A driving control method, electronic device, automatic driving vehicle and storage medium

Abstract

The present invention discloses a driving control method, an electronic device, an automatic driving vehicle and a storage medium, wherein the control method includes screening a first target driver according to the acquired online perception information; dynamically generating an interested target area according to the position and driving trend of the first target driver when the first target driver exists according to the screening result; screening a second target driver according to the positional relationship between the interested target area and the centerline of the vehicle and the positional relationship between each first target driver and the centerline of the vehicle; and outputting corresponding driving adjustment instructions according to the predetermined upper and lower limit parameters of the passing speed and the current speed information of the vehicle when the second target driver exists according to the screening result. Compared with the prior art, the method of the present invention has higher perception accuracy and does not rely on the takeover processing of the human driver, thereby reducing the probability of errors caused by human operation and effectively improving the safety of automatic driving when passing through intersections.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a driving control method, electronic equipment, an autonomous driving vehicle and a storage medium. Background Art

[0002] Existing driver assistance systems generally include lane keeping assistance systems, automatic parking assistance systems, brake assistance systems, reversing assistance systems and driving assistance systems. They are rarely designed for intersection scenarios. The existing lane centering assistance (LCC, Left-Centric Corridor) function on the market can only rely on human drivers to take over in actual intersection scenarios, and cannot achieve good assistance functions.

[0003] The solutions generally adopted by existing autonomous driving systems when facing intersection scenarios can be summarized as navigation assistance technical solutions with high-precision maps and technical solutions without maps.

[0004] The advantages of the navigation assistance technology solution with high-precision maps are more complete road information and better effects. However, the acquisition and maintenance costs of high-precision maps are too high, and they may not be suitable for all assisted driving systems. In addition, the coverage of high-precision maps is limited. In areas that the maps cannot cover, they will automatically downgrade to the LCC function or directly exit the function, so the system still has to rely on human drivers to take over.

[0005] For map-free technical solutions, the LCC-based visual lane line technical solution has a huge cost advantage over the high-precision map technical solution, but its effect is severely restricted by the perception range. For complex scenes such as intersections, its observation effect is often not ideal. At the same time, the map-free assisted driving functions currently available on the market that can pass through intersections basically pass through intersections at the speed set by the user, especially in the scene of VRU (Vulnerable Road Users). If the set speed is too high, the driver's sense of security will be very poor, and it may even bring danger. Summary of the invention

[0006] The embodiments of the present invention provide a driving control method, system, electronic device and storage medium to solve the problem that the existing automatic driving technology solutions for intersection scenarios are too costly and lack safety, which in turn leads to a poor sense of security for the driver.

[0007] According to a first aspect of the present invention, there is provided a driving control method, comprising:

[0008] Selecting a first target driver according to the acquired online perception information;

[0009] According to the screening result, when there is a first target traveler, dynamically generating an interested target area according to the position and driving trend of the first target traveler;

[0010] The second target drivers are selected according to the positional relationship between the target area of ​​interest and the center line of the vehicle and the positional relationship between each first target driver and the center line of the vehicle;

[0011] According to the screening result, when there is a second target driver, a corresponding driving adjustment instruction is output according to the predetermined upper and lower limit parameters of the passing speed and the current speed information of the vehicle.

[0012] According to a second aspect of the present invention, an electronic device is provided, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the steps of the method of the first aspect above.

[0013] According to a third aspect of the present invention, there is provided an autonomous driving vehicle, comprising the electronic device according to the second aspect.

[0014] According to a fourth aspect of the present invention, there is provided a storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method of the first aspect.

[0015] The present invention uses the relevant information obtained by online perception to detect the real-time road conditions, and screens the road drivers according to various information of the detected road drivers to screen out the first target driver who may have an impact on the driving of the vehicle, and adjusts the range of the target area of ​​interest of the vehicle according to the relevant information of the first target driver, so as to increase the range of the target area of ​​interest as much as possible under the premise of ensuring the correlation between the range of the target area of ​​interest and the driving of the vehicle, increase the sensitive perception of the dangers and emergency situations that may exist on the road, and reduce the probability of perception errors. At the same time, the first target driver is further screened according to the adjusted range of the target area of ​​interest to screen out the second target driver who is more likely to have an impact on the driving of the vehicle, and then output the driving adjustment instructions for response. Compared with the prior art, the method of the present invention has higher perception accuracy, does not rely on the takeover of human drivers, reduces the probability of errors caused by human operations, and can effectively improve the safety of automatic driving when passing through intersections, and can also improve the driver's sense of security when using automatic driving technology to pass through intersections. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0017] Figure 1 is a flow chart of a driving control method according to an embodiment of the present invention;

[0018] Figure 2 A flowchart of a method for screening a first type of driver in a driving control method according to an embodiment of the present invention;

[0019] Figure 3 A flowchart of a method for screening a second type of driver in a driving control method according to an embodiment of the present invention;

[0020] Figure 4 A flowchart of a method for screening a third type of driver in a driving control method according to an embodiment of the present invention;

[0021] Figure 5 A schematic diagram of generating an asymmetric target region of interest according to a third type of driver with a rightward traveling tendency in a driving control method according to an embodiment of the present invention;

[0022] Figure 6 A schematic diagram of generating an asymmetric target region of interest according to a third type of driver with a leftward traveling tendency in a driving control method according to an embodiment of the present invention;

[0023] Figure 7 A flow chart of a method for selecting a second target driver in a driving control method according to an embodiment of the present invention;

[0024] Figure 8 A flow chart of a method for outputting a driving adjustment instruction when a second target driver is screened out in a driving control method according to an embodiment of the present invention;

[0025] Fig. 9 A flowchart of the overall steps when a road user is sensed in a driving control method according to an embodiment of the present invention;

[0026] Fig.10 A flowchart of a method for outputting a driving adjustment instruction when there is no road driver in a driving control method according to an embodiment of the present invention;

[0027] Fig.11 A flow chart of an adjustment method for outputting a driving adjustment instruction when there is no road driver in a driving control method according to an embodiment of the present invention;

[0028] Fig.12 A flowchart of the overall steps when the absence of a road user is sensed in a driving control method according to an embodiment of the present invention;

[0029] Fig.13 is a principle block diagram of a driving control device according to an embodiment of the present invention;

[0030] Fig.14 It is a principle block diagram of a movable platform according to one embodiment of the present invention;

[0031] Fig.15 It is a schematic structural diagram of an embodiment of an electronic device of the present invention. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application may be combined with each other.

[0034] In the description of the present application, it should be understood that if the terms "center", "middle", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "axial", "radial", "circumferential" and the like are used to indicate the orientation or position relationship based on the orientation or position relationship shown in the drawings, it is only for the convenience of describing the present application and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application. The features defined as "first" and "second" are used to distinguish the feature names, rather than having special meanings. In addition, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present application, unless otherwise specified, "multiple" means two or more.

[0035] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0036] It should also be noted that, in this article, the terms "include" and "comprise" include not only those elements, but also other elements not explicitly listed, or also include elements inherent to such processes, methods, articles or equipment. In the absence of further restrictions, the elements defined by the sentence "include..." do not exclude the existence of other identical elements in the process, method, article or equipment that includes the elements. The terms used in this article are generally commonly used by those skilled in the art. If there is any inconsistency with the commonly used terms, the terms in this article shall prevail.

[0037] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] The present invention will be further described in detail below in conjunction with the accompanying drawings.

