Vehicle detour method, device, equipment and medium

Abstract

The present application discloses a vehicle detour method, device, equipment and medium, which relates to the field of autonomous driving technology, including: distinguishing each lane as a recommended lane or a non-recommended lane based on a navigation path planning scheme; if a stationary vehicle is detected in front of the vehicle, and the lane in which the vehicle is traveling is a recommended lane, and the target lane after detour is a non-recommended lane, then determining the current detour scenario; calculating a first detour probability based on the target distance between the stationary vehicle and the end point of the target lane after detour, calculating a second detour probability based on the detour decision factor corresponding to the current detour scenario, and judging whether to detour the vehicle to the target lane after detour based on the first detour probability and the second detour probability. The present application can more reasonably judge the necessity and feasibility of detour, greatly reduce the probability of wrong detour, and improve the efficiency and safety of autonomous driving.

Description

Technical Field

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

[0002] In today's urban environment, roadside parking is extremely common, which brings many challenges to the driving of autonomous vehicles. Due to the limitations of existing perception technology, even if the vehicle is equipped with advanced sensor equipment such as cameras and millimeter-wave radars, it is still difficult to accurately and comprehensively identify the actual situation of the vehicle in front when facing roadside parking scenarios, resulting in the problem of autonomous vehicles often making wrong detours or being unable to detour after turning on the autonomous driving function. For example, on narrow streets, when encountering vehicles parked randomly on the roadside, the autonomous driving system may make wrong detour decisions because it cannot accurately judge the safe distance between the obstacle and the vehicle, and even choose not to detour in some situations where it could have passed safely, greatly affecting the efficiency and safety of autonomous driving. Summary of the invention

[0003] In view of this, the purpose of the present invention is to provide a vehicle detour method, device, equipment and medium, which can more reasonably judge the necessity and feasibility of detour, greatly reduce the probability of wrong detour, and improve the efficiency and safety of automatic driving. The specific scheme is as follows:

[0004] In a first aspect, the present application discloses a vehicle detour method, comprising:

[0005] Based on the navigation path planning scheme, each lane is identified as a recommended lane or a non-recommended lane;

[0006] If a stationary vehicle is detected in front of the vehicle, and the lane of the vehicle is the recommended lane, and the target lane after detouring is the non-recommended lane, then a current detour scenario is determined;

[0007] Calculating a first detour probability according to a target distance between the stationary vehicle and an end point of the target lane after detour, and calculating a second detour probability according to a detour decision factor corresponding to the current detour scenario;

[0008] Based on the first detour probability and the second detour probability, it is determined whether to detour the vehicle to the post-detour target lane.

[0009] Optionally, the calculating the first detour probability according to the target distance between the stationary vehicle and the end point of the target lane after detour includes:

[0010] determining the smaller of a target reference length and said target distance;

[0011] The first detour probability is obtained according to a ratio of the smaller value to the target reference length.

[0012] Optionally, the process of determining the current detour scenario also includes:

[0013] Determine the lateral distance between the front of the vehicle and the center line of the lane in which the vehicle is traveling;

[0014] If the lateral distance is zero, the vehicle is controlled to deviate by a preset distance toward a target direction; wherein the target direction is the opposite direction of the stationary vehicle relative to the direction of the vehicle;

[0015] If the lateral distance is greater than a preset threshold, there is no need to offset the vehicle.

[0016] Optionally, the calculating the second detour probability according to the detour decision factor corresponding to the current detour scenario includes:

[0017] If the current detour scenario is that the first vehicle in front of the vehicle has a detour trend, determining whether the first vehicle has an actual detour behavior according to the movement trajectory of the first vehicle;

[0018] If the first vehicle actually has a detour behavior, the second detour probability is determined to be 1;

[0019] If the current detour scenario is that a second vehicle behind the vehicle has a detour trend, determining whether the second vehicle has an actual detour behavior according to the moving trajectory of the second vehicle;

[0020] If the second vehicle actually bypasses the vehicle, the second bypass probability is calculated based on the ratio of the number of the second vehicle to the number of all vehicles behind the vehicle within a preset time; wherein the number of all vehicles behind the vehicle is the number of vehicles behind the vehicle on the lane where the vehicle is traveling.

