A method and device for autonomous driving planning transition

Abstract

This application provides an autonomous driving planning transition method and device, which includes: when a target vehicle is in a line-following state, obtaining a line-following path and a vehicle-following path; when the current lane line is about to disappear, performing a first-stage planning transition control on the target vehicle from line-following driving to vehicle-following driving; when the current lane line completely disappears, performing a second-stage planning transition control on the target vehicle from line-following driving to vehicle-following driving; and when the second-stage planning transition control is determined to be completed, determining that the target vehicle enters a fully vehicle-following autonomous driving state. This method and device can integrate lane line and leading vehicle trajectory planning information to achieve a smooth transition, thereby effectively improving the stability and smoothness of autonomous driving at intersections or on roads with blurred lane lines.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and more specifically, to a method and device for autonomous driving planning transition. Background Art

[0002] Currently, with the continuous development of autonomous driving technology, Level 2 autonomous driving systems have been widely used in the market. However, these systems often experience functional exit issues in road conditions where lane markings are blurred or absent, such as when crossing intersections, which affects driving continuity and safety. To optimize this situation, some Level 2 autonomous driving systems have introduced a function called "follow the trajectory of the preceding vehicle." This function can plan based on the trajectory of the preceding vehicle when lane markings are unclear, thereby maintaining autonomous driving. However, in actual applications, when the system switches from following lane markings (line following) to following the preceding vehicle (car following), the planned trajectory often changes suddenly, affecting the smoothness of the vehicle's driving and even posing a potential driving safety hazard. Summary of the Invention

[0003] The purpose of the embodiments of the present application is to provide an autonomous driving planning transition method and device that can integrate lane lines and trajectory planning information of the preceding vehicle to achieve a smooth transition, thereby effectively improving the stability and smoothness of autonomous driving at intersections or sections with blurred lane lines.

[0004] In a first aspect, the present application provides an autonomous driving planning transition method, comprising:

[0005] When the target vehicle is in the line-following state, obtain the line-following path and vehicle-following path output by the planning module;

[0006] Get the left and right lane line perception data of the current lane line in real time;

[0007] When it is determined based on the left and right lane line sensing data that the current lane line is about to disappear, obtaining a current first moment and a first vehicle speed of the target vehicle at the first moment;

[0008] Acquire a first line-following path coefficient at the first moment and a first vehicle-following path coefficient at the first moment according to the line-following path and the vehicle-following path;

[0009] Performing a timed dynamic transition calculation based on the first vehicle speed, the first line-following path coefficient, and the first vehicle-following path coefficient to obtain a first target path coefficient and a first weighted average value in a transition state;

[0010] Performing a first-stage planning transition control from line-following driving to vehicle-following driving on the target vehicle based on the first target path coefficient and the first weighted average value;

[0011] When the target vehicle detects that the current lane line completely disappears, obtaining a second moment when the current lane line completely disappears, a first target path coefficient for performing first-stage planned transition control on the target vehicle at the second moment, a second following path coefficient at the second moment, and a preset fixed transition time;

[0012] Performing a timed dynamic transition calculation based on the first target path coefficient, the second following path coefficient, the second following path coefficient, and the fixed transition time at the second moment to obtain a second target path coefficient and a second weighted average value in a transition state;

[0013] Performing a second-stage planning transition control from line-following driving to vehicle-following driving on the target vehicle based on the second target path coefficient;

[0014] When the second target path coefficient reaches the second weighted average value, it is determined that the second stage planning transition control is completed, and it is determined that the target vehicle enters a fully following automatic driving state.

[0015] Furthermore, obtaining the line-following path and the vehicle-following path output by the planning module includes:

[0016] Obtain lane line information and the previous vehicle's historical driving trajectory;

[0017] Obtain left and right lane lines according to the lane line information;

[0018] Calculating a line-following path based on the left and right lane lines and the planning module of the target vehicle;

[0019] A following vehicle path is calculated based on the historical driving trajectory of the preceding vehicle and the planning module; wherein the line-following path and the following vehicle path are both path functions represented by cubic polynomials.

[0020] Furthermore, after acquiring the left and right lane line sensing data of the current lane line in real time, the method further includes:

[0021] Determining the effective lengths of the left and right lane lines based on the left and right lane line perception data;

[0022] Determining whether the effective lengths of the left and right lane lines are less than a preset length threshold;

[0023] If yes, it is determined that the lane line is about to disappear, and the step of obtaining the current first moment and the first vehicle speed of the target vehicle at the first moment is performed.

[0024] Furthermore, performing a timed dynamic transition calculation based on the first vehicle speed, the first line-following path coefficient, and the first vehicle-following path coefficient to obtain a first target path coefficient and a first weighted average value in a transition state includes:

[0025] Calculating a theoretical time for lane markings to disappear based on the effective lengths of the left and right lane markings and the first vehicle speed;

[0026] Determining a transition time based on the lane line disappearance theoretical time;

[0027] Calculating a first weighted average of the first line-following path coefficient and the first vehicle-following path coefficient according to a preset weighting formula and a preset weighting coefficient;

[0028] Obtaining the current control software operation cycle and determining the first historical target path coefficient of the previous control software operation cycle;

[0029] Calculating a first transition amount of the current control software operation cycle according to the current control software operation cycle, the transition time, the first weighted average value, and the first tracking path coefficient;

[0030] The first target path coefficient of the current control software operation cycle is calculated according to the first transition amount and the first historical target path coefficient.

[0031] Furthermore, the first stage planning transition control from line following driving to vehicle following driving of the target vehicle based on the first target path coefficient and the first weighted average value includes:

[0032] Performing a first-stage planning transition control from line-following driving to vehicle-following driving on the target vehicle based on the first target path coefficient;

[0033] determining whether the first target path coefficient reaches the first weighted average value;

[0034] If no, it is determined that the first phase of planning transition has not been completed;

[0035] The current first target path coefficient is determined as the first historical target path coefficient, and the first target path coefficient of the current control software operation cycle is calculated based on the first transition amount and the first historical target path coefficient.