[0039] Figure 1 The overall process of the driving control method of one embodiment of the present invention is schematically shown. The driving control method of the present invention is applicable to a movable platform with automatic driving or semi-automatic driving functions. These movable platforms can be cars, cleaning vehicles, robots, etc. In the following text, the term "car" is used to represent this type of movable platform. Figure 1 As shown, the driving control method of the present invention is implemented by comprising the following steps:

[0040] Step S11: screening a first target driver according to the acquired online perception information;

[0041] Step S12: when there is a first target driver according to the screening result, dynamically generate an interested target area according to the position and driving trend of the first target driver;

[0042] Step S13: selecting the second target drivers according to the positional relationship between the target area of ​​interest and the centerline of the vehicle and the positional relationship between each first target driver and the centerline of the vehicle;

[0043] Step S14: When there is a second target driver according to the screening result, a corresponding driving adjustment instruction is output according to the predetermined upper and lower limit parameters of the passing speed and the current speed information of the vehicle.

[0044] The online perception information described in the present invention is obtained based on the online perception devices such as radars and cameras installed on the vehicle. These online perception information can be directly output by these online perception devices, or formed by processing the data output by these online perception devices. For example, the environment around the vehicle can be perceived in real time by the radar installed on the vehicle, so as to obtain the online perception point cloud data of the surrounding environment in real time. These online perception point cloud data are processed by the front module such as the perception module to form an online map based on the online perception point cloud data. The online map includes the road topology information of the surrounding environment, and then the road topology information can be directly obtained from the front module as the online perception information. Specifically, the obtained online perception information can include traffic light information (including whether there is a traffic light, traffic light location information and the current light color of the traffic light, etc.), intersection information (including whether there is an intersection, intersection area information and intersection location information, etc.), zebra crossing location information and safety island location information, etc. In addition, the online perception information can also include the road traveler information of the perceived road traveler. Among them, the road users in the present invention specifically refer to VRU (Vulnerable Road Users), and vehicles traveling on the road are not included in the road users described in the present invention. For example, these road users may be pedestrians, non-motor vehicle (such as bicycles, electric vehicles, motorcycles, etc.) riders and other people with lower traffic safety. Specifically, there may be multiple perceived road users, and the road user information of these road users may include the location information, posture information and speed information of the road users.

[0045] In step S11, it is necessary to first screen out the first target driver according to the acquired online perception information, wherein the first target driver refers to the road driver whose road driver information meets the specific conditions among the road drivers perceived by the online perception information. There may be multiple specific conditions, and different specific conditions will screen out different types of road drivers, and these road drivers all belong to the first target driver. After the first target driver is screened out, step S12 is executed again, and when there are first target drivers according to the screening results, the target region of interest is dynamically generated according to the position information and driving trend of these first target drivers. Among them, since there may be multiple types of the screened out first target drivers, the corresponding positions and driving trends of various types of first target drivers may also correspond to multiple types, so these different types of first target drivers will have different effects on the vehicle, so the benchmarks when generating the target region of interest will also be different, and then in this step, the target region of interest needs to be dynamically generated according to the screening results.

[0046] In some possible implementations, the specific conditions for screening the first target driver can be determined based on the comparison results of the target driver's speed and a preset low-speed threshold, the comparison results of the distance between the target driver's position and the perceived zebra crossing position and the safety island position and the preset range, and the comparison results of the target driver's movement trend and the preset movement trend. Among them, the low-speed threshold is a speed threshold used to determine whether the speed of the target driver is safe for the vehicle. The low-speed threshold is a pre-set speed threshold, which can be set based on experience. In some possible implementations, the low-speed threshold can be dynamically changed according to the current position and / or time period of the vehicle. For example, different low-speed thresholds can be set in different cities, and different low-speed thresholds can also be set during rush hour and non-peak hours, and so on. The preset range is a distance threshold used to determine whether the target driver is near a zebra crossing or a safety island. The target driver being near a zebra crossing or a safety island can mean that the position of the target driver and the position of the zebra crossing or the safety island are both within the range that the vehicle's perception can detect, so that the perception judgment can be more sensitive. The target driver being located near a zebra crossing or a safety island may also mean that the target driver's location is detected to be within a preset distance threshold range of the zebra crossing or safety island area. This design can further judge the location status of the target driver to improve the accuracy of the perception judgment. The preset movement trend is a judgment condition for judging whether the target driver's driving trend is safe for the vehicle. The preset movement trend may include a movement trend to the left based on the center line of the vehicle and a movement trend to the right based on the center line of the vehicle.

[0047] Based on the above description of the specific conditions for screening, as a possible implementation, the first target driver may include a first type of driver who is within a preset range from a zebra crossing or a safety island and whose speed is lower than a preset low speed threshold. In actual scenarios, the first type of driver may be a road driver who is on or near a zebra crossing at an intersection and is crossing the road at a low speed, or a driver who is on or near a safety island at an intersection and is waiting to cross the road. Figure 2 The method flow of screening the first type of drivers in the driving control method according to one embodiment of the present invention is schematically shown. Figure 2 As shown, the method can be specifically implemented by comprising the following steps:

[0048] Step S21: screening out road drivers whose speed is lower than a preset low speed threshold according to the speed information of road drivers;

[0049] Step S22: based on the position information of the road drivers whose speed is lower than the preset low speed threshold, the zebra crossing position information and the safety island position information, the road drivers located at the zebra crossing and the safety island are selected as the first type of drivers among the first target drivers.

[0050] Step S21 and step S22 are to screen road drivers that meet the relevant specific conditions based on the speed information and position information of the road drivers in the acquired online perception information, as well as the zebra crossing position information and the safety island position information in the online perception information, so as to screen out the road drivers perceived online as the first type of drivers among the first target drivers. Among them, when screening out road drivers whose speed is lower than the preset low-speed threshold, the screening can be performed based on the comparison between the preset low-speed threshold and the speed information of each road driver perceived in the online perception information. When screening out road drivers within a preset range from the zebra crossing or the safety island, the distance between each road driver and the zebra crossing or the safety island can be determined based on the position information of each road driver perceived in the online perception information, the position information of the zebra crossing and the position information of the safety island, and then the screening is performed by comparing the distance with the preset range. It can be understood that in step S21 and step S22, whether the road travelers are first screened based on the low-speed threshold and the speed information of the road travelers, or first screened based on the position information of the road travelers, the zebra crossing position information and the safety island position information, does not affect the screening results and can be freely designed according to actual conditions.

[0051] As another possible implementation, the first target driver may also include a second type of driver who is within a preset range from the zebra crossing or the safety island, does not have a preset moving trend, and whose speed is not lower than a preset low speed threshold. In actual scenarios, the second type of driver may be a road driver who is located on the roadside of the intersection and walks along the road direction at a relatively fast walking speed. Figure 3 The method flow of screening the second type of drivers in the driving control method according to one embodiment of the present invention is schematically shown. Figure 3 As shown, the method can be specifically implemented by comprising the following steps:

[0052] Step S31: selecting road drivers whose speed is not less than a preset low speed threshold according to the speed information of road drivers;

[0053] Step S32: Based on the position information and posture information of the road drivers whose speed is not lower than the preset low-speed threshold, the current posture information of the vehicle, the zebra crossing position information and the safety island position information, the road drivers located at the zebra crossing and the safety island and who do not have a preset moving trend are screened out as the second type of drivers of the first target drivers.

