Automatic driving obstacle avoidance method, device, storage medium and vehicle

Abstract

The present application provides an automatic driving obstacle avoidance method, device, storage medium and vehicle, the method comprising: when it is detected that the vehicle in front of the main vehicle is reversing into or out of a park, a motion projection prediction is performed on the previous vehicle to obtain a motion projection area. Determine the detour width; compare the detour width with the passage threshold corresponding to the main vehicle. When the detour width is less than the passage threshold corresponding to the main vehicle, determine a first safety distance to determine the position of the termination line, and then control the main vehicle to stop before the termination line position, and detect the distance between the previous vehicle and the main vehicle in real time. When it is less than the first safety distance, control the main vehicle to perform a reverse operation. By using the motion projection area of ​​the previous vehicle, the termination line position is determined, and the distance between the previous vehicle and the main vehicle is detected in real time. In this way, the response flexibility of the automatic driving system in this scenario can be improved, thereby improving the intelligence level of the automatic driving vehicle in the scenario where the front vehicle is reversing into or out of the park.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to an autonomous driving obstacle avoidance method, device, storage medium, and vehicle. Background Art

[0002] As autonomous vehicles travel from their starting point to their destination, they must not only avoid various obstacles along the way but also respond to various special scenarios and employ effective strategies to escape obstacles based on the driving behavior of the preceding vehicle. For example, when the preceding vehicle is entering or exiting a roadside park, especially if it is a trailer and the park gate is small, the preceding vehicle often needs to reverse in and out. In this case, the preceding vehicle has a large blind spot, requiring the autonomous vehicle to implement appropriate measures to ensure the safety of both the preceding vehicle and the host vehicle.

[0003] Currently, autonomous vehicles typically handle large vehicles, including trailers, reversing into a park by stopping at a predetermined safe distance threshold and waiting for the vehicle to complete its entry or exit. This approach is overly simplistic and lacks flexibility. Consequently, the current level of intelligent control for vehicles reversing into or out of a park is low. Summary of the Invention

[0004] The purpose of this application is to solve at least one of the above-mentioned technical defects, especially the technical defect in the prior art that the autonomous driving vehicle has a low level of intelligence when the vehicle in front is reversing into or out of the park.

[0005] In a first aspect, the present application provides an autonomous driving obstacle avoidance method, the method comprising:

[0006] When it is detected that the vehicle in front of the main vehicle is reversing into or out of the park, a motion projection prediction is performed on the vehicle in front of the main vehicle based on a preset projection inference model to obtain a motion projection area corresponding to the vehicle in front of the main vehicle;

[0007] Obtaining a road width of a current road, and determining a detour width based on the motion projection area and the road width;

[0008] Comparing the detour width with a pass threshold corresponding to the main vehicle, and determining a first safety distance between the main vehicle and the preceding vehicle when the detour width is less than the pass threshold corresponding to the main vehicle;

[0009] Determining a termination line position according to the motion projection area and the first safety distance;

[0010] Controlling the main vehicle to stop before the end line position, and detecting the distance between the preceding vehicle and the main vehicle in real time;

[0011] When the distance between the preceding vehicle and the host vehicle is less than the first safety distance, controlling the host vehicle to perform a reverse operation;

[0012] When it is detected that the preceding vehicle has completed the reverse action, the host vehicle is controlled to start and move forward.

[0013] In one embodiment, determining the position of the termination line according to the motion projection area and the first safety distance includes:

[0014] Determining a boundary point in the motion projection area that is closest to the host vehicle;

[0015] Determining a boundary line perpendicular to the current travel road based on the boundary point;

[0016] The boundary line is moved parallel to the main vehicle direction by a distance matching the first safety distance to determine the end line position.

[0017] In one embodiment, the performing motion projection prediction on the preceding vehicle based on a preset projection inference model includes:

[0018] determining a vehicle type of the preceding vehicle;

[0019] Detecting the angle between the front and body of the preceding vehicle, and the position and width of the park entrance and exit;

[0020] The vehicle type, the angle between the front and body of the previous vehicle, and the position and width of the park entrance and exit are input into the projection inference model to obtain the motion projection area of ​​the previous vehicle; wherein, the projection inference model is used to analyze the input information using the principles of vehicle dynamics to output the vehicle's motion projection area.

[0021] In one embodiment, determining the detour width based on the motion projection area and the road width includes:

[0022] According to the motion projection area, obtaining a maximum width corresponding to the motion projection area;

[0023] The difference between the road width and the maximum width is determined as the detour width.

[0024] In one embodiment, the method further comprises:

[0025] When the detour width is not less than the pass threshold corresponding to the host vehicle, a detour area is determined, and whether the detour area is safe is detected in real time;

[0026] If the detour area is in a safe state, determining the traffic efficiency corresponding to the host vehicle;

[0027] If the traffic efficiency is less than a preset threshold, the main vehicle is controlled to bypass the preceding vehicle.

[0028] In one embodiment, the method further comprises:

[0029] If the detour area is in an unsafe state, or if the detour area is in a safe state and the traffic efficiency is not less than the preset threshold, the main vehicle and the preceding vehicle are controlled to maintain a distance matching the first safe distance.

[0030] In one embodiment, determining the traffic efficiency corresponding to the host vehicle includes:

[0031] Obtain multiple preset traffic indicators and coefficients corresponding to each traffic indicator;

[0032] According to each traffic indicator, obtain indicator data corresponding to each traffic indicator;

[0033] According to the coefficient corresponding to each traffic index, the index data corresponding to each traffic index is weighted and summed to obtain the traffic efficiency corresponding to the host vehicle.

[0034] In one embodiment, controlling the host vehicle to bypass the preceding vehicle includes:

[0035] During the process of the main vehicle circling, the straight-line distance between the main vehicle and the preceding vehicle is detected in real time;

[0036] When the straight-line distance between the main vehicle and the preceding vehicle is less than the first safety distance, the main vehicle is controlled to stop circling and to perform a reverse operation.

