Parallel risk-based way-giving strategy determination method and determination device

Abstract

The invention relates to the technical field of automatic driving, and provides a parallel risk-based way-giving strategy determination method and determination device. According to the method, planning path information and environment information of a target moving object are obtained, a risk moving object is determined based on the planning path information and the environment information, and defensive deceleration of the target moving object relative to the risk moving object is determined. And constructing a stress model of the target moving object at least based on the defensive deceleration and the expected motion parameters of the target moving object, determining the expected deceleration of the target moving object based on the stress model, and finally determining a way giving strategy of the target moving object based on the expected deceleration. The invention provides an effective way-giving strategy for formulating the automatic driving vehicle aiming at the parallel risk, and further improves the decision-making efficiency of the automatic driving vehicle.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a method and device for determining a yielding strategy based on parallel risk. Background Art

[0002] During the operation of an autonomous vehicle, special attention should be paid to avoid driving side by side with other vehicles. This is because driving side by side for a long time will significantly reduce the lateral space between the two vehicles, which may lead to insufficient space for escape in the event of an emergency, increasing the risk of accidents. In addition, at higher speeds, even a slight deviation in direction may lead to a drastic change in the driving trajectory, bringing a higher risk of scratches and collisions to vehicles driving side by side.

[0003] However, there is no good solution in the relevant technology on how to formulate a yielding strategy for autonomous driving vehicles to address parallel risks. Summary of the invention

[0004] In view of this, an embodiment of the present application provides a method and device for determining a yielding strategy based on parallel risk to solve the problem of imperfect autonomous driving yielding strategies in the prior art.

[0005] A first aspect of an embodiment of the present application provides a method for determining a yield strategy based on parallel risk, comprising:

[0006] Obtaining the planned path information and environmental information of the target moving object;

[0007] Determine a risky mobile object based on the planned path information and the environmental information, where the risky mobile object is a mobile object whose included angle between the moving direction and the moving direction of the target mobile object is less than a preset angle threshold and whose predicted trajectory conflicts with the planned path of the target mobile object;

[0008] Determine the defensive deceleration of the target moving object relative to the risk moving object;

[0009] constructing a force model of the target moving object based at least on the defensive deceleration and the expected motion parameters of the target moving object;

[0010] An expected deceleration of the target moving object is determined based on the force model, and a yielding strategy of the target moving object is determined based on the expected deceleration.

[0011] A second aspect of the embodiments of the present application provides a device for determining a yield strategy based on parallel risk, including:

[0012] An acquisition module is configured to acquire planning path information and environment information of a target mobile object;

[0013] A determination module is configured to determine a risky mobile object based on the planned path information and the environmental information, wherein the risky mobile object is a mobile object that has a similar travel direction to the target mobile object and has a conflict risk;

[0014] The determination module is further configured to determine a defensive deceleration of the target mobile object relative to the risk mobile object;

[0015] A construction module configured to construct a force model of the target moving object based at least on the defensive deceleration and the expected motion parameters of the target moving object;

[0016] The determination module is further configured to determine an expected deceleration of the target moving object based on the force model, and determine a yielding strategy of the target moving object based on the expected deceleration.

[0017] The beneficial effects of the embodiments of the present application compared with the prior art are as follows: the embodiments of the present application obtain the planned path information and environmental information of the target mobile object, determine the risky mobile object based on the planned path information and environmental information, determine the defensive deceleration of the target mobile object relative to the risky mobile object, construct a force model of the target mobile object based at least on the defensive deceleration and the expected motion parameters of the target mobile object, determine the expected deceleration of the target mobile object based on the force model, and finally determine the yielding strategy of the target mobile object based on the expected deceleration, thereby proposing an effective yielding strategy for autonomous driving vehicles for parallel risks, and further improving the efficiency of decision-making of autonomous driving vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 It is a flowchart of a method for determining a yield strategy based on parallel risks provided in an embodiment of the present application.

[0020] Figure 2 It is a flowchart of a method for determining risky mobile objects based on planned path information and environmental information provided in an embodiment of the present application.

