Autopilot Control Method, Device, Terminal Device and Vehicle

Abstract

The present invention relates to an automatic driving control method, device, terminal device and vehicle, and relates to the technical field of automatic driving. The method includes: obtaining the current driving state of the current vehicle; if it is determined that the current driving state of the current vehicle meets the main road switching condition, extracting the first lane line information of the main road and the second lane line information of the ramp through real-time images, and constructing a lane switching area for the current vehicle to enter the main road; determining a first passable area of the lane switching area according to the point cloud data, and determining a second passable area of the lane switching area according to the real-time images; determining an overlapping area of the first passable area and the second passable area as the target passable area of the lane switching area; determining a lane switching trajectory of the current vehicle according to the target passable area, and if it is determined that the lane switching trajectory is valid, controlling the current vehicle to enter the main road according to the lane switching trajectory. The present invention does not need to rely on a high-precision map and a high-precision positioning system, has low cost and wide application range.

Description

Technical Field

[0001] The present invention relates to the technical field of autonomous driving, and particularly to a lamp cover, a headlamp and an automobile. Background Art

[0002] Existing autonomous driving can achieve point-to-point full-autonomous driving on highways, i.e., navigation-assisted driving, by autonomously changing lanes and entering and exiting ramps. Currently, navigation-assisted driving usually uses a high-precision map and a high-precision positioning system to achieve automatic entry and exit of vehicles from ramps. The disadvantages of this solution are high cost and the need for high-precision map coverage areas for use. At the same time, the high-precision positioning system also has failure scenarios, and the limitations of assisted driving are relatively large. Summary of the Invention

[0003] One of the purposes of the present invention is to provide an autonomous driving control method to solve the problems of high cost and large application limitations in controlling vehicles to automatically enter and exit ramps in the prior art; the second purpose is to provide an autonomous driving control device; the third purpose is to provide a terminal device; the fourth purpose is to provide an automobile.

[0004] To achieve the above purposes, the technical solutions adopted by the present invention are as follows:

[0005] An autonomous driving control method includes:

[0006] When it is determined that the current vehicle is traveling in a ramp, obtain the current driving state of the current vehicle;

[0007] If it is determined that the current driving state of the current vehicle meets the main road switching condition, obtain a real-time image including the surrounding environment of the current vehicle, extract the first lane line information of the main road and the second lane line information of the ramp from the real-time image, and construct a lane switching area for the current vehicle to enter the main road based on the first lane line information and the second lane line information;

[0008] Obtain the point cloud data of the lane switching area, determine the first passable area of the lane switching area according to the point cloud data, determine the second passable area of the lane switching area according to the real-time image, and the point cloud data is obtained by detecting the lane switching area with a millimeter-wave radar;

[0009] Determine the overlapping area of the first passable area and the second passable area as the target passable area of the lane switching area;

[0010] Determine the lane switching trajectory of the current vehicle according to the target passable area, and when it is determined that the lane switching trajectory is valid, control the current vehicle to enter the main road according to the lane switching trajectory.

[0011] According to the above technical means, the lane change area is reconstructed based on the real-time images collected by the in-vehicle camera, and the target passable area of the lane change area is determined based on the millimeter wave radar and image recognition, which can effectively improve the safety of automatically controlling the vehicle to enter the main road from the ramp.

[0012] Further, determining the first passable area of the lane change area according to the point cloud data includes:

[0013] Obtain the first reflection point in the point cloud data and determine the second reflection point adjacent to the first reflection point;

[0014] Obtain the first reflection point information of the first reflection point and the second reflection point information of the second reflection point, where the first reflection point information includes the first coordinates of the first reflection point, and the second reflection point information includes the second coordinates of the second reflection point;

[0015] Determine the slope between the first reflection point and the second reflection point according to the first coordinates and the second coordinate points, and smooth the slope between the first reflection point and the second reflection point;

[0016] When the slope between the first reflection point and the second reflection point is less than a preset slope threshold, connect the first reflection point and the second reflection point;

[0017] Traverse all the reflection points in the point cloud data, repeat the above steps until all the connected reflection points form a closed area, and determine the obtained closed area as the first passable area.

