Automatic driving meeting method, device, computer equipment and storage medium

Abstract

This application relates to the field of autonomous driving technology and discloses an autonomous driving meeting method, apparatus, computer equipment, and storage medium. The method includes detecting whether there are obstacles in the main vehicle lane and oncoming vehicles in the opposite lane based on the map information, positioning information, and obstacle information of the autonomous driving main vehicle; when there are obstacles in the main vehicle lane and oncoming vehicles in the opposite lane, determining the spatial overlap between the main vehicle's driving area and the oncoming vehicle's driving area; determining the priority of passage based on the determination results; and determining the motion plan of the autonomous driving main vehicle based on the priority of passage. This application has the effect of making meeting decisions based on the characteristics of actual meeting scenarios, thereby improving the comfort and safety of meeting.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to an autonomous driving meeting method, apparatus, computer equipment, and storage medium. Background Art

[0002] As the application areas of autonomous vehicles continue to expand, the number of driving scenarios that need to be handled is also gradually increasing. Narrow road conditions are one of the most complex scenarios for L4 autonomous driving decision-making and planning algorithms.

[0003] Due to the complex and diverse road environments, the number of traffic participants fluctuates significantly across time periods and road sections, and the dynamic behavior of vehicles on the road is also highly variable. Therefore, accurate and timely decisions regarding meeting vehicles are a critical challenge for Level 4 autonomous driving. Existing meeting methods are difficult to tailor to the specific characteristics of actual meeting scenarios, resulting in poor applicability and a high risk of accidents.

[0004] With respect to the above-mentioned related technologies, the inventors have found that the existing methods of meeting vehicles have problems such as difficulty in making decisions based on the characteristics of actual meeting scenarios, poor applicability, and low safety. Summary of the Invention

[0005] In order to improve comfort and safety in narrow road conditions, the present application provides an automatic driving meeting method, apparatus, computer equipment and storage medium.

[0006] On the first aspect, the present application provides an automatic driving meeting method, which has the characteristics of improving comfort and safety in narrow road conditions.

[0007] This application is achieved through the following technical solutions:

[0008] An automatic driving method for meeting another vehicle comprises the following steps:

[0009] Based on the autonomous driving vehicle's map information, positioning information, and obstacle information, it detects whether there are obstacles in the main vehicle lane and whether there are oncoming vehicles in the opposite lane.

[0010] When there is an obstacle in the main vehicle lane and there is an oncoming vehicle in the opposite lane, the spatial overlap between the main vehicle driving area and the oncoming vehicle driving area is analyzed;

[0011] Based on the results of the judgment and research, the priority of the decision is made;

[0012] Based on traffic priority, the motion planning of the autonomous driving main vehicle is determined.

[0013] In a preferred example, the present application can be further configured as follows: the step of determining the spatial overlap between the host vehicle's driving area and the oncoming vehicle's driving area includes:

[0014] Obtaining roadside boundary information and lane information based on the map information, and then combining the positioning information and the obstacle information to generate a host vehicle trajectory reference line and an oncoming vehicle trajectory reference line;

[0015] Based on the main vehicle's trajectory reference line, the main vehicle's driving trajectory is predicted; based on the oncoming vehicle's trajectory reference line, the oncoming vehicle's driving trajectory is predicted;

[0016] Based on the host vehicle driving trajectory and the oncoming vehicle driving trajectory, it is determined whether there is overlapping space between the host vehicle driving area and the oncoming vehicle driving area.

[0017] In a preferred example, the present application may be further configured as follows: the step of determining whether there is overlapping space between the driving area of ​​the main vehicle and the driving area of ​​the oncoming vehicle based on the driving trajectory of the main vehicle and the driving trajectory of the oncoming vehicle includes:

[0018] Based on the driving trajectory of the host vehicle and the driving trajectory of the oncoming vehicle, the body width, lane width, obstacle width and preset safety distance of the host vehicle and the oncoming vehicle are obtained, and the width of the remaining space of the track lateral spacing is calculated;

[0019] If the width of the remaining space of the track lateral spacing is greater than or equal to 0, then there is no overlapping space between the host vehicle driving area and the oncoming vehicle driving area;

[0020] If the width of the remaining space of the track lateral spacing is less than 0, then the host vehicle driving area and the oncoming vehicle driving area have overlapping space.

[0021] In a preferred example, the present application can be further configured as follows: the step of deciding the priority of traffic based on the result of the judgment includes:

[0022] Establishing an avoidance cost function based on the speed of the oncoming vehicle, the speed of the autonomous driving host vehicle, the host vehicle's driving trajectory, the oncoming vehicle's driving trajectory, and the overlapping space between the host vehicle's driving area and the oncoming vehicle's driving area;

[0023] According to the avoidance cost function, the avoidance cost of the host vehicle and the avoidance cost of the oncoming vehicle are calculated respectively, and the vehicle with the greater avoidance cost has a higher priority.

[0024] In a preferred example, the present application can be further configured as follows: the functional expression of the avoidance cost function includes f(x)=Vi 2 / 2S, where f(x) refers to the cost of the vehicle, Vi refers to the current speed of the vehicle, and S refers to the distance from the current position of the vehicle to the overlapping space.

[0025] In a preferred example, the present application may be further configured as follows: the avoidance cost function also includes a road right factor;

[0026] Based on a preset road right mapping rule, the road right factor is mapped to a first constant term of the avoidance cost function.

