Automatic driving ramp entering control method and related equipment

Abstract

The invention discloses an automatic driving ramp entering control method and related equipment, and relates to the field of automatic driving, and the method comprises the steps: obtaining a target recognition lane line which comprises at least one of a visual recognition lane line and a map recognition lane line, the visual identification lane line is a lane line obtained by fitting based on a visual identification technology, and the map identification lane line is a lane line obtained based on a positioning technology; under the condition that the target vehicle does not enter the ramp lane line, obtaining distance information between the target vehicle and a ramp entrance; and controlling the target vehicle to run based on the distance information and the target recognition lane line.

Description

Technical Field

[0001] This specification relates to the field of autonomous driving. More specifically, this application relates to a method for controlling an autonomous vehicle to enter a ramp and related devices. Background Art

[0002] Vision-based lane line recognition usually obtains the front road image through a camera, and uses image processing or deep learning algorithms to detect and fit the lane lines. Map-based lane line recognition relies on high-precision maps and vehicle positioning systems, which can provide relatively accurate and stable lane line coordinate information.

[0003] Navigation on Autopilot (NOA) can reduce driver fatigue and is used more and more frequently. Automatic ramp exiting is a difficult scenario for highway NOA. In some scenarios, NOA cannot automatically enter the ramp, resulting in a risk of hitting the guardrail and an increase in takeover times.

[0004] Navigation-assisted driving can automatically enter the ramp according to the navigation path. The system completes the automatic ramp entry based on the combination of high-precision maps and camera recognition. However, there may be no lane lines at some ramp intersections, or old lane lines have not been erased, resulting in the camera not being able to recognize the lane lines or misidentifying the lane lines, or misidentifying the lane lines of the ramp exit. In some ramp intersections, the high-precision map is incorrect due to road reconstruction.

[0005] Related technologies cannot guarantee a high ramp passing rate. It is necessary to select an appropriate fusion strategy according to the ramp type to improve the success rate of ramp exiting. Therefore, it is necessary to propose a method for controlling an autonomous vehicle to enter a ramp and related devices to solve at least some of the above problems. Summary of the Invention

[0006] A series of simplified concepts are introduced in the Summary of the Invention section, which will be further described in detail in the Detailed Implementation section. The Summary of the Invention section of this application does not mean to attempt to define the key features and essential technical features of the claimed technical solution, nor does it mean to attempt to determine the protection scope of the claimed technical solution.

[0007] In a first aspect, this application proposes a method for controlling an autonomous vehicle to enter a ramp, including:

[0008] Obtain target recognized lane lines, where the target recognized lane lines include at least one of vision-based recognized lane lines and map-based recognized lane lines. The vision-based recognized lane lines are lane lines obtained by fitting based on vision recognition technology, and the map-based recognized lane lines are lane lines obtained based on positioning technology;

[0009] When the target vehicle has not entered the ramp, obtain the distance information between the target vehicle and the ramp entrance;

[0010] Based on the above distance information and the above target recognition lane lines, control the driving of the above target vehicle.

[0011] In a feasible implementation manner, the above target recognition lane lines include vision recognition lane lines and map recognition lane lines;

[0012] The above controlling the driving of the above target vehicle based on the above distance information and the above target recognition lane lines includes:

[0013] Calculate the lane line coincidence error information between the above vision recognition lane line and the above map recognition lane;

[0014] Control the driving of the above target vehicle based on the above distance information and the above lane line coincidence error information.

[0015] In a feasible implementation manner, the above controlling the driving of the above target vehicle based on the above distance information and the above lane line coincidence error information includes:

[0016] When the above lane line coincidence error information is less than or equal to the preset coincidence error information, determine a first control reference line based on the above vision recognition lane line and the above map recognition lane line;

[0017] Control the above target vehicle to drive along the above first control reference line; and / or,

[0018] When the above lane line coincidence error information is greater than the preset coincidence error information and the distance information is greater than the above preset distance, control the above target vehicle to continue driving and continuously monitor the above lane line coincidence error information.

