Automatic avoidance decision method, system, electronic device, vehicle and storage medium

Abstract

The application provides an automatic avoidance decision method, system, electronic equipment, vehicle and storage medium. The method comprises the following steps: obtaining the current positioning and motion state information of the ego vehicle, the avoidance side lane line type, and the position information and motion state information of the target obstacle; obtaining the lateral distance of the target obstacle based on the position information of the target obstacle; obtaining the relative longitudinal distance based on the current positioning and the position information of the target obstacle; judging whether to execute the automatic avoidance function based on the motion state information of the ego vehicle, the motion state information of the obstacle, the lateral distance and the relative longitudinal distance, and generating the corresponding automatic avoidance decision result; executing the automatic avoidance decision result and completing the automatic avoidance according to the avoidance side lane line type. For the behaviors such as line sticking and line pressing of the target obstacle, the target obstacle is automatically avoided, unnecessary braking caused by the behaviors such as line sticking and line pressing of the obstacle can be effectively avoided, and the safety of the driver is obviously increased.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving of vehicles, and in particular to an automatic avoidance decision method, system, electronic device, vehicle and storage medium. BACKGROUND

[0002] The existing L3 level automatic driving vehicles on the market mostly integrate adaptive cruise control (ACC), forward collision warning (FCW), automatic emergency braking (AEB) and other functions in the longitudinal control function; and mostly integrate lane departure warning (LDW), vehicle keeping assistance (LKA), vehicle centering assistance (LCC) functions in the lateral control function, and a few vehicles are equipped with emergency lane keeping (ELK) function.

[0003] Among them, the lateral control function basically adopts the in-lane centering assistance driving or the way of occupying the adjacent lane for a short time to avoid obstacles to control the vehicle. For the vehicles with line sticking / line pressing in the adjacent lane, this scenario is usually at the braking boundary of the automatic driving algorithm, that is, either deceleration following or not taking any action to directly pass, or reversing the lane to change the vehicle to another lane to avoid risks, and the above methods all have limitations.

[0004] In particular, for vehicles such as trucks with large width, the safety distance on both sides of the lane is already not much when the vehicle is driving in the center, at this time, if the adjacent lane vehicle has line sticking / line pressing driving behavior, it will bring great driving pressure to the driver, and the driver in this scenario will mostly take over to ensure the safety of the vehicle surrounding environment. How to smoothly complete the efficient passing of the potential dangerous vehicle in the surrounding in the existing L3 automatic driving lateral function design for the line sticking / line pressing driving scenario of the adjacent lane vehicle without braking, taking over, lane changing and other ways is an important issue to be solved in the industry at present. SUMMARY

[0005] In view of the problems in the prior art, the present application provides an automatic avoidance decision method, system, electronic device, vehicle and storage medium, which can effectively avoid unnecessary braking caused by the line sticking / line pressing behavior of the target obstacle in the existing algorithm, and significantly increase the safety of the driver.

[0006] The present application provides an automatic avoidance decision method, comprising:

[0007] obtaining the current positioning and motion state information of the ego vehicle, the avoidance side lane line type, and the position information and obstacle motion state information of the target obstacle;

[0008] obtaining the lateral distance of the target obstacle based on the position information of the target obstacle;

[0009] obtaining a relative longitudinal distance based on the current position and position information of the target obstacle;

[0010] judging whether to execute an automatic avoidance function and generating a corresponding automatic avoidance decision result based on the self-vehicle motion state information, the obstacle motion state information, the lateral distance and the relative longitudinal distance, and if so, executing the automatic avoidance decision result and completing automatic avoidance according to the avoidance side lane line type, and if not, maintaining the current state to perform lane center driving.

[0011] According to the automatic avoidance decision method provided by the application, the target obstacle lateral distance is obtained based on the position information of the target obstacle, which comprises: perceiving the center line of the lane line between the target obstacle and the self-vehicle, taking the center line as the reference, measuring the lateral straight-line distance between the side of the target obstacle close to the self-vehicle and the center line according to the position information of the target obstacle, and taking the lateral straight-line distance as the lateral distance.

[0012] According to the automatic avoidance decision method provided by the application, the target obstacle lateral distance is obtained based on the position information of the target obstacle, which comprises: perceiving the center line of the lane line between the target obstacle and the self-vehicle, taking the center line as the reference, measuring the lateral straight-line distance between the side of the target obstacle close to the self-vehicle and the center line according to the position information of the target obstacle, and taking the lateral straight-line distance as the lateral distance.