[0021] Optionally, the calculating the second detour probability according to the detour decision factor corresponding to the current detour scenario includes:

[0022] If the current detour scenario is that there is a first pedestrian in front of the vehicle, then whether the first pedestrian invades the target waiting area within the target time is calculated according to the travel speed of the first pedestrian; wherein the range of the target waiting area is obtained based on the width and length of the vehicle;

[0023] If the first pedestrian does not invade the target waiting area within the target time and the stationary vehicle does not start, the first pedestrian's walking state is set to the first walking state, and the second bypass probability is set to the target value; otherwise, the first pedestrian's walking state is set to the second walking state, and the second bypass probability is set to 0; wherein the target value is greater than 0.

[0024] Optionally, the calculating the second detour probability according to the detour decision factor corresponding to the current detour scenario includes:

[0025] If the current detour scenario is that there is a road gap in front of the vehicle and the parking angle of the stationary vehicle is within the target angle range, constructing a target danger zone according to the parking angle of the stationary vehicle;

[0026] When the trajectory of the second pedestrian is detected to invade the target danger zone, the timing is started, and when the second pedestrian is detected to exit the target danger zone, the timing is ended, and the corresponding timing duration is obtained;

[0027] The second detour probability is calculated according to the ratio of the timing duration to the target calibration duration.

[0028] Optionally, the determining whether to detour the vehicle to the detour target lane based on the first detour probability and the second detour probability includes:

[0029] Determine a probability addition result of the first detour probability and the second detour probability, and if the probability addition result is greater than a preset probability threshold, detour the vehicle to the detour target lane.

[0030] In a second aspect, the present application discloses a vehicle bypassing device, comprising:

[0031] A lane identification module, used to identify each lane as a recommended lane or a non-recommended lane based on a navigation path planning scheme;

[0032] A scene determination module, configured to determine a current detour scene if a stationary vehicle is detected in front of the vehicle, the vehicle's driving lane is the recommended lane, and the target lane after detour is the non-recommended lane;

[0033] a probability calculation module, configured to calculate a first detour probability according to a target distance between the stationary vehicle and the end point of the target lane after detour, and to calculate a second detour probability according to a detour decision factor corresponding to the current detour scenario,

[0034] A detour decision module is used to determine whether to detour the vehicle to the target lane after detour based on the first detour probability and the second detour probability.

[0035] In a third aspect, the present application discloses an electronic device, comprising:

[0036] Memory, used to store computer programs;

[0037] A processor is used to execute the computer program to implement the vehicle detour method disclosed above.

[0038] In a fourth aspect, the present application discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the vehicle detour method disclosed above is implemented.

[0039] It can be seen that the present application proposes a vehicle detour method, including: based on the navigation path planning scheme, each lane is judged as a recommended lane or a non-recommended lane; if a stationary vehicle is detected in front of the vehicle, and the lane of the vehicle is the recommended lane, and the target lane after detour is the non-recommended lane, then the current detour scenario is determined; the first detour probability is calculated according to the target distance between the stationary vehicle and the end point of the target lane after detour, the second detour probability is calculated according to the detour decision factor corresponding to the current detour scenario, and whether to detour the vehicle to the target lane after detour is determined based on the first detour probability and the second detour probability. It can be seen that the present application calculates the first detour probability based on the target distance between the stationary vehicle and the end point of the target lane after detour, so that the vehicle can more reasonably judge the necessity and feasibility of detour according to the actual road space situation. Secondly, the present application calculates the second detour probability according to the detour decision factor corresponding to the current detour scenario, comprehensively considering various practical factors such as road width, traffic flow, and distribution of surrounding obstacles, and further refines the basis for detour decision. This avoids misjudgments caused by relying solely on single sensor data, greatly reducing the probability of wrong detours. Finally, the decision on whether to detour is made based on the first detour probability and the second detour probability, so that when the autonomous vehicle encounters a roadside parking, it can make detour decisions more efficiently and accurately while ensuring safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0041] Figure 1 A flow chart of a vehicle detour method disclosed in this application;