[0019] In a feasible implementation manner, the above controlling the driving of the above target vehicle based on the above distance information and the above lane line coincidence error information includes:

[0020] When the above distance information is less than or equal to the preset distance and the above lane line coincidence error information is greater than the preset coincidence error information;

[0021] Determine the above vision recognition lane line as the second control reference line;

[0022] Control the above target vehicle to drive along the above second control reference line.

[0023] In a feasible implementation manner, the above controlling the driving of the above target vehicle based on the above distance information and the above lane line coincidence error information includes:

[0024] When the above distance information is greater than the preset distance, control the above target vehicle to continue moving forward, and continuously obtain the above lane line coincidence error information and the above distance information;

[0025] When the above distance information is less than or equal to the preset distance, adjust the current vehicle driving state based on the above distance information and the above lane line coincidence error information.

[0026] In a feasible implementation manner, the above target recognition lane line includes a map recognition lane line, and the control of the above target vehicle driving based on the above distance information and the above lane line coincidence error information includes:

[0027] When the above distance information is less than or equal to the preset distance, determine the above map recognition lane line as the third control reference line;

[0028] Control the above target vehicle to drive along the above third control reference line.

[0029] In a feasible implementation manner, the calculation of the lane line coincidence error information between the above visual recognition lane line and the above map recognition lane includes:

[0030] Obtain the lateral distance error between the visual recognition lane line and the lane lines of the above map recognition lane;

[0031] When the length information of the above visual recognition lane line is greater than or equal to the preset length, calculate the above lane line coincidence error information based on the starting point information of the above visual recognition lane line, the ending point information of the above visual recognition lane line, and the above lane line lateral distance error.

[0032] In a second aspect, the present application proposes an automatic driving on-ramp control device, including:

[0033] A first acquisition unit, configured to acquire a target recognition lane line, where the above target recognition lane line includes at least one of a visual recognition lane line and a map recognition lane line, the above visual recognition lane line is a lane line obtained by fitting based on visual recognition technology, and the above map recognition lane line is a lane line obtained by acquiring based on positioning technology;

[0034] A second acquisition unit, configured to acquire the distance information between the target vehicle and the ramp entrance when the target vehicle has not entered the ramp;

[0035] A control unit, configured to control the above target vehicle to drive based on the above distance information and the above target recognition lane line.

[0036] In a third aspect, an electronic device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program stored in the memory, it implements the steps of the on-ramp control method for autonomous driving according to any one of the first aspects described above.

[0037] In a fourth aspect, the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the on-ramp control method for autonomous driving according to any one of the first aspects.

[0038] In summary, by introducing two data sources, namely vision-recognized lane lines and map-recognized lane lines, the present application, on the one hand, utilizes the real-time characteristics of vision recognition to dynamically perceive the actual lane environment ahead; on the other hand, it utilizes the precise coordinate information provided by the high-precision map to improve stability in complex scenarios. When one data source has recognition deviations or anomalies, the other data source can provide a reference to improve the robustness of overall lane line recognition. Before the target vehicle enters the on-ramp, the distance information between the vehicle and the on-ramp is continuously monitored through methods such as positioning and map matching or sensor detection. By combining the distance information with multi-source lane line information, it is possible to flexibly determine whether to use vision-recognized lane lines, map-recognized lane lines, or a reference line generated by fusing the two according to the actual road conditions, such as high or low overlap, map update level, and vision recognition quality. In summary, compared with the related technologies, by acquiring vision-recognized lane lines and map-recognized lane lines, real-time monitoring of the distance information between the vehicle and the on-ramp, and performing refined vehicle control based on multi-source information, the present application can effectively handle various complex scenarios when entering the on-ramp, significantly improving the safety, smoothness, and reliability of autonomous driving. Description of the Drawings