[0018] According to the above technical means, the passable area of the lane change area can be effectively obtained using the point cloud data.

[0019] Further, the current driving state of the current vehicle includes: the driving mode of the current vehicle, the first position of the current vehicle, the second position of the current vehicle, the lane information of the current vehicle, and the vehicle speed of the current vehicle;

[0020] The main road switching conditions include:

[0021] Determine that the current vehicle is in the assisted driving state according to the driving mode of the current vehicle, determine that the current vehicle is within the electronic fence area where assisted driving is allowed according to the first position of the current vehicle, determine that the current vehicle is within the determination area for entering the main road according to the second position of the current vehicle, determine that the current vehicle is in the adjacent lane of the main road according to the lane information of the current vehicle, and determine that the vehicle speed of the current vehicle is within the speed range allowed to enter the main road.

[0022] According to the above technical means, the timing for the vehicle to enter the main road can be effectively determined.

[0023] Further, determining that the current vehicle is within the determination area for entering the main road based on the second position of the current vehicle includes:

[0024] Obtaining the navigation information of the current vehicle, and if it is determined based on the navigation information that the distance between the second position of the current vehicle and the main road is not greater than a preset distance threshold, determining that the current vehicle is within the determination area for entering the main road.

[0025] According to the above technical means, the timing for the vehicle to enter the main road can be determined using the existing navigation information, without relying on a high-precision map.

[0026] Further, the first lane line information includes:

[0027] Diversion lines, the right lane line of the main road, and the left lane line of the main road;

[0028] The second lane line information includes:

[0029] The right lane line of the ramp.

[0030] According to the above technical means, based on the recognition of the diversion lines, the right lane line of the main road, the left lane line of the main road, and the right lane line of the ramp, it is beneficial to accurately construct the lane change area.

[0031] Further, constructing the lane change area for the current vehicle to enter the main road based on the first lane line information and the second lane line information includes:

[0032] In the case where it is determined that the right lane line of the main road is a wide dashed line, using the end point of the diversion line as the starting point of the main road of the lane change area, and using the intersection point of the right lane line of the main road and the right lane line of the ramp as the ending point of the main road of the lane change area;

[0033] Determining that the right lane line of the main road is the left boundary of the ramp, and determining that the right lane line of the ramp is the right boundary of the ramp.

[0034] According to the above technical means, the lane change area can be constructed efficiently and accurately.

[0035] Further, determining the lane change trajectory of the current vehicle based on the target passable area includes:

[0036] Generating the lane change trajectory of the current vehicle based on the left lane line of the main road, the left boundary of the ramp, the right boundary of the ramp, the starting point of the main road of the lane change area, and the ending point of the main road of the lane change area;

[0037] Determining that the lane change trajectory is valid includes:

[0038] If it is determined that the maximum curvature of the lane switch trajectory is not greater than a preset curvature threshold, or the maximum curvature change rate of the lane switch trajectory is not greater than a preset curvature change rate threshold, it is determined that the lane switch trajectory is valid.

[0039] According to the above technical means, it is possible to accurately determine whether the lane switching trajectory is effective.

[0040] An automatic driving control device, comprising:

[0041] The data acquisition module is configured to acquire the current driving state of the current vehicle when it is determined that the current vehicle is driving in the ramp;

[0042] A lane switching area reconstruction module is configured to obtain a real-time image including the surrounding environment of the current vehicle if it is determined that the current driving state of the current vehicle meets the main road switching condition, extract the first lane line information of the main road and the second lane line information of the ramp through the real-time image, and construct a lane switching area for the current vehicle to enter the main road based on the first lane line information and the second lane line information;

[0043] a passable area construction module, configured to obtain point cloud data of the lane switching area, determine a first passable area of ​​the lane switching area according to the point cloud data, and determine a second passable area of ​​the lane switching area according to the real-time image, wherein the point cloud data is obtained by detecting the lane switching area by a millimeter wave radar; and

[0044] Determining an overlapping area of ​​the first traversable area and the second traversable area as a target traversable area of ​​the lane switching area;

[0045] The trajectory generation module is configured to determine a lane switching trajectory of the current vehicle according to the target passable area, and when it is determined that the lane switching trajectory is valid, control the current vehicle to enter the main road according to the lane switching trajectory.