[0042] Figure 2 A schematic diagram of a recommended lane and a non-recommended lane disclosed in this application;

[0043] Figure 3 A schematic diagram of the relationship between a stationary vehicle and a lane centerline disclosed in the present application;

[0044] Figure 4 A schematic diagram of a detour of a vehicle ahead disclosed in this application;

[0045] Figure 5 A schematic diagram of a pedestrian passing ahead disclosed in this application;

[0046] Figure 6 A schematic diagram of a gap in the road ahead disclosed in this application;

[0047] Figure 7 This is a schematic diagram of the structure of a vehicle bypassing device disclosed in this application;

[0048] Figure 8 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0050] Due to the limitations of existing perception technology, even if the vehicle is equipped with advanced sensor equipment such as cameras and millimeter-wave radars, it is still difficult to accurately and comprehensively identify the actual situation of the vehicle in front when facing roadside parking scenarios, which leads to the problem that autonomous driving vehicles often make wrong detours or cannot make detours after turning on the autonomous driving function. For example, on narrow streets, when encountering vehicles parked randomly on the roadside, the autonomous driving system may make wrong detour decisions because it cannot accurately judge the safe distance between the obstacle and the vehicle, and even choose not to detour in some situations where it could have passed safely, which greatly affects the efficiency and safety of autonomous driving.

[0051] To this end, an embodiment of the present application proposes a vehicle detour solution that can more reasonably judge the necessity and feasibility of detour, avoid misjudgment caused by relying solely on a single sensor data, greatly reduce the probability of erroneous detour, and improve the efficiency and safety of autonomous driving.

[0052] The present application embodiment discloses a vehicle detour method, see Figure 1 As shown, the method includes:

[0053] Step S11: Identify the lane as a recommended lane or a non-recommended lane based on the navigation path planning scheme.

[0054] In the process of autonomous driving, lanes are divided into recommended lanes and non-recommended lanes based on the navigation path planning scheme, see Figure 2 As shown. Specifically, a lane coordinate system is constructed, with the actual position of the vehicle as the starting point, and the lane where the vehicle is currently located is set as the reference lane, while the adjacent lanes on the left and right sides are arranged in order according to their relative position distribution relationship with the reference lane. On this basis, the roads that are determined by the navigation plan as roads where the vehicle can travel smoothly and meet the optimal path selection are marked as recommended roads (Si), such as S1 and S2, while the roads that are determined by the navigation plan as unsuitable for vehicle travel due to various restrictive factors (such as traffic control, narrow and difficult to pass, etc.) are marked as non-recommended roads (Ei), such as E1 and E2. In this way, the vehicle can plan its driving trajectory and respond to emergencies more flexibly according to the attributes of the reference lane and the adjacent lanes in which it is located.

[0055] Step S12: If it is detected that there is a stationary vehicle in front of the vehicle, and the lane of the vehicle is the recommended lane, and the target lane after detouring is the non-recommended lane, then the current detour scenario is determined.

[0056] In this embodiment, when the vehicle's driving lane is a non-recommended road, the vehicle can directly adopt a detour strategy and move in the direction of the recommended road, thereby quickly returning to a reasonable driving path and avoiding being trapped in an impassable situation. When the vehicle's driving lane is a recommended road, and the target lane after detouring is also a recommended road, the vehicle can also directly perform a detour operation to maintain the ideal driving route. However, when the vehicle's driving lane is a recommended road, but the target lane after detouring is a non-recommended road, it is necessary to comprehensively consider factors such as road conditions and surrounding obstacles to ensure the safety of the detour decision.