[0039] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to limit this specification. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0040] Figure 1 It is a schematic flowchart of an on-ramp control method for autonomous driving provided by an embodiment of the present application;

[0041] Figure 2 It is a schematic scenario diagram of a vehicle entering an on-ramp provided by an embodiment of the present application;

[0042] Figure 3 It is another schematic scenario diagram of a vehicle entering an on-ramp provided by an embodiment of the present application;

[0043] Figure 4Another schematic diagram of the scenario of an autonomous vehicle entering a ramp provided by an embodiment of the present application;

[0044] Figure 5 Still another schematic diagram of the scenario of an autonomous vehicle entering a ramp provided by an embodiment of the present application;

[0045] Figure 6 A schematic structural diagram of a control device for an autonomous vehicle to enter a ramp provided by an embodiment of the present application;

[0046] Figure 7 A schematic structural diagram of an electronic device for controlling an autonomous vehicle to enter a ramp provided by an embodiment of the present application. Detailed implementation manners

[0047] Terms such as "first", "second", "third", "fourth", etc. (if any) in the specification, claims and above-mentioned drawings of the present application are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices. Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments.

[0048] Figure 1 A schematic flowchart of a control method for an autonomous vehicle to enter a ramp provided by an embodiment of the present application. The method may specifically include:

[0049] S110. Obtain a target recognition lane line, where the target recognition lane line includes at least one of a vision recognition lane line and a map recognition lane line. The vision recognition lane line is a lane line obtained by fitting based on vision recognition technology, and the map recognition lane line is a lane line obtained by positioning technology;

[0050] Exemplarily, the vehicle identifies the driving environment where the target vehicle is located through corresponding sensors and obtains the target recognition lane line. The target recognition lane line includes, but is not limited to, a vision recognition lane line and a map recognition lane line.

[0051] Vision recognition lane lines can detect and fit lanes through vision perception devices (such as cameras) combined with vision recognition technologies (such as deep learning algorithms) to generate lane line information. Vision recognition lane lines can dynamically perceive the actual situation of the current lane environment.

[0052] Map recognition lane lines can obtain lane line information through high-precision maps combined with positioning technologies, such as GPS (Global Positioning System) and RTK (Real-Time Kinematic). The advantage of map recognition lane lines is that they provide higher accuracy and robustness, especially suitable for complex road environments.

[0053] S120. When the target vehicle has not entered the ramp, obtain the distance information between the target vehicle and the ramp entrance.

[0054] Exemplarily, when the target vehicle has not entered the ramp, the vehicle needs to continuously monitor the distance between the target vehicle and the ramp entrance. It should be noted that the ramp entrance is point B as shown in Figures 2 to 5 , that is, the merging and diverging point, rather than the entrance to the ramp. This distance information between the target vehicle and the ramp entrance can be obtained through, but not limited to, positioning and map matching and sensor detection methods.

[0055] The method of positioning and map matching can calculate the distance between the two based on the positioning information of the target vehicle and the coordinates of the ramp entrance in the high-precision map.

[0056] The method of sensor detection uses on-vehicle sensors (such as millimeter-wave radar, lidar, etc.) to detect the road environment ahead, identify the position of the ramp entrance and estimate the distance.

[0057] S130. Based on the above distance information and the above target recognition lane lines, control the driving of the target vehicle.

[0058] Exemplarily, the target vehicle comprehensively uses the above-obtained distance information and lane line information to control the driving behavior of the target vehicle. Controlling the driving behavior of the target vehicle includes, but is not limited to: generating a driving path for the vehicle to switch from the current lane to the ramp based on the position information of the ramp entrance and the target recognition lane lines. Adjusting the acceleration or deceleration of the vehicle according to the distance information between the vehicle and the ramp entrance to ensure that the vehicle can enter the ramp at an appropriate speed. Controlling the steering wheel angle of the vehicle according to the recognized lane line information so that the vehicle can smoothly drive into the ramp. Achieving precise control of the autonomous vehicle during the ramp entry process and ensuring the smoothness and safety of driving.