[0013] judging whether the lateral distance is less than a preset distance threshold;

[0014] If the lateral distance is less than the distance threshold, calculating the overtaking time according to the self-vehicle motion state information, the obstacle motion state information and the relative longitudinal distance, and judging whether the overtaking time is less than a preset time threshold;

[0015] If the overtaking time is less than the time threshold, generating the automatic avoidance decision result, which comprises turning on the left turn signal or turning on the right turn signal.

[0016] According to the automatic avoidance decision method provided by the application, the overtaking time is calculated according to the self-vehicle motion state information, the obstacle motion state information and the relative longitudinal distance, which comprises: obtaining the first driving speed and the first acceleration of the self-vehicle included in the self-vehicle motion state information, and the second driving speed and the second acceleration of the target obstacle included in the obstacle motion state information, and calculating the relative longitudinal distance according to the first driving speed, the first acceleration, the second driving speed and the second acceleration to obtain the overtaking time.

[0017] According to the automatic avoidance decision method provided by the application, the automatic avoidance decision result further comprises large-scale avoidance and small-scale avoidance, and the execution of the automatic avoidance decision result and the automatic avoidance according to the avoidance side lane line type comprise:

[0018] judging the avoidance side lane line type as solid line or dashed line;

[0019] if the avoidance side lane line type is dashed line, large-scale avoidance is adopted, that is, the ego vehicle is allowed to partially cross the avoidance side lane line to perform lateral avoidance;

[0020] if the avoidance side lane line type is solid line, small-scale avoidance is adopted, that is, the ego vehicle is allowed to perform lateral avoidance without crossing the line in the current lane;

[0021] when the target obstacle is overtaken or accelerates to drive away, the turn signal is turned off and the ego vehicle returns to the original lane to drive in the center.

[0022] According to the automatic avoidance decision method provided by the application, whether the ego vehicle completes overtaking the target obstacle is a judgment condition, that is, the tail of the ego vehicle exceeds the head of the target obstacle and the driving speed of the ego vehicle is greater than or equal to the driving speed of the target obstacle.

[0023] The application further provides an automatic avoidance decision system, comprising:

[0024] a first acquisition module for acquiring the current positioning and motion state information of the ego vehicle, the avoidance side lane line type, and the position information and motion state information of the target obstacle;

[0025] a second acquisition module connected to the first acquisition module, for acquiring the lateral distance of the target obstacle based on the position information of the target obstacle;

[0026] a third acquisition module connected to the first acquisition module, for acquiring the relative longitudinal distance based on the current positioning and the position information of the target obstacle;

[0027] an automatic avoidance decision module connected to the first acquisition module, the second acquisition module and the third acquisition module, for judging and generating corresponding automatic avoidance decision results based on the motion state information of the ego vehicle, the motion state information of the obstacle, the lateral distance and the relative longitudinal distance to determine whether to execute the automatic avoidance function;

[0028] an automatic avoidance execution module connected to the automatic avoidance decision module, for executing the automatic avoidance decision result and completing the automatic avoidance according to the avoidance side lane line type, and returning the ego vehicle to the original lane to drive in the center after the avoidance is completed.

[0029] The application further provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the automatic avoidance decision method according to any one of the above when executing the program.

[0030] The application further provides a vehicle capable of assisting driving and / or automatic driving, including the electronic device according to the above.

[0031] The application further provides a non-transitory computer-readable storage medium, which stores a computer program, wherein the computer program is executable on a processor to implement the steps of the automatic avoidance decision method according to any one of the above.

[0032] The automatic avoidance decision method, system, electronic device, vehicle and storage medium provided by the application can obtain the current positioning and motion state information of the ego vehicle, the avoidance side lane line type, and the position information and motion state information of the target obstacle, and obtain an automatic avoidance decision result, so that the target obstacle can be automatically avoided when the target obstacle has behaviors such as line following and line pressing, the safety of the driver is obviously increased, unnecessary braking caused by behaviors such as line following and line pressing of the target obstacle in the prior art is effectively avoided, the number of braking is reduced, and the fuel consumption of the vehicle is reduced. The automatic driving performance of the vehicle is improved from the aspects of comfort, safety, fuel economy and the like. BRIEF DESCRIPTION OF DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative effort on the basis of these drawings.