[0037] In one embodiment, the method further comprises:

[0038] When controlling the main vehicle to perform a reverse operation, determining a second safety distance between the main vehicle and a vehicle behind the main vehicle, and detecting the distance between the main vehicle and the vehicle behind the main vehicle;

[0039] Controlling the main vehicle to perform a reverse operation while maintaining a distance between the main vehicle and the following vehicle no less than the second safety distance;

[0040] When the main vehicle cannot perform a reverse operation and the distance between the main vehicle and the preceding vehicle is less than the first safety distance, the main vehicle is controlled to sound a horn to give a warning.

[0041] In a second aspect, the present application provides an automatic driving obstacle avoidance device, the device comprising:

[0042] A motion projection prediction module is used to perform motion projection prediction on the preceding vehicle based on a preset projection inference model when detecting that the preceding vehicle is reversing into or out of the park, and obtain a motion projection area corresponding to the preceding vehicle;

[0043] a detour width determination module, configured to obtain a road width of a current driving road and determine a detour width based on the motion projection area and the road width;

[0044] a threshold comparison module, configured to compare the detour width with a pass threshold corresponding to the host vehicle, and determine a first safe distance between the host vehicle and the preceding vehicle when the detour width is less than the pass threshold corresponding to the host vehicle;

[0045] a termination line determination module, configured to determine a termination line position according to the motion projection area and the first safety distance;

[0046] A distance detection module is used to control the main vehicle to stop before the end line position and detect the distance between the preceding vehicle and the main vehicle in real time;

[0047] A reverse control module, configured to control the main vehicle to perform a reverse operation when the distance between the preceding vehicle and the main vehicle is less than the first safety distance;

[0048] The forward control module is used to control the main vehicle to start and move forward when it is detected that the preceding vehicle has completed the reverse action.

[0049] In a third aspect, the present application provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the autonomous driving obstacle avoidance method as described in any of the above embodiments.

[0050] In a fourth aspect, the present application provides a vehicle, comprising: one or more processors, and a memory;

[0051] The memory stores computer-readable instructions, and when the one or more processors execute the computer-readable instructions, they perform the steps of the automatic driving obstacle avoidance method as described in any of the above embodiments.

[0052] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0053] This application provides an autonomous driving obstacle avoidance method, device, storage medium, and vehicle. The method comprises: upon detecting that a vehicle preceding a host vehicle is reversing into or out of a park, performing a motion projection prediction on the preceding vehicle based on a preset projection inference model to obtain a motion projection area corresponding to the preceding vehicle. The method then obtains the current road width and determines a detour width based on the motion projection area and the road width. The detour width is then compared with the corresponding threshold for the host vehicle. By predicting the motion projection area of ​​the preceding vehicle to obtain the detour width, the host vehicle is then determined to determine whether to stop and wait or detour, broadening its options for handling such scenarios. When the detour width is less than the corresponding threshold for the host vehicle, a first safety distance is determined between the host vehicle and the preceding vehicle. The position of a termination line is determined based on the motion projection area and the first safety distance. The host vehicle is then controlled to stop before the termination line and the distance between the preceding vehicle and the host vehicle is monitored in real time. If the distance between the preceding vehicle and the host vehicle is less than the first safety distance, the host vehicle is controlled to reverse. When it is detected that the preceding vehicle has completed reverse movement, the host vehicle is controlled to start and move forward. The position of the termination line is determined by the motion projection area of ​​the preceding vehicle, and the distance between the preceding vehicle and the main vehicle is detected in real time, rather than by setting a fixed safety threshold to determine the parking position. This can improve the flexibility of the autonomous driving system in this scenario, thereby improving the intelligence level of the autonomous driving vehicle in the scenario where the preceding vehicle is reversing in and out of the park. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0055] Figure 1 A diagram illustrating an application environment of an autonomous driving obstacle avoidance method provided in an embodiment of the present application;

[0056] Figure 2 A flowchart of an autonomous driving obstacle avoidance method provided in an embodiment of the present application;

[0057] Figure 3 A schematic diagram of a scene in which a vehicle is parked and waiting, provided in an embodiment of the present application;

[0058] Figure 4 This is an example diagram of a scenario in which the main vehicle performs a detour according to an embodiment of the present application;

[0059] Figure 5 A schematic diagram of a process for determining the position of a termination line provided in an embodiment of the present application;

[0060] Figure 6 A schematic diagram of motion projection prediction of a preceding vehicle provided in an embodiment of the present application;

[0061] Figure 7 A schematic diagram of a process for controlling a vehicle to perform a reverse operation according to an embodiment of the present application;

[0062] Figure 8 A schematic diagram of a scene in which a main vehicle is circling a vehicle according to an embodiment of the present application;

[0063] Figure 9 A schematic diagram of the structure of an automatic driving obstacle avoidance device provided in an embodiment of the present application;

[0064] Figure 10 This is a diagram of the internal structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0065] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only 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.

[0066] In some embodiments, the automatic driving obstacle avoidance method provided by this application can be applied to Figure 1 In the illustrated application environment, each vehicle 101 can communicate with a remote server 102 to exchange data. Each vehicle 101 can be equipped with autonomous driving capabilities, collecting real-time road data and traffic participant data, automatically planning a driving trajectory based on the collected data, and performing autonomous driving based on the planned driving trajectory. Each vehicle 101 can be equipped with a computer for data processing and a laser radar for collecting road data.

[0067] The remote server 102 may be an off-board control center, such as a remote control center, which may include one or more servers. The remote server 102 may be used to further process data reported by each vehicle 101 and / or send data to each vehicle 101 to control the vehicle 101 to implement corresponding functions.

[0068] In one embodiment, the present application provides an automatic driving obstacle avoidance method, and the following embodiments apply this method to Figure 1 The vehicle shown is described.

[0069] like Figure 2 As shown, the present application provides an automatic driving obstacle avoidance method, the method comprising:

[0070] Step S201: When it is detected that the vehicle in front of the main vehicle is reversing into or out of the park, motion projection prediction is performed on the previous vehicle based on a preset projection inference model to obtain a motion projection area corresponding to the previous vehicle.