[0059] In summary, by introducing two data sources, namely visually recognized lane lines and map-recognized lane lines, the present application, on the one hand, utilizes the real-time characteristics of visual recognition to dynamically perceive the actual lane environment ahead; on the other hand, it utilizes the precise coordinate information provided by the high-precision map to improve stability in complex scenarios. When there is an identification deviation or anomaly in one data source, the other data source can provide a reference to improve the robustness of the overall lane line recognition. When the target vehicle has not entered the ramp, the distance information between the vehicle and the ramp entrance is continuously monitored through methods such as positioning and map matching or sensor detection. By combining the distance information with multi-source lane line information, it is possible to flexibly determine whether to use visually recognized lane lines, map-recognized lane lines, or a reference line generated by fusing the two for control according to the actual road conditions, such as high or low overlap, map update level, visual recognition quality, etc. In summary, compared with the related art, by obtaining visually recognized lane lines and map-recognized lane lines, real-time monitoring of the distance information between the vehicle and the ramp entrance, and performing refined vehicle control based on multi-source information, the present application can effectively handle various complex scenarios when entering the ramp, significantly improving the safety, smoothness, and reliability of autonomous driving.

[0060] In a feasible implementation manner, the above-mentioned target recognized lane lines include visually recognized lane lines and map-recognized lane lines;

[0061] Based on the above distance information and the above target recognized lane lines, controlling the driving of the above target vehicle includes:

[0062] Calculating the lane line overlap error information between the above visually recognized lane lines and the above map-recognized lanes;

[0063] Controlling the driving of the above target vehicle based on the above distance information and the above lane line overlap error information.

[0064] Exemplarily, the visually recognized lane lines are matched and compared with the map lane lines to obtain an overlap error value. According to the distance between the vehicle and the ramp entrance and the magnitude of the overlap error, it is decided whether to continue driving along the map lane lines, along the visually recognized lane lines, or to fuse the two to generate a control reference line.

[0065] Specifically, before the vehicle is about to enter the ramp, the position of the ramp is obtained through the map; at this time, if the visually recognized lane lines and the above map recognition results are basically the same, that is, the overlap error is small, it can be considered that the recognition is more reliable, and thus the corresponding steering and deceleration strategies are executed. If there is a large deviation between the two, it is necessary to judge in combination with the actual scenario where the vehicle is located to decide which lane line to use as the main control.

[0066] In a feasible implementation manner, the above controlling the driving of the above target vehicle based on the above distance information and the above lane line overlap error information includes:

[0067] When the lane line coincidence error information is less than or equal to the preset coincidence error information, determine a first control reference line based on the visually recognized lane line and the map-recognized lane line;

[0068] Control the target vehicle to travel along the first control reference line; and / or,

[0069] When the lane line coincidence error information is greater than the preset coincidence error information and the distance information is greater than the preset distance, control the target vehicle to continue to travel and continuously monitor the lane line coincidence error information.

[0070] Exemplarily, if the lane line coincidence error information is less than or equal to the preset coincidence error information, at this time the matching degree of the visual lane line and the map lane line). The visually recognized lane line and the map-recognized lane line are fused to determine a first control reference line, and the vehicle travels along this first control reference line. The fusion method can adopt methods such as weighted average and curvature fusion to obtain the optimal first control reference line.

[0071] Such as Figure 2 , the center line of AC and A 1 C 1 can be used as the control reference line:

[0072]

[0073] When the lane line coincidence error information is greater than the preset coincidence error information and the distance information is greater than the preset distance, at this time the distance from the ramp is far, and it can continue to travel and observe. Control the target vehicle to continue to travel and continuously monitor the lane line coincidence error information for further judgment.

[0074] In a feasible implementation manner, the control of the target vehicle to travel based on the distance information and the lane line coincidence error information includes:

[0075] When the distance information is less than or equal to the preset distance and the lane line and the lane line coincidence error information is greater than the preset coincidence error information;

[0076] Determine the visually recognized lane line as the second control reference line;

[0077] Control the target vehicle to travel along the second control reference line.

