Automatic driving decision method, device, vehicle and storage medium

Abstract

The present invention discloses an automatic driving decision-making method, device, vehicle and storage medium. The method comprises: obtaining obstacle information and the planned trajectory of the current vehicle; judging whether the obstacle is within the preset range of the planned trajectory; if the obstacle is within the preset range of the planned trajectory, then determining the decision-making behavior of the current vehicle in the current decision cycle based on the static and dynamic state of the obstacle. Through the technical solution of the present invention, it is possible to make avoidance decisions according to the static and dynamic state of the obstacle, and reduce the frequent parking and avoidance of the automatic driving vehicle when facing pedestrians while ensuring traffic safety, improve the driving stability and riding comfort of the automatic driving vehicle, and improve the operation efficiency and smoothness of the traffic flow.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of autonomous driving technology, and in particular, to an autonomous driving decision-making method, device, vehicle, and storage medium. Background Art

[0002] In an open urban road environment, vehicles often need to give way to or bypass obstacles such as pedestrians. In an autonomous driving environment, cars lack the ability to understand pedestrians' intentions and cannot communicate with pedestrians about right of way as flexibly as drivers do.

[0003] In order to ensure driving safety, self-driving vehicles usually adopt conservative decision-making methods. Self-driving vehicles only stop and avoid obstacles based on the current position of obstacles. For example, when pedestrians are detected on the roadside, they will stop and give priority to pedestrians. However, the walking state of pedestrians is complex and changeable, especially in traffic environments with a large number of pedestrians. The existing self-driving car control technology will frequently stop and avoid pedestrians with changeable intentions, which seriously reduces the driving stability and riding comfort of self-driving cars, as well as the operating efficiency and smoothness of the traffic flow of self-driving cars. Summary of the invention

[0004] The embodiments of the present invention provide an autonomous driving decision-making method, device, vehicle and storage medium, so as to make avoidance decisions according to the static and dynamic states of obstacles, reduce the frequent stopping and avoiding of autonomous driving vehicles when facing pedestrians while ensuring traffic safety, improve the driving stability and riding comfort of autonomous driving vehicles, and improve the operating efficiency and smoothness of traffic flow.

[0005] In a first aspect, an embodiment of the present invention provides an automatic driving decision-making method, including:

[0006] Obtain obstacle information and the planned trajectory of the current vehicle;

[0007] Determining whether the obstacle is within a preset range of the planned trajectory;

[0008] If the obstacle is within a preset range of the planned trajectory, the decision behavior of the current vehicle in the current decision cycle is determined based on the static and dynamic states of the obstacle.

[0009] In a second aspect, an embodiment of the present invention further provides an automatic driving decision-making device, the device comprising:

[0010] The acquisition module is used to obtain obstacle information and the planned trajectory of the current vehicle;

[0011] A judgment module, used to judge whether the obstacle is within a preset range of the planned trajectory;

[0012] The determination module is used to determine the decision behavior of the current vehicle in the current decision cycle based on the static and dynamic states of the obstacle if the obstacle is within a preset range of the planned trajectory.

[0013] In a third aspect, an embodiment of the present invention further provides a vehicle, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, an autonomous driving decision-making method as described in any one of the embodiments of the present invention is implemented.

[0014] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements an autonomous driving decision-making method as described in any one of the embodiments of the present invention.

[0015] The embodiments of the present invention obtain obstacle information and the planned trajectory of the current vehicle; determine whether the obstacle is within the preset range of the planned trajectory; if the obstacle is within the preset range of the planned trajectory, determine the decision-making behavior of the current vehicle in the current decision cycle based on the static and dynamic states of the obstacle, thereby solving the problem that the existing autonomous driving vehicle control technology frequently stops to avoid pedestrians with changeable intentions, and makes avoidance decisions based on the static and dynamic states of the obstacle. While ensuring traffic safety, the frequent stops and avoidance of autonomous driving vehicles when facing pedestrians are reduced, the driving stability and riding comfort of autonomous driving vehicles are improved, and the operating efficiency and smoothness of traffic flow are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 is a flow chart of an automatic driving decision-making method in Embodiment 1 of the present invention;

[0018] Figure 2A is a flow chart of an automatic driving decision-making method in Embodiment 2 of the present invention;

[0019] Figure 2B is a flow chart of a method for determining whether an obstacle is within a preset range of a planned trajectory in Embodiment 2 of the present invention;

[0020] Figure 2C is a flow chart of a method for determining whether an obstacle crosses in front of a current vehicle in a second embodiment of the present invention;

[0021] Figure 3 is a flow chart of an automatic driving decision-making method in Embodiment 3 of the present invention;

[0022] Figure 4 is a structural schematic diagram of an automatic driving decision-making device in Embodiment 4 of the present invention;

[0023] Figure 5 It is a structural schematic diagram of a vehicle in Embodiment 5 of the present invention. DETAILED DESCRIPTION

[0024] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0025] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0026] Embodiment 1

[0027] Figure 1 This is a flow chart of an automatic driving decision-making method provided in Embodiment 1 of the present invention. This embodiment can be applied to the situation where a vehicle makes automatic decisions when encountering an obstacle on an urban road. The method can be executed by the automatic driving decision-making device in the embodiment of the present invention, which can be implemented in software and / or hardware, such as Figure 1 As shown, the method specifically comprises the following steps:

[0028] S110, obtaining obstacle information and the planned trajectory of the current vehicle.

[0029] Among them, the obstacle may be an object on the road sensed by the vehicle that may hinder the vehicle's travel. The obstacle may be a stationary object or a movable object, such as a pedestrian, an animal, or a fixed roadblock.

[0030] The planned trajectory of the current vehicle may be the trajectory planned by the current vehicle in the current prediction period. The current vehicle travels along the planned trajectory when it does not encounter any obstacles. The planned trajectory of the current vehicle may be obtained by any existing feasible method, which will not be elaborated here.

[0031] The obstacle information may include at least one of the following: the position coordinates, size, movement speed, movement direction and movement trajectory of the obstacle.