[0021] Figure 3 It is a schematic diagram of another method for determining risky moving objects provided in an embodiment of the present application.

[0022] Figure 4 It is a flowchart of a method for determining the defensive deceleration of a target moving object relative to a risk moving object provided in an embodiment of the present application.

[0023] Figure 5 It is a schematic diagram of the motion trajectories of a target moving object and a risk moving object in a target coordinate system provided by an embodiment of the present application.

[0024] Figure 6 It is a force analysis diagram of a target moving object provided in an embodiment of the present application.

[0025] Figure 7 It is a schematic diagram of force analysis when the backward moving object provided by an embodiment of the present application includes two backward moving objects behind it.

[0026] Figure 8 It is a schematic diagram of force analysis when there are multiple backward-moving objects behind the backward-moving object provided by an embodiment of the present application.

[0027] Fig. 9 It is a flowchart of another method for determining a yield strategy based on parallel risks provided in an embodiment of the present application.

[0028] Fig.10 It is a schematic diagram of a parallel risk-based yield strategy determination device provided in an embodiment of the present application.

[0029] Fig.11 It is a schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0031] A method and device for determining a yield strategy based on parallel risk according to an embodiment of the present application will be described in detail below with reference to the accompanying drawings.

[0032] As mentioned above, during the operation of autonomous driving vehicles, special attention should be paid to avoid driving side by side with other vehicles. In related technologies, the state of driving side by side is usually broken by controlling the unmanned vehicle to slow down or brake appropriately, forming a staggered structure, and then continuing to drive with the vehicle. This processing method can not only increase the lateral risk avoidance space, but also effectively reduce the risk of scratches caused by directional deviation and improve driving safety. However, when controlling the deceleration of the unmanned vehicle, how to determine the deceleration parameters, such as the deceleration rate, is a technical problem that needs to be solved.

[0033] In view of this, an embodiment of the present application provides a method for determining a yielding strategy based on parallel risks, by acquiring the planned path information and environmental information of the target moving object, determining the risky moving object based on the planned path information and environmental information, determining the defensive deceleration of the target moving object relative to the risky moving object, constructing a force model of the target moving object based at least on the defensive deceleration and the expected motion parameters of the target moving object, and determining the expected deceleration of the target moving object based on the force model, and finally determining the yielding strategy of the target moving object based on the expected deceleration, thereby proposing an effective yielding strategy for autonomous driving vehicles for parallel risks, and further improving the efficiency of decision-making of autonomous driving vehicles.

[0034] Figure 1 is a flow chart of a method for determining a yield strategy based on parallel risk provided in an embodiment of the present application. Figure 1 As shown, the method comprises the following steps:

[0035] In step S101, the planned path information and environment information of the target mobile object are obtained.

[0036] In step S102, risky mobile objects are determined based on the planned path information and environmental information.

[0037] The risky mobile object is a mobile object whose included angle between the moving direction and the moving direction of the target mobile object is less than a preset angle threshold, and whose predicted trajectory conflicts with the planned path of the target mobile object.

[0038] In step S103 , the defensive deceleration of the target mobile object relative to the risk mobile object is determined.

[0039] In step S104, a force model of the target moving object is constructed based on at least the defensive deceleration and the expected motion parameters of the target moving object.

[0040] In step S105, the expected deceleration of the target moving object is determined based on the force model, and the yielding strategy of the target moving object is determined based on the expected deceleration.

[0041] In certain embodiments of the present application, the method may be executed by a server or a terminal with certain computing capabilities to determine a yield strategy of a target mobile object based on parallel risk. The target mobile object may be an autonomous vehicle, a robot, or other mobile object, which is not limited here.

[0042] In certain embodiments of the present application, the planned path information and environmental information of the target mobile object may be first obtained. The planned path information may be obtained from the path planning module of the target mobile object, and the environmental information may be collected by the target mobile object itself, or received by the server from the target mobile object, other traffic participants, and roadside devices, and then sent to the target mobile object, or collected by the roadside device itself or received from the server or other traffic participants and then sent to the target mobile object, without limitation here.