[0027] In a preferred example, the present application may be further configured as follows: the avoidance cost function also includes a vehicle type factor;

[0028] Based on a preset vehicle type mapping rule, the vehicle type factor is mapped to a second constant term of the avoidance cost function.

[0029] In a preferred example, the present application may be further configured as follows: if the driving area of ​​the main vehicle and the driving area of ​​the oncoming vehicle have overlapping space and the autonomous driving main vehicle has a high traffic priority, the step of deciding the motion plan of the autonomous driving main vehicle includes:

[0030] The driving trajectory of the oncoming vehicle is optimized, and the autonomous driving main vehicle is made to pass through the overlapping space according to the driving trajectory of the main vehicle.

[0031] In a preferred example, the present application may be further configured as follows: if the driving area of ​​the main vehicle and the driving area of ​​the oncoming vehicle have overlapping space and the autonomous driving main vehicle has a low traffic priority, the step of deciding the motion plan of the autonomous driving main vehicle includes:

[0032] Based on the positioning information and driving trajectory of the autonomous driving main vehicle, the autonomous driving main vehicle is pulled over to a location closest to the boundary line of the overlapping space;

[0033] Alternatively, the autonomous driving vehicle may be directly pulled over based on its positioning information and driving trajectory.

[0034] Alternatively, based on the obstacle information, and when it is determined that there is an avoidance area in the lane, the autonomous driving main vehicle is driven to the avoidance area and stops.

[0035] In a preferred example, the present application may be further configured as follows: if the driving area of ​​the main vehicle and the driving area of ​​the oncoming vehicle have overlapping space and the autonomous driving main vehicle has a low traffic priority, the step of deciding the motion plan of the autonomous driving main vehicle includes:

[0036] When there is no evasive space in both the oncoming lane and the main vehicle lane, the main vehicle will reverse to avoid.

[0037] In a preferred example, the present application may be further configured as follows: if the driving area of ​​the host vehicle and the driving area of ​​the oncoming vehicle do not overlap, and the host vehicle is determined to have no priority for passage, the step of determining the motion plan of the autonomous driving host vehicle includes:

[0038] causing the autonomous driving main vehicle to travel according to the main vehicle's driving trajectory;

[0039] Alternatively, based on the oncoming vehicle's driving trajectory and roadside boundary information in the map information, detecting whether the oncoming vehicle's driving conforms to the oncoming vehicle's driving trajectory;

[0040] When the oncoming vehicle's driving trajectory is inconsistent with the oncoming vehicle's driving trajectory and the oncoming vehicle encroaches on the host vehicle's driving trajectory, the autonomous driving host vehicle will avoid the oncoming vehicle;

[0041] Alternatively, when there is a preceding vehicle circling in the lane, the width of the driving area of ​​the main vehicle is calculated;

[0042] Determining whether the width of the driving area of ​​the host vehicle is smaller than the width of the driving area of ​​the preceding vehicle;

[0043] When the width of the driving area of ​​the host vehicle is smaller than the width of the driving area of ​​the leading vehicle, the host vehicle is made to follow the leading vehicle and maintain a preset safety distance from the leading vehicle.

[0044] On the second aspect, the present application provides an automatic driving narrow road device, which has the characteristics of improving comfort and safety in narrow road conditions.

[0045] This application is achieved through the following technical solutions:

[0046] An automatic driving meeting device, comprising:

[0047] The oncoming vehicle scene recognition module is used to detect whether there are obstacles in the main vehicle lane and oncoming vehicles in the opposite lane based on the autonomous driving vehicle's map information, positioning information, and obstacle information.

[0048] The oncoming vehicle assessment module is used to assess the spatial overlap between the driving area of ​​the main vehicle and the driving area of ​​the oncoming vehicle when there is an obstacle in the main vehicle lane and there is an oncoming vehicle in the opposite lane;

[0049] Priority module, used to decide the priority of traffic based on the results of judgment and research;

[0050] The motion planning module is used to make motion plans for the autonomous driving vehicle based on traffic priority.

[0051] On the third aspect, the present application provides a computer device that has the characteristics of improving comfort and safety in narrow road conditions.

[0052] This application is achieved through the following technical solutions:

[0053] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any one of the above-mentioned automatic driving meeting methods when executing the computer program.

[0054] In a fourth aspect, the present application provides a computer-readable storage medium having the characteristics of improving comfort and safety in narrow road conditions.

[0055] This application is achieved through the following technical solutions:

[0056] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of any one of the above-mentioned automatic driving meeting methods.

[0057] In summary, compared with the prior art, the technical solution provided by this application has at least the following beneficial effects:

[0058] 1. Based on the autonomous driving vehicle's map information, positioning information, and obstacle information, the system detects whether there are obstacles in the driver's lane and oncoming vehicles in the opposite lane to identify the meeting scenario. When there is an obstacle in the driver's lane and an oncoming vehicle in the opposite lane, the system determines whether there is overlap between the driver's and oncoming vehicle's driving areas, and estimates the collision probability between the driver and oncoming vehicles based on the overlap. Based on the results of this determination, the system determines the priority of traffic flow and, in turn, the motion plan of the autonomous driving vehicle. This decision is tailored to the characteristics of the actual meeting scenario, improving the applicability and rationality of the meeting strategy, enabling the driver's safe, comfortable, and rapid passage through the meeting area, and ensuring the smoothness of autonomous driving and a comfortable ride.