[0032] The size of the obstacle refers to the length, width and height of the obstacle; the movement speed of the obstacle refers to the speed of the movable obstacle, and the movement speed may also be a vector including a direction; the movement trajectory may be the actual movement trajectory of the obstacle or the movement trajectory predicted based on the movement speed of the obstacle.

[0033] In addition, the position coordinates of the obstacle are the coordinates of the obstacle in the Frenet coordinate system, which is a coordinate system established based on the tangent vector and normal vector of the reference line with the lane centerline as the reference line, and is used to represent the positional relationship between the vehicle and the road. The coordinates in the Frenet coordinate system include: tangent direction coordinates and normal direction coordinates. The planned trajectory can be a point set composed of trajectory points of the current vehicle in the Frenet coordinate system.

[0034] The method of obtaining the position coordinates of the obstacle can be to establish a Frenet coordinate system based on the lane line where the current vehicle is located, and determine the position coordinates of the obstacle in the Frenet coordinate system, or to obtain the Cartesian coordinates of the obstacle in the global positioning system GPS coordinate system, and determine the position coordinates of the obstacle in the Frenet coordinate system based on the conversion relationship between the GPS coordinate system and the Frenet coordinate system. The Frenet coordinate system can be used to represent the position relationship between the vehicle, the road, and the obstacle. Any existing method can be used to achieve the conversion between the GPS coordinate system and the Frenet coordinate system, which will not be described in detail in the embodiments of the present invention.

[0035] S120, determining whether the obstacle is within a preset range of the planned trajectory.

[0036] The preset range may be determined according to actual conditions of the vehicle or road, and the embodiment of the present invention does not impose any limitation on this.

[0037] Specifically, based on the position coordinates of the obstacle and the position coordinates of each trajectory point in the trajectory point set corresponding to the planned trajectory, it is determined whether the position of the obstacle perceived by the current vehicle is within the preset range of the planned trajectory of the current vehicle, that is, whether the obstacle will affect the current vehicle from traveling along the planned trajectory.

[0038] S130: If the obstacle is within a preset range of the planned trajectory, a decision behavior of the current vehicle in a current decision cycle is determined based on the static and dynamic states of the obstacle.

[0039] The static and dynamic state of the obstacle is used to reflect whether the obstacle is in a static state or a moving state. The decision cycle refers to the time for the current vehicle to determine the decision behavior. Since the environment around the vehicle on the road is changing rapidly, it is necessary to make a decision in real time based on the obstacle information and the planned trajectory of the current vehicle. For example, the decision behavior can be determined once per second.

[0040] Specifically, if the obstacle is within the preset range of the planned trajectory, it means that the position of the obstacle will affect the current vehicle's driving along the planned trajectory, and the current vehicle needs to avoid the obstacle. Since obstacles include fixed obstacles and movable obstacles, and movable obstacles can be in motion or static state, the decision behavior of the current vehicle in the current decision cycle is determined based on the state information of the obstacle. The decision behavior can at least include: parking to avoid or detouring to avoid.

[0041] Optionally, if the obstacle is not within a preset range of the planned trajectory, it is determined that the decision behavior of the current vehicle in the current decision cycle is to travel along the planned trajectory.

[0042] Specifically, if the obstacle is not within the preset range of the planned trajectory, it means that the position of the obstacle perceived by the current vehicle will not affect the current vehicle traveling along the planned trajectory, and the current vehicle can travel along the planned trajectory.

[0043] The advantage of doing this is that it effectively and initially screens out obstacles that are irrelevant to the current vehicle's movement along the planned trajectory, avoids a large amount of invalid calculations, saves computing resources, and improves decision-making efficiency.

[0044] The technical solution of this embodiment obtains obstacle information and the planned trajectory of the current vehicle; determines whether the obstacle is within the preset range of the planned trajectory; if the obstacle is within the preset range of the planned trajectory, determines the decision-making behavior of the current vehicle in the current decision cycle based on the static and dynamic states of the obstacle. This can reduce the number of autonomous driving vehicles stopping to avoid pedestrians while ensuring traffic safety, improve the driving stability and riding comfort of autonomous driving vehicles, and improve the operating efficiency and smoothness of traffic flow.

[0045] Embodiment 2

[0046] Figure 2A This is a flow chart of an automatic driving decision-making method in Embodiment 2 of the present invention. This embodiment is based on the above embodiment and optimizes the decision-making behavior of the current vehicle in the current decision cycle based on the static and dynamic states of the obstacle.

[0047] like Figure 2A As shown, the method of this embodiment specifically includes the following steps:

[0048] S210, obtaining obstacle information and the planned trajectory of the current vehicle.

[0049] S220: Determine whether the obstacle is within a preset range of the planned trajectory.

[0050] S230: If the obstacle is within a preset range of the planned trajectory, determine the static or dynamic state of the obstacle.

[0051] Specifically, the static and dynamic states of the obstacle can be determined based on the speed of the obstacle collected by the sensor within a preset time. If the speed of the obstacle within the preset time is zero, the obstacle is determined to be in a static state. If the speed of the obstacle within the preset time is greater than zero, the obstacle is determined to be in a moving state. If the obstacle is in a moving state, the static and dynamic states may also include the moving direction and moving speed of the obstacle.

[0052] S240: If the obstacle is stationary, determine that the decision behavior of the current vehicle in the current decision cycle is to bypass the obstacle.

[0053] Specifically, if the obstacle is within the preset range of the planned trajectory and the obstacle is stationary, the decision behavior of the current vehicle in the current decision cycle is determined to be a detour, so that the current vehicle can re-plan the path according to the road conditions to bypass the obstacle.

[0054] S250: If the obstacle is in motion, determine whether the obstacle will cross in front of the current vehicle based on the motion trajectory of the obstacle and the planned trajectory of the current vehicle.

