A vehicle obstacle avoidance method and device, electronic equipment and storage medium

Abstract

The application discloses a vehicle obstacle avoidance method and device, electronic equipment and a storage medium, and the method comprises the following steps: when detecting an obstacle object corresponding to a target vehicle, determining a first obstacle avoidance area and a second obstacle avoidance area corresponding to the target vehicle; determining a first obstacle avoidance path of the target vehicle in the first obstacle avoidance area according to at least one first obstacle avoidance point of the target vehicle in the first obstacle avoidance area; determining a second obstacle avoidance path of the target vehicle in the second obstacle avoidance area according to at least one second obstacle avoidance point of the target vehicle in the second obstacle avoidance area; and determining a target obstacle avoidance path corresponding to the target vehicle according to the first obstacle avoidance path and the second obstacle avoidance path. The target vehicle is more accurately planned to avoid the obstacle path, and the planned obstacle avoidance path is smoother.

Description

A vehicle obstacle avoidance method, device, electronic device, and storage medium Technical Field

[0001] This invention relates to the field of path planning technology, and in particular to a vehicle obstacle avoidance method, device, electronic device, and storage medium. Background Technology

[0002] When obstacles are encountered while the vehicle is in motion, obstacle avoidance path planning is required to ensure safe driving.

[0003] Currently, when planning paths for vehicle obstacle avoidance, the vehicle obstacle avoidance module usually controls the vehicle to bypass obstacles from the left or right. However, due to the uncertainty of the obstacle's trajectory, the vehicle may have a large turning angle during obstacle avoidance, resulting in an unsmooth obstacle avoidance process.

[0004] To solve the above problems, the path planning method for vehicle obstacle avoidance needs to be improved. Summary of the Invention

[0005] This invention provides a vehicle obstacle avoidance method, device, electronic device, and storage medium to solve the problem that in the prior art, due to the uncertainty of the driving intention of the object to be identified, it is impossible to accurately plan the obstacle avoidance path of the target vehicle, which in turn leads to the target vehicle having a large turning angle and an uneven obstacle avoidance path when performing obstacle avoidance.

[0006] In a first aspect, embodiments of the present invention provide a vehicle obstacle avoidance method, comprising:

[0007] When an obstacle to be avoided corresponding to the target vehicle is detected, a first obstacle avoidance area and a second obstacle avoidance area corresponding to the target vehicle are determined; wherein, the obstacle to be avoided includes at least one of motor vehicles, non-motor vehicles and pedestrians;

[0008] Based on at least one first obstacle avoidance point of the target vehicle within the first obstacle avoidance area, determine the first obstacle avoidance path of the target vehicle within the first obstacle avoidance area;

[0009] Based on at least one second obstacle avoidance point of the target vehicle within the second obstacle avoidance area, determine the second obstacle avoidance path of the target vehicle within the second obstacle avoidance area;

[0010] Based on the first obstacle avoidance path and the second obstacle avoidance path, the target obstacle avoidance path corresponding to the target vehicle is determined.

[0011] Secondly, embodiments of the present invention also provide a vehicle obstacle avoidance device, comprising:

[0012] The obstacle avoidance area determination module is used to determine a first obstacle avoidance area and a second obstacle avoidance area corresponding to the target vehicle when an obstacle to be avoided corresponding to the target vehicle is detected; wherein, the obstacle to be avoided includes at least one of motor vehicles, non-motor vehicles and pedestrians;

[0013] The first obstacle avoidance path determination module is used to determine the first obstacle avoidance path of the target vehicle in the first obstacle avoidance area based on at least one first obstacle avoidance point of the target vehicle in the first obstacle avoidance area.

[0014] The second obstacle avoidance path determination module is used to determine the second obstacle avoidance path of the target vehicle in the second obstacle avoidance area based on at least one second obstacle avoidance point of the target vehicle in the second obstacle avoidance area;

[0015] The target obstacle avoidance path determination module is used to determine the target obstacle avoidance path corresponding to the target vehicle based on the first obstacle avoidance path and the second obstacle avoidance path.

[0016] Thirdly, embodiments of the present invention also provide an electronic device, comprising:

[0017] At least one processor; and

[0018] A memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the vehicle obstacle avoidance method according to any embodiment of the present invention.

[0020] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing computer instructions that, when executed by a processor, implement the vehicle obstacle avoidance method described in any embodiment of the present invention.

[0021] The technical solution of this invention, when an obstacle to be avoided corresponding to a target vehicle is detected, determines a first obstacle avoidance area and a second obstacle avoidance area corresponding to the target vehicle; determines a first obstacle avoidance path for the target vehicle within the first obstacle avoidance area based on at least one first obstacle avoidance point of the target vehicle within the first obstacle avoidance area; determines a second obstacle avoidance path for the target vehicle within the second obstacle avoidance area based on at least one second obstacle avoidance point of the target vehicle within the second obstacle avoidance area; and determines the target obstacle avoidance path corresponding to the target vehicle based on the first and second obstacle avoidance paths. This solves the problem in existing technologies where the uncertainty of the driving intention of the object to be identified leads to the inability to accurately plan the obstacle avoidance path for the target vehicle, resulting in large turning angles and uneven obstacle avoidance paths when the target vehicle is avoiding obstacles. By dividing the obstacle avoidance area of ​​the target vehicle into obstacle avoidance areas and planning corresponding obstacle avoidance paths within each area, more accurate obstacle avoidance path planning for the target vehicle is achieved, and the planned obstacle avoidance path is smoother.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 is a flowchart of a vehicle obstacle avoidance method according to Embodiment 1 of the present invention;

[0025] Figure 2 is a flowchart of a vehicle obstacle avoidance method according to Embodiment 2 of the present invention;

[0026] Figure 3 is a schematic diagram of a vehicle obstacle avoidance according to Embodiment 2 of the present invention;

[0027] Figure 4 is a flowchart of a vehicle obstacle avoidance method according to Embodiment 3 of the present invention;

[0028] Figure 5 is a schematic diagram of a target obstacle avoidance path for a vehicle according to Embodiment 3 of the present invention;

[0029] Figure 6 is a structural schematic diagram of a vehicle obstacle avoidance device according to Embodiment 4 of the present invention;

[0030] Figure 7 is a schematic diagram of the structure of an electronic device that implements the vehicle obstacle avoidance method of the present invention. Detailed Implementation

[0031] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0032] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in sequences other than those illustrated or described herein.

[0033] Example 1

[0034] Figure 1 is a flowchart of a vehicle obstacle avoidance method provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where, when an obstacle to be avoided is detected in front of a target vehicle, the obstacle avoidance area corresponding to the target vehicle is divided into a first obstacle avoidance area and a second obstacle avoidance area, and a first obstacle avoidance path of the target vehicle in the first obstacle avoidance area and a second obstacle avoidance path in the second obstacle avoidance area are determined respectively. Then, the target obstacle avoidance path is determined based on the first obstacle avoidance path and the second obstacle avoidance path. This method can be executed by a vehicle obstacle avoidance device, which can be implemented in hardware and / or software. The vehicle obstacle avoidance device can be configured in a computing device that can execute the vehicle obstacle avoidance method.