[0036] Furthermore, the method further comprises:

[0037] When the target vehicle detects the lane line again, the fully following automatic driving state ends and enters a transition state from following the vehicle to following the line;

[0038] Obtaining a third moment when the lane line is redetected, a starting distance between the target vehicle and the lane line at the third moment, and a second vehicle speed of the target vehicle at the third moment;

[0039] Calculating the remaining time for the target vehicle to reach the lane line based on the second vehicle speed and the starting distance;

[0040] Acquire a third target path coefficient for driving control of the target vehicle at the third moment and a second tracking path coefficient at the third moment;

[0041] performing a timed dynamic transition calculation based on the second vehicle speed, the second line-following path coefficient, and the third target path coefficient to obtain a fourth target path coefficient and a third weighted average value in a transition state;

[0042] Planning transition control from vehicle-following driving to line-following driving is performed on the target vehicle based on the fourth target path coefficient and the third weighted average value.

[0043] Furthermore, performing a timed dynamic transition calculation based on the second vehicle speed, the second following path coefficient, and the third target path coefficient to obtain a fourth target path coefficient and a third weighted average value in a transition state includes:

[0044] Calculating a third weighted average of the third target path coefficient and the second line path coefficient according to the weighting formula and the weighting coefficient;

[0045] Determine a second historical target path coefficient for the last control software operation cycle;

[0046] Calculating a second transition amount according to the current control software operation cycle, the remaining time of the lane line, the third weighted average value, and the third target path coefficient;

[0047] A fourth target path coefficient of the current control software operation cycle is calculated based on the second transition amount and the second historical target path coefficient.

[0048] Furthermore, the planning transition control of the target vehicle from vehicle-following driving to line-following driving based on the fourth target path coefficient and the third weighted average value includes:

[0049] performing planned transition control on the target vehicle from vehicle-following driving to line-following driving based on the fourth target path coefficient;

[0050] determining whether the fourth target path coefficient reaches the third weighted average value;

[0051] If no, it is determined that the planned transition has not been completed;

[0052] The current fourth target path coefficient is determined as the second historical target path coefficient, and the fourth target path coefficient of the current control software operation cycle is calculated based on the second transition amount and the second historical target path coefficient.

[0053] A second aspect of the present application provides an autonomous driving planning transition device, the autonomous driving planning transition device comprising:

[0054] A first acquisition unit is used to acquire the line-following path and the vehicle-following path output by the planning module when the target vehicle is in a line-following state;

[0055] The second acquisition unit is used to obtain the left and right lane line perception data of the current lane line in real time;

[0056] a third acquiring unit, configured to acquire a first current moment and a first vehicle speed of the target vehicle at the first moment when it is determined based on the left and right lane line sensing data that the current lane line is about to disappear;

[0057] a fourth acquiring unit, configured to acquire a first line-following path coefficient and a first vehicle-following path coefficient at the first moment according to the line-following path and the vehicle-following path;

[0058] a first calculation unit, configured to perform a timed dynamic transition calculation based on the first ego vehicle speed, the first line-following path coefficient, and the first vehicle-following path coefficient, to obtain a first target path coefficient and a first weighted average value in a transition state;

[0059] a first transition control unit, configured to perform a first-stage planning transition control from line-following driving to vehicle-following driving on the target vehicle based on the first target path coefficient and the first weighted average value;

[0060] a fifth acquisition unit, configured to, when the target vehicle detects that the current lane line completely disappears, acquire a second moment when the current lane line completely disappears, a first target path coefficient for performing first-stage planned transition control on the target vehicle at the second moment, a second following path coefficient at the second moment, and a preset fixed transition time;

[0061] a second calculation unit, configured to perform a timed dynamic transition calculation based on the first target path coefficient, the second following path coefficient, the second following path coefficient, and the fixed transition time at the second moment, to obtain a second target path coefficient and a second weighted average value in a transition state;

[0062] a second transition control unit, configured to perform a second-stage planning transition control from line-following driving to vehicle-following driving on the target vehicle based on the second target path coefficient;

[0063] The first determination unit is used to determine that the second stage planning transition control is completed when the second target path coefficient reaches the second weighted average value, and to determine that the target vehicle enters a fully following automatic driving state.

[0064] Furthermore, the first acquiring unit includes:

[0065] The first acquisition subunit is used to obtain lane line information and the historical driving trajectory of the preceding vehicle;

[0066] The first acquisition subunit is further configured to acquire left and right lane lines according to the lane line information;

[0067] A first calculation subunit, configured to calculate a line-following path according to the left and right lane lines and a planning module of the target vehicle;

[0068] The first calculation subunit is further configured to calculate a following vehicle path based on the preceding vehicle's historical driving trajectory and the planning module; wherein the following line path and the following vehicle path are both path functions represented by cubic polynomials.

[0069] Furthermore, the autonomous driving planning transition device further includes:

[0070] a second determining unit, configured to determine effective lengths of the left and right lane lines according to the left and right lane line sensing data after the second acquiring unit acquires the left and right lane line sensing data of the current lane line in real time;

[0071] The judgment unit is used to determine whether the effective length of the left and right lane lines is less than a preset length threshold; if so, it is determined that the lane lines are about to disappear, and the third acquisition unit is triggered to execute the operation of acquiring the current first moment and the first vehicle speed of the target vehicle at the first moment.

[0072] Furthermore, the first calculation unit includes:

[0073] a second calculation subunit, configured to calculate a theoretical lane line disappearance time based on the effective lengths of the left and right lane lines and the speed of the first vehicle;

[0074] A first determining subunit is configured to determine a transition time based on the lane line disappearance theoretical time;

[0075] The second calculation subunit is further configured to calculate a first weighted average value of the first line-following path coefficient and the first vehicle-following path coefficient according to a preset weighting formula and a preset weighting coefficient;

[0076] A second acquisition subunit is used to acquire the current control software operation cycle and determine the first historical target path coefficient of the previous control software operation cycle;

[0077] The second calculation subunit is further configured to calculate a first transition amount of the current control software operation cycle according to the current control software operation cycle, the transition time, the first weighted average value, and the first tracking path coefficient;

[0078] The second calculation subunit is further configured to calculate a first target path coefficient of the current control software operation cycle based on the first transition amount and the first historical target path coefficient.