[0059] 2. Based on map information, roadside boundary information and lane information are obtained. Combined with positioning information and obstacle information, these information generates reference lines for the host vehicle and oncoming vehicle. These lines serve as driving aids to ensure they can safely follow the reference lines. The system also predicts the host vehicle's or oncoming vehicle's trajectory based on the reference lines to determine if there is overlap between the host vehicle's and oncoming vehicle's driving areas. The reference lines enable more accurate predictions of the host vehicle's or oncoming vehicle's trajectory, resulting in more precise analysis results.

[0060] 3. Based on the speed of the oncoming vehicle, the speed of the autonomous driving host vehicle, the host vehicle's trajectory, the oncoming vehicle's trajectory, and the overlap between the host vehicle's and oncoming vehicle's driving areas, an avoidance cost function is established. This function measures the avoidance cost based on the deceleration of the host vehicle and oncoming vehicle, determines the priority of passage, and simultaneously considers the right-of-way factor and vehicle type factor to make the calculation result of the avoidance cost function more accurate. Since a larger calculated result indicates a greater cost, vehicles with a larger calculated result are given priority.

[0061] 4. If there is overlap between the driving area of ​​the host vehicle and the driving area of ​​the oncoming vehicle, and the autonomous driving host vehicle has high priority, the oncoming vehicle will adopt an avoidance strategy by default, intercepting the predicted trajectory of the oncoming vehicle and allowing the autonomous driving host vehicle to pass through the overlapping space first according to the driving trajectory of the host vehicle;

[0062] 5. If the driving area of ​​the host vehicle overlaps with the driving area of ​​the oncoming vehicle and the autonomous driving host vehicle has low traffic priority, the host vehicle will adopt an avoidance strategy by default. In this case, based on the positioning information and driving trajectory of the autonomous driving host vehicle, the autonomous driving host vehicle will pull over at the nearest boundary line to the overlapping space; or based on the positioning information and driving trajectory of the autonomous driving host vehicle, the autonomous driving host vehicle will pull over directly; or based on the obstacle information, if it is determined that there is an avoidance area in the lane, the autonomous driving host vehicle will drive to the avoidance area and stop;

[0063] 6. If there is no overlapping space between the host vehicle's driving area and the oncoming vehicle's driving area, the driver assumes that the oncoming vehicle can pass side by side. Based on the oncoming vehicle's driving trajectory and roadside boundary information in the map information, the driver detects whether the oncoming vehicle intends to pass side by side. If the oncoming vehicle intends to pass side by side, the driver defaults to a side-by-side passing strategy, forcing the driver to drive right, based on the driver's driving trajectory, to maintain a safe distance when passing, further improving safety. If the oncoming vehicle does not intend to pass side by side, the driver is predicted to have no intention of passing side by side, and the driver is instructed to yield to ensure safety in narrow road conditions.

[0064] 7. If the host vehicle's driving area and the oncoming vehicle's driving area do not overlap, the oncoming vehicle intends to drive close to the edge, and there is a preceding vehicle circling in the lane, the host vehicle will follow the preceding vehicle at a preset safe distance based on the width of the host vehicle's driving area and the preceding vehicle's driving area. This simplifies the algorithm's complexity, reduces the amount of computation, and facilitates faster autonomous vehicle motion planning decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 A flowchart of an autonomous driving meeting method provided as an exemplary embodiment of the present application.

[0066] Figure 2 A flowchart of an autonomous driving meeting method for determining whether there is overlapping space between the main vehicle's driving area and the oncoming vehicle's driving area based on a trajectory reference line predicted driving trajectory is provided as another exemplary embodiment of the present application.

[0067] Figure 3 A flowchart of an autonomous driving meeting method for determining whether there is overlapping space between the driving area of ​​a main vehicle and the driving area of ​​an oncoming vehicle is provided as another exemplary embodiment of the present application.

[0068] Figure 4 A schematic diagram of an autonomous driving meeting method provided as an exemplary embodiment of the present application.

[0069] Figure 5 A structural block diagram of an automatic driving meeting device provided as an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0070] This specific embodiment is merely an explanation of the present application and is not a limitation of the present application. After reading this specification, those skilled in the art may make non-creative modifications to the present embodiment as needed, but as long as they are within the scope of the claims of the present application, they are protected by the patent law.

[0071] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0072] In this document, the term "and / or" simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document, unless otherwise specified, generally indicates an "or" relationship between the related objects.

[0073] The embodiments of the present application are described in further detail below with reference to the accompanying drawings.

[0074] Reference Figure 1 , an embodiment of the present application provides an automatic driving meeting method, and the main steps of the method are described as follows.

[0075] S1: Based on the autonomous driving vehicle's map information, positioning information, and obstacle information, detect whether there are obstacles in the main vehicle lane and whether there are oncoming vehicles in the opposite lane;

[0076] S2: When there is an obstacle in the main vehicle lane and there is an oncoming vehicle in the opposite lane, the spatial overlap between the main vehicle driving area and the oncoming vehicle driving area is determined;

[0077] S3: Based on the results of the judgment and research, the priority of the decision is made;

[0078] S4: Based on traffic priority, the motion planning of the autonomous driving vehicle is determined.