[0035] As shown in Figure 1, the method includes:

[0036] S110. When an obstacle to be avoided corresponding to the target vehicle is detected, the first obstacle avoidance area and the second obstacle avoidance area corresponding to the target vehicle are determined.

[0037] In this technical solution, the target vehicle refers to the vehicle that needs to avoid an obstacle when encountering it during its journey. It is understood that the target vehicle is not limited to any particular vehicle type; for example, it can be a car, bus, or truck, or it can be an autonomous vehicle with automatic obstacle avoidance capabilities. The obstacle to be avoided refers to a movable obstacle encountered by the target vehicle during its journey, such as at least one of motor vehicles, non-motor vehicles, and pedestrians.

[0038] To ensure a smoother obstacle avoidance maneuver for the target vehicle during obstacle avoidance, this technical solution divides the obstacle avoidance area into a first obstacle avoidance area and a second obstacle avoidance area based on a preset safe distance threshold corresponding to the target vehicle when the target vehicle encounters the obstacle. The first obstacle avoidance area refers to the obstacle avoidance area within the overall obstacle avoidance area corresponding to the target vehicle that is smaller than the safe distance threshold. The second obstacle avoidance area refers to the obstacle avoidance area within the overall obstacle avoidance area that is larger than the safe distance threshold.

[0039] Optionally, determining the first obstacle avoidance area and the second obstacle avoidance area corresponding to the target vehicle includes: determining at least one driving reference point on the center line of the driving lane where the target vehicle is located according to preset spacing information; determining a target driving reference point from the at least one driving reference point according to preset length information of the first obstacle avoidance area; and dividing the obstacle avoidance area corresponding to the target vehicle into regions based on the target driving reference point to obtain the first obstacle avoidance area and the second obstacle avoidance area.

[0040] The preset spacing information refers to the distance between two adjacent driving reference points. For ease of explanation, driving reference points are defined to interpret the first and second obstacle avoidance zones corresponding to the target vehicle. A driving reference point is a custom distance reference point on the center line of the lane where the target vehicle is located. For example, starting from the target vehicle, a driving reference point is set every 1 meter along the target vehicle's direction of travel to determine the distance information corresponding to the target vehicle based on the number of driving reference points. The preset length information refers to the length of the first obstacle avoidance zone in the target vehicle's direction of travel, determined based on the number of driving reference points. The target driving reference point is a formal reference point used to divide the first and second obstacle avoidance zones.

[0041] For example, the area within 5 meters of the target vehicle is designated as the first obstacle avoidance zone. Along the target vehicle's direction of travel, a driving reference point is set every 1 meter along the vehicle's centerline. If the preset length of the first obstacle avoidance zone corresponding to the target vehicle is 5 meters, then the 5th driving reference point corresponding to the target vehicle is determined as the target driving reference point. Further, if the overall obstacle avoidance zone corresponding to the target vehicle has a length of 15 meters in the target vehicle's direction of travel, the obstacle avoidance zone corresponding to the target vehicle can be divided into a first obstacle avoidance zone and a second obstacle avoidance zone based on the target driving reference point. The first obstacle avoidance zone refers to the area within 5 meters of the target vehicle in its direction of travel, i.e., the area within 5 meters of the target vehicle in its direction of travel. The second obstacle avoidance zone refers to the area within 5 meters of the target vehicle in its direction of travel, i.e., the area between 5 and 10 meters from the target vehicle in its direction of travel, i.e., the area between 5 and 10 meters from the target vehicle.

[0042] In real-world driving, target vehicles are typically equipped with distance sensors to detect the distance between the vehicle and other objects, such as pedestrians, other vehicles, and animals. When an object smaller than a preset distance is detected, it indicates that an obstacle needs to be avoided in the target vehicle's direction of travel, and a timely obstacle avoidance warning is issued. Generally, when a target vehicle needs to avoid an obstacle, it can do so by slowing down, driving around it from the left, or driving around it from the right.

[0043] To ensure the obstacle avoidance safety of the target vehicle, if the target vehicle adopts a detour approach, sufficient obstacle avoidance area needs to be provided. However, in existing technologies, due to the unpredictable trajectory of the obstacle to be avoided, the target vehicle is typically controlled to detour around the obstacle from the left or right when it is relatively close to it. This obstacle avoidance method results in a large obstacle avoidance angle and a correspondingly large obstacle avoidance amplitude, affecting the passenger experience. Therefore, this technical solution divides the overall obstacle avoidance area corresponding to the target vehicle into a first obstacle avoidance area and a second obstacle avoidance area when the target vehicle is in different obstacle avoidance areas, thus achieving a smoother obstacle avoidance path around the obstacle.

[0044] S120. Based on at least one first obstacle avoidance point of the target vehicle in the first obstacle avoidance area, determine the first obstacle avoidance path of the target vehicle in the first obstacle avoidance area.

[0045] Here, the first obstacle avoidance point can be understood as the obstacle avoidance point planned by the target vehicle when it avoids obstacles within the first obstacle avoidance area. The first obstacle avoidance path within the first obstacle avoidance area can be obtained by connecting at least one first obstacle avoidance point planned for the target vehicle within the first obstacle avoidance area.

[0046] Specifically, when planning obstacle avoidance paths for a target vehicle, if the target vehicle is in the first obstacle avoidance zone, since the target vehicle is far from the obstacle to be avoided and the trajectory of the obstacle to be avoided is unpredictable, a general obstacle avoidance direction can be provided to the target vehicle so that the target vehicle can travel along the obstacle avoidance direction.

[0047] For example, if the obstacle to be avoided is located to the left front of the target vehicle, the obstacle avoidance direction of the target vehicle within the first obstacle avoidance area should be to the right front of the target vehicle's current position. Since the trajectory of the obstacle to be avoided at the next moment cannot be predicted, at least one first obstacle avoidance point is planned to the right front of the target vehicle's current position, and a first obstacle avoidance path of the target vehicle within the first obstacle avoidance area is obtained based on at least one first obstacle avoidance point, so that the target vehicle avoids obstacles within the first obstacle avoidance area according to the first obstacle avoidance path.

[0048] S130. Based on at least one second obstacle avoidance point of the target vehicle in the second obstacle avoidance area, determine the second obstacle avoidance path of the target vehicle in the second obstacle avoidance area.

[0049] The second obstacle avoidance point refers to the obstacle avoidance point planned for the target vehicle when it avoids obstacles within the second obstacle avoidance area. The second obstacle avoidance path within the second obstacle avoidance area can be obtained by connecting at least one of the second obstacle avoidance points within the second obstacle avoidance area.

[0050] Specifically, when the target vehicle reaches the target driving reference point, it enters the second obstacle avoidance zone. At this point, the target vehicle is relatively close to the obstacle to be avoided and needs to adjust its driving state in real time according to the driving state of the obstacle to avoid. Specifically, when the target vehicle is in the second obstacle avoidance zone, at least one second obstacle avoidance point is planned for the target vehicle based on the driving state of the obstacle to avoid, and a second obstacle avoidance path is obtained based on at least one second obstacle avoidance point, allowing the target vehicle to avoid the obstacle by detouring around it from the left or right side.