[0079] Furthermore, the first transition control unit includes:

[0080] a first transition subunit, configured to perform a first stage planning transition control from line-following driving to vehicle-following driving on the target vehicle based on the first target path coefficient;

[0081] a first judging subunit, configured to judge whether the first target path coefficient reaches the first weighted average value;

[0082] a second determining subunit, configured to determine that the first stage planning transition is not completed when the first target path coefficient does not reach the first weighted average value;

[0083] The second determination subunit is also used to determine the current first target path coefficient as the first historical target path coefficient, and trigger the second calculation subunit to perform the operation of calculating the first target path coefficient of the current control software operation cycle based on the first transition amount and the first historical target path coefficient.

[0084] Furthermore, the autonomous driving planning transition device further includes:

[0085] an ending unit, configured to end the fully vehicle-following automatic driving state and enter a transition state from vehicle-following driving to line-following driving when the target vehicle re-detects the lane line;

[0086] a sixth acquiring unit, configured to acquire a third moment when the lane line is re-detected, a starting distance between the target vehicle and the lane line at the third moment, and a second vehicle speed of the target vehicle at the third moment;

[0087] a third calculation unit, configured to calculate a remaining time for the target vehicle to reach the lane line based on the second vehicle speed and the starting distance;

[0088] The sixth acquisition unit is further configured to acquire a third target path coefficient for driving control of the target vehicle at the third moment and a second line path coefficient at the third moment;

[0089] The third calculation unit is further configured to perform a timed dynamic transition calculation based on the second vehicle speed, the second line-following path coefficient, and the third target path coefficient to obtain a fourth target path coefficient and a third weighted average value in a transition state;

[0090] A third transition control unit is used to perform planning transition control on the target vehicle from vehicle-following driving to line-following driving based on the fourth target path coefficient and the third weighted average value.

[0091] Furthermore, the third calculation unit includes:

[0092] a third calculation subunit, configured to calculate a third weighted average value of the third target path coefficient and the second line path coefficient according to the weighted formula and the weighted coefficient;

[0093] A third determining subunit is used to determine a second historical target path coefficient of a previous control software operation cycle;

[0094] The third calculation subunit is further configured to calculate a second transition amount based on the current control software operation cycle, the remaining time of the lane line, the third weighted average value, and the third target path coefficient;

[0095] The third calculation subunit is further used to calculate the fourth target path coefficient of the current control software operation cycle based on the second transition amount and the second historical target path coefficient.

[0096] Furthermore, the third transition control unit includes:

[0097] a second transition subunit, configured to perform planned transition control on the target vehicle from vehicle-following driving to line-following driving based on the fourth target path coefficient;

[0098] a second judging subunit, configured to judge whether the fourth target path coefficient reaches the third weighted average value;

[0099] a fourth determining subunit, configured to determine that the planned transition is not completed when the fourth target path coefficient does not reach the third weighted average value;

[0100] The fourth determination subunit is also used to determine the current fourth target path coefficient as the second historical target path coefficient, and trigger the third calculation subunit to perform the operation of calculating the fourth target path coefficient of the current control software operation cycle based on the second transition amount and the second historical target path coefficient.

[0101] A third aspect of the present application provides an electronic device comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the autonomous driving planning transition method described in any one of the first aspects of the present application.

[0102] In a fourth aspect, the present application provides a computer-readable storage medium storing computer program instructions. When the computer program instructions are read and executed by a processor, the autonomous driving planning transition method described in any one of the first aspects of the present application is executed.

[0103] The beneficial effects of the present application are: the method and device can calculate the time that can be used for planning mode switching based on the starting distance and effective length information of the lane line, so as to perform smooth and seamless switching between following the line and following the vehicle, thereby helping the L2 autonomous driving function to pass through intersections or sections with blurred lane lines, and improving the stability and smoothness of the intelligent driving function. BRIEF DESCRIPTION OF THE DRAWINGS

[0104] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0105] Figure 1 A flowchart of an autonomous driving planning transition method provided in an embodiment of the present application;

[0106] Figure 2 A flowchart of another autonomous driving planning transition method provided in an embodiment of the present application;

[0107] Figure 3 A schematic diagram of the structure of an autonomous driving planning transition device provided in an embodiment of the present application;

[0108] Figure 4 A schematic diagram of the structure of another autonomous driving planning transition device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0109] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0110] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and should not be understood as indicating or implying relative importance.

[0111] Example 1

[0112] Please see Figure 1 , Figure 1 This is a flow chart of an autonomous driving planning transition method provided in this embodiment. The autonomous driving planning transition method includes:

[0113] S101. When the target vehicle is in a line-following state, obtain a line-following path and a vehicle-following path output by a planning module.

[0114] S102: Acquire the left and right lane line perception data of the current lane line in real time.

[0115] S103: When it is determined based on the left and right lane line perception data that the current lane line is about to disappear, obtain the first vehicle speed at the current moment and the first vehicle speed of the target vehicle at the first moment.

[0116] S104: Obtain a first line-following path coefficient at a first moment and a first vehicle-following path coefficient at a first moment according to the line-following path and the vehicle-following path.

[0117] In this embodiment, the first tracking line path coefficient is used to indicate that each tracking line path coefficient at time Ts1 is an initial value Init.

[0118] S105 , performing a timed dynamic transition calculation based on the first own vehicle speed, the first line-following path coefficient, and the first vehicle-following path coefficient to obtain a first target path coefficient and a first weighted average value in a transition state.

[0119] S106 , performing first-stage planning transition control from line-following driving to vehicle-following driving on the target vehicle based on the first target path coefficient and the first weighted average value.

[0120] S107. When the target vehicle detects that the current lane line completely disappears, obtain the second moment when the current lane line completely disappears, the first target path coefficient for performing the first stage planned transition control on the target vehicle at the second moment, the second following path coefficient at the second moment, and the preset fixed transition time.

[0121] S108. Perform a timed dynamic transition calculation based on the first target path coefficient, the second following vehicle path coefficient, the second following vehicle path coefficient, and the fixed transition time at the second moment to obtain the second target path coefficient and the second weighted average value in the transition state.

[0122] S109: Perform second-stage planning transition control from line-following driving to vehicle-following driving on the target vehicle based on the second target path coefficient.