[0079] Specifically, the map information includes roadside boundary information and lane information, the positioning information of the autonomous driving main vehicle includes the real-time speed information and real-time position information of the autonomous driving main vehicle, the obstacle information includes static obstacle information and dynamic obstacle information, the dynamic obstacle information includes the positioning information of the oncoming vehicle, and the positioning information of the oncoming vehicle includes the real-time speed information and real-time position information of the oncoming vehicle.

[0080] Based on roadside boundary information, lane information, vehicle speed, and location information, the system can determine whether there are oncoming vehicles in the host vehicle's lane or the oncoming lane. If there is an oncoming vehicle in the oncoming lane and a static obstacle is detected in front of the host vehicle's lane, it detects an obstacle in the host vehicle's lane and an oncoming vehicle in the oncoming lane.

[0081] When there is an obstacle in the main vehicle lane and an oncoming vehicle in the opposite lane, the spatial overlap between the main vehicle's driving area and the oncoming vehicle's driving area is determined. Spatial overlap can be either no overlap or overlap.

[0082] If there is no overlap, the decision is made that the main vehicle has no priority, and it does not matter who has priority. Alternatively, the main vehicle is set to a high priority but its priority is equivalent to that of the oncoming vehicle.

[0083] If there is overlap, the priority of the main vehicle is determined based on the degree of overlap, and then the main vehicle can have different priority driving strategies.

[0084] For example, machine learning can be used to determine whether the driving area of ​​the host vehicle and the driving area of ​​oncoming vehicles overlap. Using a support vector machine algorithm, a large number of learning examples of narrow road conditions are input for training. The trained support vector machine automatically outputs the results of the analysis of whether the driving area of ​​the host vehicle and the driving area of ​​oncoming vehicles overlap.

[0085] Finally, based on the traffic priority, the motion planning of the autonomous driving main vehicle is decided.

[0086] Reference Figure 2 Furthermore, S2: when there is an obstacle in the main vehicle lane and there is an oncoming vehicle in the opposite lane, the step of determining the spatial overlap between the main vehicle driving area and the oncoming vehicle driving area includes:

[0087] S21: When there is an obstacle in the main vehicle lane and there is an oncoming vehicle in the opposite lane, obtain roadside boundary information and lane information based on map information, and then combine the positioning information and obstacle information to generate a main vehicle trajectory reference line and an oncoming vehicle trajectory reference line;

[0088] S22: Predicting the driving trajectory of the host vehicle based on the host vehicle trajectory reference line, and predicting the driving trajectory of the oncoming vehicle based on the oncoming vehicle trajectory reference line;

[0089] S23: Based on the driving trajectory of the host vehicle and the driving trajectory of the oncoming vehicle, determine whether there is overlapping space between the driving area of ​​the host vehicle and the driving area of ​​the oncoming vehicle.

[0090] Reference Figure 3 Further, S23: Based on the driving trajectory of the main vehicle and the driving trajectory of the oncoming vehicle, the step of determining whether there is overlapping space between the driving area of ​​the main vehicle and the driving area of ​​the oncoming vehicle includes:

[0091] S231: Based on the driving trajectory of the host vehicle and the driving trajectory of the oncoming vehicle, the body width, lane width, obstacle width, and preset safety distance of the host vehicle and the oncoming vehicle are obtained, and the width of the remaining space between the lateral distances of the tracks is calculated;

[0092] S2321: If the width of the remaining space of the horizontal spacing of the tracks is greater than or equal to 0, then there is no overlapping space between the host vehicle's driving area and the oncoming vehicle's driving area;

[0093] S2322: If the width of the remaining space of the track lateral spacing is less than 0, there is overlapping space between the host vehicle driving area and the oncoming vehicle driving area.

[0094] Specifically, refer to Figure 4 According to the map information, the roadside boundary information and lane information are obtained. Based on the lane, position information and static obstacle information of the main vehicle, a reference line of the main vehicle trajectory is generated to avoid static obstacles; based on the lane and dynamic obstacle information of the oncoming vehicle, a reference line of the oncoming vehicle trajectory is generated.

[0095] The host vehicle's trajectory can be predicted based on the host vehicle's trajectory reference line and the QP algorithm or the graph search algorithm, or the oncoming vehicle's trajectory can be predicted based on the oncoming vehicle's trajectory reference line and the QP algorithm or the graph search algorithm.

[0096] Based on the driving trajectory of the main vehicle and the driving trajectory of the oncoming vehicle, combined with the body width of the vehicle, the driving area of ​​the main vehicle and the driving area of ​​the oncoming vehicle are obtained, and it is determined whether the driving area of ​​the main vehicle and the driving area of ​​the oncoming vehicle have overlapping space, including the following steps:

[0097] Obtain the width of the main vehicle lane, the width of the opposite lane, the width of the obstacle, the width of the main vehicle body, the width of the oncoming vehicle body and the preset safety distance;

[0098] If the remaining space width = (main vehicle lane width + opposite lane width) - (obstacle width + main vehicle body width + oncoming vehicle body width + safety distance) >= 0, it is considered that there is no overlapping space between the main vehicle driving area and the oncoming vehicle driving area;

[0099] If the remaining space width = (main vehicle lane width + opposite lane width) - (obstacle width + main vehicle body width + oncoming vehicle body width + safety distance) < 0, it is considered that there is overlapping space between the main vehicle driving area and the oncoming vehicle driving area.