[0046] A terminal device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned automatic driving control method when executing the computer program.

[0047] A car comprises the automatic driving control device mentioned above.

[0048] Beneficial effects of the present invention:

[0049] There is no need to rely on high-precision maps and high-precision positioning systems. The lane switching area can be reconstructed based on the vehicle's own cameras and millimeter-wave radars. It has low cost and a wide range of applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 is the flowchart of the automatic driving control method of the present invention;

[0051] Figure 2 is the logic diagram of the automatic driving control method of the present invention;

[0052] Figure 3 is the schematic diagram of the principle of constructing the lane change area of the present invention;

[0053] Figure 4 is the schematic diagram of the principle of the first passable area of the present invention;

[0054] Figure 5 is the schematic block diagram of the automatic driving control device of the present invention;

[0055] Figure 6 is the schematic diagram of the structure of a terminal device of the present invention.

[0056] Wherein, 1-current vehicle, 2-right lane line of the main road, 3-right lane line of the ramp, 4-diversion line, 5-left lane line of the main road, 6-end point of the main road in the lane change area, 7-start point of the main road in the lane change area, 8-guardrail, 9-lane change trajectory, 10-terminal device, 100-processor, 101-memory, 102-computer program. Specific Embodiments

[0057] The following will describe the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for explaining the present invention, rather than for limiting the protection scope of the present invention.

[0058] As Figure 1 and Figure 2 shown, this embodiment proposes an automatic driving control method, including:

[0059] S100. When it is determined that the current vehicle is driving in the ramp, obtain the current driving state of the current vehicle;

[0060] S200. If it is determined that the current driving state of the current vehicle meets the main road switching condition, obtain a real-time image including the surrounding environment of the current vehicle, extract the first lane line information of the main road and the second lane line information of the ramp from the real-time image, and construct a lane change area for the current vehicle to enter the main road based on the first lane line information and the second lane line information;

[0061] S300. Obtain the point cloud data of the lane change area, determine the first passable area of the lane change area based on the point cloud data, and determine the second passable area of the lane change area based on the real-time image. The point cloud data is obtained by detecting the lane change area with a millimeter-wave radar;

[0062] S400. Determine the overlapping area of the first passable area and the second passable area as the target passable area of the lane change area;

[0063] S500. Determine the lane change trajectory of the current vehicle based on the target passable area. When it is determined that the lane change trajectory is valid, control the current vehicle to enter the main road according to the lane change trajectory.

[0064] In this way, the present invention does not need to rely on a high-precision map and a high-precision positioning system, and can realize the reconstruction of the lane change area based on the vehicle's own camera and millimeter-wave radar, with low cost and wide application range.

[0065] In this embodiment, the real-time image is collected by an in-vehicle camera, and the point cloud data is collected by an in-vehicle millimeter-wave radar. Among them, the millimeter-wave radar includes a forward long-distance millimeter-wave radar and a lateral medium-distance millimeter-wave radar. In step S100, it can be determined whether the vehicle is driving on the ramp based on an ordinary lane navigation map, i.e., an ADAS Map, which is used to provide lane information such as a navigation path and ramp information. Among them, the current driving state of the current vehicle at least includes the driving mode of the current vehicle, the first position of the current vehicle, the second position of the current vehicle, the lane information of the current vehicle, and the vehicle speed of the current vehicle. Among them, the driving mode indicates that the current vehicle is in an autonomous driving mode or a non-autonomous driving mode; the first position can be the positioning information of the current vehicle. For example, the positioning information obtained by an ordinary in-vehicle satellite positioning system includes, but is not limited to, non-high-precision-map-based and high-precision-positioning-integrated in-vehicle positioning systems such as GNSS, GPS, and INS; the second position represents the relative distance between the current vehicle and the target main road, such as the distance between the current vehicle and the entrance of the target main road; the lane information represents the positional relationship between the current lane of the current vehicle and the target main road. For example, whether the current lane is an adjacent lane to the target main road.