[0123] S110. When the second target path coefficient reaches the second weighted average value, it is determined that the second stage planning transition control is completed, and it is determined that the target vehicle enters a fully following automatic driving state.

[0124] In this embodiment, the execution subject of the method may be a computing device such as a computer or a server, and this is not limited in this embodiment.

[0125] In this embodiment, the execution subject of the method may also be a smart device such as a smart phone, a tablet computer, etc., which is not limited in this embodiment.

[0126] It can be seen that the implementation of the autonomous driving planning transition method described in this embodiment can integrate the lane line and the trajectory planning information of the preceding vehicle to achieve a smooth transition, thereby effectively improving the stability and smoothness of autonomous driving at intersections or sections with blurred lane lines.

[0127] Example 2

[0128] Please see Figure 2 , Figure 2 This is a flow chart of an autonomous driving planning transition method provided in this embodiment. The autonomous driving planning transition method includes:

[0129] S201. When the target vehicle is in a lane-following state, obtain lane line information and a historical driving trajectory of the preceding vehicle.

[0130] S202: Obtain left and right lanes based on lane line information.

[0131] S203: Calculate a lane-following path based on the left and right lane lines and the planning module of the target vehicle.

[0132] S204: Calculate the following vehicle path based on the previous vehicle's historical driving trajectory and the planning module.

[0133] In this embodiment, the line-following path and the vehicle-following path are input data of this method, and both are paths represented by cubic polynomials.

[0134] In this embodiment, the line-following path coefficients, from high to low order, are A3, A2, A1, and A0, and the vehicle-following path coefficients, from high to low order, are B3, B2, B1, and B0. The line-following path is calculated from lane information, typically the centerline between the left and right lanes. The vehicle-following path is derived from the historical trajectory of the preceding vehicle. When following a preceding vehicle, the ego vehicle will follow the preceding vehicle's historical trajectory.

[0135] S205: Acquire the left and right lane line perception data of the current lane line in real time.

[0136] S206. Determine the effective lengths of the left and right lane lines based on the left and right lane line perception data.

[0137] S207: Determine whether the effective lengths of the left and right lane lines are less than a preset length threshold. If so, execute step S208; if not, end this process.

[0138] S208: Determine that the lane line is about to disappear, and obtain the first vehicle speed of the current first moment and the first vehicle speed of the target vehicle at the first moment.

[0139] S209: Obtain a first line-following path coefficient at a first moment and a first vehicle-following path coefficient at a first moment according to the line-following path and the vehicle-following path.

[0140] In this embodiment, the first tracking line path coefficient is used to indicate that each tracking line path coefficient at time Ts1 is an initial value Init.

[0141] S210: Calculate a theoretical time until the lane lines disappear based on the effective lengths of the left and right lane lines and the speed of the first vehicle.

[0142] In this embodiment, the above process describes the first stage of the transition from line following to vehicle following. Specifically, when the effective length of the left or right lane marking (i.e., the perceived length of the lane marking) is less than the preset threshold Lmin, the lane marking is determined to be about to disappear, and the first stage of the transition begins. This time is recorded as Ts1. At this point, the theoretical time for the lane marking to disappear is calculated as t1 = L1 / V. Where L1 is the greater of the left or right lane marking length, and V is the vehicle's speed at Ts1.

[0143] S211. Determine a transition time based on a theoretical time when the lane line disappears.

[0144] In this embodiment, the path coefficients of the respective tracking lines at time Ts1 are initial values ​​Init.

[0145] In this embodiment, t1 is the transition time Trans.

[0146] S212: Calculate a first weighted average value of the first line-following path coefficient and the first vehicle-following path coefficient according to a preset weighting formula and a preset weighting coefficient.

[0147] In this embodiment, the weighting coefficient is a preset value P, which is used to represent the proportion of the following vehicle coefficient during weighting.

[0148] In this embodiment, the weighted average of the current vehicle following coefficient and the line following coefficient is the target value Tar.

[0149] In this embodiment, Init and Tar both contain 4 coefficients. Taking the lowest-order coefficient as an example, the weighting formula is as follows: Tar0 = B0*P+A0*(1-P). The other coefficients can be deduced accordingly.

[0150] S213: Acquire the current control software operation cycle, and determine the first historical target path coefficient of the previous control software operation cycle.

[0151] S214 , calculating a first transition amount of the current control software operation cycle according to the current control software operation cycle, the transition time, the first weighted average value, and the first tracking line path coefficient.

[0152] In this embodiment, the method can dynamically transition the four coefficients in Init and Tar respectively.

[0153] In this embodiment, since the algorithm is the same, the lowest-order coefficient is used as an example for illustration:

[0154] Calculate the transition amount S0 corresponding to the software running cycle in the current software:

[0155] S0=(Tar0-Init0) / Trans*Task

[0156] Among them, Task is the operating cycle of the control software and is a preset value.

[0157] S215. Calculate the first target path coefficient of the current control software operation cycle according to the first transition amount and the first historical target path coefficient.

[0158] In this embodiment, the target path coefficients in the transition state (such as the first historical target path coefficients) are: C3, C2, C1, C0, where:

[0159] C0=C0_old+S0

[0160] Among them, C0_old is the C0 value of the previous software running cycle.

[0161] S216 , performing first-stage planning transition control from line-following driving to vehicle-following driving on the target vehicle based on the first target path coefficient.

[0162] S217: Determine whether the first target path coefficient reaches the first weighted average value. If so, execute step S220; if not, execute step S218.

[0163] In this embodiment, the method can dynamically calculate the transition amount S of the current operation cycle based on the Init value, and continuously accumulate it until the transition is completed when the output C0 value reaches the Tar0 value.

[0164] S218. Determine that the first phase planning transition has not been completed.

[0165] S219: Determine the current first target path coefficient as the first historical target path coefficient, and execute step S215.

[0166] In this embodiment, when the first target path coefficient does not reach the first weighted average value, the method will continuously accumulate transition values ​​until the output C0 value reaches the Tar0 value, and the transition is completed.