[0051] S140. Determine the target obstacle avoidance path corresponding to the target vehicle based on the first obstacle avoidance path and the second obstacle avoidance path.

[0052] The target obstacle avoidance path is the complete obstacle avoidance path of the target vehicle when avoiding the obstacle. That is, the target obstacle avoidance path can be obtained by combining the first obstacle avoidance path and the second obstacle avoidance path.

[0053] It should be noted that the end point of the first obstacle avoidance path is the starting point of the second obstacle avoidance path. In other words, the target obstacle avoidance path obtained based on the first and second obstacle avoidance paths is a continuous obstacle avoidance path.

[0054] Optionally, the steering wheel angle corresponding to the target vehicle can be adjusted in real time according to the target obstacle avoidance path corresponding to the target vehicle, so as to control the target vehicle to avoid obstacles according to the target obstacle avoidance path.

[0055] Specifically, after determining the target obstacle avoidance path corresponding to the target vehicle, the target vehicle can avoid obstacles according to the target obstacle avoidance path. It's understandable that the target vehicle does not travel in a straight line during obstacle avoidance; instead, it adjusts its travel path based on the driving state of the obstacle to be avoided. In other words, the target obstacle avoidance path is not a straight line but a curved path with undulations. Controlling the left and right movement of the target vehicle is mainly achieved by controlling the steering wheel angle. Therefore, after determining the target obstacle avoidance path, by using the target vehicle's current position and the obstacle avoidance position it will reach in the next moment, the steering wheel angle corresponding to the target vehicle's steering wheel angle can be calculated. Based on the steering wheel angle, the steering wheel angle of the target vehicle is adjusted to control the target vehicle to avoid obstacles according to the target obstacle avoidance path.

[0056] The technical solution of this invention involves determining a first obstacle avoidance area and a second obstacle avoidance area corresponding to the target vehicle when an obstacle to be avoided is detected. In practical applications, since the driving intention of the obstacle to be avoided is uncertain when the target vehicle is avoiding it, the obstacle avoidance area corresponding to the target vehicle is divided into a first obstacle avoidance area and a second obstacle avoidance area. Based on this, a first obstacle avoidance path is determined for the target vehicle within the first obstacle avoidance area based on at least one first obstacle avoidance point of the target vehicle within the first obstacle avoidance area. That is, when the target vehicle is in the first obstacle avoidance area, which is far from the obstacle to be avoided, the first obstacle avoidance path is obtained based on the relative lateral position between the obstacle to be avoided and the target vehicle, and preliminary obstacle avoidance is performed based on the first obstacle avoidance path. Further, a second obstacle avoidance path is determined for the target vehicle within the second obstacle avoidance area based on at least one second obstacle avoidance point of the target vehicle within the second obstacle avoidance area. In other words, when the target vehicle is in the second obstacle avoidance zone, which is relatively close to the obstacle to be avoided, the vehicle's steering is adjusted in real time according to the driving state of the obstacle to be avoided. A second obstacle avoidance path is obtained based on the obstacle avoidance cost corresponding to each obstacle avoidance point of the target vehicle, and the vehicle avoids obstacles more accurately based on this second path. Based on this, the target obstacle avoidance path corresponding to the target vehicle is determined according to the first and second obstacle avoidance paths. This solves the problem in existing technologies where the uncertainty of the driving intention of the target object leads to the inability to accurately plan the obstacle avoidance path of the target vehicle, resulting in large turning angles and uneven obstacle avoidance paths. By dividing the obstacle avoidance zone of the target vehicle and planning corresponding obstacle avoidance paths in each zone, more accurate obstacle avoidance path planning for the target vehicle is achieved, and the planned obstacle avoidance path is smoother.

[0057] Example 2

[0058] Figure 2 is a flowchart of a vehicle obstacle avoidance method provided in Embodiment 2 of the present invention. Optionally, the method for determining the first obstacle avoidance path of the target vehicle in the first obstacle avoidance area based on at least one first obstacle avoidance point of the target vehicle in the first obstacle avoidance area is refined.

[0059] As shown in Figure 2, the method includes:

[0060] S210. When an obstacle to be avoided corresponding to the target vehicle is detected, the first obstacle avoidance area and the second obstacle avoidance area corresponding to the target vehicle are determined.

[0061] S220. Within the first obstacle avoidance area, based on the first lateral relative position between the object to be avoided and the target vehicle, determine the obstacle avoidance sub-area corresponding to the target vehicle from at least one obstacle avoidance sub-area.

[0062] The first lateral relative position can be understood as the relative position of the obstacle to be avoided and the target vehicle in the horizontal direction. The horizontal direction refers to the direction perpendicular to the center line of the lane where the target vehicle is located. For example, if the obstacle to be avoided is located to the right front of the target vehicle, then the first lateral relative position means that the obstacle to be avoided is located to the right of the target vehicle in the horizontal direction. The obstacle avoidance sub-region refers to a sub-region within the first obstacle avoidance region. The obstacle avoidance sub-region includes at least one of the following: the first obstacle avoidance sub-region corresponding to the left lane adjacent to the target vehicle; the second obstacle avoidance sub-region of the lane where the target vehicle is located; and the third obstacle avoidance sub-region corresponding to the right lane adjacent to the target vehicle. The obstacle avoidance sub-region to be used can be understood as the obstacle avoidance sub-region to be used, determined from the three obstacle avoidance sub-regions when avoiding the obstacle to be avoided.

[0063] In real-world scenarios, the obstacle to be avoided is typically in the same lane as the target vehicle. When the target vehicle is in the first obstacle avoidance zone, it needs to detour around the obstacle to be avoided from either its left or right side. Therefore, this technical solution further divides the first obstacle avoidance zone into three sub-zones: the first sub-zone corresponding to the left lane adjacent to the target vehicle, the second sub-zone of the lane where the target vehicle is located, and the third sub-zone corresponding to the right lane adjacent to the target vehicle. This allows the target vehicle to determine the appropriate sub-zone from these three sub-zones when avoiding the obstacle.

[0064] Specifically, when the first lateral relative position between the obstacle to be avoided and the target vehicle is determined to be that the obstacle is located to the left of the target vehicle in the horizontal direction, the target vehicle should detour around the obstacle to be avoided from the right side. Accordingly, the third obstacle avoidance sub-area corresponding to the target vehicle should be used as the obstacle avoidance sub-area.

[0065] S230. Within the obstacle avoidance sub-area to be used, determine at least one first obstacle avoidance point corresponding to the target vehicle based on the first lateral relative distance of the target vehicle at at least one first obstacle avoidance reference point.

[0066] The first obstacle avoidance reference point refers to the driving reference point on the center line of the vehicle in the lane where the target vehicle is located. The first lateral relative distance refers to the horizontal distance between the first obstacle avoidance point and the first obstacle avoidance reference point. It should be noted that there is a one-to-one correspondence between the first obstacle avoidance reference point within the first obstacle avoidance area and the driving reference point of the target vehicle within the first obstacle avoidance area.