[0100] The preset safety distance may be in the range of 0-1 meter. In this embodiment, the safety distance is 0.5 meter.

[0101] Furthermore, based on the results of the analysis, the steps for determining the priority of traffic flow include:

[0102] An avoidance cost function is established based on the speed of the oncoming vehicle, the speed of the autonomous driving host vehicle, the host vehicle's trajectory, the oncoming vehicle's trajectory, and the overlapping space between the host vehicle's and the oncoming vehicle's driving areas.

[0103] According to the avoidance cost function, the avoidance cost of the host vehicle and the avoidance cost of the oncoming vehicle are calculated respectively, and the vehicle with the larger avoidance cost has a higher priority.

[0104] The function expression of the avoidance cost function includes f(x)=Vi 2 / 2S, where f(x) refers to the cost of the vehicle, Vi refers to the current speed of the vehicle, and S refers to the distance from the current position of the vehicle to the overlapping space.

[0105] Furthermore, the avoidance cost function also includes a road right factor;

[0106] Based on the preset road right mapping rule, the road right factor is mapped to the first constant term of the avoidance cost function.

[0107] Furthermore, the avoidance cost function also includes a vehicle type factor;

[0108] Based on the preset vehicle type mapping rule, the vehicle type factor is mapped to the second constant term of the avoidance cost function.

[0109] Specifically, if there is overlapping space, by constructing the avoidance cost function f(x)=Vi 2 / 2S+A+B, where f(x) is the cost of the vehicle, Vi is the current speed of the vehicle, S is the distance from the current position of the vehicle to the overlapping space, A is the first constant term obtained by mapping using the preset right-of-way mapping rule, and B is the second constant term obtained by mapping using the preset vehicle type mapping rule corresponding to the incoming vehicle.

[0110] In this embodiment, when the vehicle's traveling direction is consistent with the road's passing direction, it is determined that the vehicle has the right of way;

[0111] When the vehicle's driving direction is inconsistent with the road's traffic direction, it is judged that the vehicle has no right of way.

[0112] According to the preset right-of-way mapping rule, when there is right-of-way, the value of the first constant term A obtained by mapping is 1, and when there is no right of way, the value of the first constant term A obtained by mapping is 0.

[0113] In this embodiment, the preset vehicle type may be a specific vehicle type, such as a truck, a bus, an ambulance, etc.

[0114] According to the preset vehicle type mapping rules, specific vehicle types correspond to preset constant values, such as the value of the second constant term B obtained by truck mapping is 0.6, the value of the second constant term B obtained by bus mapping is 0.3, and the value of the second constant term B obtained by ambulance mapping is 0.

[0115] Furthermore, the avoidance cost function of the oncoming vehicle can be different from the avoidance cost function of the host vehicle. For example, the avoidance cost function of the oncoming vehicle can be f(x)=Vi 2 / 2S, or, f(x) = Vi 2 / 2S+A.

[0116] By constructing an avoidance cost function, the avoidance cost of the host vehicle and the avoidance cost of the oncoming vehicle are calculated based on the avoidance cost function. According to the corresponding avoidance costs, the vehicle with the larger avoidance cost is given higher priority.

[0117] If there is no overlapping space, the decision is no priority.

[0118] Furthermore, if the driving area of ​​the main vehicle and the driving area of ​​the oncoming vehicle overlap and the autonomous driving main vehicle has a high traffic priority, the steps for determining the motion plan of the autonomous driving main vehicle include:

[0119] Optimize the driving trajectory of the oncoming vehicle and enable the autonomous driving main vehicle to pass through the overlapping space according to the main vehicle's driving trajectory.

[0120] Or, when there is no evasive space in both the oncoming lane and the main vehicle lane, the main vehicle waits for the oncoming vehicle to reverse and evade.

[0121] If the driving area of ​​the main vehicle and the driving area of ​​the oncoming vehicle overlap and the autonomous driving main vehicle has low traffic priority, the autonomous driving main vehicle will be pulled over at the nearest boundary line to the overlapping space based on the positioning information and driving trajectory of the autonomous driving main vehicle.

[0122] Alternatively, the autonomous driving vehicle may be directly pulled over based on its positioning information and driving trajectory.

[0123] Alternatively, based on obstacle information, if it is determined that an avoidance zone exists in the lane, the autonomous driving vehicle is driven to the avoidance zone and stops.

[0124] Or, when it is determined that there is no evasive space in both the oncoming lane and the main vehicle lane, the main vehicle is reversed to avoid.

[0125] If the driving area of ​​the host vehicle and the driving area of ​​the oncoming vehicle do not overlap, that is, the host vehicle has no priority for passage, the step of determining the motion plan of the autonomous driving host vehicle includes causing the autonomous driving host vehicle to drive according to the driving trajectory of the host vehicle;

[0126] Alternatively, based on the oncoming vehicle's driving trajectory and roadside boundary information in the map information, detecting whether the oncoming vehicle's driving trajectory conforms to the oncoming vehicle's driving trajectory;

[0127] When the oncoming vehicle's trajectory is inconsistent with that of the oncoming vehicle and the oncoming vehicle encroaches on the host vehicle's trajectory, the autonomous host vehicle will yield; or when the vehicle ahead of it is circling in its lane, the width of the host vehicle's driving area will be calculated;

[0128] Determining whether the width of the driving area of ​​the host vehicle is smaller than the width of the driving area of ​​the preceding vehicle;

[0129] When the width of the driving area of ​​the host vehicle is smaller than the width of the driving area of ​​the leading vehicle, the host vehicle is made to follow the leading vehicle and maintain a preset safety distance from the leading vehicle.