[0078] Exemplarily, if the distance information is less than or equal to a preset distance, it means that the vehicle has approached the ramp entrance. If the lane line coincidence error information is greater than the preset coincidence error information, at this time, there is a large error between the visual lane line and the map lane line. At this time, the map recognition result is abandoned, and the visual recognition lane line is separately used as the second control reference line. The vehicle travels according to this second control reference line.

[0079] As Figure 3 shown, the target vehicle entering the ramp lane line is sensed and recognized, but the lane line coincidence error information e between all the sensed lane lines and the map boundary lane lines is greater than the preset coincidence error information e 0 , and the vehicle itself is relatively close to the ramp diversion point ahead, less than or equal to the preset distance. The preset distance can be selected as 5 times the vehicle speed, that is, when the distance L of the target vehicle from point B is ≤ 5×V, the vehicle itself is controlled according to the visual recognition lane line y = y 1 (x).

[0080] In a feasible implementation manner, controlling the above-mentioned target vehicle to travel based on the above-mentioned distance information and the above-mentioned lane line coincidence error information includes:

[0081] When the above-mentioned distance information is greater than the preset distance, controlling the above-mentioned target vehicle to continue moving forward, and continuously obtaining the above-mentioned lane line coincidence error information and the above-mentioned distance information;

[0082] When the above-mentioned distance information is less than or equal to the preset distance, adjusting the current vehicle driving state based on the above-mentioned distance information and the above-mentioned lane line coincidence error information.

[0083] Exemplarily, as Figure 4 shown, the vehicle is divided into two driving stages: 1. The distance is greater than the preset distance, that is, the target vehicle has not reached the ramp approach area. The vehicle can travel according to the original plan or normal cruise, and continuously obtain the lane line coincidence error information and the distance information. 2. The distance is less than or equal to the preset distance, that is, the target vehicle enters the ramp approach area, and it is necessary to start paying attention to the coincidence error of the lane line and select an appropriate control strategy. If the vehicle is still relatively far from the ramp entrance (or the target point) (that is, greater than the preset distance), there is no need to perform operations such as merging and lane changing. The vehicle travels according to the current route and continuously updates the visual and map lane line information. When the vehicle travels to the approach area, that is, less than or equal to the preset distance, the system will combine the lane line coincidence error calculated locally in real time to determine the next control strategy.

[0084] As Figure 4As shown, when the vehicle is cruising on an ordinary road and has not reached the ramp or interchange, it only needs to maintain the normal lane keeping function and continuously obtain the lane line coincidence error information and distance information. Only when the sensor or map reminds that "there is a ramp within the preset distance ahead", it is necessary to activate a more refined ramp cut-in logic, thus saving computing resources and improving system efficiency.

[0085] In a feasible implementation manner, the above-mentioned target recognition lane line includes a map recognition lane line, and the control of the above-mentioned target vehicle to travel based on the above-mentioned distance information and the above-mentioned lane line coincidence error information includes:

[0086] When the above-mentioned distance information is less than or equal to the preset distance, the above-mentioned map recognition lane line is determined as the third control reference line;

[0087] Control the above-mentioned target vehicle to travel along the above-mentioned third control reference line.

[0088] Exemplarily, when the vehicle is less than or equal to the preset distance from the ramp entrance and the local lane line is worn or lost here, the map recognition lane line can only be directly used as the "third control reference line", and the vehicle is controlled according to the map lane line y = y 2 (x).

[0089] In a feasible implementation manner, the calculation of the lane line coincidence error information between the above-mentioned visual recognition lane line and the above-mentioned map recognition lane includes:

[0090] When the length information of the above-mentioned visual recognition lane line is greater than or equal to the preset length, obtain the lateral distance error between the visual recognition lane line and the above-mentioned map recognition lane;

[0091] Calculate the above-mentioned lane line coincidence error information based on the starting point information of the above-mentioned visual recognition lane line, the ending point information of the above-mentioned visual recognition lane line, and the above-mentioned lateral distance error of the lane line.