[0054] Steps S31 and S32 are to screen road drivers that meet the relevant specific conditions according to the speed information, posture information and position information of the road drivers in the acquired online perception information, the zebra crossing position information and the safety island position information in the online perception information, and the posture information of the vehicle, so as to screen out the road drivers perceived online as the second type of drivers in the first target drivers. Among them, when screening out road drivers whose speed is not lower than the preset low-speed threshold, the screening can be performed based on the preset low-speed threshold and the speed information of each road driver perceived in the online perception information. When screening out road drivers within a preset range from the zebra crossing or the safety island, the distance between each road driver and the zebra crossing or the safety island can be determined based on the position information of each road driver perceived in the online perception information, the position information of the zebra crossing and the position information of the safety island, and then the screening is performed by comparing the distance with the preset range. When screening out road drivers that do not have a preset moving trend, the screening can be performed based on the comparison of the posture information of each road driver and the current posture information of the vehicle. It can be understood that in step S31 and step S32, whether the road travelers are first screened based on the low-speed threshold and the speed information of the road travelers, or the road travelers are first screened based on the position information of the road travelers, the zebra crossing position information and the safety island position information, or the road travelers are first screened based on the posture information of the road travelers and the current posture information of the vehicle, does not affect the screening results and can be freely designed according to actual conditions.

[0055] Specifically, in some possible implementations, when determining whether a road traveler has a preset movement trend, it can be determined based on the posture information of each road traveler and the current posture information of the vehicle. Since the preset movement trend is a movement trend to the left based on the center line of the vehicle and a movement trend to the right based on the center line of the vehicle, it is necessary to first determine the current posture information of the vehicle when determining whether a road traveler has a preset movement trend. It can be understood that the center line of the vehicle is generally consistent with the direction of travel of the vehicle, so the current direction of travel of the vehicle is determined by the current posture information of the vehicle, which is equivalent to determining the center line of the vehicle. Then the direction of travel of each road traveler is further determined. When determining the direction of travel of the road traveler, it is determined by the posture information of the road traveler. Since there may be a certain angle between the direction of travel of the road traveler and the direction of travel of the vehicle, a two-dimensional coordinate system can be constructed based on the direction of travel of the vehicle to decompose the direction of travel of the road traveler, so that the direction of travel of the road traveler is decomposed into a Y-axis direction parallel to the direction of travel of the vehicle and an X-axis direction perpendicular to the direction of travel of the vehicle. Among these road traveler, the road traveler with an X-axis direction has a direction to the left or right based on the center line of the vehicle. When these road traveler has a certain speed, it is considered to have a preset movement trend. Since in the above-mentioned implementation method of screening the second type of traveler, the screening condition includes a speed not lower than a preset low speed threshold, therefore, in the above-mentioned implementation method, only whether there is an X-axis direction can be used as a judgment condition for whether the road traveler has a preset movement trend, that is, if there is an X-axis direction, it is considered to have a preset movement trend, and if there is no X-axis direction, it is considered to have no preset movement trend. In addition, in actual environments, some road travelers may have a slight angle with the road direction while traveling along the Y-axis direction, or the vehicle may have a slight angle with the road direction while traveling. Therefore, when judging whether the road travelers have a preset movement trend, the judgment condition can be further set to whether the speed in the X-axis direction is less than a preset threshold. If it is less than the preset threshold, it is considered that there is no preset movement trend to improve the robustness of the judgment.

[0056] As another possible implementation, the first target driver may also include a third type of driver with a preset moving trend and a speed not lower than a preset low speed threshold. In an actual scenario, the third type of driver may be a road driver at an intersection with a left-right walking direction trend based on the center line of the vehicle and a relatively fast walking speed. Figure 4 The method flow of screening the third type of driver in the driving control method according to one embodiment of the present invention is schematically shown. Figure 4 As shown, the method can be specifically implemented by comprising the following steps:

[0057] Step S41: selecting road drivers whose speed is not less than a preset low speed threshold according to the speed information of road drivers;

[0058] Step S42: Based on the posture information of the selected road travelers whose speed is not less than the preset low-speed threshold and the current posture information of the vehicle, select the road travelers with a preset moving trend as the third type of travelers of the first target travelers.

[0059] Step S41 and step S42 are to screen the road travelers that meet the relevant specific conditions according to the speed information and posture information of the road travelers in the acquired online perception information, as well as the posture information of the vehicle, so as to screen out the road travelers perceived online as the third type of drivers in the first target driver. Among them, when screening out the road travelers whose speed is not lower than the preset low-speed threshold, the screening can be performed based on the pre-set low-speed threshold and the speed information of each road traveler perceived in the online perception information. When screening out the road travelers with a preset moving trend, the screening can be performed based on the comparison of the posture information of each road traveler and the current posture information of the vehicle. The specific method can be referred to in the above text, and will not be repeated here. It can be understood that in step S41 and step S42, whether the road travelers are screened based on the low-speed threshold and the speed information of the road travelers first, or the road travelers are screened based on the posture information of the road travelers and the current posture information of the vehicle first, does not affect the screening results, and can be freely designed according to actual conditions.

[0060] The above three embodiments respectively represent three different types of drivers selected when selecting the first target driver. After selecting the first target driver, step S12 is executed again. When the first target driver exists according to the screening result, the target region of interest is dynamically generated according to the location information and driving trend of these first target drivers. Specifically, for the first type of drivers and the second type of drivers among the first target drivers, when generating the target region of interest, it can be set to generate a target region of interest with a larger coverage range than the standard target region of interest. For example, for the standard target region of interest, its width is generally set to increase the width of half a lane on the left and right sides on the basis of the original lane width (or vehicle width), that is, the width is generally set to the range of the lane width (or vehicle width) plus one lane width. When generating a target region of interest with a larger coverage range than the standard target region of interest, the width of one lane can be increased on the left and right sides on the basis of the standard target region of interest to form a target region of interest with a larger coverage range than the standard target region of interest.

[0061] As for the third type of drivers among the first target drivers, when generating the target region of interest, it can be set to generate an asymmetric target region of interest based on the center line of the vehicle, and the asymmetric target region of interest is set to have a smaller coverage on the side of the center line of the vehicle in the direction of the movement trend of the third type of drivers. When generating the asymmetric target region of interest, it is necessary to correspond to the posture information of the third type of drivers corresponding to when generating the target region of interest. Specifically, the X-axis direction of travel of the third type of drivers can be determined first according to the corresponding posture information of the third type of drivers, thereby determining the position of the side with a smaller coverage in the target region of interest. Exemplarily, referring to Figure 5 As shown, in Figure 5 In the example shown, the third type of driver has a tendency to move to the right, so in the generated target region of interest, the target region of interest on the left side of the vehicle centerline is set to be larger, and the target region of interest on the right side is set to be smaller. Figure 6 As shown, in Figure 6 In the example shown, the third type of driver has a tendency to move to the left, so in the generated target area of ​​interest, the target area of ​​interest on the left side of the center line of the vehicle is set to be smaller, and the target area of ​​interest on the right side is set to be larger. It can be seen that the side with a smaller coverage is the side where the third type of driver will move away from the vehicle during the travel. After determining the position of the side with a smaller coverage in the target area of ​​interest, it is necessary to determine the size of the target area of ​​interest. The size of the target area of ​​interest can be set on both sides based on the center line of the vehicle. Exemplarily, the size of the side with a smaller coverage can be set to half the lane width (or half the vehicle width) plus 0.5m. The size of the side with a larger coverage can be set to the product of the preset time and the preset minimum speed of the driver plus half the lane width (or half the vehicle width). Among them, the preset time and the preset minimum speed of the driver are both empirical values, which can be designed according to actual conditions. Exemplarily, in this embodiment, the preset time can be set to 3.0s, and the preset minimum speed of the driver can be set to 1m / s. Such a design can make the generated target areas of interest corresponding to the third type of drivers in the same travel direction consistent. In some other possible implementations, the preset minimum speed of the driver may also be set according to the speed information of the third category of drivers sensed, so that the generated target area of ​​interest can be more in line with the needs of the actual situation.