[0067] For example, if a 100-meter area in the direction of travel of the target vehicle is taken as the obstacle avoidance area of ​​the target vehicle, and a driving reference point is set every 10 meters on the center line of the lane where the target vehicle is located, wherein the target driving reference point is the third driving reference point, then the obstacle avoidance area corresponding to the target vehicle can be divided into a first obstacle avoidance area and a second obstacle avoidance area based on the target driving reference point.

[0068] Furthermore, based on the first lateral relative position between the obstacle to be avoided and the target vehicle, the target vehicle's designated obstacle avoidance sub-region within the first obstacle avoidance area can be determined. For example, the third obstacle avoidance sub-region corresponding to the right lane adjacent to the target vehicle can be used as the designated obstacle avoidance sub-region. To determine the target vehicle's first obstacle avoidance path within the designated obstacle avoidance sub-region, at least one driving reference point corresponding to the target vehicle within the first obstacle avoidance area can be used as the target vehicle's first obstacle avoidance reference point within the designated obstacle avoidance sub-region. Based on this, when planning the target vehicle's obstacle avoidance path within the designated obstacle avoidance sub-region, the target vehicle's first lateral relative distance in the horizontal direction at each first obstacle avoidance reference point can be determined, so as to determine the first obstacle avoidance point corresponding to the target vehicle based on the first lateral relative distance. For example, if the first lateral relative distance corresponding to the first first obstacle avoidance reference point is 1 meter, then the first obstacle avoidance point corresponding to the target vehicle is located at a driving position 1 meter to the right of the obstacle to be avoided and in the horizontal direction of the first reference point.

[0069] Optionally, based on the first lateral relative distance of the target vehicle at at least one first obstacle avoidance reference point, at least one first obstacle avoidance point corresponding to the target vehicle is determined, including: for at least one first obstacle avoidance reference point, obtaining the information to be used corresponding to at least one first obstacle avoidance point to be selected in the horizontal direction of the current first obstacle avoidance reference point; determining the first obstacle avoidance cost between at least one first obstacle avoidance point to be selected and the current first obstacle avoidance reference point based on the information to be used; and determining the first obstacle avoidance point to be selected corresponding to the minimum first obstacle avoidance cost as the current first obstacle avoidance point corresponding to the current first obstacle avoidance reference point.

[0070] The information to be used includes the distance between the first obstacle avoidance point to be selected and the current first obstacle avoidance reference point, the rate of curvature change between the first obstacle avoidance point to be selected and the current first obstacle avoidance reference point, and the interpolation information of the rate of curvature change between two adjacent rates of curvature change. Taking the current first obstacle avoidance reference point as an example, the first obstacle avoidance point to be selected can be understood as the obstacle avoidance planning position located in the horizontal direction of the current first obstacle avoidance reference point. It can be understood that there is at least one first obstacle avoidance point to be selected. The first obstacle avoidance cost can be understood as the obstacle avoidance cost corresponding to the target vehicle's current position traveling to the first obstacle avoidance point to be selected.

[0071] Specifically, as shown in Figure 3, the "vehicle" represents the target vehicle, and the obstacle refers to the object to be avoided corresponding to the target vehicle. Point C in the figure is located on the center line of the lane in the direction of travel of the target vehicle, and point C is the target driving reference point corresponding to the target vehicle. It can be used to divide the area to be avoided corresponding to the target vehicle into a first obstacle avoidance area and a second obstacle avoidance area. Among them, the area corresponding to stage 1 in the figure is the first obstacle avoidance area of ​​the target vehicle, and the area corresponding to stage 2 in the figure is the second obstacle avoidance area of ​​the target vehicle. It can be understood that within the first obstacle avoidance area, at least one driving reference point, i.e., the first obstacle avoidance reference point, is pre-set in the driving lane of the target vehicle, and at least one first obstacle avoidance point to be selected is determined in the horizontal direction from the first obstacle avoidance reference point, for example, a first obstacle avoidance point to be selected is set every 0.5m.

[0072] Taking one of the first obstacle avoidance reference points as the current first obstacle avoidance reference point as an example, if there are 5 first obstacle avoidance points to be selected corresponding to the first obstacle avoidance reference point, then obtain the information to be used corresponding to each first obstacle avoidance point to be selected, and calculate the first obstacle avoidance cost corresponding to each first obstacle avoidance point to be selected based on the corresponding information to be used.

[0073] Specifically, taking the first obstacle avoidance cost corresponding to one of the first candidate obstacle avoidance points as an example, the first obstacle avoidance cost corresponding to the first candidate obstacle avoidance point can be determined by the following formula:

[0074] cost = W ref *Cost ref +W jerk *Cost jerk +W continuity *Cost continuity

[0075] Among them, W ref Cost represents the proportionality coefficient corresponding to the distance cost between the first obstacle avoidance point and the corresponding first obstacle avoidance reference point. ref W represents the distance cost between the first obstacle avoidance point to be selected and the corresponding first obstacle avoidance reference point. jerkCost represents the proportional coefficient of the path smoothness cost corresponding to the first obstacle avoidance point to be selected. jerk W represents the path smoothness cost corresponding to the first obstacle avoidance point to be selected. continuity Cost represents the proportionality coefficient of the continuity cost corresponding to the first obstacle avoidance point to be selected. continuity This represents the continuity cost corresponding to the first obstacle avoidance point to be selected.

[0076] After obtaining the first obstacle avoidance cost corresponding to each first obstacle avoidance point to be selected, the first obstacle avoidance point corresponding to the minimum first obstacle avoidance cost is taken as the current first obstacle avoidance point corresponding to the current first obstacle avoidance reference point.

[0077] S240. Determine the first obstacle avoidance path of the target vehicle based on the driving path of the target vehicle between at least one first obstacle avoidance point in the first obstacle avoidance area.

[0078] The first obstacle avoidance path is a driving route formed based on at least one first obstacle avoidance point within the first obstacle avoidance area. Specifically, after determining the first obstacle avoidance point corresponding to each first obstacle avoidance reference point of the target vehicle within the first obstacle avoidance area, the first obstacle avoidance path of the target vehicle within the first obstacle avoidance area can be determined based on the driving route formed by at least one first obstacle avoidance point.

[0079] S250. Based on at least one second obstacle avoidance point of the target vehicle in the second obstacle avoidance area, determine the second obstacle avoidance path of the target vehicle in the second obstacle avoidance area.

[0080] S260. Based on the first obstacle avoidance path and the second obstacle avoidance path, determine the target obstacle avoidance path corresponding to the target vehicle.

[0081] The technical solution of this embodiment, within the first obstacle avoidance area, determines a target obstacle avoidance sub-area corresponding to the target vehicle from at least one obstacle avoidance sub-area based on the first lateral relative position between the obstacle to be avoided and the target vehicle. Within the target obstacle avoidance sub-area, at least one first obstacle avoidance point corresponding to the target vehicle is determined based on the first lateral relative distance between the target vehicle and at least one first obstacle avoidance reference point; and the first obstacle avoidance path of the target vehicle is determined based on the driving path between at least one first obstacle avoidance point within the first obstacle avoidance area. Specifically, when the target vehicle is in the first obstacle avoidance area, since the target vehicle is far from the obstacle to be avoided, the target obstacle avoidance sub-area corresponding to the target vehicle can be determined based on the lateral relative position information of the obstacle to be avoided relative to the target vehicle. Further, based on the first lateral relative distances corresponding to at least one first obstacle avoidance reference point corresponding to the target vehicle, the corresponding first obstacle avoidance point can be obtained, and then the first obstacle avoidance path of the target vehicle within the first obstacle avoidance area can be obtained based on each first obstacle avoidance point. This invention addresses the issue that when the obstacle to be avoided is far from the target vehicle, the target vehicle's driving intention is unpredictable, and direct obstacle avoidance may require significant adjustments to the vehicle's steering angle, resulting in an uneven driving experience. By planning a first obstacle avoidance path for the target vehicle within the first obstacle avoidance area, the target vehicle only needs to avoid obstacles according to the general direction within the first obstacle avoidance area, reducing the frequency of steering adjustments during obstacle avoidance and improving the smoothness of the target vehicle's driving.

