Autonomous driving lane-keeping control method, system and apparatus, and storage medium

Abstract

An autonomous driving lane-keeping control method, system and apparatus, and a storage medium, which can achieve a high-precision lane-keeping function in through lanes having weak GPS signals and / or in narrow through lanes. The method comprises: according to a control cycle, on the basis of the deviation of an ego vehicle with respect to a lane center line at the previous moment and the deviation observation value of the ego vehicle with respect to the lane center line at the previous moment, obtaining the deviation observation value of the ego vehicle with respect to the lane center line at the current moment; on the basis of the deviation observation value at the current moment, correcting the position of the ego vehicle at the current moment; on the basis of the corrected position of the ego vehicle, acquiring the lane center line at the current moment; and generating a current path on the basis of the lane center line, and performing lane-keeping control on the basis of the current path.

Description

Automatic driving lane keeping control method, system, device and storage medium

[0001] Cross-references

[0002] This application claims priority to Chinese invention application No. 202311033160.1 filed on August 16, 2023, the contents of which are incorporated herein by reference. Technical Field

[0003] This specification relates to the field of autonomous driving technology, and in particular to an autonomous driving lane keeping control method, system, and storage medium. Background Art

[0004] Lane keeping mode is a common mode in autonomous driving technology, enabling autonomous driving by identifying and tracking the lane centerline. However, positioning is unstable in narrow and / or weak GPS lanes (for example, narrow lanes in port yards where stacked containers block the GPS signal), potentially leading to dangerous situations.

[0005] Therefore, it is desirable to provide an autonomous driving lane keeping control solution that can achieve a high-precision lane keeping function on straight lanes with weak GPS signals and / or narrow straight lanes.

[0006] Summary of the Invention

[0007] One or more embodiments of the present specification provide a method for lane keeping control in an autonomous driving manner, the method comprising: obtaining a deviation observation value of the ego vehicle relative to the lane centerline corresponding to the current moment based on a deviation of the ego vehicle relative to the lane centerline corresponding to the previous moment and a deviation observation value of the ego vehicle relative to the lane centerline corresponding to the previous moment according to a control cycle, wherein the deviation corresponding to the previous moment is obtained according to a detection cycle; correcting the ego vehicle position corresponding to the current moment based on the deviation observation value corresponding to the current moment; obtaining the lane centerline corresponding to the current moment based on the corrected ego vehicle position; generating a current path based on the lane centerline, and performing lane keeping control based on the current path.

[0008] One or more embodiments of the present specification provide an autonomous driving lane keeping control system, the autonomous driving lane keeping control system comprising: an observation value acquisition module for obtaining a deviation observation value of the ego vehicle relative to the lane centerline corresponding to the current moment based on the deviation of the ego vehicle relative to the lane centerline corresponding to the previous moment and the deviation observation value of the ego vehicle relative to the lane centerline corresponding to the previous moment according to a control cycle, wherein the deviation corresponding to the previous moment is obtained according to a detection cycle; a correction module for correcting the ego vehicle position corresponding to the current moment based on the deviation observation value corresponding to the current moment; a lane centerline acquisition module for obtaining the lane centerline corresponding to the current moment based on the corrected ego vehicle position; and a path generation module for generating a current path based on the lane centerline and performing lane keeping control based on the current path.

[0009] One or more embodiments of this specification provide an autonomous driving lane keeping control device, which includes at least one storage medium that stores computer instructions; and at least one processor that executes the computer instructions to implement an autonomous driving lane keeping control method.

[0010] One or more embodiments of this specification provide a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes an autonomous driving lane keeping control method. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] This specification will be further described in the form of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting, and in these embodiments, like numbers represent like structures, wherein:

[0012] FIG1 is a schematic diagram of an application scenario of an exemplary autonomous driving lane keeping control system according to some embodiments of this specification;

[0013] FIG2 is a block diagram of an exemplary autonomous driving lane keeping control system according to some embodiments of this specification;

[0014] FIG3 is a flowchart of an exemplary automatic driving lane keeping control method according to some embodiments of this specification;

[0015] FIG4 is a flowchart of an exemplary method for obtaining an observation value of a vehicle deviation at a current moment according to some embodiments of this specification;

[0016] FIG5 is a flowchart of an exemplary lane control mode switching method according to some embodiments of this specification;

[0017] FIG6 is a schematic diagram of an exemplary detection cycle and a control cycle according to some embodiments of this specification;

[0018] FIG7 is a schematic diagram of an exemplary deviation of a vehicle relative to a lane centerline according to some embodiments of this specification;

[0019] 8A and 8B are schematic diagrams of exemplary generation of a current path according to some embodiments of the present specification. DETAILED DESCRIPTION

[0020] To more clearly illustrate the technical solutions of the embodiments of this specification, the following briefly describes the drawings required for describing the embodiments. Obviously, the drawings described below are merely examples or embodiments of this specification. Those skilled in the art can apply this specification to other similar scenarios based on these drawings without inventive effort. Unless otherwise apparent from the context or otherwise noted, the same reference numerals in the figures represent the same structure or operation.

[0021] It should be understood that the terms "system," "device," "unit," and / or "module" used herein are a method for distinguishing different components, elements, parts, portions, or assemblies at different levels. However, if other terms can achieve the same purpose, the terms may be replaced by other expressions.

[0022] As used in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not refer to the singular but also include the plural. Generally speaking, the terms "comprises" and "include" only indicate the inclusion of the steps and elements specifically identified, and these steps and elements do not constitute an exclusive list. A method or apparatus may also include other steps or elements.

[0023] Flowcharts are used throughout this specification to illustrate the operations performed by systems according to embodiments of this specification. It should be understood that the preceding and following operations do not necessarily need to be performed in exact order. Instead, the steps may be processed in reverse order or simultaneously. Furthermore, other operations may be added to these processes.

[0024] Figure 1 is a schematic diagram of an exemplary application scenario for an autonomous driving lane keeping control system according to some embodiments of this specification. In some embodiments, application scenarios 100 of the autonomous driving lane keeping control system may include various autonomous driving scenarios, such as private autonomous vehicles, shared autonomous vehicles, and unmanned autonomous trucks. In some embodiments, application scenarios 100 of the autonomous driving lane keeping control system may achieve high-precision lane keeping functionality by implementing the methods and / or processes disclosed herein.