[0034] Figure 1 A flowchart of an automatic avoidance decision method provided by the application;

[0035] Figure 2 A schematic diagram of collecting the environment around the vehicle in the automatic avoidance decision method provided by the application;

[0036] Figure 3 A schematic diagram of indicating the lateral distance of the target obstacle in the automatic avoidance decision method provided by the application;

[0037] Figure 4 A schematic diagram of starting the automatic avoidance function to overtake in the automatic avoidance decision method provided by the application;

[0038] Figure 5 A schematic diagram of completing overtaking and returning to the original lane of the target obstacle for an automatic avoidance decision method provided by the present application is shown in the figure;

[0039] Figure 6 A specific step flow chart of an automatic avoidance decision method provided by the embodiment of the present application is shown in the figure;

[0040] Figure 7 A structure schematic diagram of an automatic avoidance decision system provided by the present application is shown in the figure;

[0041] Figure 8 A structure schematic diagram of an electronic device provided by the present application is shown in the figure.

[0042] Reference signs:

[0043] 21: first acquisition module; 22: second acquisition module; 23: third acquisition module; 24: automatic avoidance decision module; 25: automatic avoidance execution module. DETAILED DESCRIPTION

[0044] In order to make the objectives, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below with reference to the drawings in the present application. Obviously, the described embodiments are some embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all the other embodiments obtained by those skilled in the art without creative labor fall within the protection scope of the present application.

[0045] Embodiment one

[0046] Referring to Figure 1 the figure, an automatic avoidance decision method provided by the present embodiment includes:

[0047] S1: acquiring the current positioning and motion state information of the ego vehicle, the avoidance side lane line type, and the position information and motion state information of the target obstacle;

[0048] Specifically, as Figure 2 shown, the environmental data within a certain range around the vehicle is collected by the external environment sensor mounted on the vehicle, and the external environment sensor includes a camera, an infrared sensor, a millimeter wave radar, etc. The acquired environmental data includes the current positioning of the ego vehicle, the motion state information of the ego vehicle, the avoidance side lane line type, the position information of the target obstacle, and the motion state information of the obstacle. The useful target obstacles are selected from the target obstacles for judgment, and the useful target obstacles include cars, trucks, special-shaped vehicles, pedestrians, cone barrels, water barriers, bicycles, etc. The present embodiment takes a moving vehicle as an example for description.

[0049] S2: obtaining a lateral distance of the target obstacle based on the position information of the target obstacle;

[0050] Preferably, the obtaining of the lateral distance of the target obstacle based on the position information of the target obstacle comprises: perceiving a center line of a lane line between the target obstacle and the ego vehicle, taking the center line as a reference, measuring a lateral straight-line distance between a side of the target obstacle close to the ego vehicle and the center line according to the position information of the target obstacle, and taking the lateral straight-line distance as the lateral distance.

[0051] Specifically, as shown in FIG. 2, a rectangular region A is formed with the side of the target vehicle close to the ego vehicle and the center line of the lane line as boundaries, and a width value D is taken in the rectangular region A as the lateral distance to the center line. The lateral distance is taken as a judgment condition for lateral position decision, that is, whether to enter the avoidance zone is judged according to the lateral position of the target vehicle. Figure 3

[0052] S3: obtaining a relative longitudinal distance based on the current positioning and the position information of the target obstacle;

[0053] Specifically, the relative longitudinal distance between the ego vehicle and the vehicle running in the adjacent lane can also be obtained in real time based on the vehicle-mounted sensor. The relative longitudinal distance is taken as a judgment condition for longitudinal speed decision, that is, whether the ego vehicle can overtake the target vehicle within a certain time range is judged.

[0054] S4: judging whether to execute the automatic avoidance function based on the motion state information of the ego vehicle, the motion state information of the obstacle, the lateral distance and the relative longitudinal distance, and generating a corresponding automatic avoidance decision result, if yes, executing the automatic avoidance decision result and completing the automatic avoidance according to the avoidance side lane line type, and if no, keeping the current state to perform lane centering driving.