[0082] Example 3

[0083] Figure 4 is a flowchart of a vehicle obstacle avoidance method provided in Embodiment 3 of the present invention. Optionally, the second obstacle avoidance path of the target vehicle in the second obstacle avoidance area is refined based on at least one second obstacle avoidance point of the target vehicle in the second obstacle avoidance area.

[0084] As shown in Figure 4, the method includes:

[0085] S310. When an obstacle to be avoided corresponding to the target vehicle is detected, the first obstacle avoidance area and the second obstacle avoidance area corresponding to the target vehicle are determined.

[0086] S320. Based on at least one first obstacle avoidance point of the target vehicle in the first obstacle avoidance area, determine the first obstacle avoidance path of the target vehicle in the first obstacle avoidance area.

[0087] S330. Based on the safe obstacle avoidance area corresponding to the object to be avoided, determine at least one second obstacle avoidance reference point of the target vehicle within the second obstacle avoidance area.

[0088] The safe obstacle avoidance zone is an area defined based on the length and width of the obstacle to be avoided. When the target vehicle enters the second obstacle avoidance zone, the second obstacle avoidance reference point is a reference point set based on the center line of the lane where the target vehicle is located and the safe obstacle avoidance zone corresponding to the obstacle to be avoided, as shown in Figure 5. The reference path in the figure includes at least one second obstacle avoidance reference point corresponding to the target vehicle.

[0089] More specifically, when the target vehicle has not entered the safe obstacle avoidance zone corresponding to the obstacle to be avoided, at least one second obstacle avoidance reference point is set along the center line of the lane where the target vehicle is located, along the direction of travel of the target vehicle. When the target vehicle is in the direction of travel corresponding to the safe obstacle avoidance zone of the obstacle to be avoided, a corresponding second obstacle avoidance reference point is set along the boundary line of the safe obstacle avoidance zone of the obstacle to be avoided. When the target vehicle has traveled beyond the safe obstacle avoidance zone of the obstacle to be avoided, at least one more second obstacle avoidance reference point is set along the center line of the lane in the direction of travel of the target vehicle.

[0090] It should be noted that, in actual obstacle avoidance planning for the target vehicle, to ensure the safety of the target vehicle and the obstacle to be avoided during obstacle avoidance, this technical solution expands the obstacle to be avoided upon detection to obtain a safe obstacle avoidance area corresponding to the obstacle to be avoided. For example, a safety distance of 0.5m is reserved on the left and right sides of the obstacle to be avoided, and a safety distance of 1m is reserved in front of and behind the obstacle to be avoided, so that a sufficient safety range is maintained between the target vehicle and the obstacle to be avoided during obstacle avoidance.

[0091] In this technical solution, when determining the second obstacle avoidance reference point corresponding to the target vehicle at the boundary of the safe obstacle avoidance zone, it is necessary to determine whether to set the second obstacle avoidance reference point along the left boundary or the right boundary of the safe obstacle avoidance zone based on the lateral position information of the object to be avoided relative to the target vehicle. For example, when the object to be avoided is located to the left front of the target vehicle, the target vehicle needs to avoid the obstacle from the right side of the object to be avoided. In this case, the second obstacle avoidance reference point can be set along the right boundary of the safe obstacle avoidance zone of the object to be avoided.

[0092] S340. For each second obstacle avoidance reference point, determine the vehicle turning probability and vehicle turning cost of the target vehicle at the current second obstacle avoidance reference point.

[0093] The vehicle turning probability is used to characterize the probability that the target vehicle will turn left or right. The vehicle turning probability includes the vehicle's left turn probability or the vehicle's right turn probability, and the vehicle turning cost includes the left turn cost corresponding to the vehicle's left turn probability or the right turn cost corresponding to the vehicle's right turn probability.

[0094] Specifically, when a target vehicle is attempting obstacle avoidance, the driving intention of the obstacle to be avoided is difficult to predict. Therefore, the target vehicle needs to adjust its own trajectory in real time based on the obstacle's trajectory. In other words, the target vehicle needs to adjust its steering direction in real time according to the obstacle's driving intention to accurately avoid it. Furthermore, since turning requires changing the original trajectory, the turning cost of the target vehicle during the turn needs to be determined.

[0095] In practical applications, determining the vehicle turning probability of the target vehicle at the current second obstacle avoidance reference point includes: determining the distance between the center point of the obstacle to be avoided and the left boundary of the lane where the target vehicle is located; determining the left turning probability of the target vehicle based on the ratio of the distance between the left boundary and the lane width of the lane where the target vehicle is located; and determining the right turning probability of the target vehicle based on the difference between the preset turning probability and the left turning probability.

[0096] Specifically, the probability of a target vehicle turning left can be determined based on the following formula:

[0097] p left =d left / d_width

[0098] Where, p left d represents the probability of a vehicle turning left. left d_width represents the distance between the center point of the obstacle to be avoided and the left boundary of the lane where the target vehicle is located, and d_width represents the lane width.

[0099] Based on this, the probability of a vehicle turning right can be determined by the following formula:

[0100] p right =1-p left

[0101] Where, p right p represents the probability that the vehicle will turn right. left This indicates the probability of the vehicle turning left, with 1 representing the preset turning probability.

[0102] In this technical solution, when p left The larger the value, the greater the distance between the object to be avoided and the left lane boundary, meaning the object is closer to the right. Therefore, the target vehicle is more likely to detour from the left.

[0103] Furthermore, after determining the vehicle turning probability corresponding to the target vehicle, the vehicle turning cost corresponding to the target vehicle can be determined based on the following formula:

[0104]

[0105] Cost represents the cost of turning the vehicle. stage1 p represents the vehicle steering cost of the target vehicle within the first obstacle avoidance area. left This indicates the probability of a vehicle turning left. p represents the left-turn cost when the target vehicle turns left within the second obstacle avoidance area. right This indicates the probability of a vehicle turning right. This represents the right turn cost when the target vehicle turns right within the second obstacle avoidance area.

[0106] S350. Based on the vehicle turning probability and the vehicle turning cost, determine the current second obstacle avoidance point corresponding to the current second obstacle avoidance reference point for the target vehicle.