[0025] In some embodiments, as shown in FIG1 , an application scenario 100 of an autonomous driving lane keeping control system may include a processing device 110 , a vehicle 120 , a terminal device 130 , a storage device 140 , and a network 150 .

[0026] The processing device 110 can be configured to process data and / or information from at least one component of the autonomous driving lane keeping control system application scenario 100 or an external data source (e.g., a cloud data center). For example, the processing device 110 can, based on the deviation of the ego vehicle relative to the lane centerline at a previous moment and the observed deviation of the ego vehicle relative to the lane centerline at a previous moment, determine an observed deviation of the ego vehicle relative to the lane centerline at a current moment, according to a control cycle. For another example, the processing device 110 can determine, based on an electronic map received from the first terminal device 130, a lane centerline that is a first preset distance from the corrected ego vehicle position on the electronic map as the lane centerline at the current moment. In some embodiments, the processing device 110 can include a central processing unit (CPU), a digital signal processor (DSP), a system on a chip (SoC), a microcontroller unit (MCU), a computer, a user console, or any combination thereof. In some embodiments, the processing device 110 can include a single server or a server group. The server group can be centralized or distributed. In some embodiments, the processing device 110 can be local or remote. In some embodiments, the processing device 110 can be implemented on a cloud platform. By way of example only, a cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an on-premises cloud, a multi-tier cloud, the like, or any combination thereof.

[0027] Vehicle 120 may be a transportation service vehicle for application scenario 100 of an autonomous driving lane keeping control system. In some embodiments, vehicle 120 may include a private autonomous vehicle, a shared autonomous vehicle, an unmanned autonomous freight vehicle, or the like. In some embodiments, vehicle 120 may receive instructions from processing device 110 and perform corresponding tasks in accordance with the instructions. For example, vehicle 120 may receive instructions to enter lane keeping mode, exit lane keeping mode, enter regular driving mode, or control vehicle parking, and automatically control vehicle 120 to perform the corresponding operations. In some embodiments, vehicle 120 may include a positioning component (e.g., a GPS module), an image acquisition component (e.g., a camera), sensors (e.g., a radar sensor, an ultrasonic sensor, a laser sensor, an inertial measurement unit sensor), or the like. In some embodiments, vehicle 120 may communicate with processing device 110 via network 150. For example, vehicle 120 may send its current vehicle position to processing device 110 via network 150.

[0028] The terminal device 130 may be a terminal device that displays an electronic map and / or a vehicle path. In some embodiments, the terminal device 130 may be installed on the vehicle 120 or be a component of the vehicle 120. In some embodiments, the terminal device 130 may receive the electronic map, vehicle path, etc. from the processing device 110 via a network and display the information to the user on a screen. In some embodiments, the terminal device 130 may include a mobile device, a tablet computer, a laptop computer, other devices with input and / or output functions, or any combination thereof.

[0029] The storage device 140 can be used to store data, instructions, and / or any other information. For example, the storage device can store the deviation of the vehicle relative to the lane centerline at the previous moment, the historical path, etc. In some embodiments, the storage device may include random access memory (RAM), read-only memory (ROM), mass storage, removable storage, volatile read-write memory, etc., or any combination thereof. In some embodiments, the storage device can be integrated or included in one or more other components of the application scenario 100 of the autonomous driving lane keeping control system (e.g., the processing device 110, the vehicle 120, the terminal device 130).

[0030] Network 150 can facilitate the exchange of information and / or data. In some embodiments, one or more components of the autonomous driving lane keeping control system application scenario 100 (e.g., processing device 110, vehicle 120, terminal device 130, storage device 140) can transmit information and / or data to other components of the autonomous driving lane keeping control system application scenario 100 via network 150. In some embodiments, network 150 can include any one or more of a wired network or a wireless network. In some embodiments, network 150 can include a cable network, a fiber optic network, a telecommunications network, the Internet, a local area network (LAN), a wide area network (WAN), a wireless local area network (WLAN), a metropolitan area network (MAN), a public switched telephone network (PSTN), a Bluetooth network, a ZigBee network, near-field communication (NFC), an intra-device bus, an intra-device line, a cable connection, or any combination thereof. In some embodiments, the network connections between the components of the autonomous driving lane keeping control system application scenario 100 can adopt one of the aforementioned methods or a combination of methods. In some embodiments, the network can have various topologies, such as point-to-point, shared, or centralized, or a combination of multiple topologies.

[0031] It is worth noting that the application scenario 100 of the autonomous driving lane keeping control system is provided for illustrative purposes only and is not intended to limit the scope of this specification. A person skilled in the art can make various changes and modifications based on the description of this specification. For example, the application scenario 100 of the autonomous driving lane keeping control system may also include a database, an information source, and the like. For another example, the application scenario 100 of the autonomous driving lane keeping control system may be implemented on other devices to achieve similar or different functions. However, these changes and modifications do not deviate from the scope of this specification.

[0032] FIG2 is a block diagram of an exemplary autonomous driving lane keeping control system according to some embodiments of this specification. In some embodiments, autonomous driving lane keeping control system 200 may be implemented by processing device 110. In some embodiments, as shown in FIG2 , autonomous driving lane keeping control system 200 may include an observation value acquisition module 210, a correction module 220, a lane centerline acquisition module 230, and / or a path generation module 240.