[0071] The projection inference model is a deep learning model that uses collected vehicle information and the principles of vehicle dynamics to infer the vehicle's motion over a period of time. The motion projection area refers to the area formed by the vehicle's future motion trajectory, typically an arc.

[0072] In this step, when the main vehicle is driving on the road, if it detects that the vehicle in front of the main vehicle is reversing into or out of a park on the side of the road, the autonomous driving system in the main vehicle will call the projection inference model and control the main vehicle's sensors or lidar and other equipment to collect vehicle information of the previous vehicle. The collected vehicle information is used as input data of the projection inference model to obtain the motion projection area corresponding to the previous vehicle to complete the motion projection prediction of the previous vehicle.

[0073] Furthermore, when the main vehicle is driving on the road, the status information of the vehicle in front of the main vehicle will be detected in real time. The status information includes vehicle posture, vehicle length, driving speed, driving lane, etc.

[0074] (1) When it is detected that the preceding vehicle is about to pass through a fork in the road or the entrance to the park, the direction in which the preceding vehicle is going will be determined based on the preceding vehicle's body posture, for example: continue straight, enter the fork in the road, or enter the park. When it is determined that the preceding vehicle is about to reverse into the park, the autonomous driving obstacle avoidance method is triggered. It is understandable that due to the long body of a large vehicle, such as a trailer, etc., it is generally necessary to reverse in order to enter and exit the park.

[0075] (2) When it is detected that the preceding vehicle is reversing out of the park, the autonomous driving obstacle avoidance method is triggered.

[0076] Step S202: Obtain the road width of the current driving road, and determine the detour width based on the motion projection area and the road width.

[0077] In this step, the width of the current road is detected to obtain road information. The detour width is calculated based on the motion projection area corresponding to the preceding vehicle and the detected road width. It should be understood that the detour width refers to the minimum width of the detour area for the host vehicle. Because the motion projection area is not a regular straight line, the lateral width of the motion projection area varies. Since the two sides of the road are parallel straight lines, the lateral width of the detour area also varies. The detour width refers to the minimum lateral width of the detour area.

[0078] Specifically, to determine whether there is enough space on the road for the main vehicle to bypass the outside of the previous vehicle, it is necessary to determine whether the minimum width of the bypass area is greater than or equal to the main vehicle's pass threshold. When the minimum width of the bypass area is greater than or equal to the main vehicle's pass threshold, it means that there is enough space on the road for the main vehicle to bypass the outside of the previous vehicle. At this time, when encountering a scenario where the previous vehicle is reversing in and out of the park, it can be judged based on the bypass area whether the main vehicle can safely bypass it. Compared with waiting in place for the previous vehicle to complete reversing in and out of the park, the main vehicle's response flexibility in this scenario can be improved. This improves the intelligence level of the autonomous driving system. At the same time, it can also improve the traffic efficiency of autonomous driving vehicles.

[0079] Step S203: Compare the detour width with the corresponding pass threshold of the host vehicle.

[0080] It is understood that the pass threshold corresponding to the main vehicle can be set based on the vehicle information of the main vehicle. The setting rule can be a fixed value increase, a fixed multiple, etc., and this application does not impose specific restrictions on this. For example, assuming that the width of the main vehicle is 2.2 meters, the pass threshold corresponding to the main vehicle can be set to 3 meters.

[0081] In this step, the current detour width is compared with the main vehicle's pass threshold to determine whether there is space on the road for the main vehicle to pass safely. This determines whether the main vehicle should detour around the front vehicle or wait for the front vehicle to complete reverse entry or exit before passing.

[0082] Step S204: When the detour width is less than the pass threshold corresponding to the host vehicle, a first safety distance between the host vehicle and the preceding vehicle is determined.

[0083] In this step, if the host vehicle determines that the detour width is less than the corresponding pass threshold for the host vehicle, it indicates insufficient detour space. If the host vehicle is directed to detour, there may be a collision risk. Therefore, a first safety distance is determined between the host vehicle and the preceding vehicle. It is understood that the first safety distance refers to the appropriate distance between the host vehicle and the preceding vehicle to avoid accidents or dangerous situations during driving. Specifically, the first safety distance between the host vehicle and the preceding vehicle is determined based on the host vehicle's own safety distance and the corresponding safety distance of the preceding vehicle.

[0084] Furthermore, determining the first safety distance between the main vehicle and the preceding vehicle may include: determining the vehicle type of the preceding vehicle and a first preset distance corresponding to the vehicle type; obtaining a second preset distance of the main vehicle; and determining the sum of the first preset distance and the second preset distance as the first safety distance.

[0085] It can be understood that determining the first safe distance between the host vehicle and the preceding vehicle based on the host vehicle's own safe distance and the corresponding safe distance of the preceding vehicle can fully consider the model of the host vehicle and the preceding vehicle to determine the appropriate distance. The first safe distance between the host vehicle and the preceding vehicle will also vary depending on the model of the preceding vehicle. This can improve the targeted setting of safe distances in autonomous driving, thereby enhancing the intelligence level of autonomous vehicles in scenarios where the preceding vehicle is reversing into or out of a park.

[0086] Step S205: Determine the position of the termination line according to the motion projection area and the first safety distance.

[0087] The end line position is the stopping position determined by the main vehicle when it cannot bypass.

[0088] In this step, when it is determined that the main vehicle cannot bypass, it is necessary to determine the end line position based on the motion projection area and the first safety distance to ensure that the main vehicle can reserve enough space for the previous vehicle to complete the reverse operation in and out of the park.

[0089] It can be understood that determining the end line location based on the motion projection area and the first safety distance fully considers the entire predicted space required by the preceding vehicle when reversing into or out of the park. This, combined with the first safety distance, allows the preceding vehicle to determine the end line location. This ensures sufficient space for the preceding vehicle to complete its reverse maneuver into or out of the park while maintaining the first safety distance.

[0090] Step S206: Control the main vehicle to stop before the end line position, and detect the distance between the preceding vehicle and the main vehicle in real time.