[0107] When the target vehicle is in the second obstacle avoidance zone, there is at least one second obstacle avoidance reference point in the second obstacle avoidance zone. Taking one of the second obstacle avoidance reference points as the current second obstacle avoidance reference point, there is at least one second obstacle avoidance point to be selected at the current second obstacle avoidance reference point. The second obstacle avoidance point to be selected with the lowest obstacle avoidance cost is taken as the current second obstacle avoidance point corresponding to the current second obstacle avoidance reference point.

[0108] Specifically, based on the vehicle turning probability and the vehicle turning cost, the current second obstacle avoidance point corresponding to the current second obstacle avoidance reference point is determined, including: determining a first cost to be superimposed based on the vehicle left turning probability and the vehicle left turning cost corresponding to the vehicle left turning probability; determining a second cost to be superimposed based on the vehicle right turning probability and the vehicle right turning cost corresponding to the vehicle right turning probability; determining a second obstacle avoidance cost for the target vehicle within the second obstacle avoidance area based on the first and second costs to be superimposed; determining a second lateral relative distance corresponding to the current second obstacle avoidance reference point based on the second obstacle avoidance cost; and determining the current second obstacle avoidance point corresponding to the current second obstacle avoidance reference point based on the second lateral relative distance.

[0109] Specifically, taking the current second obstacle avoidance reference point as an example, the first cost to be superimposed is obtained by multiplying the vehicle's left-turn probability and left-turn cost, and the second cost to be superimposed is obtained by multiplying the vehicle's right-turn probability and right-turn cost. Furthermore, based on the second cost to be superimposed, the second obstacle avoidance cost corresponding to the current second obstacle avoidance reference point can be obtained; that is, the obstacle avoidance cost corresponding to each second obstacle avoidance point to be selected corresponding to the current second obstacle avoidance reference point.

[0110] It is understandable that the current second obstacle avoidance reference point corresponds to one or more second obstacle avoidance points in the horizontal direction, and each second obstacle avoidance point corresponds to a second obstacle avoidance cost. Based on this, the obstacle avoidance point corresponding to the minimum second obstacle avoidance cost can be determined as the current second obstacle avoidance point.

[0111] S360. Determine the second obstacle avoidance path of the target vehicle based on the driving path of the target vehicle between at least one second obstacle avoidance point in the second obstacle avoidance area.

[0112] The second obstacle avoidance path is a driving route formed based on at least one second obstacle avoidance point within the second obstacle avoidance area.

[0113] Specifically, after determining the second obstacle avoidance points corresponding to each second obstacle avoidance reference point of the target vehicle in the second obstacle avoidance area, the second obstacle avoidance path of the target vehicle in the second obstacle avoidance area can be determined based on the driving route formed by at least one second obstacle avoidance point.

[0114] S370. Determine the target obstacle avoidance path corresponding to the target vehicle based on the first obstacle avoidance path and the second obstacle avoidance path.

[0115] The advantage of this technical solution is that when the target vehicle avoids an obstacle, the obstacle avoidance area corresponding to the target vehicle is divided into a first obstacle avoidance area and a second obstacle avoidance area. A first obstacle avoidance path is determined within the first obstacle avoidance area, and a second obstacle avoidance path is determined within the second obstacle avoidance area. By comprehensively considering the first obstacle avoidance cost corresponding to at least one first obstacle avoidance reference point and the second obstacle avoidance cost corresponding to at least one second obstacle avoidance reference point, the solution achieves the effect of minimizing the obstacle avoidance cost for the target vehicle.

[0116] The technical solution of this embodiment determines at least one second obstacle avoidance reference point for the target vehicle within the second obstacle avoidance area, based on the safe obstacle avoidance area corresponding to the obstacle to be avoided. For each second obstacle avoidance reference point, the vehicle turning probability and turning cost of the target vehicle at the current second obstacle avoidance reference point are determined. Based on the driving path of the target vehicle between at least one second obstacle avoidance point within the second obstacle avoidance area, the second obstacle avoidance path of the target vehicle is determined. In actual obstacle avoidance, when the target vehicle is in the second obstacle avoidance area, since the obstacle to be avoided is relatively close to the target vehicle, the obstacle avoidance path of the target vehicle needs to be adjusted in real time according to the driving trajectory of the obstacle to be avoided. Specifically, after determining at least one second obstacle avoidance reference point corresponding to the target vehicle, each second obstacle avoidance reference point corresponds to one or more candidate obstacle avoidance points in the horizontal direction. Based on the obstacle avoidance cost corresponding to each candidate obstacle avoidance point, a second obstacle avoidance point corresponding to each second second reference point is determined, and the second obstacle avoidance path of the target vehicle within the second obstacle avoidance area is determined based on at least one second obstacle avoidance point. By planning a second obstacle avoidance path within the second obstacle avoidance area in real time based on the driving trajectory of the object to be avoided, the target vehicle can achieve a smoother obstacle avoidance effect within the second obstacle avoidance area.

[0117] Example 4

[0118] Figure 6 is a schematic diagram of a vehicle obstacle avoidance device provided in Embodiment 4 of the present invention. As shown in Figure 6, the device includes: an obstacle avoidance area determination module 410, a first obstacle avoidance path determination module 420, a second obstacle avoidance path determination module 430, and a target obstacle avoidance path determination module 440.

[0119] The obstacle avoidance area determination module 410 is used to determine a first obstacle avoidance area and a second obstacle avoidance area corresponding to the target vehicle when an obstacle to be avoided corresponding to the target vehicle is detected; wherein the obstacle to be avoided includes at least one of motor vehicles, non-motor vehicles and pedestrians.

[0120] The first obstacle avoidance path determination module 420 is used to determine the first obstacle avoidance path of the target vehicle in the first obstacle avoidance area based on at least one first obstacle avoidance point of the target vehicle in the first obstacle avoidance area.

[0121] The second obstacle avoidance path determination module 430 is used to determine the second obstacle avoidance path of the target vehicle in the second obstacle avoidance area based on at least one second obstacle avoidance point of the target vehicle in the second obstacle avoidance area.

[0122] The target obstacle avoidance path determination module 440 is used to determine the target obstacle avoidance path corresponding to the target vehicle based on the first obstacle avoidance path and the second obstacle avoidance path.

[0123] The technical solution of this invention, when an obstacle to be avoided corresponding to a target vehicle is detected, determines a first obstacle avoidance area and a second obstacle avoidance area corresponding to the target vehicle; determines a first obstacle avoidance path for the target vehicle within the first obstacle avoidance area based on at least one first obstacle avoidance point of the target vehicle within the first obstacle avoidance area; determines a second obstacle avoidance path for the target vehicle within the second obstacle avoidance area based on at least one second obstacle avoidance point of the target vehicle within the second obstacle avoidance area; and determines the target obstacle avoidance path corresponding to the target vehicle based on the first and second obstacle avoidance paths. This solves the problem in existing technologies where the uncertainty of the driving intention of the object to be identified leads to the inability to accurately plan the obstacle avoidance path for the target vehicle, resulting in large turning angles and uneven obstacle avoidance paths when the target vehicle is avoiding obstacles. By dividing the obstacle avoidance area of ​​the target vehicle into obstacle avoidance areas and planning corresponding obstacle avoidance paths within each area, more accurate obstacle avoidance path planning for the target vehicle is achieved, and the planned obstacle avoidance path is smoother.