[0130] Specifically, if there is overlapping space and the main vehicle has high traffic priority, the driving trajectory of the oncoming vehicle is optimized, such as truncating the predicted driving trajectory of the oncoming vehicle before the overlapping space, and making the main vehicle pass through the overlapping space according to the main vehicle's driving trajectory; or, when there is no avoidance space in both the oncoming lane and the main vehicle lane, making the main vehicle wait for the oncoming vehicle to reverse and avoid.

[0131] If there is overlapping space and the main vehicle has low traffic priority, the main vehicle is pulled over at the nearest boundary line to the overlapping space, or directly pulled over based on the positioning information and the main vehicle's driving trajectory, or driven to the avoidance area and parked based on the static obstacle information and when it is determined that there is an avoidance area in this lane; or, when there is no avoidance space in both the opposite lane and the main vehicle's lane, the main vehicle is reversed to avoid the obstacle or the oncoming vehicle is reversed to avoid the obstacle.

[0132] If there is no overlapping space, that is, the main vehicle is decided to have no priority for passing, and the main vehicle and the oncoming vehicle are judged to pass side by side. At this time, the oncoming vehicle's driving is detected to see whether it conforms to the oncoming vehicle's driving trajectory; when the oncoming vehicle's driving does not conform to the oncoming vehicle's driving trajectory and the oncoming vehicle intends to pass along the side, the main vehicle and the oncoming vehicle are decided to pass side by side; when the oncoming vehicle's driving does not conform to the oncoming vehicle's driving trajectory and the oncoming vehicle intends to pass along the side, the main vehicle is decided to adopt an avoidance strategy.

[0133] Furthermore, if it is decided that the main vehicle and the oncoming vehicle pass side by side, and there is a leading vehicle in the main vehicle lane that has passed side by side in the meeting area with the oncoming vehicle in the opposite lane, the main vehicle's driving area and the leading vehicle's driving area are obtained based on the trajectory reference line, the driving trajectory and the vehicle body width to calculate the width of the main vehicle's driving area and the width of the leading vehicle's driving area; then it is determined whether the width of the main vehicle's driving area is smaller than the width of the leading vehicle's driving area; and when the width of the main vehicle's driving area is smaller than the width of the leading vehicle's driving area, the main vehicle is made to follow the leading vehicle and maintain a preset safety distance from the leading vehicle.

[0134] In summary, based on the map information, positioning information and obstacle information of the autonomous driving main vehicle, it is detected whether there are obstacles in the main vehicle lane and whether there are oncoming vehicles in the opposite lane to identify the meeting scene; when there are obstacles in the main vehicle lane and there are oncoming vehicles in the opposite lane, it is judged whether there is overlapping space in the main vehicle driving area and the oncoming vehicle driving area, so as to estimate the collision probability between the main vehicle and the oncoming vehicle based on the overlapping space; based on the results of the judgment, the traffic priority is decided, and then the motion plan of the autonomous driving main vehicle is decided, so as to make the meeting decision based on the characteristics of the actual meeting scene, improve the comfort of the meeting strategy, facilitate the main vehicle to pass through the meeting area safely and quickly, and improve the safety of the autonomous driving main vehicle in meeting.

[0135] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0136] Reference Figure 5 The embodiment of the present application also provides an automatic driving vehicle meeting device, which corresponds one-to-one with the automatic driving vehicle meeting method in the above embodiment. The automatic driving vehicle meeting device includes:

[0137] The oncoming vehicle scene recognition module is used to detect whether there are obstacles in the main vehicle lane and oncoming vehicles in the opposite lane based on the autonomous driving vehicle's map information, positioning information, and obstacle information.

[0138] The oncoming vehicle judgment module is used to judge whether there is overlap between the driving area of ​​the main vehicle and the driving area of ​​the oncoming vehicle when there is an obstacle in the main vehicle lane and there is an oncoming vehicle in the opposite lane;

[0139] Priority module, used to decide the priority of traffic based on the results of judgment and research;

[0140] The motion planning module is used to make motion plans for the autonomous driving vehicle based on traffic priority.

[0141] Among them, the vehicle meeting judgment module includes:

[0142] The trajectory reference line unit is used to obtain roadside boundary information and lane information based on map information when there is an obstacle in the main vehicle lane and there is an oncoming vehicle in the opposite lane. It then combines the positioning information and obstacle information to generate the main vehicle trajectory reference line and the oncoming vehicle trajectory reference line;

[0143] A driving trajectory unit, used to predict the driving trajectory of the host vehicle or the driving trajectory of the oncoming vehicle based on the trajectory reference line;

[0144] The overlapping space judgment unit is used to judge whether there is overlapping space between the main vehicle's driving area and the oncoming vehicle's driving area based on the main vehicle's driving trajectory and the oncoming vehicle's driving trajectory.

[0145] The motion planning module includes,

[0146] The high-priority planning unit is used to optimize the driving trajectory of the oncoming vehicle and enable the autonomous driving main vehicle to pass through the overlapping space according to the driving trajectory of the main vehicle when there is overlapping space between the main vehicle's driving area and the oncoming vehicle's driving area and the autonomous driving main vehicle has high traffic priority.