[0091] In this step, after the end line is determined, the host vehicle is controlled to stop before the end line. While the host vehicle is stopped and waiting, the distance between the preceding vehicle and the host vehicle must be monitored in real time to avoid collisions caused by errors in the motion projection area or the preceding vehicle's mis-reversing. It should be understood that measuring the distance between the preceding vehicle and the host vehicle refers to measuring the shortest straight-line distance between the preceding vehicle and the host vehicle.

[0092] In one example, if Figure 3 As shown, Figure 3 This is a schematic diagram of a scenario where a vehicle stops and waits, as provided in an embodiment of the present application. In the diagram, a curb represents a park wall. When the vehicle determines that there is insufficient space to bypass, it must stop before the stop line and wait. Steering or driving around the vehicle in front is prohibited.

[0093] Step S207: When the distance between the previous vehicle and the host vehicle is less than the first safety distance, the host vehicle is controlled to perform a reverse operation.

[0094] In this step, by detecting the distance between the preceding vehicle and the host vehicle in real time, when the host vehicle detects that the distance between the preceding vehicle and the host vehicle is less than the first safety distance, the host vehicle needs to be controlled to perform a reverse operation to avoid a collision with the preceding vehicle.

[0095] Step S208: When it is detected that the preceding vehicle has completed the reverse action, the host vehicle is controlled to start and move forward.

[0096] It can be understood that when it is detected that the previous vehicle is about to complete entering or exiting the park, the previous vehicle no longer needs to occupy the rear position to drive forward or enter the park. It can be determined that the previous vehicle has completed the reversing action. At this time, the main vehicle can be controlled to start and move forward.

[0097] Specifically, when controlling the main vehicle to start and move forward, in order to be alert to the rubbing phenomenon of the previous vehicle, you can slow down the speed appropriately. After confirming that the previous vehicle has been moving forward at a normal speed or has entered the park, you can control the main vehicle to drive at a normal speed.

[0098] This application provides an autonomous driving obstacle avoidance method, device, storage medium, and vehicle. The method comprises: upon detecting that a vehicle preceding a host vehicle is reversing into or out of a park, performing a motion projection prediction on the preceding vehicle based on a preset projection inference model to obtain a motion projection area corresponding to the preceding vehicle. The method then obtains the current road width and determines a detour width based on the motion projection area and the road width. The detour width is then compared with the corresponding threshold for the host vehicle. By predicting the motion projection area of ​​the preceding vehicle to obtain the detour width, the host vehicle is then determined to determine whether to stop and wait or detour, broadening its options for handling such scenarios. When the detour width is less than the corresponding threshold for the host vehicle, a first safety distance is determined between the host vehicle and the preceding vehicle. The position of a termination line is determined based on the motion projection area and the first safety distance. The host vehicle is then controlled to stop before the termination line and the distance between the preceding vehicle and the host vehicle is monitored in real time. If the distance between the preceding vehicle and the host vehicle is less than the first safety distance, the host vehicle is controlled to reverse. When it is detected that the preceding vehicle has completed reverse movement, the host vehicle is controlled to start and move forward. The position of the termination line is determined by the motion projection area of ​​the preceding vehicle, and the distance between the preceding vehicle and the main vehicle is detected in real time, rather than by setting a fixed safety threshold to determine the parking position. This can improve the flexibility of the autonomous driving system in this scenario, thereby improving the intelligence level of the autonomous driving vehicle in the scenario where the preceding vehicle is reversing in and out of the park.

[0099] like Figure 2 As shown, in one embodiment, the automatic driving obstacle avoidance method further includes:

[0100] Step S209: When the detour width is not less than the pass threshold corresponding to the host vehicle, a detour area is determined.

[0101] In this step, if the primary vehicle determines that the detour width is not less than the corresponding pass threshold, it indicates that there is sufficient space for the detour. The primary vehicle can be controlled to detour to improve its efficiency when the preceding vehicle is reversing into or out of the park. At this point, the primary vehicle determines the detour area based on the preceding vehicle's motion projection area. It should be understood that the detour area refers to the area within the road area where the primary vehicle and the preceding vehicle are traveling, excluding the motion projection area.

[0102] Step S210: Detect in real time whether the detour area is safe.

[0103] Specifically, when the host vehicle determines that there is enough space to bypass, since there may be vehicles coming from the front or rear of the bypass area, the host vehicle needs to check whether the bypass area is safe in real time to avoid colliding with the vehicles in front or behind or obstructing the passage of others.

[0104] Step S211: If the detour area is in a safe state, the traffic efficiency corresponding to the host vehicle is determined.

[0105] Among them, traffic efficiency can be used to describe the cost of detour.

[0106] When the detour area is determined to be safe, the main vehicle's traffic efficiency needs to be calculated. If the large vehicle is expected to reverse into or out of the park quickly, but the detour requires the main vehicle to make a large turn, which may require crossing more than one lane, then the vehicle can maintain a safe distance from the preceding vehicle and stop to wait. Conversely, if the large vehicle is expected to reverse into or out of the park for a longer period of time, the vehicle can proceed around the preceding vehicle.

[0107] Step S212: Determine whether the traffic efficiency is less than a preset threshold.

[0108] Among them, the preset threshold can be set according to factors such as the specific method for determining traffic efficiency and the needs of R&D personnel.

[0109] Step S213: If the traffic efficiency is less than the preset threshold, the host vehicle is controlled to bypass the preceding vehicle.

[0110] When the traffic efficiency of the main vehicle is less than the preset threshold, it means that it is more appropriate to take a detour and stopping and waiting may take a long time. In this case, the main vehicle is controlled to go around the previous vehicle and move forward.

[0111] In one example, if Figure 4 As shown, Figure 4 This diagram illustrates an example of a detour scenario for a vehicle in accordance with an embodiment of the present application. The diagram shows a vehicle in front of the vehicle reversing into a park, with the vehicle in the same direction as the vehicle. Curb represents the park's perimeter wall. This diagram illustrates a vehicle in front of the vehicle performing a detour when there is sufficient space outside the vehicle, and the detour area meets safety requirements and traffic efficiency is below a preset threshold.