[0124] Optionally, the obstacle avoidance area determination module includes: a driving reference point determination submodule, used to determine at least one driving reference point on the center line of the driving lane where the target vehicle is located according to preset spacing information; a target driving reference point determination submodule, used to determine a target driving reference point from at least one driving reference point according to preset length information of the first obstacle avoidance area; and an obstacle avoidance area determination submodule, used to divide the obstacle avoidance area corresponding to the target vehicle into regions based on the target driving reference point, to obtain a first obstacle avoidance area and a second obstacle avoidance area.

[0125] Optionally, the first obstacle avoidance path determination module includes: an obstacle avoidance sub-region determination sub-module, used to determine, within the first obstacle avoidance area, an obstacle avoidance sub-region corresponding to the target vehicle from at least one obstacle avoidance sub-region based on the first lateral relative position between the obstacle to be avoided and the target vehicle; wherein the obstacle avoidance sub-region includes at least one of a first obstacle avoidance sub-region corresponding to the left lane adjacent to the target vehicle, a second obstacle avoidance sub-region of the lane where the target vehicle is located, and a third obstacle avoidance sub-region corresponding to the right lane adjacent to the target vehicle; a first obstacle avoidance point determination sub-module, used to determine, within the obstacle avoidance sub-region to be used, at least one first obstacle avoidance point corresponding to the target vehicle based on the first lateral relative distance between the target vehicle and at least one first obstacle avoidance reference point; wherein the first obstacle avoidance reference point within the first obstacle avoidance area corresponds one-to-one with the driving reference point of the target vehicle within the first obstacle avoidance area; and a first obstacle avoidance path determination sub-module, used to determine the first obstacle avoidance path of the target vehicle based on the driving path between at least one first obstacle avoidance point within the first obstacle avoidance area.

[0126] Optionally, the first obstacle avoidance point determination submodule includes: a to-be-used information determination unit, used to obtain to-be-used information corresponding to at least one first obstacle avoidance point to be selected in the horizontal direction of the current first obstacle avoidance reference point for at least one first obstacle avoidance reference point; wherein, the to-be-used information includes distance information between the first obstacle avoidance point to be selected and the current first obstacle avoidance reference point, curvature change rate information between the first obstacle avoidance point to be selected and the current first obstacle avoidance reference point, and change rate interpolation information between two adjacent curvature change rates; a first obstacle avoidance cost determination unit, used to determine the first obstacle avoidance cost between at least one first obstacle avoidance point to be selected and the current first obstacle avoidance reference point based on the to-be-used information; and a first obstacle avoidance point determination unit, used to determine the first obstacle avoidance point to be selected corresponding to the minimum first obstacle avoidance cost as the current first obstacle avoidance point corresponding to the current first obstacle avoidance reference point.

[0127] Optionally, the second obstacle avoidance path determination module includes: a second obstacle avoidance reference point determination submodule, used to determine at least one second obstacle avoidance reference point of the target vehicle within the second obstacle avoidance area based on the safe obstacle avoidance area corresponding to the obstacle to be avoided; wherein, the safe obstacle avoidance area is an area set according to the length and width of the obstacle to be avoided; a steering probability determination submodule, used to determine the vehicle steering probability and vehicle steering cost of the target vehicle at the current second obstacle avoidance reference point for each second obstacle avoidance reference point; wherein, the vehicle steering probability includes the vehicle left turn steering probability or the vehicle right turn steering probability, and the vehicle steering cost includes the left turn steering cost corresponding to the vehicle left turn steering probability or the right turn steering cost corresponding to the vehicle right turn steering probability; a second obstacle avoidance point determination submodule, used to determine the current second obstacle avoidance point corresponding to the current second obstacle avoidance reference point of the target vehicle based on the vehicle steering probability and the vehicle steering cost; and a second obstacle avoidance path determination submodule, used to determine the second obstacle avoidance path of the target vehicle based on the driving path of the target vehicle between at least one second obstacle avoidance point within the second obstacle avoidance area.

[0128] Optionally, the steering probability determination submodule includes: a spacing determination unit, used to determine the distance between the center point of the obstacle to be avoided and the left boundary of the lane where the target vehicle is located; a left steering probability determination unit, used to determine the left steering probability of the target vehicle based on the ratio of the distance between the left boundary and the lane width of the lane where the target vehicle is located; and a right steering probability determination unit, used to determine the right steering probability of the target vehicle based on the difference between the preset steering probability and the left steering probability.

[0129] Optionally, the second obstacle avoidance point determination submodule includes: a first cost to be superimposed determination unit, used to determine a first cost to be superimposed based on the vehicle's left-turn probability and the vehicle's left-turn cost corresponding to the vehicle's left-turn probability; a second cost to be superimposed determination unit, used to determine a second cost to be superimposed based on the vehicle's right-turn probability and the vehicle's right-turn cost corresponding to the vehicle's right-turn probability; a second obstacle avoidance cost determination unit, used to determine a second obstacle avoidance cost for the target vehicle within the second obstacle avoidance area based on the first cost to be superimposed and the second cost to be superimposed; and a second obstacle avoidance point determination unit, used to determine a second lateral relative distance corresponding to the current second obstacle avoidance reference point based on the second obstacle avoidance cost, and to determine the current second obstacle avoidance point corresponding to the current second obstacle avoidance reference point based on the second lateral relative distance.

[0130] Optionally, the vehicle obstacle avoidance device is also used to adjust the steering wheel angle of the target vehicle in real time according to the target obstacle avoidance path corresponding to the target vehicle, so as to control the target vehicle to avoid obstacles according to the target obstacle avoidance path.

[0131] The vehicle obstacle avoidance device provided in the embodiments of the present invention can execute the vehicle obstacle avoidance method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method.

[0132] Example 5

[0133] Figure 7 shows a schematic diagram of the structure of an electronic device 10 according to an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0134] As shown in Figure 7, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer programs stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0135] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0136] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as vehicle obstacle avoidance methods. In some embodiments, the vehicle obstacle avoidance method can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the vehicle obstacle avoidance method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the vehicle obstacle avoidance method by any other suitable means (e.g., by means of firmware).

[0137] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transferring data and instructions to the storage system, the at least one input device, and the at least one output device.

[0138] Computer programs for implementing the vehicle obstacle avoidance method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0139] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium can be, but is not limited to, any suitable combination of electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. Machine-readable storage media can include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0140] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0141] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0142] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0143] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0144] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A vehicle obstacle avoidance method, characterized in that, include: When an obstacle to be avoided corresponding to the target vehicle is detected, a first obstacle avoidance area and a second obstacle avoidance area corresponding to the target vehicle are determined; wherein, the obstacle to be avoided includes at least one of motor vehicles, non-motor vehicles, and pedestrians; based on at least one first obstacle avoidance point of the target vehicle in the first obstacle avoidance area, a first obstacle avoidance path of the target vehicle in the first obstacle avoidance area is determined; based on the safe obstacle avoidance area corresponding to the obstacle to be avoided, at least one second obstacle avoidance reference point of the target vehicle in the second obstacle avoidance area is determined; wherein, the safe obstacle avoidance area is an area set according to the length and width of the obstacle to be avoided; for each second obstacle avoidance reference point, the target vehicle is determined in the current second obstacle avoidance area. The system defines the vehicle turning probability and turning cost at a reference point; wherein the vehicle turning probability includes the vehicle left turn probability or the vehicle right turn probability, and the vehicle turning cost includes the left turn cost corresponding to the vehicle left turn probability or the right turn cost corresponding to the vehicle right turn probability; based on the vehicle turning probability and the vehicle turning cost, the system determines the current second obstacle avoidance point corresponding to the current second obstacle avoidance reference point; based on the driving path of the target vehicle between at least one second obstacle avoidance point within the second obstacle avoidance area, the system determines the second obstacle avoidance path of the target vehicle; and based on the first obstacle avoidance path and the second obstacle avoidance path, the system determines the target obstacle avoidance path corresponding to the target vehicle.

