rear boundary point of the target lane change gap, V2 is the speed of the target vehicle at the longitudinal coordinate of the front boundary point, V1 is the speed of the target vehicle at the longitudinal coordinate of the rear boundary point, and x m is the longitudinal displacement of the target vehicle when the acceleration is zero.
[0093] For example, Figure 4 and 5 As shown, Figure 4 is a schematic diagram of an expected longitudinal speed curve for lane change of the target lane change gap slot1 of this embodiment, Figure 5 Schematic diagram of an expected longitudinal speed curve for lane change of the target lane change gap slot2 of this embodiment.
[0094] In the figure, the horizontal axis represents the longitudinal displacement, and the vertical axis represents the longitudinal velocity. The slope k2 corresponds to the second acceleration of this embodiment, and the slope k1 corresponds to the first acceleration of this embodiment. Figure 4 The target lane change gap FE and the expected lane change longitudinal speed can be specifically expressed as:
[0095]
[0096] Among them, f desireFE (x) is Figure 4 The expected speed of the target lane change gap FE is shown as mis the longitudinal displacement of the target vehicle when the acceleration is zero (at this time, it is the position corresponding to the maximum longitudinal velocity of the target vehicle), x is the current longitudinal displacement of the target vehicle, V xFE1 The target vehicle is at X FE1 The vehicle speed at xFE2 The target vehicle is at X FE2 The vehicle speed at that time.
[0097] Accordingly, Figure 5 Specifically, it can be calculated by the following formula:
[0098]
[0099] Among them, f desireED (x) is Figure 5 The expected speed of the target lane change gap ED, X m is the longitudinal displacement of the target vehicle when the acceleration is zero (at this time, it is the position corresponding to the minimum longitudinal velocity of the target vehicle), x is the current longitudinal displacement of the target vehicle, V xED1 The target vehicle is at X ED1 The vehicle speed at xED2 The target vehicle is at X ED2 The vehicle speed at that time.
[0100] like Figure 6 and 7 As shown, it can be understood that for the target lane change gap between car E and car F, the target vehicle starts from the initial moment, first accelerates with the first acceleration k1 to reach the lane change starting point sPoint, and then decelerates with the second acceleration k2 to reach the lane change ending point ePoint. Figure 4 Medium X FE1 With X FE2 The corresponding speed between is the longitudinal speed of the target vehicle. For the target lane change gap between vehicle E and vehicle D, the target vehicle first decelerates at the second acceleration k2 to reach the lane change starting point sPoint, and then accelerates at the first acceleration k1 until it reaches the lane change ending point ePoint. Figure 5 Medium X ED1 With X ED2 The corresponding speed between is the longitudinal speed of the target vehicle. The value range of k1 is [0.5, 1.5], and the value range of k2 is [-1.5, -0.5]. Both are calibrable values and can be calibrated according to the degree of aggressiveness.
[0101] The expected lateral velocity can be determined by the Bezier curve in the prior art.
[0102] Assume the first acceleration k1 = 1 m / s 2 , the second acceleration k2 = -1m / s 2For the target lane change gap between car E and car F, the longitudinal coordinates of sPoint and ePoint and the corresponding longitudinal speed can be obtained:
[0103] X sPoint =min((X CA +X FE1 ) / 2,(X FE1 +X FE2 ) / 2);
[0104] X ePoint =min((X CA +X FE2 ) / 2,X FE2 );
[0105] V ePoint =f desireFE (X ePoint );
[0106]
[0107] Among them, X sPoint is the vertical coordinate of point sPoint, X ePoint is the vertical coordinate of point ePoint, V ePoint is the longitudinal velocity of point ePoint, V sPoint It is the longitudinal velocity of point sPoint.
[0108] Similarly, for the target lane change gap between car E and car D, the longitudinal coordinates of sPoint and ePoint and the corresponding longitudinal speed can be obtained:
[0109] X sPoint =min((X AB +X ED1 ) / 2,(X ED1 +X ED2 ) / 2);
[0110] X ePoint =min((X AB +X ED2 ) / 2,X ED2 );
[0111] V ePoint =f desireED (X ePoint );
[0112]
[0113] Based on the above determined desired longitudinal speed and the desired lateral speed, control parameters for the target vehicle in step S103 may be determined.