[0033] The observation value acquisition module 210 can be configured to obtain an observed value of the ego vehicle's deviation relative to the lane centerline at a current moment based on the ego vehicle's deviation relative to the lane centerline at a previous moment and the observed value of the ego vehicle's deviation relative to the lane centerline at a previous moment, according to a control cycle. In some embodiments, the deviation at a previous moment is obtained according to a detection cycle. In some embodiments, the observation value acquisition module 210 can perform one or more of the following operations: obtaining an increment of the ego vehicle's deviation relative to the lane centerline at a previous moment within the control cycle based on the lateral velocity and the rate of change of the heading angle of the ego vehicle; determining an estimated deviation of the ego vehicle relative to the lane centerline at a current moment based on the increment of the ego vehicle's deviation relative to the lane centerline at a previous moment within the control cycle and the observed value of the ego vehicle's deviation relative to the lane centerline at a previous moment; and obtaining an observed value of the ego vehicle's deviation relative to the lane centerline at a current moment through an observer based on the estimated deviation of the ego vehicle relative to the lane centerline at a current moment, the ego vehicle's deviation relative to the lane centerline at a previous moment, and the observed value of the ego vehicle's deviation relative to the lane centerline at a previous moment. In some embodiments, the observation value acquisition module 210 may perform one or more of the following operations: obtaining the motion difference between the ego vehicle's deviation relative to the lane centerline at the previous moment and the observed deviation value of the ego vehicle relative to the lane centerline at the previous moment; obtaining the calculated observation value corresponding to the previous moment based on the observer and the motion difference value corresponding to the previous moment; and obtaining the observed deviation value of the ego vehicle relative to the lane centerline at the current moment based on the estimated deviation of the ego vehicle relative to the lane centerline at the current moment and the calculated observation value corresponding to the previous moment. In some embodiments, the observer is a diagonal matrix. In some embodiments, the diagonal matrix includes a first coefficient and a second coefficient, and the first coefficient and the second coefficient are greater than 0 and less than 1. In some embodiments, the first coefficient corresponds to the confidence level of the ego vehicle's deviation relative to the lane centerline at the previous moment, and the second coefficient corresponds to the confidence level of the observed deviation value of the ego vehicle relative to the lane centerline at the previous moment. In some embodiments, at least one of the first coefficient and the second coefficient is determined based on the ego vehicle's environmental information.

[0034] The correction module 220 may be configured to correct the vehicle position corresponding to the current moment based on the deviation observation value corresponding to the current moment.

[0035] The lane centerline acquisition module 230 may be configured to acquire the lane centerline corresponding to the current moment based on the corrected vehicle position.

[0036] The path generation module 240 can be used to generate a current path based on the lane centerline and perform lane keeping control based on the current path. In some embodiments, when entering lane keeping mode for the first time, the current path is based on the corrected ego vehicle position and the lane centerline curve. In some embodiments, when entering lane keeping mode for a different time, the current path is based on the concatenation of historical paths and the lane centerline. In some embodiments, the path generation module 240 can perform one or more of the following operations: determining whether the lane line detection result is valid and whether the deviation of the ego vehicle relative to the lane centerline detected during the detection cycle meets a first preset condition; in response to the lane line detection result being valid and the deviation of the ego vehicle relative to the lane centerline detected during the detection cycle meeting the first preset condition, determining the deviation observation value corresponding to the current moment; otherwise, exiting lane keeping control mode. In some embodiments, the path generation module 240 can perform one or more of the following operations: after exiting lane keeping control mode, determining whether the relative position relationship between the ego vehicle and the lane centerline meets a second preset condition; in response to the relative position relationship not meeting the second preset condition, implementing a vehicle stop; in response to the relative position relationship meeting the second preset condition, entering normal control mode.

[0037] It should be noted that the above description of the autonomous driving lane keeping control system 200 and its modules is for convenience of description only and does not limit this specification to the scope of the embodiments cited. It is understandable that for those skilled in the art, after understanding the principle of the device, it is possible to arbitrarily combine the various modules, or form sub-devices to connect with other modules without deviating from this principle. In some embodiments, the modules disclosed in Figure 2 can be different modules in a system, or a module can implement the functions of two or more modules mentioned above. For example, the modules can share a storage module, or each module can have its own storage module. Such variations are all within the scope of protection of this specification.

[0038] FIG3 is a flowchart of an exemplary autonomous driving lane keeping control method according to some embodiments of this specification. In some embodiments, process 300 can be executed by processing device 110 or autonomous driving lane keeping control system 200. For example, process 300 can be stored in a storage device in the form of a program or instructions, and when processing device 110 or autonomous driving lane keeping control system 200 executes the instructions, process 300 can be implemented. The operational diagram of process 300 presented below is illustrative. In some embodiments, the process can be completed using one or more additional operations not described and / or one or more operations not discussed. In addition, the order of the operations of process 300 shown in FIG3 and described below is not limiting.

[0039] In step 310, based on the deviation of the ego vehicle relative to the lane centerline at the previous moment and the observed deviation of the ego vehicle relative to the lane centerline at the previous moment, an observed deviation value of the ego vehicle relative to the lane centerline at the current moment is obtained, according to the control cycle. Specifically, step 310 may be performed by observation value acquisition module 210.

[0040] The control cycle can be the period for correcting the ego vehicle's position. That is, the current moment when the ego vehicle's position is corrected can be separated by a control cycle from the previous moment when the ego vehicle's position was corrected. For example, a control cycle can be 25 milliseconds or 10 milliseconds. As an example, Figure 6 is a schematic diagram of exemplary detection cycles and control cycles according to some embodiments of this specification. As shown in Figure 6 , the control cycle is Δt. After the ego vehicle's position was corrected at the previous moment tk, the ego vehicle's position needs to be corrected again at the current moment t(k+1) = tk + Δt.

[0041] The deviation of the ego vehicle relative to the lane centerline may be a deviation value between the ego vehicle and the lane centerline obtained through detection. In some embodiments, the deviation of the ego vehicle relative to the lane centerline may be represented by the ego vehicle angle deviation and the ego vehicle lateral deviation. The ego vehicle angle deviation may be the angle between the vertical axis of the ego vehicle and the lane centerline, and the ego vehicle lateral deviation may be the distance between the center point of the ego vehicle's rear wheel axle (i.e., the intersection of the rear wheel connection line and the ego vehicle's vertical axis) and the lane centerline. For example only, FIG7 is a schematic diagram of an exemplary ego vehicle's deviation relative to the lane centerline according to some embodiments of this specification. As shown in FIG7 , the ego vehicle angle deviation is The lateral deviation of the ego vehicle is Δy, and the deviation of the ego vehicle relative to the lane centerline can be

[0042] In some embodiments, the observation value acquisition module 210 can first obtain the lane sideline images on both sides of the lane where the vehicle is currently located through the vehicle's camera, and determine the lane centerline position based on the lane sideline images on both sides. Then, based on the lane centerline position and the vehicle's current position, the deviation of the vehicle relative to the lane centerline can be calculated using the vehicle's angular deviation and the vehicle's lateral deviation.

[0043] In some embodiments, the deviation corresponding to the previous moment is obtained according to a detection cycle. The detection cycle can be the period for detecting the deviation of the ego vehicle relative to the lane centerline. In other words, the interval between two adjacent moments in which the ego vehicle's deviation relative to the lane centerline is one detection cycle, for example, 100 milliseconds. As an example only, as shown in FIG6 , the detection cycle is ΔT, and the interval between adjacent moments T0 and T1 in which the ego vehicle's deviation relative to the lane centerline is one detection cycle ΔT, i.e., the first detection cycle.