[0043] In some embodiments, risky mobile objects can be determined based on planned path information and environmental information. Among them, risky mobile objects are mobile objects whose moving direction and the moving direction of the target mobile object have an angle less than a preset angle threshold, and whose predicted trajectory conflicts with the planned path of the target mobile object. In other words, risky mobile objects can be regarded as "side-by-side" obstacles that are approximately parallel to the vehicle.

[0044] In some embodiments, after the risky moving object is determined, the defensive deceleration of the target moving object relative to the risky moving object can be determined to avoid the risk of collision between the two. Furthermore, a force model of the target moving object can be constructed based on the determined defensive deceleration and the expected motion parameters of the target moving object, and the expected deceleration of the target moving object can be determined based on the force model, and then the yielding strategy of the target moving object can be determined based on the expected deceleration. For example, the target moving object is controlled to travel at the determined expected deceleration.

[0045] According to the technical solution provided in the embodiments of the present application, by acquiring the planned path information and environmental information of the target mobile object, determining the risky mobile object based on the planned path information and environmental information, determining the defensive deceleration of the target mobile object relative to the risky mobile object, constructing a force model of the target mobile object based at least on the defensive deceleration and the expected motion parameters of the target mobile object, and determining the expected deceleration of the target mobile object based on the force model, and finally determining the yielding strategy of the target mobile object based on the expected deceleration, an effective yielding strategy for autonomous driving vehicles for parallel risks is proposed, which further improves the decision-making efficiency of autonomous driving vehicles.

[0046] In certain embodiments of the present application, the environmental information includes at least a mobile object traveling side by side with the target mobile object, and the mobile object traveling side by side is a mobile object whose moving direction and the moving direction of the target mobile object have an angle less than a preset angle threshold. It can be understood that the mobile object traveling side by side to be considered can be a mobile object whose distance from the target mobile object is less than a preset threshold, such as a mobile object whose tail of the outer contour line and the head of the outer contour line of the target mobile object are less than a first preset threshold, and a mobile object whose head of the outer contour line and the tail of the outer contour line of the target mobile object are less than a second preset threshold. The distance here can be an absolute value of the distance, and the values ​​of the first preset threshold and the second preset threshold can be set according to actual needs, and are not limited here.

[0047] Figure 2 is a flow chart of a method for determining a risky mobile object based on planned path information and environmental information provided by an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:

[0048] In step S201, the target moving object is represented by n decomposition circles with the same radius.

[0049] Wherein, n is a positive integer.

[0050] In step S202, starting from the center of each decomposition circle, n line segments are drawn along the normal direction of the target moving object's travel direction, and the length of each line segment is a preset distance threshold.

[0051] In step S203, a moving object whose outer contour intersects at least one of the n line segments is determined as a risky moving object.

[0052] In certain embodiments of the present application, moving objects can be divided into three categories: moving objects in the forward direction of the driving path, moving objects in the backward direction of the driving path, and surrounding interactive moving objects. We define risky moving objects as moving objects that have a similar driving direction to the target moving object and will conflict with it in the future. For obstacles whose predicted trajectories have conflicting information with the driving path of the target moving object in the current state, the existing methods can handle them well. For "side-by-side" obstacles that are approximately parallel to the target moving object, it is necessary to slow down appropriately and keep a longitudinal distance from it to ensure driving safety.

[0053] The target moving object is represented by n decomposition circles with the same radius, and then n line segments are drawn from the center of each decomposition circle along the normal direction of the target moving object's travel direction, and the length of each line segment is the preset distance threshold. Finally, the moving object whose outer contour intersects with at least one of the n line segments can be determined as a risky moving object.

[0054] Figure 3FIG. 1 is a schematic diagram of another method for determining a risky mobile object provided by an embodiment of the present application. Figure 3 As shown in Figure 1, the target moving object is represented by three decomposition circles with the same radius r. The centers of the three decomposition circles are o1, o2, and o3 respectively. The length of the target moving object is l, the width is w, and the tangent direction of its driving direction is The normal direction is The radius of the decomposition circle is Distance between the centers of adjacent decomposition circles

[0055] Since the risk of the inner side-by-side moving objects is usually small, the embodiment of the present application only considers the moving objects outside the driving track of the target moving object when determining the risk moving objects. Figure 3 The outer side of the target moving object includes the parallel moving objects A, B and C. Three line segments are drawn from the centers o1, o2 and o3 along the normal direction to the outer side of the target moving object's driving track, and the lengths of the three line segments are the preset distance thresholds. It can be obtained that the line segments drawn from the centers o2 and o3 intersect the outer contour of the moving object B at points b2 and b1, respectively. At this time, it can be determined that the moving object B is a risky moving object.