[0112] like Figure 2 As shown, in one embodiment, the automatic driving obstacle avoidance method further includes:

[0113] Step S214: If the detour area is in an unsafe state, the host vehicle and the preceding vehicle are controlled to maintain a distance matching the first safe distance.

[0114] In this step, when the detour area is judged to be in an unsafe state, it means that there is a vehicle coming from the front or rear of the detour area. At this time, it is not appropriate to control the main vehicle to detour. The main vehicle can be controlled to stop detouring and maintain the first safe distance from the previous vehicle.

[0115] Furthermore, because the main vehicle is monitoring the safety of the detour area in real time, the vehicle's efficiency can be re-determined when the detour area transitions from an unsafe state to a safe state. If the efficiency is still below a preset threshold, the main vehicle can be controlled to bypass the preceding vehicle and proceed. If the efficiency is not less than the preset threshold, the main vehicle is controlled to remain parked and wait, and then start and proceed when the preceding vehicle completes reverse entry or exit.

[0116] Step S215: If the detour area is in a safe state and the traffic efficiency is not less than a preset threshold, the main vehicle and the preceding vehicle are controlled to maintain a distance matching the first safe distance.

[0117] When the detour area is in a safe state and the main vehicle's traffic efficiency is not less than the preset threshold, it means that the detour cost is higher. At this time, the main vehicle is controlled to stop and wait, and maintain a first safe distance from the previous vehicle. When the previous vehicle completes reversing in and out of the park, the main vehicle is controlled to start and move forward.

[0118] like Figure 5 As shown, in one embodiment, determining the termination line position according to the motion projection area and the first safety distance includes:

[0119] Step S301: Determine the boundary point closest to the host vehicle in the motion projection area.

[0120] The boundary points refer to points on the boundary of the motion projection area.

[0121] Step S302: Determine a boundary line perpendicular to the current driving road based on the boundary point.

[0122] Step S303: moving the boundary line parallel to the host vehicle by a distance matching the first safety distance to determine the position of the termination line.

[0123] In this embodiment, a boundary line perpendicular to the current road is determined using the motion projection area. Based on the first safety distance, the boundary point is translated toward the host vehicle to determine the end line. It should be understood that since the boundary line is determined by the boundary point closest to the host vehicle, it can be considered a tangent to the boundary point.

[0124] The end line is determined by using the boundary point closest to the leading vehicle in the motion projection area and the initial safe distance between the leading vehicle and the preceding vehicle. Compared to directly setting a fixed distance threshold, this embodiment is more flexible and targeted. It can improve the intelligence level of autonomous vehicles in scenarios where the preceding vehicle is reversing into or out of a park.

[0125] In one embodiment, based on a preset projection inference model, motion projection prediction of the preceding vehicle is performed, including:

[0126] Determine the vehicle type of the preceding vehicle;

[0127] Detect the angle between the front and body of the preceding vehicle, and the location and width of the park entrance and exit;

[0128] The vehicle type, the angle between the front and body of the previous vehicle, and the location and width of the park entrance and exit are input into the projection inference model to obtain the motion projection area of ​​the previous vehicle. The projection inference model is used to analyze the input information using the principles of vehicle dynamics to output the vehicle's motion projection area.

[0129] In this embodiment, since the previous vehicle entered and exited the park by reversing, its body may be long, and the blind spot at the park entrance is large, making it difficult to directly detect the body length. Therefore, it is necessary to determine the vehicle type of the previous vehicle so that the detected body length can be inferred and compensated based on the vehicle type to obtain a more accurate body length of the previous vehicle. This information is then combined with the angle between the front and body of the previous vehicle and the location and width of the park entrance and exit, and input into the projection inference model to obtain the motion projection area of ​​the previous vehicle. Specifically, the vehicle type of the previous vehicle can be determined using a trained deep learning model for recognition.

[0130] Understandably, current autonomous driving algorithms typically only analyze interactions within the first eight seconds of the vehicle's interaction with an obstacle. However, in scenarios where a preceding vehicle is reversing into or out of a park, the entire process typically takes longer than eight seconds, and the preceding vehicle may also require significant road space to complete this maneuver. Therefore, a deep learning model is used to predict the area formed by the preceding vehicle's trajectory during the entire reverse maneuver. This allows for a more comprehensive prediction of the preceding vehicle's trajectory, better assisting the primary vehicle in decision-making. This can broaden the primary vehicle's response options and understanding in such scenarios, thereby enhancing the intelligence of autonomous vehicles in such situations.

[0131] In one example, if Figure 6 As shown, Figure 6 A schematic diagram of the motion projection prediction of the preceding vehicle provided in an embodiment of the present application. In the figure, the curb represents the park's perimeter wall, the inner area of ​​the vehicle's rotation formed by the safety line is the motion projection area, and the outer safety area is the detour area.

[0132] In one embodiment, determining the detour width based on the motion projection area and the road width includes:

[0133] According to the motion projection area, obtain the maximum width corresponding to the motion projection area;

[0134] The difference between the road width and the maximum width is determined as the detour width.

[0135] In this embodiment, the maximum width of the preceding vehicle's motion projection area is obtained. The difference between the road width and the maximum width of the motion projection area is then used as the detour width. It is understood that the difference between the road width and the maximum width of the motion projection area is equivalent to the minimum width of the detour area. Using the minimum width of the detour area as the detour width ensures sufficient space on the road for the host vehicle to bypass the preceding vehicle.

[0136] In one embodiment, determining the traffic efficiency corresponding to the host vehicle includes:

[0137] Obtain multiple preset traffic indicators and coefficients corresponding to each traffic indicator;

[0138] According to each traffic indicator, obtain indicator data corresponding to each traffic indicator;

[0139] According to the coefficient corresponding to each traffic index, the index data corresponding to each traffic index is weighted and summed to obtain the traffic efficiency corresponding to the main vehicle.

[0140] Traffic indicators are used to evaluate traffic efficiency. They can be set and updated by R&D personnel. For example, traffic indicators may include the number of lanes required to complete a detour, the detour distance, the estimated time required for the preceding vehicle to reverse into or out of the park, and other parameters related to the detour.