[0044] In some embodiments, the deviation of the ego vehicle relative to the lane centerline at any time within the same detection cycle is the same as the deviation of the ego vehicle relative to the lane centerline detected at the first time within the detection cycle. As an example only, as shown in FIG6 , the deviation of the ego vehicle relative to the lane centerline at any time (e.g., t0 and t1) within the first detection cycle is equal to the deviation of the ego vehicle relative to the lane centerline detected at the first time T0 within the detection cycle, that is, z(t0)=z(t1)=z(1)=z(T0).

[0045] In some embodiments, the observation value acquisition module 210 may determine the detection period corresponding to the previous moment, and then determine the deviation of the ego vehicle relative to the lane centerline corresponding to the detection period corresponding to the previous moment as the deviation corresponding to the previous moment. As an example, as shown in FIG6 , if the last moment tk at which the ego vehicle position was corrected falls within the nth detection period, the deviation of the ego vehicle relative to the lane centerline corresponding to the nth detection period corresponding to tk is used as the deviation corresponding to tk, i.e., z(tk) = z(n).

[0046] When the previous moment is the starting moment of the ego vehicle movement, the corresponding deviation observation value of the ego vehicle relative to the lane centerline is 0. For example, if the current moment is t1, the deviation observation value of the ego vehicle relative to the lane centerline corresponding to the previous moment t0 is When the previous moment is not the start moment of the ego vehicle's motion, the corresponding deviation observation value of the ego vehicle relative to the lane centerline can be obtained by referring to Figure 4 and its related description. For example, if the current moment is t(k+1), then the deviation observation value of the ego vehicle relative to the lane centerline corresponding to the previous moment tk is The deviation of the ego vehicle relative to the lane centerline at the previous moment t(k-1) of tk can be calculated based on the increment μ(t(k-1)) of the deviation of the ego vehicle relative to the lane centerline during the control cycle and the corresponding observation value of the deviation of the ego vehicle relative to the lane centerline. Get.

[0047] The deviation observation value of the ego vehicle relative to the lane centerline at the current moment is used to correct the position of the ego vehicle in the lateral deviation direction and the angular deviation direction at the current moment. For example, For a detailed description of obtaining the deviation observation value of the ego vehicle relative to the lane centerline corresponding to the current moment, please refer to Figure 4 and its related description, which will not be repeated here.

[0048] Step 320 , based on the deviation observation value corresponding to the current moment, correct the vehicle position corresponding to the current moment. Specifically, step 320 may be performed by the correction module 220 .

[0049] The vehicle position corresponding to the current moment may be the vehicle's position in the world coordinate system at the current moment. In some embodiments, the correction module 220 may obtain the vehicle position at the current moment using the vehicle's GPS module. For example, the vehicle position corresponding to the current moment is p(t(k+1)).

[0050] In some embodiments, the correction module 220 can convert the deviation observation value corresponding to the current moment in the vehicle coordinate system into the conversion deviation observation value corresponding to the current moment in the world coordinate system, and then use the conversion deviation observation value corresponding to the previous moment to correct the vehicle position corresponding to the current moment to obtain the corrected vehicle position. Convert to world coordinate system Then, the vehicle position corresponding to the current moment is corrected to obtain the corrected vehicle position p'(t(k+1)) in the world coordinate system = By correcting the vehicle's position, lane keeping can be achieved even if the vehicle's position obtained by satellite positioning changes due to the signal.

[0051] Step 330 , based on the corrected vehicle position, obtain the lane centerline corresponding to the current moment. Specifically, step 330 may be performed by the lane centerline acquisition module 230 .

[0052] In some embodiments, the lane centerline acquisition module 230 may determine a lane centerline that is a first preset length from the corrected vehicle position on the electronic map as the lane centerline corresponding to the current moment. The first preset length may be a pre-set length, for example, 50 meters.

[0053] Step 340 : Generate a current path based on the lane centerline and perform lane keeping control based on the current path. Specifically, step 340 may be performed by the path generation module 240 .

[0054] In some embodiments, when lane keeping mode is first entered, the current path may be connected by a curve based on the corrected vehicle position and the lane centerline. Specifically, the path generation module 240 may first determine a point on the electronic map that is a second preset distance from the corrected vehicle position, and then connect this point with a point on the lane centerline using a curve to generate the current path. The second preset length may be a manually set length that is less than the first preset length, for example, 20 meters.

[0055] As an example only, Figures 8A and 8B are schematic diagrams of exemplary generation of the current path according to some embodiments of this specification. As shown in Figure 8A, when the vehicle enters the lane keeping mode for the first time, the path generation module 240 can first determine point A 20 meters away from the corrected vehicle position on the electronic map, and then use the Dubin curve to connect point A and point B on the lane centerline corresponding to the current moment to generate the current path.

[0056] In some embodiments, when this is not the first time the lane keeping mode is entered, the current path can be spliced ​​with the lane centerline based on the historical path. The historical path can be a path generated at the previous moment. Specifically, the path generation module 240 can first intercept the historical path from the corrected vehicle position on the electronic map, and then splice it with the lane centerline corresponding to the current moment into the current path. As an example only, as shown in Figure 8B, when this is not the first time the vehicle enters the lane keeping mode, the path generation module 240 can intercept the historical path of a first preset length from the corrected vehicle position on the electronic map, and then splice the intercepted historical path of the first preset length and the lane centerline corresponding to the current moment into the current path.

[0057] In order to avoid point jumps on the current path, in some embodiments, the path generation module 240 may smooth the current path using a smoothing algorithm.

[0058] In some embodiments of this specification, the current path is generated by splicing the lane centerline corresponding to the current moment based on the corrected vehicle position, which can prevent point jumps on the current path.

[0059] Lane keeping mode is an assisted autonomous driving mode that uses a lateral controller to track the current path. In some embodiments, the path generation module 240 can convert the current path in the world coordinate system to the current vehicle path in the vehicle coordinate system, and then input the current vehicle path into the lateral controller of the vehicle, thereby controlling the vehicle to perform lane keeping control.