[0056] Figure 4 FIG. 1 is a flow chart of a method for determining the defensive deceleration of a target moving object relative to a risk moving object provided in an embodiment of the present application. Figure 4 As shown, the method comprises the following steps:

[0057] In step S401, a target coordinate system is determined.

[0058] The abscissa of the target coordinate system is the tangent of the outer contour of the tail of the risky moving object after the yield time τ, and the ordinate of the target coordinate system is the tangent of the outer contour of the tail of the risky moving object at present.

[0059] In step S402, solve the formula Get defensive deceleration a s .

[0060] In some implementations, a target coordinate system may be first determined, wherein the horizontal axis of the target coordinate system is the tangent of the outer contour of the tail of the risky moving object after the yield time τ, and the vertical axis of the target coordinate system is the tangent of the outer contour of the tail of the risky moving object at present. The value of the yield time τ is determined by the path planning module, which will not be described in detail here.

[0061] Figure 5 Schematic diagram of the motion trajectory of the target moving object and the risk moving object in the target coordinate system provided by the embodiment of the present application. Figure 5As shown, the target moving object moves from the position of the solid line frame 1 to the position of the dotted line frame 1 after time τ, and the risk moving object moves from the position of the solid line frame 2 to the dotted line frame 2 after time τ. The horizontal axis of the target coordinate system is the tangent of the outer contour line of the tail of the dotted line frame 2, and the vertical axis is the tangent of the outer contour line of the tail of the solid line frame 2.

[0062] With the origin of the target coordinate system as the center, the motion trajectory of the target moving object is the first arc, and the motion trajectory of the risk moving object is the second arc. Let the center angle difference between the current risk moving object and the target moving object be α0, and the center angle corresponding to the trajectory of the target moving object within the yield time τ be dα ego , the central angle of the trajectory of the risky mobile object within the yield time τ is dα agent , then it is necessary to satisfy α0+(dα agent -dα ego )≥0. Furthermore, the distance traveled by the target moving object within the yield time τ is The distance traveled by the risky moving object within the yield time τ is

[0063] That is, the need to satisfy Among them, Δs is the distance from the tail of the current risk moving object to the head of the target moving object in the target coordinate system, that is, in the target coordinate system, the first tangent line is drawn from the origin to the tail of the outer contour line of the current risk moving object, and the second tangent line is drawn to the tail of the outer contour line of the head of the target moving object. The distance between the two tangent lines of the motion trajectory of the risk moving object is recorded as Δs. agent is the current speed of the risk moving object, v ego is the current speed of the target moving object, k is the curvature of the current driving path of the target moving object, and d is the lateral distance of the target moving object.

[0064] Furthermore, the yield time τ = β d -t0, β is the yield strength, and the yield strength varies for different vehicle types. For example, the default value for large vehicles is 1.3, and the default value for small vehicles is 1..5. The default value of t0 can be 1.0, for example.

[0065] Using this method, the defensive deceleration a of the target moving object relative to the risk moving object can be determined: s Furthermore, a force analysis may be performed on the target moving object, and its force conditions may be comprehensively considered, so as to further optimize the deceleration of the target moving object to obtain a desired deceleration.

[0066] In some embodiments of the present application, a social force model may be used to perform force analysis on a target moving object. A social force model is a computational model that uses the concept of social forces to describe the interactions between traffic participants. The social force model takes into account the influence of the environment and other traffic participants and describes how the expected movement changes with these influences.