[0066] In step S200, it is judged whether the current driving state of the current vehicle meets the main road switching conditions, including:

[0067] S201. Determine that the current vehicle is already in the assisted driving mode, that is, the assisted driving function has been turned on and the navigation destination has been set;

[0068] S202. Match the positioning information of the current vehicle with a preset electronic fence area to determine that the current vehicle is within the electronic fence area where assisted driving is allowed;

[0069] S203. Determine that the current vehicle is already within the determination area of the main road based on the navigation information. For example, determine that the distance between the second position of the current vehicle and the main road is not greater than a preset distance threshold by obtaining the navigation information of the current vehicle. When the navigation information indicates that there are still 50 m to enter the main road from the ramp, determine that the current vehicle is within the determination area of entering the main road;

[0070] S204. Determine that the lane where the current vehicle is located is an adjacent lane to the main road based on the navigation information;

[0071] S205. Obtain the real-time vehicle speed of the current vehicle and determine that the vehicle speed of the current vehicle is within the speed range allowed to enter the main road.

[0072] When it is determined that the current driving state of the current vehicle meets steps S201 to S205, determine that the current vehicle meets the main road switching condition and enter the scene reconstruction step of the lane switching area, that is, the ramp area. Otherwise, continuously obtain the current driving state of the current vehicle until the current driving state meets steps S201 to S205.

[0073] In step S200, when constructing the lane switching area, collect the real-time images around the vehicle through the in-vehicle camera, extract the lane line features through image recognition, and then extract the first lane line information of the main road and the second lane line information of the ramp. Among them, the first lane line information includes the guide line, the right lane line of the main road, and the left lane line of the main road; the second lane line information includes the right lane line of the ramp.

[0074] It can be understood that the detection and extraction of lane lines can be realized through machine learning algorithms. For example, lane line detection can use algorithms such as the RANSAC algorithm, the least squares method, and the Hough transform. The lane lines are extracted from the road surface area by extracting the underlying features of the lane lines such as color, edge, texture, and gradient change; or, lane line detection is performed through machine learning algorithms such as convolutional neural networks and the LaneNet algorithm. This is not limited here.

[0075] When constructing the lane switching area, it is also necessary to identify whether the right lane line of the main road is a wide dashed line and the guide line. In this embodiment, the identification process of the guide line is as follows:

[0076] First, obtain multiple images including guide lines at different angles as training samples, and construct an initial training sample set. Among them, in order to avoid overfitting and ensure the recognition accuracy of the model, before model training, this embodiment also performs data augmentation processing on the training samples. For example, random white noise or Gaussian noise can be added to the images in the initial training sample set to generate new sample images, so as to achieve sample amplification and obtain the final training sample set. Among them, the amount of added noise, such as the standard deviation, can be adjusted according to the input variables, which is not limited here. Another example is that the image brightness, contrast, saturation, and hue of the images in the initial training sample set can be randomly adjusted to generate more sample images.

[0077] After obtaining the final training sample set, using the sample images in the training sample set as input, machine learning algorithms such as SCNN and RESA are used to learn the guide line features to obtain a guide line recognition model;

[0078] The guide line features are extracted by semantic segmentation of the acquired real-time image through the guide line recognition model, so as to realize the recognition of the guide line.

[0079] Similarly, the above steps can be used to recognize wide dashed lines, which will not be elaborated here.