[0060] In some embodiments, before entering the lane keeping mode, the path generation module 240 may first determine whether the vehicle has entered the lane keeping mode. A detailed description of determining whether the vehicle has entered the lane keeping mode can be found in FIG. 5 and its related description, which will not be repeated here.

[0061] It should be noted that the above description of process 300 is provided for illustrative purposes only and is not intended to limit the scope of this specification. A person of ordinary skill in the art may make various changes and modifications based on the description of this specification. However, such changes and modifications do not depart from the scope of this specification. In some embodiments, process 300 may include one or more additional operations, or may omit one or more of the above operations.

[0062] In some embodiments of this specification, the vehicle position corresponding to the current moment is corrected according to the deviation observation value corresponding to the current moment, and a path is generated in combination with the lane centerline obtained from the electronic map, thereby achieving a high-precision lane keeping function.

[0063] FIG4 is a flowchart of an exemplary method for obtaining an observation value of the vehicle deviation at the current moment according to some embodiments of this specification. In some embodiments, process 400 can be executed by the processing device 110 or the autonomous driving lane keeping control system 200 (e.g., the observation value acquisition module 210). For example, process 400 can be stored in a storage device in the form of a program or instructions, and when the processing device 110 or the autonomous driving lane keeping control system 200 (e.g., the observation value acquisition module 210) executes the instructions, process 400 can be implemented. The operational diagram of process 400 presented below is illustrative. In some embodiments, the process can be completed using one or more additional operations not described and / or one or more operations not discussed. In addition, the order of the operations of process 400 shown in FIG4 and described below is not restrictive.

[0064] Step 410 : Based on the lateral velocity and the rate of change of the heading angle of the ego vehicle, obtain the increment of the deviation of the ego vehicle relative to the lane centerline corresponding to the last moment within the control cycle.

[0065] The lateral velocity of the ego vehicle is the velocity of the ego vehicle in the lateral deviation direction at the last moment. For example, v y (tk). The ego vehicle's heading angle change rate is the speed at which the ego vehicle rotates in the direction of the ego vehicle's angle deviation at the previous moment. For example, ω(tk).

[0066] The increment of the ego vehicle's deviation from the lane centerline at the previous moment within the control cycle includes the increment of the ego vehicle's lateral deviation within the control cycle and the increment of the ego vehicle's angular deviation within the control cycle. The increment of the ego vehicle's lateral deviation within the control cycle is the length of movement of the ego vehicle in the direction of the ego vehicle's lateral deviation from the previous moment to the current moment in the control cycle. The increment of the ego vehicle's angular deviation within the control cycle is the rotation angle of the ego vehicle in the direction of the ego vehicle's angular deviation from the previous moment to the current moment in the control cycle.

[0067] Specifically, the observation value acquisition module 210 can obtain the increment of the lateral deviation of the ego vehicle relative to the lane centerline during the control cycle corresponding to the last moment based on the lateral speed of the ego vehicle and the time length of the control cycle; and obtain the increment of the angular deviation of the ego vehicle relative to the lane centerline during the control cycle corresponding to the last moment based on the heading angle change rate of the ego vehicle and the time length of the control cycle. In some embodiments, the observation value acquisition module 210 can obtain the increment of the deviation of the ego vehicle relative to the lane centerline during the control cycle corresponding to the last moment using formula (1). μ(tk)=[v y (tk)*Δt,ω(tk)*Δt] (1)

[0068] Among them, tk is the previous moment, v y (tk) is the lateral velocity of the ego vehicle at the previous moment, ω(tk) is the rate of change of the ego vehicle's heading angle at the previous moment, Δt is the duration of the control cycle, and μ(tk) is the increment of the ego vehicle's deviation from the lane centerline at the previous moment within the control cycle.

[0069] Step 420 , based on the increment of the deviation of the ego vehicle relative to the lane centerline corresponding to the previous moment within the control cycle and the observed deviation value of the ego vehicle relative to the lane centerline corresponding to the previous moment, determine the deviation estimate of the ego vehicle relative to the lane centerline corresponding to the current moment.

[0070] The estimated deviation of the ego vehicle relative to the lane centerline at the current moment is the calculated deviation value of the ego vehicle relative to the lane centerline at the current moment. In some embodiments, the observation value acquisition module 210 can calculate the estimated deviation of the ego vehicle relative to the lane centerline at the current moment based on the sum of the increment of the deviation of the ego vehicle relative to the lane centerline at the previous moment within the control cycle and the observed deviation value of the ego vehicle relative to the lane centerline at the previous moment. In some embodiments, the observation value acquisition module 210 can calculate the estimated deviation of the ego vehicle relative to the lane centerline at the current moment using formula (2).

[0071] Among them, tk is the previous moment, t(k+1) is the current moment, is the observed deviation of the ego vehicle relative to the lane centerline at the previous moment, μ(tk) is the increment of the deviation of the ego vehicle relative to the lane centerline at the previous moment within the control cycle, is the deviation estimate of the vehicle relative to the lane centerline at the current moment.

[0072] In step 430, an observer is used to obtain an observed deviation value of the ego vehicle relative to the lane centerline corresponding to the current moment based on the estimated deviation of the ego vehicle relative to the lane centerline corresponding to the current moment, the deviation of the ego vehicle relative to the lane centerline corresponding to the previous moment, and the observed deviation value of the ego vehicle relative to the lane centerline corresponding to the previous moment.

[0073] In some embodiments, the observation value acquisition module 210 may obtain a motion difference between the deviation of the ego vehicle relative to the lane centerline at a previous moment and the observed deviation of the ego vehicle relative to the lane centerline at a previous moment. The motion difference between the deviation of the ego vehicle relative to the lane centerline at a previous moment and the observed deviation of the ego vehicle relative to the lane centerline at a previous moment may reflect the difference between the deviations of the ego vehicle relative to the lane centerline at a previous moment obtained by both detection and calculation.

[0074] In some embodiments, the observation value acquisition module 210 may acquire the observation calculation value corresponding to the previous moment based on the motion difference between the observer and the previous moment.

[0075] The observer can be a matrix used to observe the motion difference corresponding to the previous moment, that is, a matrix that assigns confidence levels to the deviation values ​​of the ego vehicle relative to the lane centerline corresponding to the previous moment obtained using two methods. In some embodiments, the observer is a diagonal matrix that can include a first coefficient and a second coefficient. In some embodiments, the first coefficient and the second coefficient are greater than 0 and less than 1. For example only, the observer can be a Luenberger linear observer.