[0114] Step S103: Based on the expected longitudinal speed and the expected lateral speed, controlling the target vehicle to complete lane change, so that the target vehicle enters the target lane change gap.
[0115] In this step, when the number of the target lane change gaps is greater than one, the cost of each target lane change gap can be calculated separately by a preset cost function; and the target vehicle is controlled to complete the lane change so that the target vehicle enters the target lane change gap with the minimum cost.
[0116] Exemplarily, the cost function includes:
[0117] F cost =w1×cost safe +w2×cost efficiency +w3×cost comfort ;
[0118] Among them, F cost is the cost function, cost safe Represents the security cost, cost efficiency Indicates the execution efficiency cost, cost comfort represents the comfort cost, w1, w2 and w3 are the weights of safety cost, execution efficiency cost and comfort cost respectively, and the weights can be calibrated values.
[0119] The safety cost is calculated based on the distance between the target vehicle and the vehicle in front of the target vehicle and the longitudinal length of the target lane change gap; the execution efficiency cost is calculated based on the position of the lane change starting point, the position of the lane change ending point, the speed of the target vehicle at the lane change starting point, the speed of the target vehicle at the lane change ending point and the speed of the target vehicle at the initial moment; the comfort cost is calculated based on the variance of the target vehicle, the vehicle in front of the target lane change gap and the vehicle behind the target lane change gap at the same time.
[0120] For example, taking the target lane change gap between car E and car F as an example, the safety cost can be:
[0121] cost safe =0.2×(X CA -X FE1 )+0.1×(X FE2 -X CA )+0.3×X CA +0.4×(X FE2 -X FE1 );
[0122] Among them, cost safeis the safety cost, which may indicate the safety of the target lane change gap, Figure 3 The larger the space between E and F (or the longitudinal length of the target lane change gap EF), the safer it is.
[0123] The execution efficiency cost can be expressed as:
[0124] cost efficiency =|2×X sPoint / (V0+V sPoint )|+|2×(X ePoint -X sPoint ) / (V sPoint +V ePoint )|;
[0125] Among them, cost efficiency represents the execution efficiency cost, and V0 represents the speed of the target vehicle at the initial moment of lane change. The execution efficiency cost mainly refers to the time consumed in the entire lane change process.
[0126] The comfort cost can be expressed as:
[0127] cost comfort =D(V A ,V F ,V E );
[0128] Among them, V A 、V F and V E They are respectively represented as the speed of the target vehicle, vehicle F and vehicle E, and cost comfort represents the comfort cost, and D represents the variance.
[0129] The calculation method of the safety cost, execution efficiency cost and comfort cost of the target lane change gap between car D and car E is similar to the calculation method of the target lane change gap between car E and car F, and will not be repeated in this embodiment.
[0130] After the costs of each target lane change gap are calculated by the cost function, the target lane change gap with the minimum cost can be selected for the lane change of the target vehicle.
[0131] In some preferred embodiments, before step S101, the vehicle lane change control method may further include: obtaining an initial lane change gap; when the distance between the target vehicle and the vehicle in front of the target vehicle, the longitudinal length of the initial lane change gap, the acceleration of the vehicle in front of the initial lane change gap, and the acceleration of the vehicle behind the initial lane change gap meet preset conditions, determining the initial lane change gap as the target lane change gap.
[0132] For example, for the target lane change gap between car E and car F, the conditions satisfied can be specifically expressed as:
[0133] X FE2 -X FE1 >15 (in meters);
[0134] X CA >X FE1 ;
[0135] a F +0.3×(X FE2 -X sPoint )>-0.5(Unit: m / s 2 );
[0136] a E +0.3×(X xPoint -X FE1 )<0.5(Unit: m / s 2 );
[0137] Among them, a E and a F are the accelerations of car E and car F, respectively. The conditions that need to be met for the remaining lane change gaps can be derived by similar reasoning from the expression of the target lane change gap between car E and car F, and will not be described in detail in this embodiment. By screening the initial lane change gap through the above preferred implementation, a target lane change gap that meets the requirements is obtained, which can further improve the safety of lane change.