[0080] Then, as Figure 3 shown, in step S200, based on the first lane line information and the second lane line information, a lane switching area for the current vehicle to enter the main road is constructed, including:

[0081] First, obtain the processing result of the real-time image. For the extracted first lane line information and second lane line information, if a guide line is recognized and the right lane line of the main road is a wide dashed line, the end point of the guide line is used as the starting point of the main road in the lane switching area, and the intersection point of the right lane line of the main road and the right lane line of the ramp is used as the ending point of the main road in the lane switching area. For example, by performing semantic segmentation on the real-time image, the feature information of the intersection point of the left and right lane lines of the current lane is extracted. If it is recognized that one side of the current lane is an ordinary lane line and the other side is a wide dashed line, the intersection point of the ordinary lane line and the wide dashed line is the ending point of the main road in the lane switching area. Among them, the end point of the guide line refers to the connection point of the guide line and the wide dashed line, the starting point of the main road in the lane switching area is the starting point where the vehicle is allowed to enter the main road from the ramp, and the ending point of the main road in the lane switching area is the ending point where the vehicle is allowed to enter the main road from the ramp.

[0082] Secondly, the right lane line of the main road is used as the left boundary of the ramp, and the right lane line of the ramp is used as the right boundary of the ramp, so as to obtain a lane switching area composed of the guide line, the left lane line of the main road, the right lane line of the main road, the left boundary of the ramp, and the boundary of the ramp.

[0083] In step S300, after initially constructing the lane change area, the construction accuracy of the lane change area is further improved to ensure the safety of autonomous driving. In this embodiment, the passable area of the lane change area is further determined. The passable area of the lane change area is established respectively through real-time images and millimeter-wave radar, and the first passable area obtained through real-time images and the second passable area obtained through millimeter-wave radar are matched, and the overlapping area of the two is used as the target passable area.

[0084] It can be understood that the point cloud data of the millimeter-wave radar can be regarded as a matrix arranged in sequence by the information of each reflection point. For example, taking a 16-line millimeter-wave radar as an example, the scanning range is 360 degrees, and there are 16 detection lines in total. Then its horizontal angular resolution is 0.2 degrees. The maximum number of reflection points on each detection line is 360 / 0.2 = 1800. Then the information of each reflection point can be stored in a 16×1800 matrix in sequence to form the point cloud data of the millimeter-wave radar. Among them, the reflection point information includes at least the coordinate information of the reflection point.

[0085] Then, as Figure 4 shown, determining the first passable area of the lane change area based on the point cloud data includes:

[0086] S301. Obtain the first reflection point in the point cloud data, and determine the second reflection point adjacent to the first reflection point, where the first reflection point and the second reflection point are points on adjacent angular detection lines.

[0087] S302. Obtain the first reflection point information of the first reflection point and the second reflection point information of the second reflection point. For example, in the matrix of the point cloud data, the first reflection point information and the second reflection point information are the data of two adjacent columns in the same row. Among them, the first reflection point information includes the first coordinate of the first reflection point, and the second reflection point information includes the second coordinate of the second reflection point.

[0088] S303. Determine the slope between the first reflection point and the second reflection point based on the first coordinate and the second coordinate point, and smooth the slope between the first reflection point and the second reflection point. It can be understood that the slope between the first reflection point and the second reflection point is the slope of the line connecting the two points of the first reflection point and the second reflection point in the same coordinate system. In this embodiment, the Savitsky-Golay filter is used to smooth the obtained slope.

[0089] S304. When the slope between the first reflection point and the second reflection point is less than the preset slope threshold, connect the first reflection point and the second reflection point. If the slope between the first reflection point and the second reflection point is too large, it indicates that it may be the reflection point of an obstacle.

[0090] S305. Traverse all the reflection points in the point cloud data, and repeat the above steps until all the connected reflection points form a closed area. Determine the obtained closed area as the first passable area. In this embodiment, the point cloud data is traversed by the BFS algorithm. If the obtained connection lines can form a closed area, determine that the area is a passable area; otherwise, determine that the area is impassable, generate an alarm message and prompt the driver to take over the steering wheel.

[0091] For the recognition of the second passable area, in this example, the passable area is recognized by recognizing the edges in the real-time image. Common recognition methods include edge detection algorithms based on traditional machine vision such as sobel and prewitt operators, or semantic segmentation algorithms or SVM classification algorithms based on machine learning, all of which can realize the detection of the passable area. The above algorithms are prior arts and will not be elaborated here. For example, according to the main road starting point, the left and right boundaries of the ramp that have been reconstructed in the above steps, extract the points representing the road boundary guardrails from the radar point cloud data and the passable area segmentation point cloud of the real-time image, and then judge whether the reconstructed lane change area is in a passable state as a safety check. When it is determined that any area is impassable, generate an alarm message and prompt the driver to take over the steering wheel.