[0057] Specifically, if it is detected that there is a stationary vehicle in front of the vehicle, and the lane in which the vehicle is traveling is the recommended lane, and the target lane after detouring is the non-recommended lane, the current detour scenario is determined.

[0058] Furthermore, the lateral distance between the front of the vehicle and the center line of the lane where the vehicle is traveling is determined. If the lateral distance is zero, the vehicle is controlled to shift in the target direction by a preset distance; wherein the target direction is the opposite direction of the stationary vehicle relative to the direction of the vehicle; if the lateral distance is greater than a preset threshold, there is no need to shift the vehicle. In this way, by shifting in the opposite direction by a preset distance, the vehicle can avoid the stationary vehicle and avoid collision, thereby ensuring driving safety. For example, see Figure 3As shown, l is the lateral distance from the front of the vehicle to the center line of the lane in which the vehicle is traveling. Figure 3 In the figure, the stationary vehicle is in the right direction relative to the vehicle itself, and the opposite direction of the stationary vehicle relative to the vehicle itself is the left direction. When l is greater than 5 meters, the offset preset distance is 0. When l is 0, the offset preset distance reaches the maximum offset of 15 cm. It should be noted that after the above steps, if there is still a stationary vehicle in front of the stationary vehicle, the following-stop judgment is made. If there is no vehicle in front of the stationary vehicle, a detour is made.

[0059] Step S13: Calculate the first detour probability according to the target distance between the stationary vehicle and the end point of the target lane after detour, and calculate the second detour probability according to the detour decision factors corresponding to the current detour scenario.

[0060] In this embodiment, the smaller value between the target reference length and the target distance is determined, and the first detour probability is obtained according to the ratio of the smaller value to the target reference length. The calculation model of the first detour probability is:

[0061] ;

[0062] Wherein, is the first detour probability, is the target distance between the stationary vehicle and the end point of the target lane after detour, is the target reference length, which can be taken as 1000 meters.

[0063] Further, calculate the second detour probability according to the detour decision factors corresponding to the current detour scenario. The calculation methods of the second detour probability in different detour scenarios are described in detail below:

[0064] In the first embodiment, if the first vehicle in front of the vehicle has a tendency to circle around the vehicle in the current detour scenario, it is determined whether the first vehicle has an actual circling behavior according to the moving trajectory of the first vehicle. If the first vehicle has an actual circling behavior, the second detour probability is determined to be 1. Among them, the first vehicle in front of the vehicle is the vehicle in front of the vehicle in the lane in which the vehicle is traveling. See Figure 4 As shown, the camera can capture the distance from the left line to the center of the vehicle. Assume this distance is Dw. When the millimeter-wave radar or the camera detects that the center point Dv of the first vehicle crosses the line, it can indicate that the first vehicle has an actual circling behavior. Among them, determining that the line crossing is established means determining that Dv t-1 < Dw and Dv t > Dw is established.

[0065] In the second embodiment, if the current detour scenario is that the second vehicle behind the own vehicle has a detour trend, then it is determined whether the second vehicle has an actual detour behavior based on the moving trajectory of the second vehicle. If the second vehicle has an actual detour behavior, the second detour probability is calculated based on the ratio of the number of the second vehicle to the number of all vehicles behind the own vehicle within a preset time. Among them, the second vehicle behind the own vehicle is the vehicle behind the own vehicle on the own vehicle's driving lane, the number of all vehicles behind the own vehicle is the number of vehicles behind the own vehicle on the own vehicle's driving lane, and the number of vehicles behind the own vehicle on the own vehicle's driving lane can be obtained by detecting the corner radar on the own vehicle. The preset time can be set according to an empirical value, such as 3s, and the preset time starts when a stationary vehicle is detected in front of the own vehicle. In this detour scenario, the second detour probability calculation model is:

[0066] ;

[0067] in, is the second detour probability, is the vehicle number of the second vehicle, is the number of all vehicles behind the vehicle within the preset time, Represents the conditional parameter used to adjust the probability. It reflects the ratio of the second vehicle behind the vehicle to all vehicles behind the vehicle. If the value is large, the second detour probability is also large, and the vehicle may be more inclined to consider detour. As a conditional parameter, it can be set to different values ​​to adjust the detour probability under certain road conditions or traffic rules. Larger, then even if The smaller the value of is, the final detour probability may also be larger, which makes the vehicle more inclined to detour.