[0062] After completing step S11 and step S12, step S13 is executed to further filter out the second target driver. The second target driver is the first target driver located in the target area of ​​interest. Specifically, since there are many different types of first target drivers, and the target areas of interest corresponding to these different types of drivers may also be different, there may be many different screening methods when executing step S13. In some possible implementations, it is possible to determine whether each first target driver is located in the target area of ​​interest corresponding to it one by one, thereby filtering out the second target driver, and this scheme has high screening accuracy. In other possible implementations, multiple different target areas of interest can be combined to form a combined target area of ​​interest, and then determine whether each first target driver is located in the combined target area of ​​interest, thereby filtering out the second target driver. Compared with the former implementation, this implementation can greatly reduce the amount of calculation, thereby improving the response speed of the system. In some other possible implementations, the first target drivers can be further classified according to the shape and size of the target area of ​​interest, so as to obtain the first and second types of drivers corresponding to the target area of ​​interest with a larger coverage than the standard target area of ​​interest, the third type of drivers corresponding to the asymmetric target area of ​​interest with a smaller coverage on the left side of the center line of the vehicle, and the third type of drivers corresponding to the asymmetric target area of ​​interest with a smaller coverage on the right side of the center line of the vehicle. Then, the corresponding first target drivers are judged according to the corresponding target area of ​​interest to determine whether each first target driver is located in the corresponding target area of ​​interest, so as to screen out the second target drivers. In this implementation, the accuracy and speed of screening can be taken into account, so that the response speed of the system can be improved under the premise of ensuring the accuracy of screening.

[0063] Specifically, when the second target drivers are screened out in step S13, the screening may be performed based on the positional relationship between the target region of interest and the centerline of the vehicle and the positional relationship between each first target driver and the centerline of the vehicle. Figure 7 The method flow of selecting the second target driver in the driving control method according to one embodiment of the present invention is schematically shown. Figure 7 As shown, the method can be specifically implemented by comprising the following steps:

[0064] Step S51: determining the distances between the two sides of the target region of interest and the center line of the vehicle and the length of the target region of interest according to the positional relationship between the target region of interest and the center line of the vehicle;

[0065] Step S52: determining the projection position information of each first target driver on the center line of the vehicle according to the position information of each first target driver;

[0066] Step S53: Filter out the first target driver in the target area of ​​interest as the second target driver according to the projection position information of the first target driver on the center line of the vehicle, the length of the target area of ​​interest, and the distance between the two sides of the target area of ​​interest and the center line of the vehicle.

[0067] In step S51, since the target region of interest has been determined in step S12, the distance between the two sides of the target region of interest and the center line of the vehicle and the length of the target region of interest can be determined based on the generated target region of interest. Specifically, whether the distance between the two sides of the target region of interest and the center line of the vehicle is located on the left or right side of the center line of the vehicle can be indicated by positive and negative signs. For example, the distance between the edge of the target region of interest on the left side of the center line of the vehicle and the center line of the vehicle can be a negative number, and the distance between the edge of the target region of interest on the right side of the center line of the vehicle and the center line of the vehicle can be a positive number, thereby indicating whether the distance between the two sides of the target region of interest and the center line of the vehicle is located on the left or right side of the center line of the vehicle by means of left negative and right positive. The length of the determined target region of interest can be determined based on the length parameter of the generated target region of interest. In other possible implementations, the length of the determined target region of interest can also be determined by projecting the end of the target region of interest onto the center line of the vehicle. For example, the end of the target region of interest away from the vehicle is projected onto the center line of the vehicle to determine the distance between the end of the target region of interest and the end (or tail) of the vehicle as the length of the target region of interest. For another example, the two ends of the target region of interest in the length direction are projected onto the center line of the vehicle to determine the distance between the two ends of the target region of interest in the length direction and the projection positions on the center line of the vehicle as the length of the target region of interest.

[0068] In step S52, the position of the first target driver can be projected onto the center line of the vehicle, and the lateral distance between the first target driver and the center line of the vehicle can be determined in the same manner of negative on the left and positive on the right, and the longitudinal distance between the first target driver and the center line of the vehicle can be determined in the manner of positive on the front and negative on the back. When determining the longitudinal distance between the first target driver and the center line of the vehicle, when the position of the first target driver is projected onto the center line of the vehicle, if the projected position is located behind the end (or tail) of the vehicle, the longitudinal distance between the first target driver and the center line of the vehicle can be set to a negative number to indicate that the first target driver is located behind the end (or tail) of the vehicle, otherwise the longitudinal distance between the first target driver and the center line of the vehicle can be set to a positive number to indicate that the first target driver is located in front of the end (or tail) of the vehicle. It is understandable that for some movable platforms with a larger perception range, it is possible to perceive road travelers behind the vehicle, and these road travelers are usually outside the target area of ​​interest. Therefore, the position state of the first target traveler relative to the vehicle can be judged by the positive or negative longitudinal distance of the projection of the first target traveler on the center line of the vehicle.

[0069] Finally, step S53 is executed to compare the distances between the two sides of the target area of ​​interest and the center line of the vehicle and the length of the target area of ​​interest, and the lateral distance and longitudinal distance between the first target driver and the center line of the vehicle, to determine whether the lateral distance of the first target driver is within the interval between 0 and the length of the target area of ​​interest. When the lateral distance and longitudinal distance between the first target driver and the center line of the vehicle are both within the interval, it is considered that the first target driver is within the target area of ​​interest, and is used as the second target driver. Otherwise, it is considered that the first target driver is not within the target area of ​​interest. It should be noted that in the process from step S51 to step S53, the order between step S51 and step S52 can be interchanged, and will not affect the screened results, and can be freely designed according to actual conditions.