[0138] Correspondingly, such as Figure 8 As shown, the present invention also provides a vehicle lane change control device 800, which includes an acquisition module 801, a speed determination module 802 and a control module 803; wherein,
[0139] The acquisition module 801 is used to acquire the longitudinal boundary point of the target lane change gap;
[0140] The speed determination module 802 is used to calculate the expected longitudinal speed of the target vehicle according to the longitudinal boundary point and the preset acceleration; the preset acceleration is designed based on the time optimal principle; and the expected lateral speed is determined by the Bezier curve;
[0141] The control module 803 is used for controlling the target vehicle to complete lane change based on the expected longitudinal speed and the expected lateral speed, so that the target vehicle enters the target lane change gap.
[0142] As a preferred solution, the acquisition module 801 acquires the longitudinal boundary point of the target lane change gap, including:
[0143] The acquisition module 801 acquires the current longitudinal speed of the target vehicle, the longitudinal coordinate of the preceding vehicle of the target lane change gap, the current longitudinal speed of the preceding vehicle of the target lane change gap, the longitudinal coordinate of the following vehicle of the target lane change gap, and the current longitudinal speed of the following vehicle of the target lane change gap;
[0144] According to the preset vehicle length and the preset following time distance, in combination with the current longitudinal speed of the target vehicle, the longitudinal coordinate of the leading vehicle and the current longitudinal speed of the leading vehicle, a front boundary point of the target lane change gap is calculated; according to the vehicle length and the following time distance, in combination with the current longitudinal speed of the target vehicle, the longitudinal coordinate of the following vehicle and the current longitudinal speed of the following vehicle, a rear boundary point of the target lane change gap is calculated;
[0145] Based on the front boundary point and the rear boundary point, the longitudinal boundary point is obtained.
[0146] As a preferred solution, the preset acceleration includes a first acceleration and a second acceleration, the first acceleration is a positive value, and the second acceleration is a negative value;
[0147] The speed determination module 802 calculates the expected longitudinal speed of the target vehicle according to the longitudinal boundary point and the preset acceleration, including:
[0148] When the target lane change gap is located in front of the target vehicle, the speed determination module 802 calculates the expected longitudinal speed according to the following formula:
[0149]
[0150] When the target lane change gap is located behind the target vehicle, the speed determination module 802 calculates the expected longitudinal speed according to the following formula:
[0151]
[0152] Wherein, f1(x) is the expected longitudinal speed when the target lane change gap is located in front of the target vehicle, f2(x) is the expected longitudinal speed when the target lane change gap is located behind the target vehicle, k1 is the first acceleration, k2 is the second acceleration, x is the current longitudinal displacement of the target vehicle, X1 is the longitudinal coordinate of the front boundary point of the target lane change gap, X2 is the longitudinal coordinate of the rear boundary point of the target lane change gap, V2 is the speed of the target vehicle at the longitudinal coordinate of the front boundary point, V1 is the speed of the target vehicle at the longitudinal coordinate of the rear boundary point, and x m is the longitudinal displacement of the target vehicle when the acceleration is zero.
[0153] As a preferred solution, the control module 803 controls the target vehicle to complete the lane change so that the target vehicle enters the target lane change gap, including:
[0154] When the number of the target lane change gaps is greater than one, the control module 803 calculates the cost of each of the target lane change gaps using a preset cost function, and controls the target vehicle to complete the lane change so that the target vehicle enters the target lane change gap with the minimum cost.
[0155] As a preferred solution, the cost function includes:
[0156] F cost =w1×cost safe +w2×cost efficiency +w3×cost comfort ;
[0157] Among them, F cost is the cost function, cost safe Represents the security cost, cost efficiency Indicates the execution efficiency cost, cost comfort represents the comfort cost, w1, w2 and w3 are the weights of safety cost, execution efficiency cost and comfort cost respectively.