[0167] For example, a first calculation is performed based on the obtained historical transition state target path coefficient, and a determination is made as to whether the first target path coefficient reaches the first weighted average value. If not, a second accumulation (i.e., adding the transition value) is performed based on the first target path coefficient obtained from the first calculation (as the historical transition state target path coefficient), and then a determination is made as to whether the first weighted average value is reached. If not, the second calculation process is repeated.

[0168] S220. When the target vehicle detects that the current lane line completely disappears, obtain the second moment when the current lane line completely disappears, the first target path coefficient for performing the first stage planned transition control on the target vehicle at the second moment, the second following path coefficient at the second moment, and the preset fixed transition time.

[0169] In this embodiment, the method can determine whether the transition is completed (it may not be completed at this time) based on the estimated situation of t1 (transition time Trans) at the moment when the lane line completely disappears, and this moment is recorded as Ts2.

[0170] In this embodiment, the method denotes the target path C at time Ts2 as Init, the current following path as Tar, and the preset fixed transition time Tt1 as Trans. The same dynamic transition algorithm described above is used to dynamically transition the output value at time Ts2 to the following path, and once the transition is complete, the system enters the full following state.

[0171] S221. Perform a timed dynamic transition calculation based on the first target path coefficient, the second following vehicle path coefficient, the second following vehicle path coefficient, and the fixed transition time at the second moment to obtain the second target path coefficient and the second weighted average value in the transition state.

[0172] S222: Based on the second target path coefficient, the target vehicle is subjected to second-stage planning transition control from line-following driving to vehicle-following driving.

[0173] S223. When the second target path coefficient reaches the second weighted average value, it is determined that the second stage planning transition control is completed, and it is determined that the target vehicle enters the full vehicle-following automatic driving state.

[0174] As an optional implementation, the method further includes:

[0175] When the target vehicle detects the lane line again, the fully following autonomous driving state ends and the transition state from following the vehicle to following the lane begins.

[0176] Obtaining a third moment when the lane line is re-detected, a starting distance between the target vehicle and the lane line at the third moment, and a second vehicle speed of the target vehicle at the third moment;

[0177] Calculate the remaining time from the target vehicle to the lane line based on the second vehicle's speed and starting distance;

[0178] Obtaining a third target path coefficient for driving control of the target vehicle at a third moment and a second line path coefficient at the third moment;

[0179] Performing a timed dynamic transition calculation based on the second vehicle speed, the second line-following path coefficient, and the third target path coefficient to obtain a fourth target path coefficient and a third weighted average value in a transition state;

[0180] The target vehicle is controlled to undergo a planned transition from vehicle-following driving to line-following driving based on the fourth target path coefficient and the third weighted average value.

[0181] As a further optional implementation, a timed dynamic transition calculation is performed based on the second vehicle speed, the second line-following path coefficient, and the third target path coefficient to obtain a fourth target path coefficient and a third weighted average value in the transition state, including:

[0182] Calculate the third weighted average value of the third target path coefficient and the second line path coefficient according to the weighted formula and the weighted coefficient;

[0183] Determine a second historical target path coefficient for the last control software operation cycle;

[0184] Calculating a second transition amount based on a current control software operation cycle, a remaining time of the lane line, a third weighted average value, and a third target path coefficient;

[0185] The fourth target path coefficient of the current control software operation cycle is calculated based on the second transition amount and the second historical target path coefficient.

[0186] As a further optional implementation, performing planned transition control on the target vehicle from vehicle-following driving to line-following driving based on the fourth target path coefficient and the third weighted average value includes:

[0187] Performing planning transition control on the target vehicle from vehicle-following driving to line-following driving based on the fourth target path coefficient;

[0188] determining whether the fourth target path coefficient reaches the third weighted average;

[0189] If no, it is determined that the planned transition has not been completed;

[0190] The current fourth target path coefficient is determined as the second historical target path coefficient, and the fourth target path coefficient of the current control software operation cycle is calculated based on the second transition amount and the second historical target path coefficient.

[0191] In this embodiment, after the lane line is re-detected by perception, the following state is ended and the transition state from following the vehicle to following the line is entered, which is recorded as Te.

[0192] Specifically, this method obtains the starting distance L2 of the lane line at time Te. When two lane lines in the main lane are detected simultaneously, L2 is the smaller of the starting distances of the two lane lines. The remaining time from the ego vehicle to the lane line is then calculated as t2 = L2 / V, where V is the ego vehicle's speed at time Te.

[0193] At this point, the target path C at time Te is designated as Init, the current tracking path is designated as Tar, and t2 is designated as Trans. Based on this, the method continues to use the dynamic transition algorithm described in the previous steps to dynamically transition the output value at time Te to the tracking path. Once the transition is complete, the system enters the fully tracking state.

[0194] In this embodiment, the execution subject of the method may be a computing device such as a computer or a server, and this is not limited in this embodiment.

[0195] In this embodiment, the execution subject of the method may also be a smart device such as a smart phone, a tablet computer, etc., which is not limited in this embodiment.

[0196] It can be seen that the implementation of the autonomous driving planning transition method described in this embodiment can integrate the lane line and the trajectory planning information of the preceding vehicle to achieve a smooth transition, thereby effectively improving the stability and smoothness of autonomous driving at intersections or sections with blurred lane lines.

[0197] Example 3

[0198] Please see Figure 3 , Figure 3This is a schematic diagram of the structure of an automatic driving planning transition device provided in this embodiment. Figure 3 As shown, the automatic driving planning transition device includes:

[0199] The first acquisition unit 310 is used to acquire the line-following path and the vehicle-following path output by the planning module when the target vehicle is in the line-following state;

[0200] The second acquisition unit 320 is used to obtain the left and right lane line perception data of the current lane line in real time;

[0201] The third acquisition unit 330 is configured to acquire the first vehicle speed at the current first moment and the first vehicle speed of the target vehicle at the first moment when it is determined based on the left and right lane line sensing data that the current lane line is about to disappear;

[0202] A fourth acquiring unit 340 is configured to acquire a first line-following path coefficient at a first moment and a first vehicle-following path coefficient at a first moment according to the line-following path and the vehicle-following path;