[0068] In a third embodiment, if the current detour scenario is that there is a first pedestrian in front of the vehicle, then whether the first pedestrian invades the target waiting area within the target time is calculated based on the first pedestrian's travel speed, wherein the range of the target waiting area is obtained based on the vehicle width and the vehicle length of the vehicle, and if the first pedestrian does not invade the target waiting area within the target time and the stationary vehicle is not started, then the first pedestrian's passing state is set to the first passing state, and the second detour probability is set to the target value, otherwise the first pedestrian's passing state is set to the second passing state, and the second detour probability is set to 0; wherein the target value is greater than 0. Exemplary, Figure 5 The length of the target waiting area is the vehicle width, and the width is 0.5 times the vehicle width. The calculation model of the target time is:

[0069] ;

[0070] in, is the proportionality coefficient, is the travel speed, For example, when the first pedestrian's walking state is set to the first walking state, the second detour probability is set to 0.5, otherwise, the first pedestrian's walking state is set to the second walking state, and the second detour probability is set to 0.

[0071] In a fourth embodiment, if the current detour scenario is that there is a gap in the road in front of the vehicle and the parking angle of the stationary vehicle is within the target angle range, a target danger zone is constructed according to the parking angle of the stationary vehicle; timing is started when the trajectory of a second pedestrian is detected to invade the target danger zone, and timing is ended when the second pedestrian is detected to exit the target danger zone, and the corresponding timing duration is obtained; the second detour probability is calculated according to the ratio of the timing duration to the target calibration duration.

[0072] Exemplary. See Figure 6 As shown, when there is a gap in the road in front of the vehicle and the parking angle of the stationary vehicle is between 0 and 85 degrees, a target danger zone is constructed in front of the stationary vehicle. It can be seen that the first second pedestrian's pedestrian trajectory has invaded the target danger zone, and the timing is started at this time. Then it can be seen that the pedestrian trajectory of the next second pedestrian overlaps with the pedestrian trajectory of the first second pedestrian. At this time, the timing continues until there is no overlap between the pedestrian trajectory of the next second pedestrian and the pedestrian trajectory of the previous second pedestrian, and the timing ends when the last pedestrian exits the target danger zone, and the corresponding timing duration is obtained as , in this detour scenario, the second detour probability calculation model is:

[0073] ;

[0074] in, is the second detour probability, The target duration is set. is the target scale factor, It reflects the ratio of the time the pedestrian stays in the target danger zone to the target calibration time. If the value is large, that is, the pedestrian stays in the target danger zone for a long time, then the second detour probability will be large, which means that in this case, the vehicle may be more inclined to consider detouring, because the pedestrian stays in the danger zone for a long time, which increases the risk of collision. is the target proportionality coefficient. Under certain road conditions or traffic rules, it can be set to different values ​​to adjust the detour probability. If the target proportionality coefficient is large, then even if The smaller the value, the higher the final detour probability may be, which will make the vehicle more inclined to detour.