[0055] Specifically, if the obstacle is within the preset range of the planned trajectory and the obstacle is in motion, it can only be determined that the obstacle may affect the current vehicle's travel along the planned trajectory. However, since the obstacle is in motion, the obstacle's movement trajectory may not conflict with the vehicle's planned trajectory. In existing decision-making methods, the decision is usually made to stop or slow down to avoid the obstacle. In the case of many obstacles on urban roads, the current vehicle will frequently stop or slow down, which seriously reduces the driving stability and riding comfort of the autonomous vehicle, as well as the operating efficiency and smoothness of the autonomous vehicle's traffic flow.

[0056] Therefore, in an embodiment of the present invention, if an obstacle is within a preset range of the planned trajectory and the obstacle is in motion, it is judged whether the obstacle will cross in front of the current vehicle based on the movement trajectory of the obstacle and the planned trajectory of the current vehicle, thereby determining the decision behavior of the current vehicle in the current decision cycle based on the judgment result.

[0057] S260: If the result of the judgment is that an obstacle is crossing in front of the current vehicle, it is determined that the decision behavior of the current vehicle in the current decision cycle is to stop and avoid.

[0058] For example, if a pedestrian crosses in front of the current vehicle, it is determined that the decision behavior of the current vehicle in the current decision cycle is to stop and avoid, thereby giving way to the pedestrian.

[0059] S270: If the result of the judgment is that the obstacle is not crossing in front of the current vehicle, it is determined that the decision behavior of the current vehicle in the current decision cycle is to bypass and avoid.

[0060] For example, if the obstacle is not crossing in front of the current vehicle, for example, a pedestrian is traveling in the same direction as the current vehicle in front of the right side of the road, then the current vehicle can go around to the left to pass the pedestrian; or if the current vehicle is traveling forward in the middle of the road and the pedestrian is in the middle of the road and walking to the left side of the road, then the current vehicle can go around to the right to avoid the pedestrian.

[0061] The technical solution of this embodiment obtains obstacle information and the planned trajectory of the current vehicle; determines whether the obstacle is within the preset range of the planned trajectory; if the obstacle is within the preset range of the planned trajectory, determines the static and dynamic states of the obstacle; if the obstacle is in a static state, determines that the decision-making behavior of the current vehicle in the current decision cycle is to detour and avoid the obstacle; if the obstacle is in a moving state, determines whether the obstacle will cross in front of the current vehicle based on the movement trajectory of the obstacle and the planned trajectory of the current vehicle; determines the decision-making behavior of the current vehicle in the current decision cycle based on the judgment result, which can reduce the frequent stopping and avoiding of autonomous driving vehicles when facing pedestrians while ensuring traffic safety, improve the driving stability and riding comfort of autonomous driving vehicles, and improve the operating efficiency and smoothness of traffic flow.

[0062] Optional, such as Figure 2B As shown, step S220, determining whether the obstacle is within a preset range of the planned trajectory, specifically includes:

[0063] S221, determining a trajectory point set corresponding to the planned trajectory, where the trajectory point set is a point set consisting of trajectory points of the current vehicle in a Frenet coordinate system.

[0064] S222, determining whether the first tangent direction coordinate of the trajectory point set includes the second tangent direction coordinate of the position coordinate; if so, executing step S223; if not, executing step S224.

[0065] Among them, the position coordinates of the obstacle in the Frenet coordinate system are (s o , l o ),s o and l o They represent the tangent direction coordinates and normal direction coordinates of the obstacle respectively. The coordinates of the trajectory point corresponding to the planned trajectory of the current vehicle in the Frenet coordinate system are (s tj, l tj ), s tj and l tj They respectively represent the tangent direction coordinates and normal direction coordinates of the trajectory point j corresponding to the planned trajectory of the current vehicle. The value range of j is [1,M], and M is the number of trajectory points in the trajectory point set.

[0066] Specifically, obtain the first tangent direction coordinate s of each trajectory point in the trajectory point set tj , the second tangent direction coordinate s of the obstacle's position coordinate o , determine whether there is an s in the trajectory point set tj With s o If so, execute step S223. If not, execute step S224.

[0067] S223, determining that the obstacle is within a preset range of the planned trajectory, and ending the determination.

[0068] S224, determining a first trajectory point in the trajectory point set that is closest to the position coordinates, and obtaining first normal direction coordinates of the first trajectory point and second normal direction coordinates of the position coordinates.

[0069] The first trajectory point is the trajectory point in the trajectory point set that is closest to the position coordinates of the obstacle. Let the coordinates of the first trajectory point be (s t1 , l t1 ), respectively obtain the first normal direction coordinate l of the first trajectory point t1 and the second normal direction coordinate l of the obstacle's position coordinate o .

[0070] S225, if the first difference between the first normal direction coordinate and the second normal direction coordinate is less than a preset threshold, execute S223; otherwise, execute S226.

[0071] The first difference may be set according to the actual conditions of the road and the vehicle. Based on the first difference, a preset range of the planned trajectory may be determined.

[0072] Specifically, calculate the first normal direction coordinate l t1 and the second normal direction coordinate l o The first difference is determined, and by judging the magnitude relationship between the first difference and a preset threshold, it is determined that the obstacle is not within the preset range of the planned trajectory.

[0073] S226, determining that the obstacle is not within the preset range of the planned trajectory, and ending the determination.

[0074] The technical solution provided in this embodiment first determines whether the tangent direction coordinates of the obstacle are on the planned trajectory; if not, it means that the obstacle is not in front of the current vehicle, and there is no need to determine whether the normal direction coordinates of the obstacle are within the preset range of the planned trajectory. It is directly determined that the obstacle is not within the preset range of the planned trajectory, which can reduce the amount of calculation and improve the decision-making efficiency of the vehicle.

[0075] Optional, such as Figure 2C As shown, step S250, based on the motion trajectory of the obstacle and the planned trajectory of the current vehicle, determines whether the obstacle crosses in front of the current vehicle, specifically including:

[0076] S251, obtaining the starting point and the end point of the movement trajectory of the obstacle in the current prediction period, where the end point is determined based on the starting point and the movement speed of the obstacle.