[0203] A first calculation unit 350 is configured to perform a timed dynamic transition calculation based on the first ego vehicle speed, the first line-following path coefficient, and the first vehicle-following path coefficient to obtain a first target path coefficient and a first weighted average value in a transition state;

[0204] A first transition control unit 360 is configured to perform a first stage planning transition control from line-following driving to vehicle-following driving on the target vehicle based on the first target path coefficient and the first weighted average value;

[0205] A fifth acquisition unit 370 is configured to, when the target vehicle detects that the current lane line has completely disappeared, acquire a second moment when the current lane line completely disappears, a first target path coefficient for performing first-stage planned transition control on the target vehicle at the second moment, a second following path coefficient at the second moment, and a preset fixed transition time;

[0206] a second calculation unit 380 for performing a timed dynamic transition calculation based on the first target path coefficient, the second following path coefficient, the second following path coefficient, and the fixed transition time at the second moment to obtain a second target path coefficient and a second weighted average value in a transition state;

[0207] A second transition control unit 390 is configured to perform a second-stage planning transition control from line-following driving to vehicle-following driving on the target vehicle based on the second target path coefficient;

[0208] The first determination unit 400 is configured to determine that the second stage planning transition control is completed and that the target vehicle enters a fully following automatic driving state when the second target path coefficient reaches a second weighted average value.

[0209] In this embodiment, the explanation of the automatic driving planning transition device can refer to the description in Example 1 or Example 2, and will not be further elaborated in this embodiment.

[0210] It can be seen that the implementation of the autonomous driving planning transition device described in this embodiment can integrate the lane lines and the trajectory planning information of the preceding vehicle to achieve a smooth transition, thereby effectively improving the stability and smoothness of autonomous driving at intersections or sections with blurred lane lines.

[0211] Example 4

[0212] Please see Figure 4 , Figure 4 This is a schematic diagram of the structure of an automatic driving planning transition device provided in this embodiment. Figure 4 As shown, the automatic driving planning transition device includes:

[0213] The first acquisition unit 310 is used to acquire the line-following path and the vehicle-following path output by the planning module when the target vehicle is in the line-following state;

[0214] The second acquisition unit 320 is used to obtain the left and right lane line perception data of the current lane line in real time;

[0215] The third acquisition unit 330 is configured to acquire the first vehicle speed at the current first moment and the first vehicle speed of the target vehicle at the first moment when it is determined based on the left and right lane line sensing data that the current lane line is about to disappear;

[0216] A fourth acquiring unit 340 is configured to acquire a first line-following path coefficient at a first moment and a first vehicle-following path coefficient at a first moment according to the line-following path and the vehicle-following path;

[0217] A first calculation unit 350 is configured to perform a timed dynamic transition calculation based on the first ego vehicle speed, the first line-following path coefficient, and the first vehicle-following path coefficient to obtain a first target path coefficient and a first weighted average value in a transition state;

[0218] A first transition control unit 360 is configured to perform a first stage planning transition control from line-following driving to vehicle-following driving on the target vehicle based on the first target path coefficient and the first weighted average value;

[0219] A fifth acquisition unit 370 is configured to, when the target vehicle detects that the current lane line has completely disappeared, acquire a second moment when the current lane line completely disappears, a first target path coefficient for performing first-stage planned transition control on the target vehicle at the second moment, a second following path coefficient at the second moment, and a preset fixed transition time;

[0220] a second calculation unit 380 for performing a timed dynamic transition calculation based on the first target path coefficient, the second following path coefficient, the second following path coefficient, and the fixed transition time at the second moment to obtain a second target path coefficient and a second weighted average value in a transition state;

[0221] A second transition control unit 390 is configured to perform a second-stage planning transition control from line-following driving to vehicle-following driving on the target vehicle based on the second target path coefficient;

[0222] The first determination unit 400 is configured to determine that the second stage planning transition control is completed and that the target vehicle enters a fully following automatic driving state when the second target path coefficient reaches a second weighted average value.

[0223] As an optional implementation, the first acquiring unit 310 includes:

[0224] The first acquisition subunit 311 is used to acquire lane line information and the historical driving trajectory of the preceding vehicle;

[0225] The first acquisition subunit 311 is further used to acquire the left and right lane lines according to the lane line information;

[0226] A first calculation subunit 312 is configured to calculate a line-following path based on the left and right lane lines and the planning module of the target vehicle;

[0227] The first calculation subunit 312 is further configured to calculate a following vehicle path based on the preceding vehicle's historical driving trajectory and the planning module; wherein both the line-following path and the following vehicle path are path functions represented by cubic polynomials.

[0228] As an optional implementation, the autonomous driving planning transition device further includes:

[0229] A second determining unit 410 is configured to determine the effective lengths of the left and right lane lines according to the left and right lane line sensing data after the second acquiring unit 320 acquires the left and right lane line sensing data of the current lane line in real time;

[0230] The judgment unit 420 is used to determine whether the effective length of the left and right lane lines is less than a preset length threshold; if so, it is determined that the lane lines are about to disappear, and the third acquisition unit 330 is triggered to execute the operation of acquiring the current first moment and the first vehicle speed of the target vehicle at the first moment.

[0231] As an optional implementation, the first calculation unit 350 includes:

[0232] The second calculation subunit 351 is used to calculate the lane line disappearance theoretical time based on the effective lengths of the left and right lane lines and the speed of the first vehicle;

[0233] A first determining subunit 352 is configured to determine a transition time based on a theoretical lane line disappearance time;

[0234] The second calculation subunit 351 is further configured to calculate a first weighted average value of the first line-following path coefficient and the first vehicle-following path coefficient according to a preset weighting formula and a preset weighting coefficient;

[0235] The second acquisition subunit 353 is used to acquire the current control software operation cycle and determine the first historical target path coefficient of the previous control software operation cycle;

[0236] The second calculation subunit 351 is further configured to calculate a first transition amount of the current control software operation cycle according to the current control software operation cycle, the transition time, the first weighted average value, and the first tracking line path coefficient;

[0237] The second calculation subunit 351 is further configured to calculate a first target path coefficient of a current control software operation cycle according to the first transition amount and the first historical target path coefficient.