[0076] In some embodiments, the first coefficient corresponds to the confidence level of the ego vehicle's deviation from the lane centerline at the previous moment, and the second coefficient corresponds to the confidence level of the observed deviation from the lane centerline at the previous moment. It will be appreciated that a larger first coefficient indicates a higher level of confidence in the ego vehicle's deviation from the lane centerline obtained through detection, while a larger second coefficient indicates a higher level of confidence in the ego vehicle's deviation from the lane centerline obtained through calculation.

[0077] In some embodiments, at least one of the first coefficient and the second coefficient is determined based on vehicle environment information. Vehicle environment information is information reflecting the current driving environment of the vehicle. In some embodiments, vehicle environment information may include, but is not limited to, weather information, road condition information, and time information.

[0078] Weather information can indicate the weather conditions during driving, such as clear, rainy, and foggy weather. When the weather is clear, detection accuracy is higher, the first coefficient is larger, and the observer has higher confidence in the deviation value of the ego vehicle relative to the lane centerline obtained through detection. When the weather is rainy or foggy, detection accuracy is lower, the second coefficient is larger, and the observer has higher confidence in the deviation value of the ego vehicle relative to the lane centerline obtained through calculation.

[0079] Road condition information can reflect information about road markings (e.g., whether lane edges are clear or obscured) and road surface roughness (e.g., whether the road surface is smooth). When road markings are unclear and / or the road surface is rough, detection accuracy is low, and the second coefficient is larger, indicating a higher degree of confidence in the calculated deviation of the ego vehicle from the lane centerline. Conversely, when the first coefficient is larger, the observer has a higher degree of confidence in the detected deviation of the ego vehicle from the lane centerline.

[0080] Time information can reflect whether the lane is in peak traffic. During peak traffic hours, the lane is congested and detection accuracy is low, so the second coefficient is larger, and the observer has greater confidence in the calculated deviation of the ego vehicle from the lane centerline. Conversely, when the first coefficient is larger, the observer has greater confidence in the detected deviation of the ego vehicle from the lane centerline.

[0081] In some embodiments, the observation value acquisition module 210 may determine the first coefficient and the second coefficient using an observer model. Specifically, the observation value acquisition module 210 may fuse the input vehicle environment information into a vector and map the vector into the first coefficient and the second coefficient. In some embodiments, the observer model may include, but is not limited to, a support vector machine model, a logistic regression model, a naive Bayesian classification model, a Gaussian distribution Bayesian classification model, a decision tree model, a random forest model, a KNN classification model, a neural network model, and the like.

[0082] In some embodiments of the present specification, an observer determines a first coefficient and a second coefficient based on information about the vehicle's environment, and then determines, based on the first coefficient and the second coefficient, a confidence level of a deviation value of the vehicle relative to the lane centerline corresponding to a previous moment obtained using two methods, such that the motion calculation value corresponding to the previous moment obtained by the observer can change based on changes in the vehicle's environment, thereby achieving autonomous driving lane keeping in different environments.

[0083] The observed calculation value corresponding to the previous moment can be a deviation correction of the ego vehicle relative to the lane centerline calculated after observing the motion difference corresponding to the previous moment (i.e., assigning confidence to the deviation values ​​of the ego vehicle relative to the lane centerline corresponding to the previous moment obtained by two methods).

[0084] In some embodiments, the observation value acquisition module 210 can obtain the motion calculation value corresponding to the previous moment through formula (3).

[0085] Among them, tk is the previous moment, is the motion difference corresponding to the previous moment, G is the observer, and H(tk) is the motion calculation value corresponding to the previous moment.

[0086] In some embodiments, the observation value acquisition module 210 can obtain the deviation observation value of the vehicle relative to the lane centerline corresponding to the current moment based on the deviation estimate of the vehicle relative to the lane centerline corresponding to the current moment and the motion calculation value corresponding to the previous moment.

[0087] In some embodiments, the observation value acquisition module 210 can obtain the deviation observation value of the vehicle relative to the lane centerline corresponding to the current moment through formula (4).

[0088] Among them, tk is the previous moment, t(k+1) is the current moment, is the deviation observation value of the vehicle relative to the lane centerline at the current moment, is the deviation estimate of the vehicle relative to the lane centerline at the current moment, and H(tk) is the motion calculation value corresponding to the previous moment.

[0089] In some embodiments of the present specification, an observer is used to observe the deviation estimates of the ego vehicle relative to the lane centerline obtained by two methods. When the detection period and the control period are inconsistent, resulting in a low degree of confidence in the deviation estimate of the ego vehicle relative to the lane centerline obtained by detection, the deviation estimate of the ego vehicle relative to the lane centerline obtained by calculation can be further relied upon to determine the motion calculation value corresponding to the previous moment, thereby improving the control accuracy of lane keeping.

[0090] It should be noted that the above description of process 400 is provided for illustrative purposes only and is not intended to limit the scope of this specification. Those skilled in the art may make various changes and modifications based on the description of this specification. However, such changes and modifications do not depart from the scope of this specification. In some embodiments, process 400 may include one or more additional operations, or may omit one or more of the above operations.

[0091] In some embodiments of the present specification, based on the deviation estimate of the ego vehicle relative to the lane centerline corresponding to the current moment and the motion calculation value corresponding to the previous moment obtained by the observer, the deviation observation value of the ego vehicle relative to the lane centerline corresponding to the current moment is obtained. The deviation estimate of the ego vehicle relative to the lane centerline corresponding to the current moment obtained by inspection can be corrected by the observer, thereby resolving the error caused by the inconsistency between the detection cycle and the control cycle, thereby improving the control accuracy of lane keeping.

[0092] FIG5 is a flowchart of an exemplary lane control mode switching method according to some embodiments of the present specification. In some embodiments, process 500 can be executed by processing device 110 or autonomous driving lane keeping control system 200 (e.g., path generation module 240). For example, process 500 can be stored in a storage device in the form of a program or instructions, and process 500 can be implemented when processing device 110 or autonomous driving lane keeping control system 200 (e.g., path generation module 240) executes the instructions. The operational diagram of process 500 presented below is illustrative. In some embodiments, the process can be completed using one or more additional operations not described and / or one or more operations not discussed. In addition, the order of the operations of process 500 shown in FIG5 and described below is not restrictive.