[0077] Among them, the current prediction period is the same as the prediction period of the planned trajectory of the current vehicle.

[0078] Specifically, the movement speed of the obstacle is obtained through existing sensor technology. The movement speed is a vector of the packet direction. The starting point of the obstacle in the current prediction period is obtained. The end point of the obstacle's movement trajectory can be determined by combining the movement speed of the obstacle and the current prediction period.

[0079] S252, determining a second trajectory point in the trajectory point set that is closest to the position coordinates of the obstacle, and determining an angle difference between a first heading angle corresponding to the second trajectory point and a second heading angle corresponding to the motion trajectory of the obstacle.

[0080] The second trajectory point is the trajectory point in the trajectory point set that is closest to the position coordinates of the obstacle. Let the coordinates of the second trajectory point be (s t2 , l t2 ). Based on the tangent direction coordinate s of the second trajectory point t2 and the normal direction coordinate l t2 , determine the first heading angle θ corresponding to the second trajectory point 1 = atan(l t2 / s t2 );Determine the second heading angle θ based on the direction of movement of the obstacle 2 , calculate the first heading angle θ 1 and the second heading angle θ 2 The angle difference Δθ.

[0081] S253, determining whether the angle difference is greater than an angle threshold. If so, executing S254; if not, executing S255.

[0082] The angle threshold may be determined according to actual conditions of the vehicle or road, and the embodiment of the present invention does not impose any limitation on this.

[0083] S254, determining that an obstacle is crossing in front of the current vehicle.

[0084] S255, determining a first relative position between the starting point and the planned trajectory of the current vehicle, and a second relative position between the end point and the planned trajectory of the current vehicle.

[0085] Specifically, determine the first relative position of the starting point and the planned trajectory of the current vehicle, that is, whether the starting point is located on the left or right side of the planned trajectory of the current vehicle; and the second relative position of the end point and the planned trajectory of the current vehicle, that is, whether the end point is located on the left or right side of the planned trajectory of the current vehicle.

[0086] S256, based on the first relative position and the second relative position, determine whether the starting point and the end point are on the same side of the planned trajectory of the current vehicle, if so, execute step S257; if not, execute S254;

[0087] Specifically, if the starting point and the end point are both located on the left side of the planned trajectory of the current vehicle, or if the starting point and the end point are both located on the right side of the planned trajectory of the current vehicle, it is determined that the starting point and the end point are on the same side of the planned trajectory of the current vehicle, and step S257 is executed; otherwise, the starting point and the end point are on opposite sides of the planned trajectory of the current vehicle, and step S254 is executed.

[0088] S257, determining that an obstacle is not crossing in front of the current vehicle.

[0089] Optionally, determining the relative position of the target point and the planned trajectory of the current vehicle includes:

[0090] Determine a third trajectory point in the trajectory point set that is closest to the target point;

[0091] Acquire the third normal direction coordinate of the third trajectory point and the fourth normal direction coordinate of the target point;

[0092] Calculating a second difference between the third normal direction coordinate and the fourth normal direction coordinate;

[0093] Determining a relative position of the target point and the planned trajectory of the current vehicle based on the second difference;

[0094] The target point includes: the starting point or the end point, and the relative position includes: a first relative position corresponding to the starting point or a second relative position corresponding to the end point.

[0095] Specifically, the method of determining the first relative position between the starting point and the planned trajectory of the current vehicle and the method of determining the second relative position between the end point and the planned trajectory of the current vehicle are basically the same. Therefore, taking the determination of the first relative position between the starting point and the planned trajectory of the current vehicle as an example, step S255 specifically includes:

[0096] S2551, determining a third trajectory point in the trajectory point set that is closest to the starting point.

[0097] The third trajectory point is the trajectory point in the trajectory point set that is closest to the position coordinates of the starting point. Suppose the coordinates of the starting point of the obstacle's motion trajectory in the current prediction period are (s o1 , l o1 ), the coordinates of the third trajectory point are (s t3 , l t3 ).

[0098] S2552, calculating a second difference between the third normal direction coordinate of the third trajectory point and the fourth normal direction coordinate of the starting point.

[0099] Specifically, the third normal direction coordinate of the third trajectory point is l t3 , the second difference of the fourth normal direction coordinate of the starting point is l o1 , the second difference is Δl=l t3 -l o1 .

[0100] S2553: Determine a first relative position between the starting point and the planned trajectory of the current vehicle based on the second difference.

[0101] Exemplarily, if the second difference is less than zero, it is determined that the starting point is located on the left side of the planned trajectory of the current vehicle, and if the second difference is greater than zero, it is determined that the starting point is located on the right side of the planned trajectory of the current vehicle.

[0102] Determining the second relative position between the end point and the planned trajectory of the current vehicle is the same as the above step, and will not be described in detail in this embodiment of the present invention.

[0103] Embodiment 3

[0104] Figure 3 This is a flow chart of an automatic driving decision-making method in Embodiment 3 of the present invention. This embodiment is further optimized based on the above embodiment.

[0105] S310, obtaining obstacle information and the planned trajectory of the current vehicle.

[0106] S320: Determine whether the obstacle is within a preset range of the planned trajectory.

[0107] S330: If the obstacle is within a preset range of the planned trajectory, the decision behavior of the current vehicle in the current decision cycle is determined based on the static and dynamic states of the obstacle.

[0108] S340: Obtain an obstacle identification number of the obstacle.

[0109] When the current vehicle senses an obstacle for the first time in the current cycle, it assigns an obstacle identification number to the obstacle to mark each obstacle.

[0110] S350, determining whether the obstacle identification number can be found in the historical decision information of the current vehicle; the historical decision information includes the historical decision behavior determined when the current vehicle encounters an obstacle.

[0111] When the current vehicle senses an obstacle for the first time in the current cycle, it will assign an obstacle identification number to the obstacle to mark each obstacle. The historical decision-making behaviors include: detouring or stopping to avoid.