[0067] According to the social force model, the net force on the target traffic participant is the sum of the gravitational force of the desired motion, the repulsive force of other traffic participants, and the repulsive force of the road environment. i attr Indicates that Where m i is the mass of target traffic participant i, is the expected speed of i, is the expected motion direction of i, v i is the current speed of i, τ i is the relaxation time, i.e. the time interval required to reach the desired speed and desired direction of motion.

[0068] For example, if the repulsive force of other traffic participants on target traffic participant i is expressed as F i rep Indicates that in, is the mutual repulsion between target traffic participant i and other traffic participants j, is the obstructive repulsion between the target traffic participant i and the static obstacle o, is the set of all mobile obstacles, O is the set of all static obstacles in the environment. Further, N is a positive integer, i and j are positive integers less than or equal to N.

[0069] Among them, the repulsive force between the target traffic participant i and the obstacle k is By formula Calculated, k∈P∪O, a k Indicates the magnitude of the force, b k represents the range of force, then r i,k =r i +r k , r i The available radius of the rotationally invariant circular envelope of the target moving object, r k is the available radius of the rotationally invariant circular envelope of obstacle k, d ik is the Euclidean distance between the target moving object and the obstacle k; is the normalized vector from obstacle k to the target moving object. k is a positive integer less than or equal to N.

[0070] That is, it may not be possible to maintain the desired direction and speed of movement in the presence of other traffic participants or obstacles in the environment. In the social force model, the repulsive effects from these influences are described as interaction forces. This force prevents the traffic participant from moving in the intended direction and is modeled as the sum of the forces introduced by other traffic participants or static obstacles.

[0071] In some embodiments, an anisotropy factor c may also be introduced. ik Representing the limitations of human vision,

[0072] λ is the anisotropy strength. It should be noted that there is no need to introduce this anisotropy factor in the autonomous driving scenario.

[0073] For example, if the road environment repulsion force on the target traffic participant i is expressed as F i env Indicates that in, c k is the magnitude of the repulsive force. When x>=0, g(x)=x, otherwise, g(x)=0. e The set of all moving obstacles for the target moving object.

[0074] In this way, the resultant force on the target traffic participant can be calculated, and the acceleration (or deceleration) of the target traffic participant can be obtained by dividing the resultant force by the mass of the target traffic participant.

[0075] By applying the social force model to the target moving object in the embodiment of the present application, it can be obtained that the resultant force on the target moving object includes the forward attraction, surrounding repulsion and backward repulsion of the target moving object. Among them, the surrounding repulsion can only consider the repulsion of the risk moving object to the target moving object.

[0076] Figure 6 is a force analysis diagram of a target moving object provided in an embodiment of the present application. Figure 6 As shown, the target moving object has a force radius r e , the forward moving object of the target moving object has a force radius r f , the backward moving object of the target moving object has a force radius r r The force on the moving object includes the forward gravitational force Backward repulsion and surrounding repulsion

[0077] Among them, the backward repulsion The repulsive force generated by the backward moving object on the target moving object has the same direction as the forward attractive force, so the resultant force on the target moving object can be determined to be the sum of the forward attractive force and the backward repulsive force minus the difference between the surrounding repulsive forces. Further, the quotient of the resultant force on the target moving object and the mass of the target moving object is determined to be the expected deceleration.

[0078] In some embodiments of the present application, determining the forward gravitational force on the target moving object may be to obtain the expected motion parameters of the target moving object, where the expected motion parameters at least include the expected velocity v0, the expected acceleration a, and the expected deceleration b of the target moving object. Using the formula Calculate the forward gravity of the target moving object

[0079] Among them, m ego is the mass of the target moving object, a f is the forward following deceleration,

[0080] δ is an adjustable parameter. In one example, the empirical value 4 can be used. v is the current speed of the target moving object. Δv is the speed difference between the target moving object and the forward moving object. The forward moving object is the moving object that is in front of and adjacent to the target moving object. T is the expected following time distance. Its value can be set according to actual needs and is not limited here.

[0081] In other embodiments of the present application, when determining the surrounding repulsive force on the target moving object, if only the repulsive force exerted on it by the risk moving object is considered, the formula can be used: Calculate the surrounding repulsion of the target moving object Among them, m ego is the mass of the target moving object, a s Defensive deceleration.