[0238] As an optional implementation manner, the first transition control unit 360 includes:

[0239] A first transition subunit 361 is configured to perform a first stage planning transition control from line-following driving to vehicle-following driving on the target vehicle based on the first target path coefficient;

[0240] A first judging subunit 362 is configured to judge whether the first target path coefficient reaches a first weighted average value;

[0241] The second determining subunit 363 is configured to determine that the first stage planning transition is not completed when the first target path coefficient does not reach the first weighted average value;

[0242] The second determination subunit 363 is also used to determine the current first target path coefficient as the first historical target path coefficient, and trigger the second calculation subunit 351 to perform the operation of calculating the first target path coefficient of the current control software operation cycle based on the first transition amount and the first historical target path coefficient.

[0243] As an optional implementation, the autonomous driving planning transition device further includes:

[0244] The ending unit 430 is configured to end the full vehicle-following automatic driving state and enter a transition state from vehicle-following driving to lane-following driving when the target vehicle re-detects the lane line;

[0245] A sixth acquiring unit 440 is configured to acquire a third moment when the lane line is re-detected, a starting distance between the target vehicle and the lane line at the third moment, and a second vehicle speed of the target vehicle at the third moment;

[0246] The third calculation unit 450 is used to calculate the remaining time from the target vehicle to the lane line according to the speed of the second vehicle and the starting distance;

[0247] The sixth acquisition unit 440 is further configured to acquire a third target path coefficient for driving control of the target vehicle at a third moment and a second line path coefficient at the third moment;

[0248] The third calculation unit 450 is further configured to perform a time-long dynamic transition calculation based on the second vehicle speed, the second line-following path coefficient, and the third target path coefficient to obtain a fourth target path coefficient and a third weighted average value in the transition state;

[0249] The third transition control unit 460 is configured to perform planned transition control on the target vehicle from vehicle-following driving to line-following driving based on the fourth target path coefficient and the third weighted average value.

[0250] As an optional implementation, the third calculation unit 450 includes:

[0251] The third calculation subunit 451 is used to calculate a third weighted average value of the third target path coefficient and the second line path coefficient according to the weighting formula and the weighting coefficient;

[0252] The third determining subunit 452 is used to determine the second historical target path coefficient of the previous control software operation cycle;

[0253] The third calculation subunit 451 is further configured to calculate a second transition amount based on the current control software operation cycle, the remaining time of the lane line, the third weighted average value, and the third target path coefficient;

[0254] The third calculation subunit 451 is further configured to calculate a fourth target path coefficient of the current control software operation cycle according to the second transition amount and the second historical target path coefficient.

[0255] As an optional implementation manner, the third transition control unit 460 includes:

[0256] A second transition subunit 461 is configured to perform planned transition control on the target vehicle from vehicle-following driving to line-following driving based on the fourth target path coefficient;

[0257] The second judging subunit 462 is used to judge whether the fourth target path coefficient reaches the third weighted average value;

[0258] a fourth determining subunit 463, configured to determine that the planned transition is not completed when the fourth target path coefficient does not reach the third weighted average value;

[0259] The fourth determination subunit 463 is also used to determine the current fourth target path coefficient as the second historical target path coefficient, and trigger the third calculation subunit 451 to perform the operation of calculating the fourth target path coefficient of the current control software operation cycle based on the second transition amount and the second historical target path coefficient.

[0260] In this embodiment, the explanation of the automatic driving planning transition device can refer to the description in Example 1 or Example 2, and will not be further elaborated in this embodiment.

[0261] It can be seen that the implementation of the autonomous driving planning transition device described in this embodiment can integrate the lane lines and the trajectory planning information of the preceding vehicle to achieve a smooth transition, thereby effectively improving the stability and smoothness of autonomous driving at intersections or sections with blurred lane lines.

[0262] An embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the autonomous driving planning transition method in embodiment 1 or embodiment 2 of the present application.

[0263] An embodiment of the present application provides a computer-readable storage medium storing computer program instructions. When the computer program instructions are read and executed by a processor, the autonomous driving planning transition method in embodiment 1 or embodiment 2 of the present application is executed.

[0264] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions and operations of the devices, methods and computer program products according to the multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions.

[0265] In addition, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0266] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0267] The foregoing is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included within the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined or explained in subsequent figures.

[0268] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

[0269] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

Claims

1. A method for planning transition of an autonomous driving system, characterized in that: include: When the target vehicle is in the line-following state, obtain the line-following path and vehicle-following path output by the planning module; Get the left and right lane line perception data of the current lane line in real time; When it is determined based on the left and right lane line sensing data that the current lane line is about to disappear, obtaining a current first moment and a first vehicle speed of the target vehicle at the first moment; Acquire a first line-following path coefficient at the first moment and a first vehicle-following path coefficient at the first moment according to the line-following path and the vehicle-following path; Performing a timed dynamic transition calculation based on the first vehicle speed, the first line-following path coefficient, and the first vehicle-following path coefficient to obtain a first target path coefficient and a first weighted average value in a transition state; Performing a first-stage planning transition control from line-following driving to vehicle-following driving on the target vehicle based on the first target path coefficient and the first weighted average value; When the target vehicle detects that the current lane line completely disappears, obtaining a second moment when the current lane line completely disappears, a first target path coefficient for performing first-stage planned transition control on the target vehicle at the second moment, a second following path coefficient at the second moment, and a preset fixed transition time; Performing a timed dynamic transition calculation based on the first target path coefficient, the second following path coefficient, the second following path coefficient, and the fixed transition time at the second moment to obtain a second target path coefficient and a second weighted average value in a transition state; Performing a second-stage planning transition control from line-following driving to vehicle-following driving on the target vehicle based on the second target path coefficient; When the second target path coefficient reaches the second weighted average value, it is determined that the second stage planning transition control is completed, and it is determined that the target vehicle enters a fully following automatic driving state.

2. The autonomous driving planning transition method according to claim 1, characterized in that: The obtaining of the line-following path and the vehicle-following path output by the planning module includes: Obtain lane line information and the previous vehicle's historical driving trajectory; Obtain left and right lane lines according to the lane line information; Calculating a line-following path based on the left and right lane lines and the planning module of the target vehicle; A following vehicle path is calculated based on the historical driving trajectory of the preceding vehicle and the planning module; wherein the line-following path and the following vehicle path are both path functions represented by cubic polynomials.