2. The method according to claim 1, characterized in that, The step of determining the first obstacle avoidance area and the second obstacle avoidance area corresponding to the target vehicle includes: determining at least one driving reference point on the center line of the driving lane where the target vehicle is located according to preset spacing information; determining a target driving reference point from the at least one driving reference point according to preset length information of the first obstacle avoidance area; and dividing the obstacle avoidance area corresponding to the target vehicle into regions based on the target driving reference point to obtain the first obstacle avoidance area and the second obstacle avoidance area.

3. The method according to claim 1, characterized in that, The step of determining the first obstacle avoidance path of the target vehicle within the first obstacle avoidance area based on at least one first obstacle avoidance point of the target vehicle within the first obstacle avoidance area includes: within the first obstacle avoidance area, determining a target vehicle-corresponding obstacle avoidance sub-area from at least one obstacle avoidance sub-area based on the first lateral relative position of the obstacle to be avoided and the target vehicle; wherein the obstacle avoidance sub-area includes at least one of a first obstacle avoidance sub-area corresponding to the left lane adjacent to the target vehicle, a second obstacle avoidance sub-area of ​​the lane where the target vehicle is located, and a third obstacle avoidance sub-area corresponding to the right lane adjacent to the target vehicle; within the target vehicle-corresponding obstacle avoidance sub-area, determining at least one first obstacle avoidance point of the target vehicle based on the first lateral relative distance of the target vehicle to at least one first obstacle avoidance reference point; wherein the first obstacle avoidance reference point within the first obstacle avoidance area corresponds one-to-one with the driving reference point of the target vehicle within the first obstacle avoidance area; and determining the first obstacle avoidance path of the target vehicle based on the driving path of the target vehicle between at least one first obstacle avoidance point within the first obstacle avoidance area.

4. The method according to claim 3, characterized in that, The step of determining at least one first obstacle avoidance point corresponding to the target vehicle based on the first lateral relative distance of the target vehicle at at least one first obstacle avoidance reference point includes: for the at least one first obstacle avoidance reference point, obtaining the information to be used corresponding to at least one first candidate obstacle avoidance point in the horizontal direction of the current first obstacle avoidance reference point; wherein, the information to be used includes distance information between the first candidate obstacle avoidance point and the current first obstacle avoidance reference point, curvature change rate information between the first candidate obstacle avoidance point and the current first obstacle avoidance reference point, and change rate interpolation information between two adjacent curvature change rates; determining the first obstacle avoidance cost between the at least one first candidate obstacle avoidance point and the current first obstacle avoidance reference point based on the information to be used; and determining the first candidate obstacle avoidance point corresponding to the minimum first obstacle avoidance cost as the current first obstacle avoidance point corresponding to the current first obstacle avoidance reference point.

5. The method according to claim 1, characterized in that, Determining the vehicle turning probability of the target vehicle at the current second obstacle avoidance reference point includes: determining the unused boundary distance from the center point of the obstacle to be avoided to the left boundary of the lane where the target vehicle is located; determining the vehicle left turning probability corresponding to the target vehicle based on the ratio of the unused boundary distance to the lane width of the lane where the target vehicle is located; and determining the vehicle right turning probability corresponding to the target vehicle based on the difference between the preset turning probability and the vehicle left turning probability.

6. The method according to claim 5, characterized in that, The step of determining the current second obstacle avoidance point corresponding to the current second obstacle avoidance reference point for the target vehicle based on the vehicle turning probability and the vehicle turning cost includes: determining a first cost to be superimposed based on the vehicle left turning probability and the vehicle left turn turning cost corresponding to the vehicle left turning probability; determining a second cost to be superimposed based on the vehicle right turning probability and the vehicle right turn turning cost corresponding to the vehicle right turning probability; determining a second obstacle avoidance cost for the target vehicle within the second obstacle avoidance area based on the first cost to be superimposed and the second cost to be superimposed; determining a second lateral relative distance corresponding to the current second obstacle avoidance reference point based on the second obstacle avoidance cost; and determining the current second obstacle avoidance point corresponding to the current second obstacle avoidance reference point based on the second lateral relative distance.

7. The method according to claim 1, characterized in that, Also includes: Based on the target obstacle avoidance path corresponding to the target vehicle, the steering wheel angle corresponding to the target vehicle is adjusted in real time to control the target vehicle to avoid obstacles according to the target obstacle avoidance path.

8. A vehicle obstacle avoidance device, characterized in that, include: An obstacle avoidance area determination module is used to determine a first obstacle avoidance area and a second obstacle avoidance area corresponding to the target vehicle when an obstacle to be avoided object corresponding to the target vehicle is detected; wherein the obstacle to be avoided object includes at least one of motor vehicles, non-motor vehicles, and pedestrians; a first obstacle avoidance path determination module is used to determine a first obstacle avoidance path of the target vehicle in the first obstacle avoidance area based on at least one first obstacle avoidance point of the target vehicle in the first obstacle avoidance area; a second obstacle avoidance reference point determination submodule is used to determine at least one second obstacle avoidance reference point of the target vehicle in the second obstacle avoidance area based on a safe obstacle avoidance area corresponding to the obstacle to be avoided; wherein the safe obstacle avoidance area is an area set according to the length and width of the obstacle to be avoided object; a steering probability determination submodule is used to determine the steering probability of the target vehicle in the current obstacle avoidance area for each second obstacle avoidance reference point. The system includes: a vehicle turning probability and a vehicle turning cost at the previous second obstacle avoidance reference point; wherein the vehicle turning probability includes a left turn probability or a right turn probability, and the vehicle turning cost includes a left turn cost corresponding to the left turn probability or a right turn cost corresponding to the right turn probability; a second obstacle avoidance point determination submodule, used to determine the current second obstacle avoidance point corresponding to the current second obstacle avoidance reference point of the target vehicle based on the vehicle turning probability and the vehicle turning cost; a second obstacle avoidance path determination submodule, used to determine the second obstacle avoidance path of the target vehicle based on the driving path of the target vehicle between at least one second obstacle avoidance point in the second obstacle avoidance area; and a target obstacle avoidance path determination module, used to determine the target obstacle avoidance path corresponding to the target vehicle based on the first obstacle avoidance path and the second obstacle avoidance path.

9. An electronic device, characterized in that, The electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the vehicle obstacle avoidance method according to any one of claims 1-7.

Images