[0055] Preferably, the judging based on the lateral distance and the relative longitudinal distance to generate a corresponding automatic avoidance decision result to determine whether to execute the automatic avoidance function comprises:

[0056] judging whether the lateral distance is less than a preset distance threshold;

[0057] if the lateral distance is less than the distance threshold, calculating an overtaking time according to the relative longitudinal distance, and judging whether the overtaking time is less than a preset time threshold;

[0058] if the overtaking time is less than the time threshold, generating an automatic avoidance decision result, and the automatic avoidance decision result comprises turning on a left turn signal or a right turn signal.

[0059] ​Preferably, the overtakeable time is calculated according to the relative longitudinal distance, comprising: obtaining the first running speed and the first acceleration of the ego vehicle, and the second running speed and the second acceleration of the target obstacle, and calculating the relative longitudinal distance according to the first running speed, the first acceleration, the second running speed and the second acceleration to obtain the overtakeable time.

[0060] Preferably, whether the ego vehicle completes the overtaking of the target obstacle so that the tail of the ego vehicle exceeds the head of the target obstacle and the running speed of the ego vehicle is greater than or equal to the running speed of the target obstacle is a judgment condition.

[0061] Specifically, first, the lateral position decision is used to judge the lateral distance. In this embodiment, the distance threshold D1 is set to 50 CM. If the lateral distance D is within the distance threshold D1, it indicates that the adjacent vehicle is driving close to / pressing the line. However, meeting the lateral position decision is not enough to activate the automatic avoidance function. The longitudinal speed decision is also needed to judge the relative longitudinal distance. The first running speed and the first acceleration of the ego vehicle are obtained through the vehicle speed sensor, and the second running speed and the second acceleration of the target vehicle are obtained through the external environment sensor. The relative longitudinal distance is calculated according to the first running speed, the first acceleration, the second running speed and the second acceleration to obtain the overtakeable time T. In this embodiment, the time threshold T1 is set to 10 seconds. If T calculated is less than T1, it indicates that the overtaking can be successfully completed within T seconds in the future, and the automatic avoidance function is activated. If T calculated is greater than or equal to T1, it indicates that the overtaking cannot be completed within T seconds in the future, and the current lane center driving state is maintained without activating the automatic avoidance function.

[0062] After the automatic avoidance function is activated, the automatic avoidance decision result is executed, and the turn signal on the avoidance side (the other side of the ego vehicle relative to the target vehicle as the avoidance side) is turned on, as shown in FIG. 6. That is, the left turn signal is turned on to warn the traffic participants behind the left side, and to indicate that the ego vehicle performs lateral avoidance and acceleration to start overtaking. Figure 4 By using the linkage mechanism of the automatic avoidance function and the turn signal system, the corresponding turn signal is turned on before the automatic avoidance function is turned on, and the motion trajectory of the ego vehicle is used to remind the traffic participants behind the side, so as to make a psychological preparation to give a deceleration space in advance, so as to avoid collision risk of the automatic avoidance of the ego vehicle.

[0063] Simultaneously, the automatic avoidance decision also needs to be assessed in conjunction with the lane marking type on the avoidance side. The automatic avoidance decision includes large-amplitude and small-amplitude avoidance. If the lane marking type on the avoidance side is dashed, a large-amplitude avoidance is adopted, allowing the vehicle to partially cross the lane marking for lateral avoidance. If the lane marking type on the avoidance side is solid, a small-amplitude avoidance is adopted, allowing the vehicle to perform limited lateral avoidance within the current lane without crossing the lane marking. By combining the lane marking type detection on the avoidance side with the automatic avoidance decision, different levels of automatic avoidance are applied based on the different lane marking types on the avoidance side. This avoids simply applying small-amplitude avoidance, effectively utilizes the space of adjacent lanes, further reduces the risk of collision, and improves safety performance.

[0064] After the automatic avoidance function is activated, it acquires the target vehicle's position data in real time based on external sensors and determines whether overtaking is complete. If overtaking is successful or the target vehicle accelerates away, the automatic avoidance decision determines that avoidance has been completed. At this point, the turn signal is turned off, the steering wheel is straightened, and the vehicle returns to the center of its original lane. Figure 5 As shown. If overtaking is still in progress, meaning the target vehicle is driving alongside your vehicle within the avoidance zone, the automatic avoidance decision will continue to be executed and the turn signal will remain active. Overtaking is completed when the rear of your vehicle passes the front of the target vehicle and your vehicle's speed is greater than or equal to the target vehicle's speed.