[0075] In addition, in some scenarios, if the stationary vehicle ahead is in the rightmost lane, Can be set to 0.5, otherwise It can be set to 0.05. Furthermore, if there is a stationary vehicle in the target lane after the detour, the detour will be canceled. The above setting is due to the following reasons: In many road traffic regulations, the rightmost lane may usually be used for parking, temporary parking or low-speed vehicles. When the autonomous vehicle detects that the stationary vehicle ahead is in the rightmost lane, it will Set to 0.5, which means that the vehicle has a relatively high probability of considering detouring in this case. This setting can ensure the smoothness of vehicle driving. Set to 0.05, which makes the vehicle consider detouring with only a very low probability. Because the presence of a stationary vehicle in a lane other than the rightmost lane may be due to an emergency (such as a vehicle failure), if the vehicle easily detoured, it may enter other unsafe or unsuitable lanes. In this way, this application ensures that the vehicle drives along the normal route as much as possible to maintain traffic order. Furthermore, when there is a stationary vehicle in the target lane after the detour, the detour is canceled. In this way, the vehicle can avoid falling into a new dilemma, avoid frequent route changes during the detour, and reduce the complexity and uncertainty of vehicle operations.

[0076] Step S14: Determine whether to detour the vehicle to the post-detour target lane based on the first detour probability and the second detour probability.

[0077] In this embodiment, the probability addition result of the first detour probability and the second detour probability is determined. If the probability addition result is greater than the preset probability threshold, the vehicle is detoured to the detour target lane. This helps to ensure the driving safety of the vehicle. In some complex traffic scenarios, such as when the road is narrow and there are many vehicles, it is possible to more carefully determine whether to detour based on the comprehensive probability, preventing the vehicle from blindly entering a potentially dangerous detour route to avoid collisions with other vehicles.

[0078] In addition, when the vehicle is performing a detour, it will send data such as the detour trigger time, the longitude and latitude of the vehicle's location, and the distance from the intersection or destination when the detour is initiated to the map. If the vehicle fails to detour (i.e., it cannot return to the vehicle's driving lane after the detour or the driver manually pulls it back to the vehicle's driving lane), the map will mark the detour on the current road, such as a "no detour" sign. When the vehicle drives to the same section again, the "no detour" flag of the section and the previously recorded distance from the intersection or destination when the detour was initiated can be obtained based on the vehicle's location. At this time, the vehicle will compare the distance from the intersection or destination when the current detour decision was initiated with the distance recorded on the map. If the current distance is greater than the distance recorded on the map, the vehicle will continue to detour. If the current distance is less than the distance recorded on the map, the vehicle will stop detouring directly. In this way, through the cloud memory function, the vehicle can use previous detour experience to make more accurate decisions. This decision-making method based on historical data can effectively avoid blind detours on sections that are not suitable for detours, thereby improving the success rate of vehicle detours.

[0079] It can be seen that the present application proposes a vehicle detour method, including: based on the navigation path planning scheme, each lane is judged as a recommended lane or a non-recommended lane; if a stationary vehicle is detected in front of the vehicle, and the lane of the vehicle is the recommended lane, and the target lane after detour is the non-recommended lane, then the current detour scenario is determined; the first detour probability is calculated according to the target distance between the stationary vehicle and the end point of the target lane after detour, the second detour probability is calculated according to the detour decision factor corresponding to the current detour scenario, and whether to detour the vehicle to the target lane after detour is determined based on the first detour probability and the second detour probability. It can be seen that the present application calculates the first detour probability based on the target distance between the stationary vehicle and the end point of the target lane after detour, so that the vehicle can more reasonably judge the necessity and feasibility of detour according to the actual road space situation. Secondly, the present application calculates the second detour probability according to the detour decision factor corresponding to the current detour scenario, comprehensively considering various practical factors such as road width, traffic flow, and distribution of surrounding obstacles, and further refines the basis for detour decision. This avoids misjudgments caused by relying solely on single sensor data, greatly reducing the probability of wrong detours. Finally, the decision on whether to detour is made based on the first detour probability and the second detour probability, so that when the autonomous vehicle encounters a roadside parking, it can make detour decisions more efficiently and accurately while ensuring safety.