[0147] The low-priority planning unit is used to, when there is overlapping space between the main vehicle's driving area and the oncoming vehicle's driving area and the autonomous driving main vehicle has a low traffic priority, make the autonomous driving main vehicle pull over at the nearest boundary line position to the overlapping space based on the positioning information of the autonomous driving main vehicle and the main vehicle's driving trajectory; or, based on the positioning information of the autonomous driving main vehicle and the main vehicle's driving trajectory, make the autonomous driving main vehicle pull over directly; or, based on the obstacle information, and when it is determined that there is an avoidance area in the lane, make the autonomous driving main vehicle drive to the avoidance area and park.

[0148] The non-sequence traffic planning unit is used to detect whether the oncoming vehicle intends to pass along the side of the road based on the oncoming vehicle's driving trajectory and the roadside boundary information in the map information when there is no overlapping space between the main vehicle's driving area and the oncoming vehicle's driving area; when the oncoming vehicle intends to pass along the side of the road, the main vehicle is made to drive to the right based on the main vehicle's driving trajectory; when the oncoming vehicle does not intend to pass along the side of the road, the main vehicle is made to avoid it.

[0149] The specific definition of an autonomous driving passing device can be found in the definition of an autonomous driving passing method above and will not be repeated here. The various modules in the above-mentioned autonomous driving passing device can be implemented in whole or in part through software, hardware, or a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0150] In one embodiment, a computer device is provided, which may be a server. The computer device includes a processor, memory, a network interface, and a database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When executed by the processor, the computer program implements any of the above-mentioned autonomous driving meeting methods.

[0151] In one embodiment, a computer-readable storage medium is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented:

[0152] S1: Based on the autonomous driving vehicle's map information, positioning information, and obstacle information, detect whether there are obstacles in the main vehicle lane and whether there are oncoming vehicles in the opposite lane;

[0153] S2: When there is an obstacle in the main vehicle lane and there is an oncoming vehicle in the opposite lane, the spatial overlap between the main vehicle driving area and the oncoming vehicle driving area is determined;

[0154] S3: Based on the results of the judgment and research, the priority of the decision is made;

[0155] S4: Based on traffic priority, the motion planning of the autonomous driving vehicle is determined.

[0156] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0157] Those skilled in the art will clearly understand that for the sake of convenience and brevity in description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

Claims

1. An automatic driving method for meeting other vehicles, characterized in that: The following steps are involved: Based on the autonomous driving vehicle's map information, positioning information, and obstacle information, the system detects whether there are obstacles in the vehicle's lane and whether there are oncoming vehicles in the opposite lane. The obstacle information includes dynamic obstacle information, which includes the positioning information of the oncoming vehicle, which includes the vehicle's real-time speed and position information. When there is an obstacle in the main vehicle lane and there is an oncoming vehicle in the opposite lane, the spatial overlap between the main vehicle driving area and the oncoming vehicle driving area is analyzed; Based on the results of the judgment and research, the priority of the decision is made; Based on traffic priority, the autonomous driving vehicle's motion planning is determined; The determining of the spatial overlap between the host vehicle's driving area and the oncoming vehicle's driving area includes: Obtaining roadside boundary information and lane information based on the map information, and then combining the positioning information and the obstacle information to generate a host vehicle trajectory reference line and an oncoming vehicle trajectory reference line; The main vehicle's trajectory is predicted based on the main vehicle's trajectory reference line, and the oncoming vehicle's trajectory is predicted based on the oncoming vehicle's trajectory reference line; Based on the driving trajectory of the host vehicle and the driving trajectory of the oncoming vehicle, determining whether there is overlapping space between the driving area of ​​the host vehicle and the driving area of ​​the oncoming vehicle; The steps of determining the priority of traffic based on the results of the judgment and research include: An avoidance cost function is established based on the speed of the oncoming vehicle, the speed of the autonomous driving host vehicle, the host vehicle's trajectory, the oncoming vehicle's trajectory, and the overlapping space between the host vehicle's and the oncoming vehicle's driving areas. According to the avoidance cost function, the avoidance cost of the host vehicle and the avoidance cost of the oncoming vehicle are calculated respectively, and the vehicle with the greater avoidance cost is determined to have a higher priority; The functional expression of the avoidance cost function includes f(x)= / 2S, where f(x) refers to the cost of the vehicle, Vi refers to the current speed of the vehicle, and S refers to the distance from the current position of the vehicle to the overlapping space.

2. The automatic driving meeting method according to claim 1, characterized in that: The step of determining whether there is overlap between the driving area of ​​the host vehicle and the driving area of ​​the oncoming vehicle based on the driving trajectory of the host vehicle and the driving trajectory of the oncoming vehicle comprises: Based on the driving trajectory of the host vehicle and the driving trajectory of the oncoming vehicle, the body width, lane width, obstacle width and preset safety distance of the host vehicle and the oncoming vehicle are obtained, and the width of the remaining space of the lateral spacing between the tracks is calculated; If the width of the remaining space of the track lateral spacing is greater than or equal to 0, then there is no overlapping space between the host vehicle driving area and the oncoming vehicle driving area; If the width of the remaining space of the track lateral spacing is less than 0, then the host vehicle driving area and the oncoming vehicle driving area have overlapping space.