[0065] In addition, for stationary objects such as traffic cones and water-filled barriers, since the motion parameters in the acquired obstacle motion information are all zero, automatic avoidance can be completed simply by acquiring its position information, generating and executing automatic avoidance decision results.

[0066] Therefore, this invention obtains an automatic obstacle avoidance decision by acquiring the vehicle's current location, vehicle motion state information, avoidance lane line type, and the location and motion state information of the target obstacle. For actions such as touching / crossing the lane lines of the target obstacle, executing this automatic obstacle avoidance decision can automatically avoid the target obstacle, significantly increasing the driver's sense of security. Simultaneously, it effectively avoids unnecessary braking caused by actions such as touching / crossing lane lines in existing algorithms, reducing the number of braking operations and lowering the vehicle's fuel consumption. This improves the vehicle's autonomous driving performance from multiple perspectives, including comfort, safety, and fuel economy.

[0067] The above solution applies to yielding on the left. If overtaking on the right is permitted, the technical solution of this invention also applies to overtaking on the right, and the turn signal solution can be modified accordingly.

[0068] like Figure 6 As shown, this embodiment can also be implemented through the following detailed steps:

[0069] Step S101: obtaining the current positioning of the ego vehicle, the ego vehicle motion state information, the avoidance side lane line type, and the position information and the obstacle motion state information of the target obstacle;

[0070] Step S102: obtaining the lateral distance of the target obstacle based on the position information of the target obstacle, and obtaining the relative longitudinal distance based on the current positioning and the position information of the target obstacle;

[0071] Step S103: determining whether the target obstacle is in the avoidance area according to the lateral distance;

[0072] If yes, step S104 is executed, and if no, the vehicle is kept to drive in the center and returns to step S103 for continuous determination;

[0073] Step S104: determining whether the ego vehicle overtakes the target obstacle within a preset time threshold according to the ego vehicle motion state information, the obstacle motion state information, and the relative longitudinal distance;

[0074] If yes, step S105 is executed, and if no, the vehicle is kept to drive in the center and returns to step S103 for continuous determination;

[0075] Step S105: turning on the avoidance side turn signal;

[0076] Step S106: determining whether the avoidance side lane line type is a solid line or a dashed line;

[0077] If it is a dashed line, step S107 is executed, and if it is a solid line, step S108 is executed;

[0078] Step S107: adopting a large-amplitude avoidance to allow the ego vehicle to partially cross the avoidance side lane line for lateral avoidance;

[0079] Step S108: adopting a small-amplitude avoidance to allow the ego vehicle to perform lateral avoidance without crossing the line in the current lane;

[0080] Step S109: obtaining the position and motion state data of the target obstacle in real time and determining whether the avoidance is completed;

[0081] If yes, step S110 is executed, and if no, the determination continues until the avoidance is completed by returning to step S109;

[0082] Step S110: turning off the turn signal and returning the vehicle to drive in the original lane in the center.

[0083] The above steps are completed through three main modules: the environmental perception acquisition module, the automatic avoidance decision module, and the decision execution module. The environmental perception acquisition module executes steps S101 to S102. The automatic avoidance decision module includes: a lateral position decision submodule, which executes step S103; a longitudinal position decision submodule, which executes step S104; a turn signal decision submodule, which executes step S105; an avoidance range decision submodule, which executes steps S106 to S108; and a vehicle centering decision submodule, which executes steps S109 to S110. The decision execution module performs corresponding actions based on the output of the automatic avoidance decision module, including turning the turn signals on / off, different lateral avoidance ranges of the vehicle, and steering wheel control.

[0084] Example 2

[0085] like Figure 7 As shown, this embodiment provides an automatic obstacle avoidance decision-making system, including:

[0086] The first acquisition module 21 is used to acquire the current location of the vehicle, the vehicle's motion status information, the type of the side lane line to avoid, and the location information and motion status information of the target obstacle.