[0112] Specifically, the vehicle can automatically record the decision-making behaviors performed when encountering an obstacle within a preset number of decision cycles, and constitute historical decision information, that is, the historical decision information includes the decision-making behaviors determined when the vehicle encounters a certain obstacle within a preset number of decision cycles before the current decision cycle.

[0113] The historical decision information is queried based on the obstacle identification number of the obstacle, and it is determined whether the historical decision information can query the obstacle identification number.

[0114] S360: If not, maintain the current vehicle's decision behavior in the current cycle as detour avoidance.

[0115] Specifically, if the obstacle identification number cannot be found in the historical decision information, it means that the obstacle appears for the first time in the current cycle and a decision behavior has never been determined for this obstacle. Therefore, the decision behavior of the current vehicle in the current cycle is maintained.

[0116] S370: If yes, then based on the obstacle identification number, obtain the historical decision-making behavior of the current vehicle when encountering the obstacle, and correct the decision-making behavior of the current vehicle in the current decision cycle based on the historical decision-making behavior.

[0117] Specifically, if the obstacle identification number can be found in the historical decision information, it means that the obstacle does not appear for the first time in the current cycle. The historical decision information is queried through the obstacle identification number to obtain the historical decision behavior of the current vehicle when encountering the obstacle, and the decision behavior of the current vehicle in the current decision cycle is further corrected based on the historical decision behavior.

[0118] The technical solution of this embodiment obtains obstacle information and the planned trajectory of the current vehicle; determines whether the obstacle is within the preset range of the planned trajectory; if the obstacle is within the preset range of the planned trajectory, determines the decision behavior of the current vehicle in the current decision cycle based on the static and dynamic states of the obstacle; obtains the obstacle identification number of the obstacle, and determines whether the obstacle identification number can be queried in the historical decision information of the current vehicle; if not, maintains the decision behavior of the current vehicle in the current cycle as detour avoidance; if so, obtains the historical decision behavior of the current vehicle when encountering the obstacle based on the obstacle identification number, and corrects the decision behavior of the current vehicle in the current decision cycle based on the historical decision behavior, which can reduce the frequent parking and avoidance of the autonomous driving vehicle when facing pedestrians while ensuring traffic safety, and further realizes the correction of the decision behavior of the current decision cycle in combination with the historical decision information of the vehicle on the obstacle, so as to minimize the frequent changes of the vehicle's decision behavior between parking and avoidance and detour avoidance, further improve the driving stability and riding comfort of the autonomous driving vehicle, and improve the operation efficiency and smoothness of the traffic flow.

[0119] Optionally, step S370, correcting the decision-making behavior of the current vehicle in the current decision cycle based on the historical decision-making behavior, includes:

[0120] If the historical decision behavior is the same as the decision behavior of the current decision cycle, then the decision behavior of the current decision cycle is maintained;

[0121] If the historical decision behavior is different from the decision behavior of the current decision cycle, the decision count corresponding to the historical decision behavior is increased by one;

[0122] If the decision count is less than a preset value, the decision behavior of the current decision cycle is maintained;

[0123] If the decision count is greater than or equal to a preset value, the decision behavior of the current vehicle in the current decision cycle is corrected to the historical decision behavior.

[0124] Specifically, determine whether the historical decision behavior is the same as the decision behavior of the current cycle. If they are the same, maintain the decision behavior of the current decision cycle. Because the static and dynamic states of movable obstacles on the road, such as pedestrians, are instantaneous and changeable, if they are different, the decision count corresponding to the historical decision behavior is increased by one, wherein the decision count is used to count the number of cycles of historical decision behaviors determined by the vehicle when encountering obstacles. And based on the decision count of the historical decision behavior determined by the vehicle for the obstacle, further determine whether to correct the decision behavior of the current cycle. If the decision count is less than the preset value, maintain the decision behavior of the current decision cycle; if the decision count is greater than or equal to the preset value, the decision behavior of the current vehicle in the current decision cycle is corrected to the historical decision behavior.

[0125] Exemplarily, the initial value of the initial historical decision behavior is set to 0, and the preset value is 3. If the decision behavior of the first decision cycle determined by the current vehicle for the obstacle with the obstacle identification number 001 is detour avoidance, and the historical decision information finds that the historical decision behavior determined by the current vehicle for the obstacle with the obstacle identification number 001 is parking avoidance, and the historical decision behavior is different from the decision behavior of the current decision cycle, the decision count of parking avoidance is increased by 1, and the decision count of parking avoidance is 1 at this time, and the decision behavior of the current decision cycle is maintained as detour avoidance. If the decision behaviors determined in the second decision cycle are all parking avoidance, which is different from the decision behavior of the first decision cycle, the decision count of parking avoidance is increased by 1, and the decision count of parking avoidance is 2 at this time; if the decision behaviors determined in the third decision cycle are all detour avoidance, which is different from the decision behavior of the second decision cycle, the decision count of parking avoidance is increased by 1, and the decision count of parking avoidance is 3 at this time; the decision count of parking avoidance is equal to the preset value, and the decision behavior of the current vehicle in the current decision cycle is corrected from detour avoidance to historical decision behavior, that is, parking avoidance.

[0126] The advantage of doing this is that when the decision behavior of the current decision cycle repeatedly changes due to changes in the state of obstacles, the decision behavior of the current decision cycle can be corrected based on the historical decision behavior, avoiding the current vehicle's decision behavior from frequently switching between parking avoidance and detour avoidance, thereby improving the driving stability and riding comfort of the autonomous driving car, and thus also improving the operating efficiency and smoothness of the traffic flow.

[0127] Optionally, if the historical decision behavior is the same as the decision behavior of the current decision cycle, then maintaining the decision behavior of the current decision cycle further includes:

[0128] If the decision behavior of the current decision cycle is detour avoidance, the parking avoidance decision count corresponding to the obstacle identification number is cleared;

[0129] If the decision behavior of the current decision cycle is parking avoidance, the detour avoidance decision count corresponding to the obstacle identification number is cleared.