[0093] In step 510 , the path generation module 240 may determine whether the lane detection result is valid and whether the deviation of the ego vehicle relative to the lane centerline detected during the detection period meets a first preset condition.

[0094] The lane detection result may be an image of the lane borders on both sides of the lane in which the vehicle is currently located. For a description of obtaining the lane detection result, see step 310 and will not be repeated here. In some embodiments, the path generation module 240 may use an image recognition model to identify whether the lane borders on both sides of the image are missing, damaged, or obscured. If so, the lane detection result is invalid; otherwise, the lane detection result is valid.

[0095] The first preset condition can be a condition for determining whether the deviation of the vehicle relative to the lane centerline detected during the detection period can safely enter the lane keeping mode. The first preset condition can be a condition set manually. For example, the first preset condition can be the vehicle angle deviation The lateral deviation of the vehicle Δy≤5m.

[0096] In step 520, the path generation module 240 determines the deviation observation value corresponding to the current moment in response to the lane line detection result being valid and the deviation of the vehicle relative to the lane centerline detected during the detection period meeting the first preset condition. Otherwise, the lane keeping control mode is exited. For a detailed description of determining the deviation observation value corresponding to the current moment, please refer to step 310 and will not be repeated here. For example only, the lane line detection result at the current moment t(k+1) is valid, and Δy(t(k+1))=3m<5m, then the deviation observation value corresponding to the current time t(k+1) can be determined

[0097] In some embodiments, in response to exiting the lane keeping control mode, the path generation module 240 determines whether the relative position relationship between the ego vehicle and the lane centerline satisfies a second preset condition. The second preset condition can be a condition for determining whether the current relative position relationship between the ego vehicle and the lane centerline is safe for entering the normal driving mode. The second preset condition can be a manually preset condition. For example, the second preset condition can be the ego vehicle angle deviation The lateral deviation of the vehicle Δy≤2m.

[0098] In some embodiments, the path generation module 240 implements parking in response to the relative position relationship not meeting the second preset condition. Δy(t(k+1))=3m>2m, the path generation module 240 implements parking.

[0099] In some embodiments, the path generation module 240 enters the normal control mode in response to the relative position relationship meeting the second preset condition. The normal driving mode can be a fully autonomous driving mode achieved by combining the vehicle sensors and the current path. In some embodiments, the path generation module 240 can input the current vehicle path into the lateral controller of the vehicle, so that the lateral controller controls the vehicle to drive in the normal mode based on the current vehicle path and other information obtained by the sensors. For example only, Δy(t(k+1))=2m=2m, the path generation module 240 exits the lane keeping control mode and controls the vehicle to perform the normal driving mode.

[0100] In some embodiments of the present specification, through the first preset condition and the second preset condition, it is determined that the vehicle can safely switch between lane keeping mode, conventional driving mode and parking, and the generated current path is used as the input of the lateral controller in both lane keeping mode and conventional driving mode, so that the switching between the two automatic driving modes is smoother, thereby improving the control accuracy of the automatic driving.

[0101] The beneficial effects that may be brought about by the embodiments of this specification include but are not limited to: (1) correcting the position of the ego vehicle at the current moment according to the deviation observation value corresponding to the current moment, and generating a path in combination with the lane centerline obtained from the electronic map, thereby realizing a high-precision lane keeping function; (2) obtaining the deviation observation value of the ego vehicle relative to the lane centerline at the current moment based on the deviation estimation of the ego vehicle relative to the lane centerline at the current moment and the motion calculation value corresponding to the previous moment obtained by the observer, and correcting the deviation estimation of the ego vehicle relative to the lane centerline at the current moment obtained by the inspection method by the observer, solving the error caused by the inconsistency between the detection cycle and the control cycle, thereby improving the control accuracy of lane keeping; (3) using the observer to observe the deviation estimation of the ego vehicle relative to the lane centerline obtained by the two methods, so that when the deviation estimation of the ego vehicle relative to the lane centerline obtained by the detection is low due to the inconsistency between the detection cycle and the control cycle, it is possible to further rely on the calculated deviation estimation of the ego vehicle relative to the lane centerline. The deviation estimation from the lane centerline is used to determine the motion calculation value corresponding to the previous moment, thereby improving the control accuracy of lane keeping; (4) the observer determines the first coefficient and the second coefficient based on the vehicle environment information, and then determines the confidence of the deviation value of the vehicle relative to the lane centerline corresponding to the previous moment obtained by the two methods based on the first coefficient and the second coefficient, so that the motion calculation value corresponding to the previous moment obtained by the observer can change based on the change of the vehicle environment, thereby realizing automatic driving lane keeping in different environments; (5) the lane centerline corresponding to the current moment is spliced ​​based on the corrected vehicle position to generate the current path, which can prevent point jumps on the current path: (6) through the first preset condition and the second preset condition, it is determined that the vehicle can safely switch between lane keeping mode, conventional driving mode and parking mode, and at the same time, the generated current path is used as the input of the lateral controller in the lane keeping mode and the conventional driving mode, so that the switching between the two automatic driving modes is smoother, thereby improving the control accuracy of automatic driving.

[0102] It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects that may be produced may be any one or a combination of the above, or any other possible beneficial effects.

[0103] While the basic concepts have been described above, it will be apparent to those skilled in the art that the detailed disclosure is merely illustrative and does not limit this specification. Although not explicitly stated herein, various modifications, improvements, and revisions to this specification may be made by those skilled in the art. Such modifications, improvements, and revisions are suggested in this specification and remain within the spirit and scope of the exemplary embodiments of this specification.

[0104] This specification also uses specific terms to describe the embodiments of this specification. For example, "one embodiment," "an embodiment," and / or "some embodiments" refer to a feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "one embodiment," "an embodiment," or "an alternative embodiment" two or more times in different locations in this specification do not necessarily refer to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of this specification may be appropriately combined.

[0105] In addition, unless expressly stated in the claims, the order of the processing elements and sequences, the use of alphanumeric characters, or the use of other names described in this specification are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some of the invention embodiments currently considered useful through various examples, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the spirit and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0106] Similarly, it should be noted that, in order to simplify the presentation of this specification and thus facilitate understanding of one or more embodiments of the invention, the foregoing descriptions of the embodiments of this specification sometimes combine multiple features into a single embodiment, figure, or description thereof. However, this disclosure method does not imply that the subject matter of this specification requires more features than those recited in the claims. In fact, an embodiment may have fewer features than all of the features of a single disclosed embodiment.