[0092] In step S500, determining the lane change trajectory of the current vehicle according to the target passable area includes: generating the lane change trajectory of the current vehicle according to the left lane line of the main road, the left boundary of the ramp, the right boundary of the ramp, the main road starting point of the lane change area and the main road end point of the lane change area. Among them, when planning the lane change trajectory, it can be determined according to the navigation information whether the current vehicle drives on the left or right side of the main road after entering the main road. Combining the left lane line of the main road, the left boundary of the ramp, the right boundary of the ramp, the main road starting point of the lane change area and the main road end point of the lane change area, by setting reasonable control points, a cubic polynomial curve equation is generated to obtain the lane change trajectory. Among them, the calculation process of the cubic polynomial curve equation is a prior art and will not be limited here.

[0093] After generating the lane change trajectory, in order to further ensure the safety of autonomous driving and improve the control accuracy, this embodiment further determines the validity of the generated lane change trajectory. Among them, determining that the lane change trajectory is valid includes: if it is determined that the maximum curvature of the lane change trajectory is not greater than a preset curvature threshold, or the maximum curvature change rate of the lane change trajectory is not greater than a preset curvature change rate threshold, it is determined that the lane change trajectory is valid. Among them, if the maximum curvature in the lane change trajectory is greater than the curvature threshold, or the maximum curvature change rate in the curve is greater than the curvature change rate threshold, it means that the current trajectory cannot meet the control followability of the vehicle, and the current lane change trajectory is invalid, and an alarm message is generated to prompt the driver to take over the steering wheel. It can be understood that in this embodiment, when it is judged that the current distance from the end of the main road is too close to plan an effective trajectory, or when it is judged that there is a collision risk between the current trajectory and other targets, an alarm message is generated to prompt the driver to take over the steering wheel.

[0094] As Figure 5 shown, this embodiment also proposes an autonomous driving control device, including:

[0095] A data acquisition module, configured to acquire the current driving state of the current vehicle when it is determined that the current vehicle is driving on the ramp;

[0096] A lane change area reconstruction module, configured to, if it is determined that the current driving state of the current vehicle meets the main road switching condition, acquire a real-time image including the surrounding environment of the current vehicle, extract the first lane line information of the main road and the second lane line information of the ramp from the real-time image, and construct a lane change area for the current vehicle to enter the main road based on the first lane line information and the second lane line information;

[0097] A passable area construction module, configured to acquire the point cloud data of the lane change area, determine the first passable area of the lane change area according to the point cloud data, determine the second passable area of the lane change area according to the real-time image, and the point cloud data is obtained by detecting the lane change area with a millimeter wave radar; and

[0098] Determine the overlapping area of the first passable area and the second passable area as the target passable area of the lane change area;

[0099] A trajectory generation module, configured to determine the lane change trajectory of the current vehicle according to the target passable area, and control the current vehicle to enter the main road according to the lane change trajectory when it is determined that the lane change trajectory is valid.

[0100] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment 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 integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working process of the units and modules in the above system can refer to the corresponding process in the foregoing method embodiment and will not be elaborated here.

[0101] This embodiment also provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned autonomous driving control method is implemented.

[0102] As Figure 6 shown is a schematic diagram of the terminal device provided by the embodiment of the present application. As Figure 6 shown, the terminal device 10 of this embodiment includes: a processor 100, a memory 101, and a computer program 102 stored in the memory 101 and executable on the processor 100. When the processor 100 executes the computer program 102, the steps in the foregoing method embodiment are implemented. Alternatively, when the processor 100 executes the computer program 102, the functions of each module / unit in the foregoing device embodiments are implemented.

[0103] Exemplarily, the computer program 102 can be divided into one or more modules / units. One or more modules / units are stored in the memory 101 and executed by the processor 100 to complete the present application. One or more modules / units can be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program 102 in the terminal device 10.