[0070] After the second target driver is screened out, when it is determined that the second target driver exists, step S14 will be further executed to output a driving adjustment instruction, and when it is determined that the second target driver does not exist, a control instruction that does not trigger the driving adjustment is output to allow the vehicle to continue driving without adjusting the driving of the vehicle. When it is determined that the second target driver exists, the output driving adjustment instruction is determined based on the predetermined upper and lower limit parameters of the passing speed and the current speed information of the vehicle. Among them, the predetermined upper and lower limit parameters of the passing speed can be set according to the intersection area and traffic light conditions determined by the online perception information. For example, when there is no intersection area, the upper and lower limit parameters of the passing speed can be set to the first upper and lower limit parameters of the passing speed; when there is an intersection area and there is no traffic light, the upper and lower limit parameters of the passing speed can be set to the second upper and lower limit parameters of the passing speed; when there is an intersection area and the traffic light is green, the upper and lower limit parameters of the passing speed can be set to the third upper and lower limit parameters of the passing speed. Among the above three different upper and lower limit parameters of the passing speed, when there is no intersection area, the corresponding set first upper and lower limit parameters of the passing speed can be appropriately adjusted higher. When there is an intersection and a traffic light, since the number of target drivers may be larger when there is a traffic light than in other scenarios, the corresponding set third upper and lower limit parameters of the passing speed can be appropriately adjusted lower to ensure safety. When there is an intersection but no traffic light, the corresponding set second upper and lower limit parameters of the passing speed are set to medium to form upper and lower limit parameters of the passing speed corresponding to the three different environmental conditions. Therefore, according to the currently acquired online perception information, the upper and lower limit parameters of the passing speed adopted by the current intersection can be determined accordingly. In addition, the potential safety hazard of passing at an intersection without street lights will be greater, and a lower speed range is required to deal with each road driver. Therefore, in other embodiments, more groups of different upper and lower limit parameters of the passing speed can be further set according to whether there are street lights at the perceived intersection. For example, when it is perceived that there is a street lamp at the intersection, the corresponding upper and lower limit parameters of the speed can be appropriately adjusted higher, and when it is perceived that there is no street lamp at the intersection, the corresponding upper and lower limit parameters of the speed can be appropriately adjusted lower to ensure safety. The specific values ​​and groups of the upper and lower limit parameters of the speed can be designed according to the influencing factors that may exist in the actual environment, and this embodiment does not limit this.

[0071] Figure 8 The method flow of outputting driving adjustment instructions when the second target driver is screened out in the driving control method of one embodiment of the present invention is schematically shown, referring to Figure 8 As shown, the method can be specifically implemented by comprising the following steps:

[0072] Step S61: when the current speed of the vehicle is greater than the upper limit parameter of the passing speed, output a driving adjustment instruction to set the deceleration of the vehicle to the target deceleration and the deceleration speed of the vehicle to the target deceleration speed;

[0073] Step S62: when the current speed of the vehicle is less than the lower limit parameter of the passing speed, outputting a driving adjustment instruction to set the acceleration of the vehicle to the target acceleration and the jerk of the vehicle to the target jerk;

[0074] Step S63: When the current speed of the vehicle is not less than the lower speed limit parameter and not greater than the upper speed limit parameter, output a driving adjustment instruction to set the maximum acceleration of the vehicle to less than zero.

[0075] Specifically, the corresponding driving adjustment instruction is output according to the comparison between the current speed of the vehicle and the current upper and lower limit parameters of the passing speed. In step S61, the current speed of the vehicle is greater than the upper limit parameter of the passing speed. At this time, the speed of the vehicle is too fast, which is not conducive to coping with complex scenes. Therefore, the driving adjustment instruction output is to apply a deceleration with a deceleration to the vehicle, so that the deceleration value gradually decreases, the deceleration amplitude gradually increases, and the comfort is improved. Among them, the deceleration refers to the rate of change of the deceleration. Exemplarily, the rate of change value can be expressed by the rate of change of acceleration jerk. If the initial deceleration is set to -0.3 m / s, when jerk is set to a value less than 0, even if the deceleration has a deceleration, the deceleration will gradually decrease (for example, from -0.3 m / s to -0.6 m / s). Specifically, the set deceleration can be set to not less than -0.5m / s, and the set deceleration can be set to -0.6. In step S62, it is a scenario where the current speed of the vehicle is less than the lower limit parameter of the passing speed. At this time, the speed of the vehicle is too slow, so the output driving adjustment instruction is to apply an acceleration with jerk to the vehicle. Among them, jerk refers to the rate of change of acceleration. Exemplarily, it can be represented by the rate of change of acceleration jerk. When jerk is set to a value greater than 0, the acceleration will gradually increase. Specifically, the set acceleration can be set to be designed according to the current speed of the vehicle. The higher the current speed of the vehicle, the smaller the initial acceleration is set. The set jerk can be set to 0.4. In step S63, it is a scenario where the current speed of the vehicle is between the upper and lower limit parameters of the passing speed. At this time, the speed of the vehicle is more appropriate, but it is not suitable for further acceleration. Therefore, the output driving adjustment instruction is a non-acceleration strategy, that is, the maximum acceleration (a_max) of the vehicle is set to less than zero.

[0076] It is understandable that, in the process of passing through the intersection, the speed of the vehicle will continue to adjust, and when the speed of the vehicle is adjusted from satisfying the first condition to satisfying the second condition, the output driving adjustment instruction will also change accordingly. For example, when the speed of the vehicle is greater than the upper limit parameter of the passing speed at the beginning, the driving adjustment instruction to slow down the vehicle is output at this time. When the speed of the vehicle drops to between the upper and lower limit parameters of the passing speed, the output driving adjustment instruction will be switched to a non-acceleration strategy until the entire intersection is passed.

[0077] In step S61 to step S63, the set deceleration and deceleration rate, acceleration and jerk are all obtained based on a large amount of empirical data and can simulate the human brake release and accelerator strategy, so that the driving adjustment instructions output by the present invention can make the speed adjustment of the vehicle during the control process more comfortable, improve the safety of the vehicle when driving through the intersection, and at the same time will not make the driver feel out of control, so that the driver can feel more at ease when passing through the intersection.

[0078] The above are all corresponding steps executed when the first target driver is screened out in step S11. In some possible implementations, if in the online perception information obtained in step S11, each road driver perceived does not meet the specific conditions of being the first target driver, then a control instruction that does not trigger the driving adjustment can be output at this time to allow the vehicle to continue driving without making any adjustments to the driving of the vehicle. Fig. 9 The following is a schematic flow chart showing the overall steps of sensing a road user in a driving control method according to an embodiment of the present invention. Fig. 9As shown, the distance (lateral and longitudinal distances s, d) from the road traveler (i.e., VRU) to the center line of the ego vehicle (ego) is first calculated, and then the speed of the road traveler is judged. When the speed of the road traveler is lower than the preset low-speed threshold, it is further judged whether the road traveler is near a zebra crossing or a safety island. If so, the target area of ​​interest is expanded to generate a target area of ​​interest with a larger coverage range, otherwise a control instruction that does not trigger driving adjustment is output. When the speed of the road traveler is not less than the preset low-speed threshold, it is judged whether the road traveler has a preset movement trend (relative to the movement trend to the left or right of the ego vehicle). If it has a preset movement trend, the target area of ​​interest is adjusted to an asymmetric target area of ​​interest; otherwise, it is further judged whether the road traveler is near a zebra crossing or a safety island. If so, the target area of ​​interest is expanded to generate a target area of ​​interest with a larger coverage range, otherwise a control instruction that does not trigger driving adjustment (NOT Trigger) is output. After generating the target area of ​​interest, the position of the road user is judged to determine whether the road user is located in the target area of ​​interest. If so, different driving adjustment instructions (Trigger) are output according to the current ego vehicle speed (ego_vel) and the upper and lower limit parameters of the passing speed (V_MAX and V_MIN). Otherwise, a control instruction that does not trigger the driving adjustment is output. For the specific driving adjustment instructions output according to the current ego vehicle speed and the upper and lower limit parameters of the passing speed, please refer to the relevant description in the previous text, and this part will not be repeated here.