[0130] Specifically, if the historical decision behavior and the decision behavior of the current decision cycle are both detour avoidance, the decision behavior of the current decision cycle is maintained as detour avoidance, and the parking avoidance decision count corresponding to the obstacle identification number is cleared; if the historical decision behavior and the decision behavior of the current decision cycle are both parking avoidance, the decision behavior of the current decision cycle is maintained as parking avoidance, and the detour avoidance decision count corresponding to the obstacle identification number is cleared.

[0131] The advantage of doing this is that if the historical decision behavior is the same as the decision behavior of the current decision cycle, the count of the other decision behavior will be cleared and the counting will start from zero, avoiding the historical decision behavior from over-correcting the decision behavior of the current decision cycle, so that the current vehicle can make adaptive decision behaviors as the obstacle information changes.

[0132] Embodiment 4

[0133] Figure 4 This is a schematic diagram of the structure of an automatic driving decision-making device provided in the third embodiment of the present invention. This embodiment can be applied to the situation where a vehicle automatically makes a decision when encountering an obstacle on an urban road. The device can be implemented in software and / or hardware. The device can be integrated in a vehicle, such as Figure 4 As shown, the autonomous driving decision-making device specifically includes: a first acquisition module 410, a judgment module 420 and a first decision module 430.

[0134] A first acquisition module 410 is used to acquire obstacle information and a planned trajectory of the current vehicle;

[0135] A determination module 420 is used to determine whether the obstacle is within a preset range of the planned trajectory;

[0136] The first decision module 430 is used to determine the decision behavior of the current vehicle in the current decision cycle based on the static and dynamic states of the obstacle if the obstacle is within a preset range of the planned trajectory.

[0137] Optionally, the obstacle information includes at least one of the following: position coordinates, size, movement speed, movement direction and movement trajectory of the obstacle;

[0138] The position coordinates are the coordinates of the obstacle in the Frenet coordinate system, which is a coordinate system established based on the tangent vector and normal vector of the reference line with the lane centerline as the reference line; the coordinates in the Frenet coordinate system include: tangent direction coordinates and normal direction coordinates.

[0139] Optionally, the determination module 420 is specifically configured to:

[0140] Determine a trajectory point set corresponding to the planned trajectory, where the trajectory point set is a point set consisting of trajectory points of the current vehicle in a Frenet coordinate system;

[0141] Determine whether the first tangent direction coordinate of the trajectory point set contains the second tangent direction coordinate of the position coordinate;

[0142] If so, determining that the obstacle is within a preset range of the planned trajectory;

[0143] If not, determining a first trajectory point in the trajectory point set that is closest to the position coordinates, and obtaining a first normal direction coordinate of the first trajectory point and a second normal direction coordinate of the position coordinates;

[0144] If a first difference between the first normal direction coordinate and the second normal direction coordinate is less than a preset threshold, it is determined that the obstacle is within a preset range of the planned trajectory.

[0145] Optionally, the first decision module 430 includes:

[0146] A determination unit, used to determine the static and dynamic states of the obstacle;

[0147] A first decision unit is used to determine that the decision behavior of the current vehicle in the current decision cycle is to bypass and avoid the obstacle if the obstacle is in a stationary state;

[0148] The second decision unit is used to determine whether the obstacle is crossing in front of the current vehicle based on the movement trajectory of the obstacle and the planned trajectory of the current vehicle if the obstacle is in motion, and determine the decision behavior of the current vehicle in the current decision cycle based on the judgment result.

[0149] Optionally, the second decision unit includes:

[0150] An acquisition subunit, used to acquire a starting point and an end point of a movement trajectory of the obstacle in a current prediction period, wherein the end point is determined based on the starting point and a movement speed of the obstacle;

[0151] A first determining subunit is used to determine a second trajectory point in the trajectory point set that is closest to the position coordinates of the obstacle, and determine an angle difference between a first heading angle corresponding to the second trajectory point and a second heading angle corresponding to the motion trajectory of the obstacle;

[0152] a second determination subunit, configured to determine that the obstacle is crossing in front of the current vehicle if the angle difference is greater than an angle threshold;

[0153] The third determination subunit is used to determine whether an obstacle is crossing in front of the current vehicle based on a first relative position of the starting point and the planned trajectory of the current vehicle, and a second relative position of the end point and the planned trajectory of the current vehicle if the angle difference is less than or equal to an angle threshold.

[0154] Optionally, the third determining subunit is specifically configured to:

[0155] Determining a first relative position of the starting point and the planned trajectory of the current vehicle, and a second relative position of the end point and the planned trajectory of the current vehicle;

[0156] Based on the first relative position and the second relative position, determining whether the starting point and the end point are on the same side of the planned trajectory of the current vehicle;

[0157] If yes, determining that the obstacle is crossing in front of the current vehicle;

[0158] If not, it is determined that the obstacle is not crossing in front of the current vehicle.

[0159] Optionally, the third determining subunit is further used to:

[0160] Determine a third trajectory point in the trajectory point set that is closest to the target point;

[0161] Calculating a second difference between a third normal direction coordinate of the third trajectory point and a fourth normal direction coordinate of the starting point;

[0162] Determining a relative position of the target point and the planned trajectory of the current vehicle based on the second difference;

[0163] The target point includes: the starting point or the end point, and the relative position includes: a first relative position corresponding to the starting point or a second relative position corresponding to the end point.

[0164] Optionally, the second decision unit is specifically configured to:

[0165] If the judgment result is that the obstacle crosses in front of the current vehicle, determining that the decision behavior of the current vehicle in the current decision cycle is to stop and avoid;

[0166] If the judgment result is that the obstacle is not crossing in front of the current vehicle, it is determined that the decision behavior of the current vehicle in the current decision cycle is to detour and avoid.