[0104] The terminal device 10 can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The terminal device 10 may include, but is not limited to, a processor 100 and a memory 101. Those skilled in the art can understand that Figure 6 merely an example of the terminal device 10, which does not constitute a limitation on the terminal device 10, and may include more or fewer components than shown in the figure, or combine some components, or different components. For example, the terminal device may further include input / output devices, network access devices, buses, etc.

[0105] The processor 100 may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0106] The memory 101 may be an internal storage unit of the terminal device 10, such as the hard disk or memory of the terminal device 10. The memory 101 may also be an external storage device of the terminal device 10, such as a plug-in hard disk equipped on the terminal device 10, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the memory 101 may also include both the internal storage unit and the external storage device of the terminal device 10. The memory 101 is used to store computer programs and other programs and data required by the terminal device 10. The memory 101 may also be used to temporarily store data that has been output or is to be output.

[0107] Those skilled in the art should understand that the embodiments of the present application may be provided as a method, a system, or a computer program product. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application may 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.

[0108] This embodiment also proposes a vehicle, including the above-mentioned automatic driving control device.

[0109] In summary, the present invention does not need to rely on a high-precision map and a high-precision positioning system. It only needs to use the information of existing mainstream driving assistance sensors, detect the information of the guide line / lane line through a camera, reconstruct the scene of the lane change area, and combine the radar point cloud data and the camera to determine the passable area and judge the collision risk of the passable area, thereby improving the safety during the process of automatically controlling the vehicle to enter the main road from the ramp.

[0110] It should also be noted that the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, commodity or device including the element.

[0111] The above embodiments are only preferred embodiments given to fully illustrate the present invention, and the protection scope of the present invention is not limited thereto. Equivalent substitutions or transformations made by those skilled in the art on the basis of the present invention are all within the protection scope of the present invention.

Claims

1. An automatic driving control method, characterized in that, Including: When it is determined that the current vehicle is driving on the ramp, obtain the current driving state of the current vehicle; If it is determined that the current driving state of the current vehicle meets the main road switching condition, obtain a real-time image including the surrounding environment of the current vehicle, extract the first lane line information of the main road and the second lane line information of the ramp through the real-time image, and construct a lane switching area for the current vehicle to enter the main road based on the first lane line information and the second lane line information; Obtain the point cloud data of the lane switching area, determine the first passable area of the lane switching area according to the point cloud data, and determine the second passable area of the lane switching area according to the real-time image. The point cloud data is obtained by detecting the lane switching area with a millimeter wave radar; Determine the overlapping area of the first passable area and the second passable area as the target passable area of the lane switching area; Determine the lane switching trajectory of the current vehicle according to the target passable area. When it is determined that the lane switching trajectory is valid, control the current vehicle to enter the main road according to the lane switching trajectory; Determining the first passable area of the lane switching area according to the point cloud data includes: Obtain the first reflection point in the point cloud data and determine the second reflection point adjacent to the first reflection point; Obtain the first reflection point information of the first reflection point and the second reflection point information of the second reflection point. The first reflection point information includes the first coordinate of the first reflection point, and the second reflection point information includes the second coordinate of the second reflection point; determine the slope between the first reflection point and the second reflection point according to the first coordinate and the second coordinate and smooth the slope between the first reflection point and the second reflection point; When the slope between the first reflection point and the second reflection point is less than a preset slope threshold, connect the first reflection point and the second reflection point; Traverse all the reflection points in the point cloud data, and repeat the step of determining the first passable area of the lane switching area according to the point cloud data until all the connected reflection points form a closed area, and determine the obtained closed area as the first passable area.

2. The automatic driving control method according to claim 1, wherein The current driving state of the current vehicle includes: the driving mode of the current vehicle, the first position of the current vehicle, the second position of the current vehicle, the lane information of the current vehicle, and the vehicle speed of the current vehicle; The main road switching conditions include: Determine that the current vehicle is in the assisted driving state according to the driving mode of the current vehicle, determine that the current vehicle is in the electronic fence area where assisted driving is allowed according to the first position of the current vehicle, determine that the current vehicle is in the determination area for entering the main road according to the second position of the current vehicle, determine that the current vehicle is in the adjacent lane of the main road according to the lane information of the current vehicle, and determine that the vehicle speed of the current vehicle is in the speed range allowed to enter the main road.