[0141] In this embodiment, the host vehicle can activate the detection device and data processing device in the host vehicle based on the acquired traffic indicators to obtain indicator data corresponding to each traffic indicator, and then obtain the coefficient corresponding to each traffic indicator, that is, the weight of each traffic indicator. Finally, the weighted sum of the indicator data corresponding to each traffic indicator is used as the current traffic efficiency of the host vehicle.

[0142] For example, assume there are traffic index a (the number of lanes required to complete the detour), traffic index b (the detour distance), and traffic index c (the estimated time required for the preceding vehicle to reverse into or out of the park), and the coefficients for traffic index a, traffic index b, and traffic index c are 0.3, 0.3, and 0.4, respectively. If the index data A corresponding to traffic index a is 2, the index data B corresponding to traffic index b is 100 meters, and the index data C corresponding to traffic index c is 30 seconds, then the traffic efficiency is 42.6 (0.3*2 + 0.3*100 + 0.4*30).

[0143] It's understandable that when the driver vehicle determines that a detour is possible based on objective conditions, it also calculates the traffic efficiency and determines whether to proceed based on subjective conditions. If the traffic efficiency doesn't meet the conditions, the detour is not performed. This improves the traffic efficiency of autonomous vehicles in scenarios where the preceding vehicle is reversing into or out of a park.

[0144] In one embodiment, controlling the host vehicle to bypass the preceding vehicle includes:

[0145] During the main vehicle's detour, the straight-line distance between the main vehicle and the preceding vehicle is detected in real time;

[0146] When the straight-line distance between the main vehicle and the preceding vehicle is less than the first safety distance, the main vehicle is controlled to stop circling and to perform a reverse operation.

[0147] In this embodiment, during the main vehicle's detour, if the main vehicle infers that the preceding vehicle has no intention of allowing the main vehicle to detour, and the main vehicle detects that the preceding vehicle is too close to the main vehicle, the main vehicle is controlled to stop detouring and perform a reverse operation.

[0148] like Figure 7 As shown, in one embodiment, the automatic driving obstacle avoidance method further includes:

[0149] Step S401: When controlling the host vehicle to perform a reverse operation, determining a second safety distance between the host vehicle and a vehicle behind the host vehicle, and detecting the distance between the host vehicle and the vehicle behind the host vehicle.

[0150] In this step, when controlling the host vehicle to reverse, the distance to the following vehicle must also be considered to prevent the following vehicle from unaware of the host vehicle's reverse operation and failing to reverse in time with the host vehicle. In this case, if the host vehicle does not consider the distance to the following vehicle, a collision with the following vehicle may occur. It is understood that the description of determining the second safe distance between the host vehicle and the following vehicle can be found in the description of determining the first safe distance between the host vehicle and the preceding vehicle in the above embodiment.

[0151] Step S402: Control the main vehicle to perform a backward operation while maintaining the distance between the main vehicle and the following vehicle to be no less than a second safety distance.

[0152] When controlling the main vehicle to perform a reverse operation, it is necessary to reverse while ensuring that the distance between the main vehicle and the following vehicle is not less than the second safety distance.

[0153] Step S403: When the host vehicle cannot perform a reverse operation and the distance between the host vehicle and the preceding vehicle is less than a first safety distance, the host vehicle is controlled to sound a horn to give a warning.

[0154] When the main vehicle is too close to the vehicle in front, but the vehicle behind does not move backward as the main vehicle moves backward, the main vehicle cannot move backward while maintaining the second safe distance between the main vehicle and the vehicle behind. In this case, the main vehicle is controlled to sound the horn to warn the vehicle behind to move backward.

[0155] In one example, if Figure 8 As shown, Figure 8 A schematic diagram of a scene in which the main vehicle of an embodiment of the present application is in the process of bypassing a vehicle. In the figure, the curb represents the fence of the park. The danger range can refer to when the distance between the main vehicle and the preceding vehicle is less than the first safe distance. When the main vehicle determines that it can bypass, but because the preceding vehicle does not give the main vehicle a chance to bypass, the main vehicle detects that the distance between the preceding vehicle and the main vehicle is too close. At this time, it is necessary to control the main vehicle to stop bypassing and perform a reverse operation while maintaining a second safe distance from the following vehicle. The last picture in the figure shows when the preceding vehicle has completed the reverse operation. At this time, the main vehicle can be controlled to start and follow the preceding vehicle forward.

[0156] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0157] The following describes the autonomous driving obstacle avoidance device provided in an embodiment of the present application. The autonomous driving obstacle avoidance device described below and the autonomous driving obstacle avoidance method described above can be referenced to each other.

[0158] like Figure 9 As shown, the present application provides an automatic driving obstacle avoidance device 500, which includes:

[0159] The motion projection prediction module 501 is used to predict the motion projection of the preceding vehicle based on a preset projection inference model when detecting that the preceding vehicle is reversing into or out of the park, and obtain a motion projection area corresponding to the preceding vehicle;

[0160] The detour width determination module 502 is used to obtain the road width of the current driving road and determine the detour width based on the motion projection area and the road width;

[0161] A threshold comparison module 503 is configured to compare the detour width with a corresponding pass threshold of the host vehicle, and determine a first safe distance between the host vehicle and the preceding vehicle when the detour width is less than the corresponding pass threshold of the host vehicle;

[0162] The termination line determination module 504 is configured to determine the termination line position according to the motion projection area and the first safety distance;

[0163] The distance detection module 505 is used to control the main vehicle to stop before the end line and detect the distance between the preceding vehicle and the main vehicle in real time;

[0164] The back-up control module 506 is configured to control the host vehicle to back up when the distance between the preceding vehicle and the host vehicle is less than a first safety distance;

[0165] The forward control module 507 is used to control the host vehicle to start and move forward when it is detected that the preceding vehicle has completed the reverse action.