[0087] The second acquisition module 22, connected to the first acquisition module 21, is used to acquire the lateral distance of the target obstacle based on the location information of the target obstacle;

[0088] The third acquisition module 23, connected to the first acquisition module 21, is used to acquire the relative longitudinal distance based on the current location and the location information of the target obstacle;

[0089] Automatic avoidance decision module 24, connected to first acquisition module 21, second acquisition module 22 and third acquisition module 23, is used to make judgments based on vehicle motion state information, obstacle motion state information, lateral distance and relative longitudinal distance to generate corresponding automatic avoidance decision results to determine whether to execute automatic avoidance function;

[0090] The automatic avoidance execution module 25 is connected to the automatic avoidance decision module 24. It is used to execute the automatic avoidance decision results and complete the automatic avoidance according to the avoidance side lane line type. After the avoidance is completed, the vehicle will return to the original lane and drive in the center.

[0091] The specific implementation process of the functions and roles of each module in the above system can be found in the implementation process of the corresponding steps in the above method. Therefore, relevant details can be found in the description of the method embodiment, and will not be repeated here. The system embodiment described above is merely illustrative, and some or all of the modules can be selected to achieve the purpose of the present invention according to actual needs.

[0092] Example 3

[0093] As Figure 8 shown, the embodiment provides an electronic device, which comprises a processor 310, a communications interface 320, a memory 330 and a communications bus 340, wherein the processor 310, the communications interface 320 and the memory 330 complete mutual communication through the communications bus 340. The processor 310 can call logical instructions in the memory 330, and the processor 310 executes an automatic avoidance decision method, which comprises:

[0094] obtaining current positioning and vehicle motion state information of a vehicle, avoidance side lane line types, and position information and obstacle motion state information of a target obstacle;

[0095] obtaining a lateral distance of the target obstacle based on the position information of the target obstacle;

[0096] obtaining a relative longitudinal distance based on the current positioning and the position information of the target obstacle;

[0097] judging whether to execute an automatic avoidance function and generating a corresponding automatic avoidance decision result based on the vehicle motion state information, the obstacle motion state information, the lateral distance and the relative longitudinal distance, if yes, executing the automatic avoidance decision result and completing automatic avoidance according to the avoidance side lane line types, and if no, keeping a current state to perform lane center driving.

[0098] In addition, the logical instructions in the memory 330 described above can be implemented in the form of a software function unit and sold or used as an independent product, and can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0099] Embodiment Four

[0100] The embodiment provides a vehicle capable of assisting driving and / or automatic driving, and the vehicle comprises the electronic device described above.

[0101] Embodiment Five

[0102] The embodiment provides a non-transitory computer-readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement an automatic avoidance decision method as described above, and the method comprises the following steps:

[0103] Obtaining current positioning and vehicle motion state information of a vehicle, avoidance side lane line types, and position information and obstacle motion state information of a target obstacle;

[0104] Obtaining a lateral distance of the target obstacle based on the position information of the target obstacle;

[0105] Obtaining a relative longitudinal distance based on the current positioning and the position information of the target obstacle;

[0106] Judging whether to execute an automatic avoidance function based on the vehicle motion state information, the obstacle motion state information, the lateral distance and the relative longitudinal distance, and generating a corresponding automatic avoidance decision result, if yes, executing the automatic avoidance decision result and completing automatic avoidance according to the avoidance side lane line types, and if no, keeping a current state to perform lane center driving.

[0107] From the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be realized by means of software plus a necessary universal hardware platform, and of course, can also be realized by hardware. Based on such understanding, the above technical solutions, essentially or in other words, the part that makes a contribution to the prior art, can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0108] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement to some technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An automatic avoidance decision method characterized by, The method comprises the following steps: acquiring the current position and motion state information of the ego vehicle, the type of the avoidance side lane line, and the position information and motion state information of the target obstacle; acquiring the lateral distance of the target obstacle based on the position information of the target obstacle; acquiring the relative longitudinal distance based on the current position and the position information of the target obstacle; judging whether to execute the automatic avoidance function and generating the corresponding automatic avoidance decision result based on the motion state information of the ego vehicle, the motion state information of the obstacle, the lateral distance, and the relative longitudinal distance, and if so, executing the automatic avoidance decision result and completing the automatic avoidance according to the type of the avoidance side lane line, and if not, keeping the current state to perform lane centering driving; the judgment of whether to execute the automatic avoidance function based on the motion state information of the ego vehicle, the motion state information of the obstacle, the lateral distance, and the relative longitudinal distance comprises: judging whether the lateral distance is less than a preset distance threshold; if the lateral distance is less than the distance threshold, calculating the overtaking time based on the motion state information of the ego vehicle, the motion state information of the obstacle, and the relative longitudinal distance, and judging whether the overtaking time is less than a preset time threshold; if the overtaking time is less than the time threshold, generating the automatic avoidance decision result, which comprises turning on the left turn signal or the right turn signal.