3. The automatic driving control method according to claim 2, wherein Determining that the current vehicle is in the determination area for entering the main road according to the second position of the current vehicle includes: Obtain the navigation information of the current vehicle. If it is determined that the distance between the second position of the current vehicle and the main road is not greater than a preset distance threshold based on the navigation information, it is determined that the current vehicle is in the determination area for entering the main road.

4. The automatic driving control method according to claim 1, wherein The first lane line information includes: a guide line, the right lane line of the main road, and the left lane line of the main road; The second lane line information includes: The right lane line of the ramp.

5. The automatic driving control method according to claim 4, wherein Construct the lane change area for the current vehicle to enter the main road based on the first lane line information and the second lane line information, including: In the case where it is determined that the right lane line of the main road is a wide dashed line, use the end point of the guide line as the starting point of the main road in the lane change area, and use the intersection of the right lane line of the main road and the right lane line of the ramp as the ending point of the main road in the lane change area; Determine that the right lane line of the main road is the left boundary of the ramp, and determine that the right lane line of the ramp is the right boundary of the ramp.

6. The automatic driving control method according to claim 5, wherein Determine the lane change trajectory of the current vehicle according to the target passable area, including: Generate the lane change trajectory of the current vehicle based on the left lane line of the main road, the left boundary of the ramp, the right boundary of the ramp, the starting point of the main road in the lane change area, and the ending point of the main road in the lane change area; Determine that the lane change trajectory is valid, including: If it is determined that the maximum curvature of the lane change trajectory is not greater than a preset curvature threshold, or the maximum curvature change rate of the lane change trajectory is not greater than a preset curvature change rate threshold, it is determined that the lane change trajectory is valid.

7. An automatic driving control device, characterized in that, Include: A data acquisition module, configured to obtain the current driving state of the current vehicle when it is determined that the current vehicle is driving in the ramp; A lane change area reconstruction module, configured to, if it is determined that the current driving state of the current vehicle meets the main road switching condition, obtain a real-time image including the surrounding environment of the current vehicle, extract the first lane line information of the main road and the second lane line information of the ramp through the real-time image, and construct the lane change area for the current vehicle to enter the main road based on the first lane line information and the second lane line information; A passable area construction module, configured to obtain the point cloud data of the lane change area, determine the first passable area of the lane change area according to the point cloud data, determine the second passable area of the lane change area according to the real-time image, and the point cloud data is obtained by detecting the lane change area with a millimeter wave radar; And Determine the overlapping area of the first passable area and the second passable area as the target passable area of the lane change area; A trajectory generation module, configured to determine the lane change trajectory of the current vehicle according to the target passable area, and control the current vehicle to enter the main road according to the lane change trajectory when it is determined that the lane change trajectory is valid; Determine the first passable area of the lane change area according to the point cloud data, including: Obtain the first reflection point in the point cloud data, and determine the second reflection point adjacent to the first reflection point; Obtain the first reflection point information of the first reflection point and the second reflection point information of the second reflection point. The first reflection point information includes the first coordinate of the first reflection point, and the second reflection point information includes the second coordinate of the second reflection point; determine the slope between the first reflection point and the second reflection point based on the first coordinate and the second coordinate and smooth the slope between the first reflection point and the second reflection point; When the slope between the first reflection point and the second reflection point is less than a preset slope threshold, connect the first reflection point and the second reflection point; Traverse all the reflection points in the point cloud data, and repeat the step of determining the first passable area of the lane change area according to the point cloud data until all the connected reflection points form a closed area, and determine the obtained closed area as the first passable area.

8. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the automatic driving control method described in any one of claims 1 to 6.

9. A vehicle, characterized in that, It includes the automatic driving control device described in claim 7.

Images