[0167] Optionally, the device further comprises:

[0168] A second acquisition module, configured to acquire an obstacle identification number of the obstacle after determining a decision behavior of the current vehicle in a current decision cycle;

[0169] A determination module, used to determine whether the obstacle identification number can be found in the historical decision information of the current vehicle; the historical decision information includes the historical decision behavior determined when the current vehicle encounters an obstacle;

[0170] A maintaining module, configured to maintain the decision behavior of the current vehicle in the current cycle if the obstacle identification number cannot be found in the historical decision information of the current vehicle;

[0171] A correction module is used to obtain the historical decision-making behavior of the current vehicle when encountering the obstacle based on the obstacle identification number if the obstacle identification number can be queried in the historical decision-making information of the current vehicle, and to correct the decision-making behavior of the current vehicle in the current decision cycle based on the historical decision-making behavior.

[0172] Optionally, the correction module includes:

[0173] If the historical decision behavior is the same as the decision behavior of the current decision cycle, then the decision behavior of the current decision cycle is maintained;

[0174] If the historical decision behavior is different from the decision behavior of the current decision cycle, the decision count corresponding to the historical decision behavior is increased by one;

[0175] If the decision count is less than a preset value, the decision behavior of the current decision cycle is maintained;

[0176] If the decision count is greater than or equal to a preset value, the decision behavior of the current vehicle in the current decision cycle is corrected to the historical decision behavior.

[0177] Optionally, the correction module further includes:

[0178] A first clearing unit is used for, if the historical decision behavior is the same as the decision behavior of the current decision cycle, maintaining the decision behavior of the current decision cycle, and if the decision behavior of the current decision cycle is detour avoidance, clearing the parking avoidance decision count corresponding to the obstacle identification number;

[0179] The second clearing unit is used to clear the detour avoidance decision count corresponding to the obstacle identification number if the decision behavior of the current decision cycle is parking avoidance.

[0180] Optionally, the device further comprises:

[0181] The second decision module is used to determine that the decision behavior of the current vehicle in the current decision cycle is to travel along the planned trajectory if the obstacle is not within a preset range of the planned trajectory.

[0182] The above-mentioned product can execute the autonomous driving decision-making method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0183] Embodiment 5

[0184] Figure 5 A structural block diagram of a vehicle provided in Embodiment 5 of the present invention is shown in FIG. Figure 5As shown, the vehicle includes a processor 510, a memory 520, an input device 530, and an output device 540; the number of processors 510 in the vehicle can be one or more. Figure 5 A processor 510 is taken as an example; the processor 510, the memory 520, the input device 530 and the output device 540 in the vehicle can be connected via a bus or other means. Figure 5 The example of connecting through bus is taken in the following.

[0185] The memory 520, as a computer-readable storage medium, can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the automatic driving decision-making method in the embodiment of the present invention (for example, the first acquisition module 410, the judgment module 420 and the first decision module 430 in the automatic driving decision-making device). The processor 510 executes various functional applications and data processing of the vehicle by running the software programs, instructions and modules stored in the memory 520, that is, realizes the above-mentioned automatic driving decision-making method.

[0186] The memory 520 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 520 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 520 may further include a memory remotely arranged relative to the processor 510, and these remote memories may be connected to the vehicle via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0187] The input device 530 may be used to sense the environment around the vehicle and obtain the vehicle's positioning information, such as acquisition devices such as radar, speed sensor, image sensor, etc. The output device 540 may include a vehicle system that performs decision-making actions, such as a braking system, steering system, or other vehicle control systems.

[0188] Embodiment 5

[0189] Embodiment 5 of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the automatic driving decision-making method provided in all the embodiments of the invention of this application is implemented: obtaining obstacle information and the planned trajectory of the current vehicle; determining whether the obstacle is within a preset range of the planned trajectory; if the obstacle is within the preset range of the planned trajectory, determining the decision-making behavior of the current vehicle in the current decision cycle based on the static and dynamic state of the obstacle.

[0190] Any combination of one or more computer-readable media can be used. Computer-readable media can be computer-readable signal media or computer-readable storage media. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: electrical connections with one or more wires, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this document, computer-readable storage media can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0191] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0192] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0193] Computer program code for performing the operation of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0194] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. An automatic driving decision-making method, characterized in that: include: Obtain obstacle information and the planned trajectory of the current vehicle; Determining whether the obstacle is within a preset range of the planned trajectory; If the obstacle is within a preset range of the planned trajectory, determining the decision behavior of the current vehicle in the current decision cycle based on the static and dynamic states of the obstacle; Wherein, the obstacle information includes the position coordinates of the obstacle; The position coordinates are the coordinates of the obstacle in the Frenet coordinate system, which is a coordinate system established based on the tangent vector and normal vector of the reference line and the center line of the lane as a reference line; the coordinates in the Frenet coordinate system include: tangent direction coordinates and normal direction coordinates; Wherein, the determining whether the obstacle is within a preset range of the planned trajectory includes: Determine a trajectory point set corresponding to the planned trajectory, where the trajectory point set is a point set consisting of trajectory points of the current vehicle in a Frenet coordinate system; Determine whether the first tangent direction coordinate of the trajectory point set contains the second tangent direction coordinate of the position coordinate; If so, determining that the obstacle is within a preset range of the planned trajectory; If not, determining a first trajectory point in the trajectory point set that is closest to the position coordinates, and obtaining a first normal direction coordinate of the first trajectory point and a second normal direction coordinate of the position coordinates; If a first difference between the first normal direction coordinate and the second normal direction coordinate is less than a preset threshold, it is determined that the obstacle is within a preset range of the planned trajectory.

2. The method according to claim 1, characterized in that The obstacle information includes at least one of the following: the size, movement speed, movement direction and movement trajectory of the obstacle.

3. The method according to claim 1, characterized in that Determining a decision behavior of the current vehicle in a current decision cycle based on the static and dynamic states of the obstacle includes: determining the static and dynamic states of the obstacle; If the obstacle is stationary, determining that the decision behavior of the current vehicle in the current decision cycle is to bypass and avoid the obstacle; If the obstacle is in motion, it is determined whether the obstacle crosses in front of the current vehicle based on the motion trajectory of the obstacle and the planned trajectory of the current vehicle, and the decision behavior of the current vehicle in the current decision cycle is determined based on the judgment result.