2. The automatic collision avoidance decision method of claim 1, wherein, the acquisition of the lateral distance of the target obstacle based on the position information of the target obstacle comprises: perceiving the center line of the lane line between the target obstacle and the ego vehicle, taking the center line as the reference, measuring the lateral straight-line distance between the side of the target obstacle close to the ego vehicle and the center line according to the position information of the target obstacle, and taking the lateral straight-line distance as the lateral distance.

3. The automatic collision avoidance decision method of claim 1, wherein, the calculation of the overtaking time based on the motion state information of the ego vehicle, the motion state information of the obstacle, and the relative longitudinal distance comprises: acquiring the first driving speed and the first acceleration of the ego vehicle included in the motion state information of the ego vehicle, and the second driving speed and the second acceleration of the target obstacle included in the motion state information of the obstacle, and calculating the relative longitudinal distance based on the first driving speed, the first acceleration, the second driving speed, and the second acceleration to obtain the overtaking time.

4. The automatic collision avoidance decision method of claim 1, wherein, the automatic avoidance decision result further comprises large-scale avoidance and small-scale avoidance, and the execution of the automatic avoidance decision result and the completion of the automatic avoidance according to the type of the avoidance side lane line comprises: judging whether the type of the avoidance side lane line is a solid line or a dashed line; if the type of the avoidance side lane line is a dashed line, large-scale avoidance is adopted, that is, the ego vehicle is allowed to partially cross the avoidance side lane line for lateral avoidance; if the type of the avoidance side lane line is a solid line, small-scale avoidance is adopted, that is, the ego vehicle is allowed to perform lateral avoidance without crossing the line in the current lane; when overtaking the target obstacle or the target obstacle accelerates to drive away, the turn signal is turned off and the original driving lane is returned to centering driving.

5. The automatic collision avoidance decision method of claim 4, wherein, The self-vehicle completes passing the target obstacle with the rear of the self-vehicle passing the head of the target obstacle and the driving speed of the self-vehicle being greater than or equal to the driving speed of the target obstacle.

6. An automatic avoidance decision system characterized by, Comprise: The first acquisition module is configured to acquire the current positioning of the self-vehicle, the motion state information of the self-vehicle, the type of the lane line on the side to be avoided, and the position information and the motion state information of the target obstacle. The second acquisition module is connected to the first acquisition module and is configured to acquire the lateral distance of the target obstacle based on the position information of the target obstacle. The third acquisition module is connected to the first acquisition module and is configured to acquire the relative longitudinal distance based on the current positioning and the position information of the target obstacle. The automatic avoidance decision module is connected to the first acquisition module, the second acquisition module, and the third acquisition module, and is configured to generate a corresponding automatic avoidance decision result based on the motion state information of the self-vehicle, the motion state information of the obstacle, the lateral distance, and the relative longitudinal distance to determine whether to execute the automatic avoidance function. The automatic avoidance execution module is connected to the automatic avoidance decision module and is configured to execute the automatic avoidance decision result and complete the automatic avoidance according to the type of the lane line on the side to be avoided, and to return the self-vehicle to the original lane for central driving after the avoidance is completed. The automatic avoidance decision module is further configured to: determine whether the lateral distance is less than a preset distance threshold; if the lateral distance is less than the distance threshold, calculate a passing time based on the motion state information of the self-vehicle, the motion state information of the obstacle, and the relative longitudinal distance, and determine whether the passing time is less than a preset time threshold; if the passing time is less than the time threshold, generate the automatic avoidance decision result, which includes turning on the left turn signal or turning on the right turn signal.

7. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the program to implement the steps of the automatic avoidance decision method according to any one of claims 1-5.

8. A vehicle capable of assisted driving and / or autonomous driving, characterized in that The vehicle comprises the electronic device according to claim 7. 9.A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the automatic avoidance decision method according to any one of claims 1-5. The computer program is executed by the processor to implement the steps of the automatic avoidance decision method according to any one of claims 1-5.

Images