[0080] Correspondingly, the embodiment of the present application also discloses a vehicle bypassing device, see Figure 7 As shown, the device comprises:

[0081] A lane identification module 11, used to identify each lane as a recommended lane or a non-recommended lane based on a navigation path planning scheme;

[0082] A scene determination module 12 is used to determine a current detour scene if a stationary vehicle is detected in front of the vehicle, the lane in which the vehicle is traveling is the recommended lane, and the target lane after detour is the non-recommended lane;

[0083] The probability calculation module 13 is used to calculate a first detour probability according to a target distance between the stationary vehicle and the end point of the target lane after detour, and calculate a second detour probability according to a detour decision factor corresponding to the current detour scenario,

[0084] The detour decision module 14 is used to determine whether to detour the vehicle to the post-detour target lane based on the first detour probability and the second detour probability.

[0085] Among them, for more specific working processes of the above-mentioned modules, please refer to the corresponding contents disclosed in the aforementioned embodiments, which will not be repeated here.

[0086] It can be seen that the present application proposes a vehicle detour method, including: based on the navigation path planning scheme, each lane is judged as a recommended lane or a non-recommended lane; if a stationary vehicle is detected in front of the vehicle, and the lane of the vehicle is the recommended lane, and the target lane after detour is the non-recommended lane, then the current detour scenario is determined; the first detour probability is calculated according to the target distance between the stationary vehicle and the end point of the target lane after detour, the second detour probability is calculated according to the detour decision factor corresponding to the current detour scenario, and whether to detour the vehicle to the target lane after detour is determined based on the first detour probability and the second detour probability. It can be seen that the present application calculates the first detour probability based on the target distance between the stationary vehicle and the end point of the target lane after detour, so that the vehicle can more reasonably judge the necessity and feasibility of detour according to the actual road space situation. Secondly, the present application calculates the second detour probability according to the detour decision factor corresponding to the current detour scenario, comprehensively considering various practical factors such as road width, traffic flow, and distribution of surrounding obstacles, and further refines the basis for detour decision. This avoids misjudgments caused by relying solely on single sensor data, greatly reducing the probability of wrong detours. Finally, the decision on whether to detour is made based on the first detour probability and the second detour probability, so that when the autonomous vehicle encounters a roadside parking, it can make detour decisions more efficiently and accurately while ensuring safety.

[0087] Furthermore, an embodiment of the present application also provides an electronic device. Figure 8 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the diagram cannot be considered as any limitation on the scope of use of the present application.

[0088] Figure 8The present invention provides a schematic diagram of the structure of an electronic device 20 provided in an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a display screen 23, an input / output interface 24, a communication interface 25, a power supply 26, and a communication bus 27. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the vehicle detour method disclosed in any of the aforementioned embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0089] In this embodiment, the power supply 26 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 25 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 24 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0090] In addition, the memory 22, as a carrier for storing resources, may be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon may include a computer program 221, and the storage method may be temporary storage or permanent storage. In addition to the computer program that can be used to complete the vehicle detour method performed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 221 may further include a computer program that can be used to complete other specific tasks.

[0091] Furthermore, an embodiment of the present application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the vehicle detour method disclosed above is implemented.

[0092] For the specific steps of the method, reference may be made to the corresponding contents disclosed in the aforementioned embodiments, which will not be described in detail here.

[0093] The various embodiments in this application are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0094] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0095] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0096] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0097] The above is a detailed introduction to a vehicle bypass method, device, equipment, and storage medium provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A vehicle detour method, characterized in that: include: Based on the navigation path planning scheme, each lane is identified as a recommended lane or a non-recommended lane; If a stationary vehicle is detected in front of the vehicle, and the lane of the vehicle is the recommended lane, and the target lane after detouring is the non-recommended lane, then a current detour scenario is determined; Calculating a first detour probability according to a target distance between the stationary vehicle and an end point of the target lane after detour, and calculating a second detour probability according to a detour decision factor corresponding to the current detour scenario; Based on the first detour probability and the second detour probability, it is determined whether to detour the vehicle to the post-detour target lane.