[0092] Exemplarily, let the equation of the visual recognition lane line AC recognized by the camera be y 1 (x), the starting point of the visual recognition lane line is S, the ending point is E, and the equation of the map lane line is y 2 (x),

[0093] When the length information of the visual recognition lane line is greater than or equal to the preset length, for the visual recognition lane line, no judgment is made. Let Z be the set length, that is:

[0094] (E - S) ≥ Z (1)

[0095] Let the lateral distance error between the two lane lines be w(x):

[0096] w(x) = |y1 (x) - y 2 (x) | (2)

[0097] Within the range of the starting point S and the ending point E, the position coincidence error between the two is

[0098]

[0099] When the formula (1) meets the requirements, then calculate the position coincidence error according to formula (2) and formula (3). When e ≤ e 0 At this time, it is considered that the position coincidence degree between the two is high; when e > e0, it is considered that the position coincidence degree between the two is not high.

[0100] If the old lane lines on the road are not eliminated, then more than two lane lines will be recognized on the right during perception, such as Figure 5 shown as AC and DE, so it is necessary to perform a coincidence check on each lane line recognized by perception and the road boundary line of the map, and obtain e AC and e DE

[0101] Such as Figure 6 shown, this application proposes an automatic driving ramp entry control device, including:

[0102] The first acquisition unit 21 is used to acquire the target recognized lane line, where the target recognized lane line includes at least one of the visually recognized lane line and the map recognized lane line. The visually recognized lane line is a lane line obtained by fitting based on visual recognition technology, and the map recognized lane line is a lane line obtained by positioning technology;

[0103] The second acquisition unit 22 is used to acquire the distance information between the target vehicle and the ramp entrance when the target vehicle has not entered the ramp;

[0104] The control unit 23 is used to control the driving of the target vehicle based on the distance information and the target recognized lane line.

[0105] The above automatic driving ramp entry control device can also perform the following steps,

[0106] In a feasible implementation manner, the target recognized lane line includes a visually recognized lane line and a map recognized lane line;

[0107] The above controlling the driving of the target vehicle based on the distance information and the target recognized lane line includes:

[0108] Calculating the lane line coincidence error information between the visually recognized lane line and the map recognized lane line;

[0109] Control the target vehicle to travel based on the above distance information and the above lane line coincidence error information.

[0110] In a feasible implementation manner, the above control of the target vehicle to travel based on the above distance information and the above lane line coincidence error information includes:

[0111] When the above lane line coincidence error information is less than or equal to the preset coincidence error information, determine a first control reference line based on the above vision recognition lane line and the above map recognition lane line;

[0112] Control the target vehicle to travel along the above first control reference line; and / or,

[0113] When the above lane line coincidence error information is greater than the preset coincidence error information and the distance information is greater than the above preset distance, control the target vehicle to continue to travel and continuously monitor the above lane line coincidence error information.

[0114] In a feasible implementation manner, the above control of the target vehicle to travel based on the above distance information and the above lane line coincidence error information includes:

[0115] When the above distance information is less than or equal to the preset distance and the above lane line and the above lane line coincidence error information is greater than the preset coincidence error information;

[0116] Determine the above vision recognition lane line as the second control reference line;

[0117] Control the target vehicle to travel along the above second control reference line.

[0118] In a feasible implementation manner, the above control of the target vehicle to travel based on the above distance information and the above lane line coincidence error information includes:

[0119] When the above distance information is greater than the preset distance, control the target vehicle to continue to move forward and continuously obtain the above lane line coincidence error information and the above distance information;

[0120] When the above distance information is less than or equal to the preset distance, adjust the current vehicle driving state based on the above distance information and the above lane line coincidence error information.