[0079] In some other possible implementations, it may be possible to sense that there is no road person according to the acquired online perception information. In this case, a driving adjustment instruction for the environment where there is no road person may be output according to the acquired online perception information. Fig.10 The method flow of outputting driving adjustment instructions when there is no road driver in the driving control method of one embodiment of the present invention is schematically shown, referring to Fig.10 As shown, the method can be specifically implemented by comprising the following steps:

[0080] Step S71: when there is no road user according to the screening result, confirm the positional relationship between the vehicle and the intersection area according to the current position of the vehicle and the acquired online perception information;

[0081] Step S72: Outputting corresponding driving adjustment instructions according to the positional relationship between the vehicle and the intersection area, the predetermined upper and lower limit parameters of the travel speed, and the current speed of the vehicle.

[0082] Step S71 is a step for confirming the current positional relationship between the vehicle and the intersection area. It is understandable that the positional relationship between the vehicle and the intersection area includes the vehicle approaching the intersection, the vehicle being in the intersection, and the vehicle leaving the intersection. When the vehicle is driving, it will switch between the above three positional relationships in turn. When confirming the current positional relationship between the vehicle and the intersection area, it can be determined whether there is an intersection based on the acquired online perception information, and the intersection area information and intersection position information can be determined based on the intersection information in the online perception information, and then the distance between the vehicle's current position and the intersection area can be further determined based on the current position of the vehicle and the range of the determined intersection area, thereby determining the current positional relationship between the vehicle and the intersection area. For example, if the intersection area is in front of the current position of the vehicle and the distance between the intersection area and the current position of the vehicle is within 5 meters, then the positional relationship between the vehicle and the intersection area can be considered as the vehicle being in the intersection; if the intersection area is in front of the current position of the vehicle and the distance between the intersection area and the current position of the vehicle is beyond 5 meters and within 50 meters, then the positional relationship between the vehicle and the intersection area can be considered as the vehicle approaching the intersection. The distance values ​​in the specific above examples can be adjusted according to the perception range and application environment of each device, and the above examples are not limited to this. It can be understood that when the vehicle is neither approaching the intersection nor in the intersection, the positional relationship between the vehicle and the intersection area can be regarded as the vehicle leaving the intersection. When the positional relationship between the vehicle and the intersection area is that the vehicle has left the intersection, since it has left the intersection area, a control instruction that does not trigger the driving adjustment can be output at this time to allow the vehicle to continue driving without adjusting the driving of the vehicle. In addition, in some possible implementations, the positional relationship between the vehicle and the intersection area can also be determined in combination with the traffic light information in the acquired online perception information, to further add information on whether there is a traffic light at the intersection and the current color of the traffic light, so that the positional relationship between the vehicle and the intersection area can include the vehicle approaching the intersection and there is no traffic light, the vehicle approaching the intersection and the traffic light is green, the vehicle approaching the intersection and the traffic light is not green, the vehicle is in the intersection, and the vehicle leaves the intersection.

[0083] After determining the positional relationship between the vehicle and the intersection area, step S72 is executed to output corresponding driving adjustment instructions according to different positional relationships between the vehicle and the intersection area. Fig.11 The present invention schematically illustrates a method for adjusting a driving adjustment command output when there is no road user in a driving control method according to an embodiment of the present invention, referring to Fig.11 As shown, the method can be specifically implemented by comprising the following steps:

[0084] Step S81: when the ego vehicle approaches an intersection and there is no traffic light, or when the ego vehicle approaches an intersection and the traffic light is green, if the ego vehicle's current speed is greater than the upper speed limit parameter, output a driving adjustment instruction to set the ego vehicle's deceleration to the target deceleration and the ego vehicle's deceleration speed to the target deceleration speed;

[0085] Step S82: when the vehicle approaches an intersection and there is no traffic light, or when the vehicle approaches an intersection and the traffic light is green, if the current speed of the vehicle is less than the lower limit parameter of the passing speed, output a driving adjustment instruction to set the maximum acceleration of the vehicle to less than zero;

[0086] Step S83: when the vehicle is at the intersection, outputting a driving adjustment instruction to set the maximum acceleration of the vehicle to be less than zero;

[0087] Step S84: When the vehicle approaches the intersection and the traffic light is not green, output a driving adjustment instruction to set the deceleration of the vehicle to the target deceleration and the deceleration speed of the vehicle to the target deceleration speed.

[0088] Step S81 and step S82 are driving adjustment instructions executed in the scenario when the vehicle approaches the intersection and there is no traffic light, or when the vehicle approaches the intersection and the traffic light is green. In these two scenarios, the strategies implemented are similar, but due to different actual scenarios, the upper and lower limit parameters of the speed adopted will be different. In the scenario when the vehicle approaches the intersection and there is no traffic light, the upper and lower limit parameters of the speed adopted will be relatively low, and in the scenario when the vehicle approaches the intersection and the traffic light is green, the upper and lower limit parameters of the speed adopted will be relatively high. In step S81, it is a scenario where the current speed of the vehicle is greater than the upper limit parameter of the speed. At this time, the speed of the vehicle is too fast, which is not conducive to coping with complex scenarios. Therefore, the output driving adjustment instruction is to apply a deceleration with a deceleration to the vehicle. Specifically, the set deceleration can be set to no more than 0.5m / s, and the set deceleration can be set to 0.6. In step S82, the current speed of the vehicle is less than the lower limit parameter of the passing speed. At this time, the speed of the vehicle is too slow, but in order to ensure safe passage through the intersection, it is not appropriate to accelerate the vehicle. Therefore, the output driving adjustment instruction is a non-acceleration strategy, that is, the maximum acceleration of the vehicle is set to be less than zero. In the scenario where the current speed of the vehicle is between the upper and lower limit parameters of the passing speed, a control instruction that does not trigger the driving adjustment can be output, so that the vehicle continues to drive without making any adjustments to the driving of the vehicle.

[0089] Step S83 is a driving adjustment instruction executed in the scenario when the vehicle is at an intersection. It is not appropriate to accelerate the vehicle when passing through an intersection, so the output driving adjustment instruction is a no-acceleration strategy, that is, the maximum acceleration of the vehicle is set to less than zero.

[0090] Step S84 is a driving adjustment instruction executed in a scenario when the vehicle approaches an intersection and the traffic light is not green. Since the traffic light is not green, the vehicle cannot pass smoothly, and the driving adjustment instruction output is to apply a deceleration with a deceleration speed to the vehicle. Specifically, the deceleration speed can be set to no more than 0.5 m / s, and the deceleration speed can be set to 0.6.

[0091] Similarly, in steps S81 to S84, the set deceleration and deceleration rate, acceleration and jerk are all obtained based on a large amount of empirical data and can simulate the human strategy of releasing the brake and stepping on the accelerator, so that the driving adjustment instructions output by the present invention can make the speed adjustment of the vehicle during the control process more comfortable, improve the safety of the vehicle when driving through the intersection, and at the same time will not make the driver feel out of control, so that the driver can feel more at ease when passing through the intersection.

[0092] Fig.12 The following is a schematic flow chart showing the overall steps of a driving control method according to an embodiment of the present invention when it is detected that there is no person driving on the road. Fig.12 As shown, the distance from the vehicle to the junction area (d_to_junk) is calculated first, and then the positional relationship between the vehicle and the junction area is judged. When the positional relationship between the vehicle and the junction is not that the vehicle is approaching the junction, it is further judged whether the vehicle is in the junction. If the vehicle is in the junction, a no-acceleration strategy is output. If the vehicle is not in the junction, it means that the positional relationship between the vehicle and the junction area is that the vehicle is leaving the junction. At this time, a control instruction that does not trigger driving adjustment is output. When the positional relationship between the vehicle and the junction is that the vehicle is approaching the junction, it is further judged whether a traffic light is detected based on the traffic light information in the perceived online perception information. When no traffic light is detected, the upper and lower limit parameters of the speed corresponding to the junction without traffic lights are compared with the current speed of the vehicle, and different driving adjustment instructions are output. When a traffic light is detected, it is further determined whether the traffic light is green. When the traffic light is green, the upper and lower limit parameters of the speed corresponding to the intersection with the traffic light are compared with the current speed of the vehicle, and different driving adjustment instructions are output. When the traffic light is not green, a driving adjustment instruction for slowing down the vehicle is output. For the specific driving adjustment instructions output according to the current vehicle speed and the upper and lower limit parameters of the speed, please refer to the relevant description in the previous text, and this part will not be repeated here.