4. The method according to claim 3, characterized in that The determining, based on the motion trajectory of the obstacle and the planned trajectory of the current vehicle, whether the obstacle crosses in front of the current vehicle comprises: Acquire a starting point and an end point of a movement trajectory of the obstacle in a current prediction period, wherein the end point is determined based on the starting point and a movement speed of the obstacle; Determine a second trajectory point in the trajectory point set that is closest to the position coordinates of the obstacle, and determine an angle difference between a first heading angle corresponding to the second trajectory point and a second heading angle corresponding to the motion trajectory of the obstacle; If the angle difference is greater than an angle threshold, it is determined that the obstacle is crossing in front of the current vehicle; If the angle difference is less than or equal to the angle threshold, it is determined whether an obstacle crosses in front of the current vehicle based on a first relative position between the starting point and the planned trajectory of the current vehicle and a second relative position between the end point and the planned trajectory of the current vehicle.

5. The method according to claim 4, characterized in that Determining whether an obstacle crosses in front of the current vehicle based on a first relative position of the starting point and the planned trajectory of the current vehicle and a second relative position of the end point and the planned trajectory of the current vehicle includes: Determining a first relative position of the starting point and the planned trajectory of the current vehicle, and a second relative position of the end point and the planned trajectory of the current vehicle; Based on the first relative position and the second relative position, determining whether the starting point and the end point are on the same side of the planned trajectory of the current vehicle; If yes, determining that the obstacle is crossing in front of the current vehicle; If not, it is determined that the obstacle is not crossing in front of the current vehicle.

6. The method according to claim 5, characterized in that Determining the relative position of the target point and the planned trajectory of the current vehicle includes: Determine a third trajectory point in the trajectory point set that is closest to the target point; Calculating a second difference between a third normal direction coordinate of the third trajectory point and a fourth normal direction coordinate of the starting point; Determining a relative position of the target point and the planned trajectory of the current vehicle based on the second difference; The target point includes: the starting point or the end point, and the relative position includes: a first relative position corresponding to the starting point or a second relative position corresponding to the end point.

7. The method according to claim 3, characterized in that The determining of the decision behavior of the current vehicle in the current decision cycle based on the judgment result includes: If the judgment result is that the obstacle crosses in front of the current vehicle, determining that the decision behavior of the current vehicle in the current decision cycle is to stop and avoid; If the judgment result is that the obstacle is not crossing in front of the current vehicle, it is determined that the decision behavior of the current vehicle in the current decision cycle is to detour and avoid.

8. The method according to any one of claims 1 to 7, characterized in that: After determining the decision behavior of the current vehicle in the current decision cycle, the method further includes: Obtaining an obstacle identification number of the obstacle; Determine whether the obstacle identification number can be found in the historical decision information of the current vehicle; the historical decision information includes the historical decision behavior determined when the current vehicle encounters the obstacle; If not, maintaining the decision-making behavior of the current vehicle in the current cycle; If so, based on the obstacle identification number, the historical decision-making behavior of the current vehicle when encountering the obstacle is obtained, and the decision-making behavior of the current vehicle in the current decision cycle is corrected based on the historical decision-making behavior.

9. The method according to claim 8, characterized in that Modifying the decision behavior of the current vehicle in the current decision cycle based on the historical decision behavior includes: If the historical decision behavior is the same as the decision behavior of the current decision cycle, then the decision behavior of the current decision cycle is maintained; If the historical decision behavior is different from the decision behavior of the current decision cycle, the decision count corresponding to the historical decision behavior is increased by one; If the decision count is less than a preset value, the decision behavior of the current decision cycle is maintained; If the decision count is greater than or equal to a preset value, the decision behavior of the current vehicle in the current decision cycle is corrected to the historical decision behavior.

10. The method according to claim 9, characterized in that If the historical decision behavior is the same as the decision behavior of the current decision cycle, then the decision behavior of the current decision cycle is maintained, further comprising: If the decision behavior of the current decision cycle is detour avoidance, the parking avoidance decision count corresponding to the obstacle identification number is cleared; If the decision behavior of the current decision cycle is parking avoidance, the detour avoidance decision count corresponding to the obstacle identification number is cleared.

11. The method according to claim 1, characterized in that: Also includes: If the obstacle is not within the preset range of the planned trajectory, it is determined that the decision behavior of the current vehicle in the current decision cycle is to travel along the planned trajectory.

12. An automatic driving decision-making device, characterized in that: include: The first acquisition module is used to acquire obstacle information and the planned trajectory of the current vehicle; wherein the obstacle information includes the position coordinates of the obstacle; the position coordinates are the coordinates of the obstacle in the Frenet coordinate system, the Frenet coordinate system is a coordinate system established based on the tangent vector and normal vector of the reference line with the lane center line as the reference line; the coordinates in the Frenet coordinate system include: tangent direction coordinates and normal direction coordinates; A judgment module, used to judge whether the obstacle is within a preset range of the planned trajectory; A first decision module, configured to determine a decision behavior of the current vehicle in a current decision cycle based on a static or dynamic state of the obstacle if the obstacle is within a preset range of the planned trajectory; Wherein, the judging module is used to: Determine a trajectory point set corresponding to the planned trajectory, where the trajectory point set is a point set composed of trajectory points of the current vehicle in the Frenet coordinate system; determine whether the first tangent direction coordinate of the trajectory point set contains the second tangent direction coordinate of the position coordinate; if so, determine that the obstacle is within a preset range of the planned trajectory; if not, determine the first trajectory point in the trajectory point set that is closest to the position coordinate, and obtain the first normal direction coordinate of the first trajectory point and the second normal direction coordinate of the position coordinate; if a first difference between the first normal direction coordinate and the second normal direction coordinate is less than a preset threshold, determine that the obstacle is within the preset range of the planned trajectory.

13. A vehicle, characterized in that: It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the automatic driving decision method as described in any one of claims 1 to 11 is implemented.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, it implements the automatic driving decision-making method as described in any one of claims 1-11.

Images