[0121] In a feasible implementation manner, the above target recognition lane line includes a map recognition lane line, and the above control of the target vehicle to travel based on the above distance information and the above lane line coincidence error information includes:

[0122] When the above distance information is less than or equal to the preset distance, determine the above map recognition lane line as the third control reference line;

[0123] Control the target vehicle to travel along the third control reference line described above.

[0124] In a feasible implementation, calculating the lane line coincidence error information between the visually recognized lane line and the map-recognized lane line includes:

[0125] When the length information of the visually recognized lane line is greater than or equal to a preset length, obtain the lateral distance error between the visually recognized lane line and the map-recognized lane line.

[0126] Calculate the lane line coincidence error information based on the starting point information of the visually recognized lane line, the ending point information of the visually recognized lane line, and the lateral distance error of the lane line.

[0127] In this application, by introducing two data sources, namely the visually recognized lane line and the map-recognized lane line, on the one hand, the real-time characteristics of visual recognition are utilized to dynamically perceive the actual lane environment ahead; on the other hand, the precise coordinate information provided by the high-precision map is utilized to improve stability in complex scenarios. When there is an identification deviation or anomaly in one data source, the other data source can provide a reference to improve the robustness of the overall lane line recognition. When the target vehicle has not entered the ramp, the distance information between the vehicle and the ramp entrance is continuously monitored through methods such as positioning and map matching or sensor detection. By combining the distance information with multi-source lane line information, it is possible to flexibly determine whether to use the visually recognized lane line, the map-recognized lane line, or the reference line generated by fusing the two according to the actual road conditions, such as high or low coincidence, map update level, visual recognition quality, etc. for control. In summary, compared with the related art, this application can effectively handle various complex scenarios when entering the ramp, significantly improving the safety, smoothness, and reliability of autonomous driving by obtaining the visually recognized lane line and the map-recognized lane line, real-time monitoring the distance information between the vehicle and the ramp entrance, and performing refined vehicle control based on multi-source information.

[0128] As Figure 7 shown, an embodiment of this application also provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored on the memory 310 and executable on the processor. When the processor 320 executes the computer program 311, the steps of any of the methods for controlling the entry of an autonomous vehicle into a ramp described above are implemented.

[0129] Since the electronic device introduced in this embodiment is the device used in implementing an on-ramp control device for autonomous driving in an embodiment of the present application, based on the method introduced in the embodiment of the present application, those skilled in the art can understand the specific implementation manners of the electronic device in this embodiment and their various variations. Therefore, the specific implementation of how this electronic device implements the method in the embodiment of the present application will not be described in detail herein. As long as the device used by those skilled in the art to implement the method in the embodiment of the present application falls within the scope of protection of the present application.

[0130] In the specific implementation process, when the computer program 311 is executed by the processor, it can implement any implementation manner in the corresponding embodiment of the first aspect.

[0131] It should be noted that in the above embodiments, the descriptions of each embodiment have their own focuses. For the parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0132] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0133] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0134] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0135] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide for implementing the process Figure 1 a process or multiple processes and / or blocks Figure 1 the steps of the functions specified in a block or multiple blocks.

[0136] The embodiment of the present application also provides a computer program product, which includes computer software instructions. When the computer software instructions run on a processing device, the processing device is caused to execute the process of the automatic driving on-ramp control in the corresponding embodiment.

[0137] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, a computer, a server, or a data center to another website, a computer, a server, or a data center in a wired manner (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or a wireless manner (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be stored by a computer or a data storage device such as a server or a data center that includes one or more integrated available media. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state disk (SSD)), etc.

[0138] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments and will not be described herein again.

[0139] In several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling, direct coupling, or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of devices or units can be in electrical, mechanical, or other forms.

[0140] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0141] In addition, each functional unit in various embodiments of the present application can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0142] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0143] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the 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 various embodiments of the present application.