2. The vehicle detour method according to claim 1, characterized in that: The calculating the first detour probability according to the target distance between the stationary vehicle and the end point of the target lane after detour comprises: determining the smaller of a target reference length and said target distance; The first detour probability is obtained according to a ratio of the smaller value to the target reference length.

3. The vehicle detour method according to claim 1, characterized in that: The process of determining the current detour scenario also includes: Determine the lateral distance between the front of the vehicle and the center line of the lane in which the vehicle is traveling; If the lateral distance is zero, the vehicle is controlled to deviate by a preset distance toward a target direction; wherein the target direction is the opposite direction of the stationary vehicle relative to the direction of the vehicle; If the lateral distance is greater than a preset threshold, there is no need to offset the vehicle.

4. The vehicle detour method according to claim 1, characterized in that: The calculating the second detour probability according to the detour decision factor corresponding to the current detour scenario includes: If the current detour scenario is that the first vehicle in front of the vehicle has a detour trend, determining whether the first vehicle has an actual detour behavior according to the movement trajectory of the first vehicle; If the first vehicle actually has a detour behavior, the second detour probability is determined to be 1; If the current detour scenario is that a second vehicle behind the vehicle has a detour trend, determining whether the second vehicle has an actual detour behavior according to the moving trajectory of the second vehicle; If the second vehicle actually bypasses the vehicle, the second bypass probability is calculated based on the ratio of the number of the second vehicle to the number of all vehicles behind the vehicle within a preset time; wherein the number of all vehicles behind the vehicle is the number of vehicles behind the vehicle on the lane where the vehicle is traveling.

5. The vehicle detour method according to claim 1, characterized in that: The calculating the second detour probability according to the detour decision factor corresponding to the current detour scenario includes: If the current detour scenario is that there is a first pedestrian in front of the vehicle, then whether the first pedestrian invades the target waiting area within the target time is calculated according to the travel speed of the first pedestrian; wherein the range of the target waiting area is obtained based on the width and length of the vehicle; If the first pedestrian does not invade the target waiting area within the target time and the stationary vehicle does not start, the first pedestrian's walking state is set to the first walking state, and the second bypass probability is set to the target value; otherwise, the first pedestrian's walking state is set to the second walking state, and the second bypass probability is set to 0; wherein the target value is greater than 0.

6. The vehicle detour method according to claim 1, characterized in that: The calculating the second detour probability according to the detour decision factor corresponding to the current detour scenario includes: If the current detour scenario is that there is a road gap in front of the vehicle and the parking angle of the stationary vehicle is within the target angle range, constructing a target danger zone according to the parking angle of the stationary vehicle; When the trajectory of the second pedestrian is detected to invade the target danger zone, the timing is started, and when the second pedestrian is detected to exit the target danger zone, the timing is ended, and the corresponding timing duration is obtained; The second detour probability is calculated according to the ratio of the timing duration to the target calibration duration.

7. The vehicle detour method according to any one of claims 1 to 6, characterized in that: The determining whether to detour the vehicle to the detour target lane based on the first detour probability and the second detour probability includes: Determine a probability addition result of the first detour probability and the second detour probability, and if the probability addition result is greater than a preset probability threshold, detour the vehicle to the detour target lane.

8. A vehicle bypassing device, characterized in that: include: A lane identification module, used to identify each lane as a recommended lane or a non-recommended lane based on a navigation path planning scheme; A scene determination module, configured to determine a current detour scene if a stationary vehicle is detected in front of the vehicle, the vehicle's driving lane is the recommended lane, and the target lane after detour is the non-recommended lane; a probability calculation module, configured to calculate a first detour probability according to a target distance between the stationary vehicle and the end point of the target lane after detour, and to calculate a second detour probability according to a detour decision factor corresponding to the current detour scenario, A detour decision module is used to determine whether to detour the vehicle to the target lane after detour based on the first detour probability and the second detour probability.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the vehicle detour method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store a computer program; wherein, when the computer program is executed by a processor, the vehicle detour method according to any one of claims 1 to 7 is implemented.

Images