[0158] As a preferred solution, the safety cost is calculated based on the distance between the target vehicle and the vehicle in front of the target vehicle and the longitudinal length of the target lane change gap; the execution efficiency cost is calculated based on the position of the lane change starting point, the position of the lane change ending point, the speed of the target vehicle at the lane change starting point, the speed of the target vehicle at the lane change ending point and the speed of the target vehicle at the initial moment; the comfort cost is calculated based on the variance of the target vehicle, the vehicle in front of the target lane change gap and the vehicle behind the target lane change gap at the same time.
[0159] As a preferred solution, the vehicle lane change control device 800 further includes a target lane change gap determination module, and the target lane change gap determination module is used to, before the acquisition module 801 acquires the longitudinal boundary point of the target lane change gap:
[0160] Obtaining the initial lane change gap;
[0161] When the distance between the target vehicle and the vehicle ahead of the target vehicle, the longitudinal length of the initial lane change gap, the acceleration of the vehicle ahead of the initial lane change gap, and the acceleration of the vehicle behind the initial lane change gap meet preset conditions, the initial lane change gap is determined as the target lane change gap.
[0162] Correspondingly, the present application also provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and the processor implements the vehicle lane change control method when executing the computer program.
[0163] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal, and various interfaces and lines are used to connect various parts of the entire terminal.
[0164] The memory can be used to store the computer program, and the processor realizes various functions of the terminal by running or executing the computer program stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can 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 can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.
[0165] Correspondingly, the present application also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the vehicle lane change control method.
[0166] Wherein, if the module integrated in the vehicle lane change control device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.
[0167] Compared with the prior art, the embodiments of the present invention have at least the following beneficial effects:
[0168] The embodiment of the present invention provides a vehicle lane change control method, device, equipment and computer-readable storage medium, the method comprising: obtaining the longitudinal boundary point of the target lane change gap; calculating the expected longitudinal speed of the target vehicle according to the longitudinal boundary point and the preset acceleration; the preset acceleration is designed based on the time optimal principle; and determining the expected lateral speed through the Bezier curve; based on the expected longitudinal speed and the expected lateral speed, controlling the target vehicle to complete the lane change so that the target vehicle enters the target lane change gap. In the implementation of the embodiment of the present invention, based on the longitudinal boundary point of the target lane change gap and the preset acceleration, the expected longitudinal speed of the target vehicle is calculated, and the expected lateral speed is determined through the Bezier curve, so as to control the target vehicle to complete the lane change and merge into the target lane change gap. Compared with the existing technology of lane change control based on probability, by considering the properties of the target lane change gap itself to control the vehicle to change lanes, the timing of lane change can be grasped, the success rate and stability of lane change of the target vehicle can be effectively improved, and the probability of collision with surrounding vehicles can be reduced.
[0169] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.
Claims
1. A vehicle lane change control method, characterized in that: include: Obtaining the longitudinal boundary point of the target lane change gap; Calculating a desired longitudinal velocity of the target vehicle based on the longitudinal boundary point and the preset acceleration; The preset acceleration is designed based on the time optimization principle; and the expected lateral speed is determined by the Bezier curve; Based on the expected longitudinal speed and the expected lateral speed, the target vehicle is controlled to complete the lane change so that the target vehicle enters the target lane change gap.
2. A vehicle lane change control method as claimed in claim 1, characterized in that: The step of obtaining the longitudinal boundary point of the target lane change gap includes: Acquire the current longitudinal speed of the target vehicle, the longitudinal coordinate of the preceding vehicle of the target lane change gap, the current longitudinal speed of the preceding vehicle of the target lane change gap, the longitudinal coordinate of the following vehicle of the target lane change gap, and the current longitudinal speed of the following vehicle of the target lane change gap; According to the preset vehicle length and the preset following time distance, in combination with the current longitudinal speed of the target vehicle, the longitudinal coordinate of the leading vehicle and the current longitudinal speed of the leading vehicle, a front boundary point of the target lane change gap is calculated; according to the vehicle length and the following time distance, in combination with the current longitudinal speed of the target vehicle, the longitudinal coordinate of the following vehicle and the current longitudinal speed of the following vehicle, a rear boundary point of the target lane change gap is calculated; Based on the front boundary point and the rear boundary point, the longitudinal boundary point is obtained.