Claims

1. A method for controlling an automatic driving vehicle entering a ramp, characterized in that: include: Obtaining a target recognition lane line, wherein the target recognition lane line includes at least one of a visual recognition lane line and a map recognition lane line, wherein the visual recognition lane line is a lane line obtained by fitting based on a visual recognition technology, and the map recognition lane line is a lane line obtained by obtaining based on a positioning technology; When the target vehicle has not entered the ramp, obtain the distance information between the target vehicle and the ramp entrance; Based on the distance information and the target identification lane line, the target vehicle is controlled to travel.

2. The automatic driving ramp entry control method according to claim 1, characterized in that: The target recognition lane lines include visual recognition lane lines and map recognition lane lines; The step of controlling the target vehicle to travel based on the distance information and the target identification lane line includes: Calculating lane line overlap error information between the visually recognized lane line and the map recognized lane line; The target vehicle is controlled to travel based on the distance information and the lane line coincidence error information.

3. The method for controlling the ramp entry of the automatic driving according to claim 2, wherein the step of controlling the target vehicle to travel based on the distance information and the lane line overlap error information comprises: When the lane line coincidence error information is less than or equal to the preset coincidence error information, determining a first control reference line based on the visually recognized lane line and the map-recognized lane line; Controlling the target vehicle to travel along the first control reference line; and / or, When the lane line overlap error information is greater than the preset overlap error information and the distance information is greater than the preset distance, the target vehicle is controlled to continue driving and the lane line overlap error information is continuously monitored.

4. The automatic driving ramp entry control method according to claim 2, characterized in that: The controlling the target vehicle to travel based on the distance information and the lane line coincidence error information includes: When the distance information is less than or equal to the preset distance and the lane line coincidence error information is greater than the preset coincidence error information; Determining the visually recognized lane line as a second control reference line; The target vehicle is controlled to travel along the second control reference line.

5. The automatic driving ramp entry control method according to claim 2, characterized in that: The controlling the target vehicle to travel based on the distance information and the lane line coincidence error information includes: When the distance information is greater than a preset distance, the target vehicle is controlled to continue moving forward, and the lane line overlap error information and the distance information are continuously acquired; When the distance information is less than or equal to the preset distance, the current vehicle driving state is adjusted based on the distance information and the lane line coincidence error information.

6. The automatic driving ramp entry control method according to claim 1, characterized in that: The target recognition lane line includes a map recognition lane line, and the controlling the target vehicle to travel based on the distance information and the lane line overlap error information includes: When the distance information is less than or equal to a preset distance, determining the map-recognized lane line as a third control reference line; The target vehicle is controlled to travel along the third control reference line.

7. The automatic driving ramp entry control method according to any one of claims 2 to 5, characterized in that: The calculating the lane line overlap error information between the visually recognized lane line and the map recognized lane line includes: When the length information of the visually recognized lane line is greater than or equal to a preset length, obtaining a lateral distance error between the visually recognized lane line and the lane line of the map-recognized lane; The lane line coincidence error information is calculated based on the starting point information of the visually recognized lane line, the end point information of the visually recognized lane line and the lateral distance error of the lane line.

8. An automatic driving ramp entry control device, characterized in that: include: A first acquisition unit is used to acquire a target recognition lane line, wherein the target recognition lane line includes at least one of a visual recognition lane line and a map recognition lane line, the visual recognition lane line is a lane line obtained by fitting based on a visual recognition technology, and the map recognition lane line is a lane line obtained based on a positioning technology; A second acquisition unit, used for acquiring distance information between the target vehicle and the ramp entrance when the target vehicle has not entered the ramp; A control unit is used to control the target vehicle to travel based on the distance information and the target identification lane line.

9. An electronic device, comprising: A memory and a processor, wherein the processor is used to implement the steps of the automatic driving ramp entry control method as described in any one of claims 1 to 7 when executing the computer program stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the automatic driving ramp entry control method as described in any one of claims 1 to 7 are implemented.

Images