[0107] In some embodiments, numbers are used to describe the quantity of components and attributes. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise stated, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the description and claims are approximate values, which may change according to the required characteristics of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the settings of such numerical values ​​are as accurate as possible within the feasible range.

[0108] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, and documents, cited in this specification is hereby incorporated by reference in its entirety. This includes application history documents that are inconsistent with or conflict with the content of this specification, as well as documents (currently or subsequently attached to this specification) that limit the broadest scope of the claims of this specification. It should be noted that if the descriptions, definitions, and / or terminology used in the accompanying materials are inconsistent or conflicting with the content of this specification, the descriptions, definitions, and / or terminology used in this specification will control.

[0109] Finally, it should be understood that the embodiments described in this specification are intended only to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly described and illustrated in this specification.

Claims

1. An automatic driving lane keeping control method, characterized in that: The method comprises: According to the control cycle, based on the deviation of the ego vehicle relative to the lane centerline corresponding to the last moment and the deviation observation value of the ego vehicle relative to the lane centerline corresponding to the last moment, the deviation observation value of the ego vehicle relative to the lane centerline corresponding to the last moment is obtained according to the detection cycle; Based on the deviation observation value corresponding to the current moment, correcting the vehicle position corresponding to the current moment; Based on the corrected vehicle position, obtaining the lane centerline corresponding to the current moment; A current path is generated based on the lane centerline, and lane keeping control is performed based on the current path.

2. The method according to claim 1, characterized in that The method of obtaining the deviation observation value of the ego vehicle relative to the lane centerline corresponding to the current moment based on the deviation of the ego vehicle relative to the lane centerline corresponding to the previous moment and the deviation observation value of the ego vehicle relative to the lane centerline corresponding to the previous moment according to the control cycle includes: Based on the lateral speed and the heading angle change rate of the vehicle, obtaining the increment of the deviation of the vehicle relative to the lane centerline corresponding to the last moment within the control cycle; Based on the increment of the deviation of the self-vehicle relative to the lane centerline corresponding to the previous moment within the control cycle and the observed value of the deviation of the self-vehicle relative to the lane centerline corresponding to the previous moment, determine the estimated deviation of the self-vehicle relative to the lane centerline corresponding to the current moment; through the observer, based on the estimated deviation of the self-vehicle relative to the lane centerline corresponding to the current moment, the deviation of the self-vehicle relative to the lane centerline corresponding to the previous moment and the observed value of the deviation of the self-vehicle relative to the lane centerline corresponding to the previous moment, obtain the observed value of the deviation of the self-vehicle relative to the lane centerline corresponding to the current moment.

3. The method according to claim 2, characterized in that The passing observer obtains the observed value of the deviation of the ego vehicle relative to the center line of the lane corresponding to the current moment based on the estimated deviation of the ego vehicle relative to the center line of the lane corresponding to the current moment, the deviation of the ego vehicle relative to the center line of the lane corresponding to the previous moment, and the observed value of the deviation of the ego vehicle relative to the center line of the lane corresponding to the previous moment, including: Obtaining a motion difference between the deviation of the ego vehicle relative to the lane centerline corresponding to the last moment and an observed value of the deviation of the ego vehicle relative to the lane centerline corresponding to the last moment; Based on the observer and the motion difference value corresponding to the previous moment, obtaining the observation calculation value corresponding to the previous moment; Based on the estimated deviation of the vehicle relative to the lane centerline corresponding to the current moment and the observed calculated value corresponding to the previous moment, the observed deviation value of the vehicle relative to the lane centerline corresponding to the current moment is obtained.

4. The method according to claim 1, characterized in that The observer is a diagonal matrix, the diagonal matrix includes a first coefficient and a second coefficient, the first coefficient and the second coefficient are greater than 0 and less than 1; The first coefficient corresponds to the confidence of the deviation of the ego vehicle relative to the lane centerline corresponding to the previous moment, and the second coefficient corresponds to the confidence of the deviation observation value of the ego vehicle relative to the lane centerline corresponding to the previous moment; At least one of the first coefficient and the second coefficient is determined based on own vehicle environment information.

5. The method according to claim 1, characterized in that The generating a current path based on the lane centerline includes: When entering the lane keeping mode for the first time, the current path is connected based on the corrected ego vehicle position and the lane centerline curve; When it is not the first time to enter the lane keeping mode, the current path is spliced ​​with the lane centerline based on the historical path.

6. The method according to claim 1, characterized in that Also includes: Determine whether the lane line detection result is valid and whether the deviation of the vehicle relative to the lane center line detected during the detection period meets a first preset condition; In response to the lane line detection result being valid and the deviation of the vehicle relative to the lane center line detected within the detection period meeting a first preset condition, the deviation observation value corresponding to the current moment is determined, otherwise the lane keeping control mode is exited.

7. The method according to claim 6, characterized in that Also includes: After exiting the lane keeping control mode, determining whether the relative position relationship between the vehicle and the lane centerline satisfies a second preset condition; In response to the relative position relationship not satisfying the second preset condition, parking is implemented; In response to the relative position relationship satisfying the second preset condition, entering the normal control mode.

8. An automatic driving lane keeping control method system, characterized in that: The system comprises: The observation value acquisition module is used to obtain the observation value according to the control cycle based on the deviation of the vehicle relative to the lane centerline corresponding to the previous moment and the The deviation observation value of the vehicle relative to the lane centerline corresponding to a moment is obtained to obtain the deviation observation value of the vehicle relative to the lane centerline corresponding to the current moment, wherein the deviation corresponding to the previous moment is obtained according to the detection cycle; A correction module, used for correcting the vehicle position corresponding to the current moment based on the deviation observation value corresponding to the current moment; A lane centerline acquisition module, used to acquire the lane centerline corresponding to the current moment based on the corrected vehicle position; A path generation module is used to generate a current path based on the lane centerline and perform lane keeping control based on the current path.

9. An automatic driving lane keeping control device, characterized in that: The device comprises: at least one storage medium storing computer instructions; At least one processor executes the computer instructions to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing computer instructions. When a computer reads the computer instructions, the computer executes the automatic driving lane keeping control method according to any one of claims 1 to 7.

Images