3. A vehicle lane change control method as claimed in claim 2, characterized in that: The preset acceleration includes a first acceleration and a second acceleration, the first acceleration is a positive value, and the second acceleration is a negative value; The step of calculating the expected longitudinal speed of the target vehicle according to the longitudinal boundary point and the preset acceleration includes: When the target lane change gap is located in front of the target vehicle, the expected longitudinal speed is calculated according to the following formula: When the target lane change gap is located behind the target vehicle, the expected longitudinal speed is calculated according to the following formula: Wherein, f1(x) is the expected longitudinal speed when the target lane change gap is located in front of the target vehicle, f2(x) is the expected longitudinal speed when the target lane change gap is located behind the target vehicle, k1 is the first acceleration, k2 is the second acceleration, x is the current longitudinal displacement of the target vehicle, X1 is the longitudinal coordinate of the front boundary point of the target lane change gap, X2 is the longitudinal coordinate of the rear boundary point of the target lane change gap, V2 is the speed of the target vehicle at the longitudinal coordinate of the front boundary point, V1 is the speed of the target vehicle at the longitudinal coordinate of the rear boundary point, and x m is the longitudinal displacement of the target vehicle when the acceleration is zero.
4. A vehicle lane change control method as claimed in claim 1, characterized in that: The controlling the target vehicle to complete the lane change so that the target vehicle enters the target lane change gap includes: When the number of the target lane change gaps is greater than one, the costs of the target lane change gaps are calculated respectively by a preset cost function; and the target vehicle is controlled to complete the lane change so that the target vehicle enters the target lane change gap with the minimum cost.
5. A vehicle lane change control method as claimed in claim 4, characterized in that: The cost function includes: F cost =w1×cost safe +w2×cost efficiency +w3×cost comfort ; Among them, F cost is the cost function, cost safe Represents the security cost, cost efficiency Indicates the execution efficiency cost, cost comfort represents the comfort cost, w1, w2 and w3 are the weights of safety cost, execution efficiency cost and comfort cost respectively.
6. A vehicle lane change control method as claimed in claim 5, characterized in that: The safety cost is calculated based on the distance between the target vehicle and the vehicle in front of the target vehicle and the longitudinal length of the target lane change gap; The execution efficiency cost is calculated based on the position of the lane change starting point, the position of the lane change ending point, the speed of the target vehicle at the lane change starting point, the speed of the target vehicle at the lane change ending point, and the speed of the target vehicle at the initial moment; The comfort cost is calculated according to the variance of the target vehicle, a preceding vehicle of the target lane change gap, and a following vehicle of the target lane change gap at the same time.
7. A vehicle lane change control method as claimed in claim 1, characterized in that: Before obtaining the longitudinal boundary point of the target lane change gap, the vehicle lane change control method further includes: Obtaining the initial lane change gap; When the distance between the target vehicle and the vehicle ahead of the target vehicle, the longitudinal length of the initial lane change gap, the acceleration of the vehicle ahead of the initial lane change gap, and the acceleration of the vehicle behind the initial lane change gap meet preset conditions, the initial lane change gap is determined as the target lane change gap.
8. A vehicle lane change control device, characterized in that: The vehicle lane change control device includes an acquisition module, a speed determination module and a control module; wherein, The acquisition module is used to acquire the longitudinal boundary point of the target lane change gap; The speed determination module is used to calculate the expected longitudinal speed of the target vehicle according to the longitudinal boundary point and the preset acceleration; the preset acceleration is designed based on the time optimal principle; and the expected lateral speed is determined by the Bezier curve; The control module is used for controlling the target vehicle to complete lane change based on the expected longitudinal speed and the expected lateral speed, so that the target vehicle enters the target lane change gap.
9. A terminal device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the vehicle lane change control method as claimed in any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the vehicle lane change control method according to any one of claims 1 to 7.