[0166] In one embodiment, the termination line determination module includes:

[0167] The boundary point determination submodule is used to determine the boundary point closest to the main vehicle in the motion projection area;

[0168] A boundary line determination submodule is used to determine a boundary line in a form perpendicular to the current driving road based on the boundary points;

[0169] The termination line determination submodule is used to move the boundary line parallel to the main vehicle direction by a distance matching the first safety distance to determine the position of the termination line.

[0170] In one embodiment, the motion projection prediction module includes:

[0171] A vehicle type determination submodule is used to determine the vehicle type of the previous vehicle;

[0172] The vehicle information detection submodule is used to detect the angle between the front and body of the preceding vehicle, and the location and width of the park entrance and exit;

[0173] The motion projection prediction submodule is used to input the vehicle type, the angle between the front and body of the previous vehicle, and the location and width of the park entrance and exit into the projection inference model to obtain the motion projection area of ​​the previous vehicle; among them, the projection inference model is used to analyze the input information using the principles of vehicle dynamics to output the vehicle's motion projection area.

[0174] In one embodiment, the detour width determination module includes:

[0175] A width maximum value determination submodule is used to obtain the maximum width corresponding to the motion projection area according to the motion projection area;

[0176] The detour width determination submodule is used to determine the difference between the road width and the maximum width as the detour width.

[0177] In one embodiment, the automatic driving obstacle avoidance device further includes:

[0178] A detour area determination module is used to determine the detour area when the detour width is not less than the corresponding pass threshold of the main vehicle, and to detect in real time whether the detour area is safe;

[0179] A traffic efficiency determination module is used to determine the traffic efficiency corresponding to the host vehicle if the detour area is in a safe state;

[0180] The bypass control module is used to control the main vehicle to bypass the previous vehicle if the traffic efficiency is less than a preset threshold.

[0181] In one embodiment, the automatic driving obstacle avoidance device further includes:

[0182] The vehicle distance control module is used to control the main vehicle and the preceding vehicle to maintain a distance matching the first safe distance if the detour area is in an unsafe state, or if the detour area is in a safe state and the traffic efficiency is not less than a preset threshold.

[0183] In one embodiment, the traffic efficiency determination module includes:

[0184] The indicator acquisition submodule is used to obtain multiple preset traffic indicators and the coefficient corresponding to each traffic indicator;

[0185] The indicator data acquisition submodule is used to obtain the indicator data corresponding to each traffic indicator according to each traffic indicator;

[0186] The traffic efficiency calculation submodule is used to perform weighted summation on the index data corresponding to each traffic index according to the coefficient corresponding to each traffic index to obtain the traffic efficiency corresponding to the main vehicle.

[0187] In one embodiment, the bypass control module includes:

[0188] The distance detection submodule is used to detect the straight-line distance between the main vehicle and the preceding vehicle in real time during the main vehicle's detour.

[0189] The detour stop submodule is used to control the main vehicle to stop detouring and to control the main vehicle to perform a reverse operation when the straight-line distance between the main vehicle and the preceding vehicle is less than a first safety distance.

[0190] In one embodiment, the automatic driving obstacle avoidance device further includes:

[0191] The rear vehicle distance detection module is used to determine the second safe distance between the main vehicle and the vehicle behind the main vehicle when controlling the main vehicle to perform a reverse operation, and to detect the distance between the main vehicle and the vehicle behind the main vehicle;

[0192] A vehicle control module is used to control the main vehicle to perform a reverse operation while maintaining the distance between the main vehicle and the following vehicle at least a second safety distance;

[0193] The horn warning module is used to control the main vehicle to sound a horn to warn when the main vehicle cannot perform a reverse operation and the distance between the main vehicle and the vehicle in front is less than a first safety distance.

[0194] The division of the modules in the aforementioned autonomous driving obstacle avoidance device is for illustrative purposes only. In other embodiments, the autonomous driving obstacle avoidance device can be divided into different modules as needed to perform all or part of the functions of the aforementioned autonomous driving obstacle avoidance device. Each module in the aforementioned autonomous driving obstacle avoidance device can be implemented in whole or in part through software, hardware, or a combination thereof. Each of the modules can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a memory in the computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0195] In one embodiment, the present application also provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the autonomous driving obstacle avoidance method as described in any of the above embodiments.

[0196] In one embodiment, the present application also provides a vehicle, wherein the computer device stores computer-readable instructions, and when the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the automatic driving obstacle avoidance method as described in any of the above embodiments.

[0197] In one embodiment, the vehicle may include a computer device for data processing and a laser radar or sensor device for collecting road data and vehicle information. Figure 10 As shown, Figure 10 This is a schematic diagram of the internal structure of a computer device provided in an embodiment of the present application. The computer device 600 can be provided as a server. Figure 10Computer device 600 includes a processing component 602, which further includes one or more processors, and a memory resource represented by memory 601 for storing instructions executable by processing component 602, such as an application. The application stored in memory 601 may include one or more modules, each corresponding to a set of instructions. In addition, processing component 602 is configured to execute the instructions to perform the autonomous driving obstacle avoidance method of any of the above-mentioned embodiments.

[0198] The computer device 600 may further include a power supply component 603 configured to perform power management of the computer device 600, a wired or wireless network interface 604 configured to connect the computer device 600 to a network, and an input / output (I / O) interface 605. The computer device 600 may operate based on an operating system stored in the memory 701, such as Windows Server™, Mac OS X™, Unix™, Linux™, Free BSD™, or the like.

[0199] Those skilled in the art will understand that Figure 10 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0200] 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 that there is any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or equipment comprising a series of elements not only include those elements, but also include other elements not clearly listed, or also include elements inherent to such process, method, article or equipment. In the absence of more restrictions, the elements limited by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or equipment comprising the elements. Herein, the singular forms "one", "an" and "said / the" may also include plural forms, unless the context clearly indicates otherwise. It should also be understood that the terms "include / comprise" or "have" etc. specify the existence of stated features, wholes, steps, operations, components, parts or combinations thereof, but do not exclude the possibility of the existence or addition of one or more other features, wholes, steps, operations, components, parts or combinations thereof. At the same time, the term "and / or" used in this specification includes any and all combinations of the relevant listed items.