[0093] The driving control method of the present invention detects the real-time road conditions using the relevant information obtained by online perception, and screens the road drivers according to the various information of the detected road drivers, so as to screen out the first target driver who may have an impact on the driving of the vehicle, and adjust the range of the target area of ​​interest of the vehicle according to the relevant information of the first target driver, so as to increase the range of the target area of ​​interest as much as possible under the premise of ensuring the correlation between the range of the target area of ​​interest and the driving of the vehicle, increase the sensitive perception of the dangers and emergency situations that may exist on the road, and reduce the probability of perception errors. At the same time, the first target driver is further screened according to the adjusted range of the target area of ​​interest to screen out the second target driver who is more likely to have an impact on the driving of the vehicle, and then output the driving adjustment instruction for the response. Compared with the prior art, the method of the present invention has higher perception accuracy, does not rely on the takeover of the human driver, reduces the probability of errors caused by human operation, and can effectively improve the safety of automatic driving when passing through intersections, and can also improve the driver's sense of security when using automatic driving technology to pass through intersections.

[0094] Fig.13 The module composition of the driving control device of one embodiment of the present invention is schematically shown. Fig.13 As shown, the driving control device of the present invention is implemented as comprising:

[0095] A first target driver screening module 1, used for screening a first target driver according to the acquired online perception information;

[0096] An interested target region generating module 2 is used to dynamically generate an interested target region according to the location and driving trend of the first target driver when the first target driver exists according to the screening result;

[0097] The second target driver screening module 3 is used to screen the second target driver according to the positional relationship between the target area of ​​interest and the center line of the vehicle and the positional relationship between each first target driver and the center line of the vehicle;

[0098] The driving adjustment instruction output module 4 is used to output corresponding driving adjustment instructions according to the predetermined upper and lower limit parameters of the passing speed and the current speed information of the vehicle when there is a second target driver according to the screening result.

[0099] It should be noted that the implementation process and implementation principle of the driving control device of the embodiment of the present invention can be specifically referred to the corresponding description of the above method embodiment, such as the corresponding description of the acquisition of online perception information, the screening of the first target driver, the dynamic generation of the target area of ​​interest, the screening of the second target driver, and the output of the driving adjustment instructions corresponding to the current situation in the method embodiment, so they are not repeated here. Exemplarily, the driving control device of the embodiment of the present invention can be any intelligent device with a processor, including but not limited to computers, smart phones, personal computers, robots, cloud servers, etc.

[0100] In some embodiments, an embodiment of the present invention provides a non-volatile computer-readable storage medium, in which one or more programs including execution instructions are stored. The execution instructions can be read and executed by an electronic device (including but not limited to a computer, a server, or a network device, etc.) to execute the driving control method of any of the above embodiments of the present invention.

[0101] In some embodiments, an embodiment of the present invention also provides a computer program product, which includes a computer program stored on a non-volatile computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the driving control method of any one of the above embodiments.

[0102] In some embodiments, an embodiment of the present invention also provides an electronic device, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the driving control method of any of the above embodiments.

[0103] In some embodiments, the present invention further provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the driving control method of any of the above embodiments.

[0104] In some embodiments, an embodiment of the present invention also provides an autonomous driving vehicle, which includes the above-mentioned electronic device, so that the autonomous driving vehicle can implement the driving control method of running any of the above-mentioned embodiments.

[0105] Fig.14 A movable platform according to an embodiment of the present invention is schematically shown. Fig.14 As shown, its implementation includes:

[0106] Body 50;

[0107] A memory 51 disposed on the body, for storing executable instructions; and

[0108] The processor 52 disposed on the fuselage is used to execute the executable instructions stored in the memory 51 . When the executable instructions are executed by the processor 52 , the steps of the driving control method in the above-mentioned embodiments are implemented.

[0109] It should be noted that the movable platform in the embodiment of the present invention may be a car, a cleaning vehicle, a robot, etc. with automatic driving or semi-automatic driving functions. The specific implementation process and implementation principle of the driving control method involved in the movable platform in the embodiment of the present invention can be found in the corresponding description of the above method embodiment, which will not be repeated here.

[0110] Fig.15 is a schematic diagram of the hardware structure of an electronic device for executing a driving control method provided by another embodiment of the present application, such as Fig.15 As shown, the device includes:

[0111] One or more processors 610 and memory 620, Fig.15 A processor 610 is taken as an example.

[0112] The device for executing the driving control method may further include: an input device 630 and an output device 640 .

[0113] The processor 610, the memory 620, the input device 630 and the output device 640 may be connected via a bus or other means. Fig.15 The example of connecting through bus is taken in the following.

[0114] The memory 620 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions / modules corresponding to the driving control method in the embodiment of the present application. The processor 610 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory 620, that is, implementing the driving control method of the above method embodiment.

[0115] The memory 620 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the driving control method, etc. In addition, the memory 620 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 620 may optionally include a memory remotely arranged relative to the processor 610, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0116] The input device 630 may receive input digital or character information and generate signals related to user settings and function control of the image processing device. The output device 640 may include a display device such as a display screen.

[0117] The one or more modules are stored in the memory 620, and when executed by the one or more processors 610, the driving control method in any of the above method embodiments is executed.

[0118] The above-mentioned product can execute the method provided in the embodiment of the present application, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not fully described in this embodiment, please refer to the method provided in the embodiment of the present application.

[0119] The electronic devices of the embodiments of the present application exist in various forms, including but not limited to:

[0120] (1) Mobile communication devices: These devices are characterized by their mobile communication functions and their main purpose is to provide voice and data communications. These terminals include: smart phones (such as iPhone), multimedia phones, functional phones, and low-end phones.

[0121] (2) Ultra-mobile personal computer devices: These devices fall into the category of personal computers, have computing and processing capabilities, and generally also have mobile Internet access features. These terminals include: PDA, MID and UMPC devices, such as iPad.

[0122] (3) Portable entertainment devices: These devices can display and play multimedia content. They include audio and video players (such as iPods), handheld game consoles, e-books, as well as smart toys and portable car navigation devices.

[0123] (4) Server: A device that provides computing services. The server consists of a processor, hard disk, memory, system bus, etc. The server is similar to a general computer architecture, but because it needs to provide highly reliable services, it has higher requirements in terms of processing power, stability, reliability, security, scalability, and manageability.

[0124] (5) Other electronic devices with data interaction functions.

[0125] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0126] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution, in essence, or the part that contributes to the relevant technology, can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiment.