3. The autonomous driving planning transition method according to claim 1, characterized in that: After acquiring the left and right lane line sensing data of the current lane line in real time, the method further includes: Determining the effective lengths of the left and right lane lines based on the left and right lane line perception data; Determining whether the effective lengths of the left and right lane lines are less than a preset length threshold; If yes, it is determined that the lane line is about to disappear, and the step of obtaining the current first moment and the first vehicle speed of the target vehicle at the first moment is performed.

4. The autonomous driving planning transition method according to claim 3, characterized in that: The performing of a timed dynamic transition calculation based on the first vehicle speed, the first line-following path coefficient, and the first vehicle-following path coefficient to obtain a first target path coefficient and a first weighted average value in a transition state includes: Calculating a theoretical time for lane markings to disappear based on the effective lengths of the left and right lane markings and the first vehicle speed; Determining a transition time based on the lane line disappearance theoretical time; Calculating a first weighted average of the first line-following path coefficient and the first vehicle-following path coefficient according to a preset weighting formula and a preset weighting coefficient; Obtaining the current control software operation cycle and determining the first historical target path coefficient of the previous control software operation cycle; Calculating a first transition amount of the current control software operation cycle according to the current control software operation cycle, the transition time, the first weighted average value, and the first tracking path coefficient; The first target path coefficient of the current control software operation cycle is calculated according to the first transition amount and the first historical target path coefficient.

5. The autonomous driving planning transition method according to claim 4, characterized in that: The first-stage planning transition control from line-following driving to vehicle-following driving of the target vehicle based on the first target path coefficient and the first weighted average value includes: Performing a first-stage planning transition control from line-following driving to vehicle-following driving on the target vehicle based on the first target path coefficient; determining whether the first target path coefficient reaches the first weighted average value; If no, it is determined that the first phase of planning transition has not been completed; The current first target path coefficient is determined as the first historical target path coefficient, and the first target path coefficient of the current control software operation cycle is calculated based on the first transition amount and the first historical target path coefficient.

6. The autonomous driving planning transition method according to claim 4, characterized in that: The method further comprises: When the target vehicle detects the lane line again, the fully following automatic driving state ends and enters a transition state from following the vehicle to following the line; Obtaining a third moment when the lane line is redetected, a starting distance between the target vehicle and the lane line at the third moment, and a second vehicle speed of the target vehicle at the third moment; Calculating the remaining time for the target vehicle to reach the lane line based on the second vehicle speed and the starting distance; Acquire a third target path coefficient for driving control of the target vehicle at the third moment and a second tracking path coefficient at the third moment; performing a timed dynamic transition calculation based on the second vehicle speed, the second line-following path coefficient, and the third target path coefficient to obtain a fourth target path coefficient and a third weighted average value in a transition state; Planning transition control from vehicle-following driving to line-following driving is performed on the target vehicle based on the fourth target path coefficient and the third weighted average value.

7. The autonomous driving planning transition method according to claim 6, characterized in that: The performing of a timed dynamic transition calculation based on the second vehicle speed, the second following path coefficient, and the third target path coefficient to obtain a fourth target path coefficient and a third weighted average value in a transition state includes: Calculating a third weighted average of the third target path coefficient and the second line path coefficient according to the weighting formula and the weighting coefficient; Determine a second historical target path coefficient for the last control software operation cycle; Calculating a second transition amount according to the current control software operation cycle, the remaining time of the lane line, the third weighted average value, and the third target path coefficient; A fourth target path coefficient of the current control software operation cycle is calculated based on the second transition amount and the second historical target path coefficient.

8. The autonomous driving planning transition method according to claim 7, characterized in that: The planning transition control of the target vehicle from vehicle-following driving to line-following driving based on the fourth target path coefficient and the third weighted average value includes: performing planned transition control on the target vehicle from vehicle-following driving to line-following driving based on the fourth target path coefficient; determining whether the fourth target path coefficient reaches the third weighted average value; If no, it is determined that the planned transition has not been completed; The current fourth target path coefficient is determined as the second historical target path coefficient, and the fourth target path coefficient of the current control software operation cycle is calculated based on the second transition amount and the second historical target path coefficient.

9. An automatic driving planning transition device, characterized in that: The automatic driving planning transition device includes: A first acquisition unit is used to acquire the line-following path and the vehicle-following path output by the planning module when the target vehicle is in a line-following state; The second acquisition unit is used to obtain the left and right lane line perception data of the current lane line in real time; a third acquiring unit, configured to acquire a first current moment and a first vehicle speed of the target vehicle at the first moment when it is determined based on the left and right lane line sensing data that the current lane line is about to disappear; a fourth acquiring unit, configured to acquire a first line-following path coefficient and a first vehicle-following path coefficient at the first moment according to the line-following path and the vehicle-following path; a first calculation unit, configured to perform a timed dynamic transition calculation based on the first ego vehicle speed, the first line-following path coefficient, and the first vehicle-following path coefficient, to obtain a first target path coefficient and a first weighted average value in a transition state; a first transition control unit, configured to perform a first-stage planning transition control from line-following driving to vehicle-following driving on the target vehicle based on the first target path coefficient and the first weighted average value; a fifth acquisition unit, configured to, when the target vehicle detects that the current lane line completely disappears, acquire a second moment when the current lane line completely disappears, a first target path coefficient for performing first-stage planned transition control on the target vehicle at the second moment, a second following path coefficient at the second moment, and a preset fixed transition time; a second calculation unit, configured to perform a timed dynamic transition calculation based on the first target path coefficient, the second following path coefficient, the second following path coefficient, and the fixed transition time at the second moment, to obtain a second target path coefficient and a second weighted average value in a transition state; a second transition control unit, configured to perform a second-stage planning transition control from line-following driving to vehicle-following driving on the target vehicle based on the second target path coefficient; The first determination unit is used to determine that the second stage planning transition control is completed when the second target path coefficient reaches the second weighted average value, and to determine that the target vehicle enters a fully following automatic driving state.

10. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the autonomous driving planning transition method according to any one of claims 1 to 8.

Images