[0201] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can be referenced to each other.

[0202] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An automatic driving obstacle avoidance method, characterized in that: The method comprises: When it is detected that the vehicle in front of the main vehicle is reversing into or out of the park, a motion projection prediction is performed on the vehicle in front of the main vehicle based on a preset projection inference model to obtain a motion projection area corresponding to the vehicle in front of the main vehicle; Obtaining a road width of a current road, and determining a detour width based on the motion projection area and the road width; Comparing the detour width with a pass threshold corresponding to the main vehicle, and determining a first safety distance between the main vehicle and the preceding vehicle when the detour width is less than the pass threshold corresponding to the main vehicle; Determining a termination line position according to the motion projection area and the first safety distance; Controlling the main vehicle to stop before the end line position, and detecting the distance between the preceding vehicle and the main vehicle in real time; When the distance between the preceding vehicle and the host vehicle is less than the first safety distance, controlling the host vehicle to perform a reverse operation; When it is detected that the preceding vehicle has completed the reverse action, the host vehicle is controlled to start and move forward.

2. The automatic driving obstacle avoidance method according to claim 1, characterized in that: The determining the position of the termination line according to the motion projection area and the first safety distance includes: Determining a boundary point in the motion projection area that is closest to the host vehicle; Determining a boundary line perpendicular to the current travel road based on the boundary point; The boundary line is moved parallel to the main vehicle direction by a distance matching the first safety distance to determine the end line position.

3. The automatic driving obstacle avoidance method according to claim 1, characterized in that: The performing motion projection prediction on the preceding vehicle based on a preset projection inference model includes: determining a vehicle type of the preceding vehicle; Detecting the angle between the front and body of the preceding vehicle, and the position and width of the park entrance and exit; The vehicle type, the angle between the front and body of the previous vehicle, and the position and width of the park entrance and exit are input into the projection inference model to obtain the motion projection area of ​​the previous vehicle; wherein, the projection inference model is used to analyze the input information using the principles of vehicle dynamics to output the vehicle's motion projection area.

4. The automatic driving obstacle avoidance method according to claim 1, characterized in that: The determining of the detour width according to the motion projection area and the road width includes: According to the motion projection area, obtaining a maximum width corresponding to the motion projection area; The difference between the road width and the maximum width is determined as the detour width.

5. The automatic driving obstacle avoidance method according to claim 1, characterized in that: The method further comprises: When the detour width is not less than the pass threshold corresponding to the host vehicle, a detour area is determined, and whether the detour area is safe is detected in real time; If the detour area is in a safe state, determining the traffic efficiency corresponding to the host vehicle; If the traffic efficiency is less than a preset threshold, the main vehicle is controlled to bypass the preceding vehicle.

6. The automatic driving obstacle avoidance method according to claim 5, characterized in that: The method further comprises: If the detour area is in an unsafe state, or if the detour area is in a safe state and the traffic efficiency is not less than the preset threshold, the main vehicle and the preceding vehicle are controlled to maintain a distance matching the first safe distance.

7. The automatic driving obstacle avoidance method according to claim 5, characterized in that: The determining of the traffic efficiency corresponding to the host vehicle includes: Obtain multiple preset traffic indicators and coefficients corresponding to each traffic indicator; According to each traffic indicator, obtain indicator data corresponding to each traffic indicator; According to the coefficient corresponding to each traffic index, the index data corresponding to each traffic index is weighted and summed to obtain the traffic efficiency corresponding to the host vehicle.

8. The automatic driving obstacle avoidance method according to claim 5, characterized in that: The controlling the host vehicle to bypass the preceding vehicle comprises: During the process of the main vehicle circling, the straight-line distance between the main vehicle and the preceding vehicle is detected in real time; When the straight-line distance between the main vehicle and the preceding vehicle is less than the first safety distance, the main vehicle is controlled to stop circling and to perform a reverse operation.

9. The automatic driving obstacle avoidance method according to any one of claims 1 to 8, characterized in that: The method further comprises: When controlling the main vehicle to perform a reverse operation, determining a second safety distance between the main vehicle and a vehicle behind the main vehicle, and detecting the distance between the main vehicle and the vehicle behind the main vehicle; Controlling the main vehicle to perform a reverse operation while maintaining a distance between the main vehicle and the following vehicle no less than the second safety distance; When the main vehicle cannot perform a reverse operation and the distance between the main vehicle and the preceding vehicle is less than the first safety distance, the main vehicle is controlled to sound a horn to give a warning.

10. An automatic driving obstacle avoidance device, characterized in that: The device comprises: A motion projection prediction module is used to perform motion projection prediction on the preceding vehicle based on a preset projection inference model when detecting that the preceding vehicle is reversing into or out of the park, and obtain a motion projection area corresponding to the preceding vehicle; a detour width determination module, configured to obtain a road width of a current driving road and determine a detour width based on the motion projection area and the road width; a threshold comparison module, configured to compare the detour width with a pass threshold corresponding to the host vehicle, and determine a first safe distance between the host vehicle and the preceding vehicle when the detour width is less than the pass threshold corresponding to the host vehicle; a termination line determination module, configured to determine a termination line position according to the motion projection area and the first safety distance; A distance detection module is used to control the main vehicle to stop before the end line position and detect the distance between the preceding vehicle and the main vehicle in real time; A reverse control module, configured to control the main vehicle to perform a reverse operation when the distance between the preceding vehicle and the main vehicle is less than the first safety distance; The forward control module is used to control the main vehicle to start and move forward when it is detected that the preceding vehicle has completed the reverse action.

11. A storage medium, characterized in that: The storage medium stores computer-readable instructions, which, when executed by one or more processors, cause the one or more processors to execute the steps of the automatic driving obstacle avoidance method as described in any one of claims 1 to 9.

12. A vehicle, characterized in that: include: one or more processors, and memory; The memory stores computer-readable instructions, which, when executed by the one or more processors, execute the steps of the automatic driving obstacle avoidance method as described in any one of claims 1 to 9.

Images