3. The automatic driving meeting method according to claim 1, characterized in that: The avoidance cost function also includes a road right factor; Based on a preset road right mapping rule, the road right factor is mapped to a first constant term of the avoidance cost function.

4. The automatic driving meeting method according to claim 1, characterized in that: The avoidance cost function also includes a vehicle type factor; Based on a preset vehicle type mapping rule, the vehicle type factor is mapped to a second constant term of the avoidance cost function.

5. The automatic driving meeting method according to claim 1, characterized in that: If the driving area of ​​the main vehicle and the driving area of ​​the oncoming vehicle have overlapping space and the autonomous driving main vehicle has a high traffic priority, the step of deciding the motion plan of the autonomous driving main vehicle includes: The driving trajectory of the oncoming vehicle is optimized, and the autonomous driving main vehicle is made to pass through the overlapping space according to the driving trajectory of the main vehicle.

6. The automatic driving meeting method according to claim 1, characterized in that: If the driving area of ​​the main vehicle and the driving area of ​​the oncoming vehicle overlap and the autonomous driving main vehicle has a low traffic priority, the step of deciding the motion plan of the autonomous driving main vehicle includes: Based on the positioning information and driving trajectory of the autonomous driving main vehicle, the autonomous driving main vehicle is pulled over to a location closest to the boundary line of the overlapping space; Alternatively, the autonomous driving vehicle may be directly pulled over based on its positioning information and driving trajectory. Alternatively, based on the obstacle information, and when it is determined that there is an avoidance area in the lane, the autonomous driving main vehicle is driven to the avoidance area and stops.

7. The automatic driving meeting method according to claim 6, characterized in that: If the driving area of ​​the main vehicle and the driving area of ​​the oncoming vehicle overlap and the autonomous driving main vehicle has a low traffic priority, the step of deciding the motion plan of the autonomous driving main vehicle includes: When there is no evasive space in both the oncoming lane and the main vehicle lane, the main vehicle will reverse to avoid.

8. The automatic driving meeting method according to claim 1, characterized in that: If there is no overlapping space between the host vehicle's driving area and the oncoming vehicle's driving area, and the host vehicle is determined to have no priority for passage, the steps for determining the motion plan of the autonomous driving host vehicle include: causing the autonomous driving main vehicle to travel according to the main vehicle's driving trajectory; or, Based on the oncoming vehicle's driving trajectory and the roadside boundary information in the map information, detecting whether the oncoming vehicle's driving conforms to the oncoming vehicle's driving trajectory; When the oncoming vehicle's driving trajectory is inconsistent with the oncoming vehicle's driving trajectory and the oncoming vehicle encroaches on the host vehicle's driving trajectory, the autonomous driving host vehicle will avoid the oncoming vehicle; or, When there is a preceding vehicle circling in this lane, calculate the width of the driving area of ​​the main vehicle; Determining whether the width of the driving area of ​​the main vehicle is smaller than the width of the driving area of ​​the preceding vehicle; When the width of the driving area of ​​the host vehicle is smaller than the width of the driving area of ​​the leading vehicle, the host vehicle is made to follow the leading vehicle and maintain a preset safety distance from the leading vehicle.

9. An automatic driving vehicle meeting device, characterized in that: include: The oncoming vehicle scene recognition module is used to detect whether there are obstacles in the main vehicle lane and oncoming vehicles in the opposite lane based on the autonomous driving main vehicle's map information, positioning information, and obstacle information. The obstacle information includes dynamic obstacle information, which includes the positioning information of the oncoming vehicle, and the positioning information of the oncoming vehicle includes the real-time speed and position information of the oncoming vehicle. The oncoming vehicle judgment module is used to judge the spatial overlap between the driving area of ​​the main vehicle and the driving area of ​​the oncoming vehicle when there is an obstacle occupying the main vehicle lane and there is an oncoming vehicle in the opposite lane; specifically, it is used to obtain roadside boundary information and lane information based on the map information, and then combine the positioning information and the obstacle information to generate a main vehicle trajectory reference line and an oncoming vehicle trajectory reference line; predict the main vehicle driving trajectory based on the main vehicle trajectory reference line, and predict the oncoming vehicle driving trajectory based on the oncoming vehicle trajectory reference line; and judge whether there is spatial overlap between the main vehicle driving area and the oncoming vehicle driving area based on the main vehicle driving trajectory and the oncoming vehicle driving trajectory; The priority module is used to determine the passage priority based on the results of the judgment and analysis, including establishing an avoidance cost function based on the speed of the oncoming vehicle, the speed of the autonomous driving host vehicle, the driving trajectory of the host vehicle, the driving trajectory of the oncoming vehicle, and the overlapping space of the host vehicle's driving area and the oncoming vehicle's driving area; according to the avoidance cost function, the avoidance cost of the host vehicle and the avoidance cost of the oncoming vehicle are calculated respectively, and the passage priority of the vehicle with the larger corresponding avoidance cost is determined to be higher; the functional expression of the avoidance cost function includes f(x)= / 2S, where f(x) refers to the cost of the vehicle, Vi refers to the current speed of the vehicle, and S refers to the distance from the current position of the vehicle to the overlapping space; The motion planning module is used to make motion plans for the autonomous driving vehicle based on traffic priority.

10. A computer device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images