[0127] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A driving control method, characterized in that: include: Selecting a first target driver according to the acquired online perception information; According to the screening result, when there is a first target driver, dynamically generating an interested target region according to the position and driving trend of the first target driver, wherein the driving trend includes speed information and posture information of the first target driver; The second target drivers are selected according to the positional relationship between the target area of ​​interest and the center line of the vehicle and the positional relationship between each first target driver and the center line of the vehicle; According to the screening result, when there is a second target driver, a corresponding driving adjustment instruction is output according to the predetermined upper and lower limit parameters of the passing speed and the current speed information of the vehicle.

2. The method according to claim 1, characterized in that The first target driver includes a first type of driver who is within a preset range from a zebra crossing or a safety island and whose speed is lower than a preset low-speed threshold, and the online perception information includes position information and posture information of the road driver, speed information of the road driver, zebra crossing position information, and safety island position information; The first target driver is selected according to the acquired online perception information, including: Screening out road drivers whose speed is lower than a preset low-speed threshold according to the speed information of road drivers; According to the position information of the road drivers whose speed is lower than the preset low speed threshold, the zebra crossing position information and the safety island position information, the road drivers located at the zebra crossing and the safety island are selected as the first type of drivers among the first target drivers; The dynamically generating the target area of ​​interest according to the position and driving trend of the first target driver includes: For the first type of drivers among the first target drivers, an object of interest region having a larger coverage area than the standard object of interest region is generated.

3. The method according to claim 1, characterized in that The first target driver includes a second type of driver who is within a preset range from a zebra crossing or a safety island, does not have a preset moving trend, and whose speed is not lower than a preset low-speed threshold, and the online perception information includes position information and posture information of the road driver, speed information of the road driver, current posture information of the vehicle, zebra crossing position information, and safety island position information; The screening of the first target driver according to the acquired online perception information includes: Screening out road drivers whose speed is not less than a preset low-speed threshold according to the speed information of road drivers; According to the position information and posture information of the road drivers whose speed is not less than the preset low-speed threshold, the current posture information of the vehicle, the zebra crossing position information and the safety island position information, the road drivers located at the zebra crossing and the safety island and not having the preset moving trend are selected as the second type of drivers of the first target drivers; The dynamically generating the target area of ​​interest according to the position and driving trend of the first target driver includes: For the second type of drivers among the first target drivers, an object region of interest having a larger coverage area than the standard object region of interest is generated.

4. The method according to any one of claims 1 to 3, characterized in that: The first target driver includes a third type of driver having a preset moving trend and a speed not lower than a preset low speed threshold, and the online perception information includes posture information of the road driver, speed information of the road driver, and current posture information of the vehicle; The screening of the first target driver according to the acquired online perception information includes: Screening out road drivers whose speed is not less than a preset low-speed threshold according to the speed information of road drivers; According to the posture information of the selected road drivers whose speed is not less than the preset low-speed threshold and the current posture information of the vehicle, the road drivers with the preset moving trend are selected as the third type of drivers of the first target drivers; The dynamically generating the target area of ​​interest according to the position and driving trend of the first target driver includes: For the third type of driver among the first target drivers, an asymmetric target area of ​​interest is generated based on the center line of the vehicle according to the movement trend of the third type of driver, wherein the generated asymmetric target area of ​​interest has a smaller coverage area on the side of the center line of the vehicle toward which the movement trend of the third type of driver is directed.

5. The method according to claim 4, characterized in that The preset movement trend includes a movement trend to the left based on the center line of the vehicle and a movement trend to the right based on the center line of the vehicle; The third type of drivers selected from the posture information of the selected road drivers whose speed is not less than the preset low-speed threshold and the current posture information of the vehicle, wherein the road drivers having a preset moving trend are selected as the first target drivers, comprises: Determine the moving direction of the vehicle based on the current posture information of the vehicle; Determine the moving trend direction of the road driver whose speed is not less than a preset low-speed threshold according to the posture information of the selected road driver; According to the moving trend direction of the vehicle and the moving trend direction of the screened road drivers whose speed is not less than a preset low-speed threshold, the road drivers with the preset moving trend are screened as the third type of drivers of the first target drivers.

6. The method according to claim 1, characterized in that The online perception information includes location information of road users; The method of selecting the second target drivers according to the positional relationship between the target area of ​​interest and the center line of the vehicle and the positional relationship between each first target driver and the center line of the vehicle includes: According to the positional relationship between the target region of interest and the center line of the vehicle, the distance between the two sides of the target region of interest and the center line of the vehicle and the length of the target region of interest are determined; Determining projection position information of each first target driver on the center line of the vehicle according to the position information of each first target driver; According to the projection position information of the first target driver on the center line of the vehicle, the length of the target area of ​​interest, and the distances between the two sides of the target area of ​​interest and the center line of the vehicle, the first target driver located in the target area of ​​interest is screened out as the second target driver.

7. The method according to claim 1, characterized in that The outputting of corresponding driving adjustment instructions according to the predetermined upper and lower limit parameters of the passing speed and the current speed information of the vehicle includes: When the current speed of the ego vehicle is greater than the upper limit parameter of the passing speed, outputting a driving adjustment instruction to set the deceleration of the ego vehicle to the target deceleration and the deceleration speed of the ego vehicle to the target deceleration speed; When the current speed of the vehicle is less than the lower limit parameter of the passing speed, outputting a driving adjustment instruction to set the acceleration of the vehicle to the target acceleration and the jerk of the vehicle to the target jerk; When the current speed of the vehicle is not less than the lower speed limit parameter and not greater than the upper speed limit parameter, a driving adjustment instruction is output to set the maximum acceleration of the vehicle to less than zero.

8. The method according to claim 1, characterized in that: The upper and lower limit parameters of the travel speed are set according to the intersection area and traffic light conditions determined by online perception information.

9. The method according to claim 1, characterized in that: The method also includes: According to the screening results, when there is no road user, the positional relationship between the vehicle and the intersection area is confirmed based on the current position of the vehicle and the acquired online perception information; The corresponding driving adjustment instructions are output according to the positional relationship between the vehicle and the intersection area, the predetermined upper and lower limit parameters of the passing speed and the current speed of the vehicle.

10. The method according to claim 9, characterized in that The positional relationship between the vehicle and the intersection area includes the vehicle approaching the intersection and there is no traffic light, the vehicle approaching the intersection and the traffic light is green, the vehicle approaching the intersection and the traffic light is not green, and the vehicle is in the intersection; The outputting of corresponding driving adjustment instructions according to the positional relationship between the vehicle and the intersection area, the predetermined upper and lower limit parameters of the passing speed and the current speed of the vehicle includes: When the vehicle is approaching an intersection and there is no traffic light, or when the vehicle is approaching an intersection and the traffic light is green, If the current speed of the vehicle is greater than the upper speed limit parameter, the output is a driving adjustment instruction to set the deceleration of the vehicle to the target deceleration and the deceleration speed of the vehicle to the target deceleration speed. If the current speed of the vehicle is less than the lower limit parameter of the passing speed, a driving adjustment instruction is output to set the maximum acceleration of the vehicle to less than zero; When the ego vehicle is at an intersection, outputting a driving adjustment instruction to set the maximum acceleration of the ego vehicle to be less than zero; When the own vehicle approaches an intersection and the traffic light is not green, a driving adjustment instruction is outputted to set the deceleration of the own vehicle to the target deceleration and the deceleration speed of the own vehicle to the target deceleration speed.

11. An electronic device, characterized in that: include: At least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the steps of the method described in any one of claims 1 to 10.

12. An autonomous driving vehicle, characterized in that: Comprising the electronic device according to claim 11.

13. A storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 10 are implemented.

Images