[0082] In some other embodiments of the present application, determining the backward repulsive force on the target moving object may be to calculate the forward repulsive force on the target moving object. Determine forward repulsion The reaction force is the backward repulsive force of the target moving object. The backward moving object is a moving object that is behind the target moving object and adjacent to the target moving object.

[0083] Among them, the forward repulsion of the backward moving object is It can be obtained by performing force analysis on the backward moving object.

[0084] In some cases, there may be no moving object within a preset distance behind the backward moving object. Figure 6 As shown, there is no other moving object behind the backward moving object. At this time, the force on the backward moving object only includes the forward gravitational force. and the backward repulsion of the target moving object The target moving object exerts a backward repulsive force on the backward moving object. The forward repulsive force exerted by the backward moving object on the target moving object Equal in size and opposite in direction, that is

[0085] At this time, the resultant force of the backward moving object can be first determined according to the mass of the backward moving object and the acceleration of the backward moving object. Then, the forward gravitational force of the backward moving object is calculated by the method for calculating the forward gravitational force of the target moving object. Finally, the forward repulsive force of the backward moving object can be obtained by subtracting the forward gravitational force of the backward moving object from the resultant force of the backward moving object.

[0086] In other cases, there may be one or more backward moving objects within a preset distance behind the backward moving object. In this case, a different method is needed to calculate the forward repulsion of the backward moving object.

[0087] If there is only one backward moving object within the preset distance behind the backward moving object, the forward repulsive force of the last moving object is first obtained by using the calculation method when there is no backward moving object within the preset distance behind the backward moving object.

[0088] After analysis, it can be known that the resultant force on the backward moving object at this time includes the forward attractive force, the backward repulsive force generated by the last moving object and the forward repulsive force generated by the target moving object.

[0089] Therefore, the mass and acceleration of the last moving object can be multiplied to get the resultant force it receives, and then the sum of the forward attraction and the backward repulsion it receives can be subtracted from the resultant force to get the forward repulsion of the backward moving object.

[0090] When there are multiple backward moving objects within a preset distance behind the backward moving object, we can first use the force model that the resultant force is equal to the forward attraction minus the forward repulsion to calculate the forward repulsion of the current last backward moving object. The forward repulsion of the last backward moving object is equal to the backward repulsion of the second to last backward moving object in magnitude and opposite in direction.

[0091] Then, using the force model in which the resultant force is equal to the forward attractive force plus the backward repulsive force minus the forward repulsive force, the forward repulsive force of each moving object is recursively calculated forward in turn until the forward repulsive force of the backward moving object is calculated.

[0092] That is, in response to determining that there are m backward-moving objects within a preset distance behind the backward-moving object, where m is a positive integer, the forward repulsive force of the backward-moving object The determination is carried out in the following manner: the forward repulsion of the m-th backward moving object is determined by the aforementioned method for calculating the forward repulsion of the last backward moving object, and the reaction force of the forward repulsion is determined to be the backward repulsion of the m-1th backward moving object; the resultant force of the m-1th backward moving object is determined according to the mass of the m-1th backward moving object and the acceleration of the m-1th backward moving object; the forward attraction of the m-1th backward moving object is determined by the aforementioned method for calculating the target moving object; the sum of the forward attraction of the m-1th backward moving object and the backward repulsion of the m-1th backward moving object is determined to be the forward component; the difference between the forward component and the resultant force of the m-1th backward moving object is determined to be the forward repulsion of the m-1th backward moving object; the forward repulsion of each backward moving object is iteratively calculated from back to front by the aforementioned method for calculating the forward repulsion of the m-1th backward moving object, and the forward repulsion of the backward moving object is obtained.

[0093] Figure 7 FIG. 1 is a schematic diagram of force analysis when the backward moving object provided by the embodiment of the present application includes two backward moving objects behind it. Figure 7 The backward moving object 0 also includes two backward moving objects, namely, moving object 1 and moving object 2. There is no more moving object behind the moving object 1 and moving object 2, and the moving object 1 and moving object 2 are not located in a straight line with the backward moving object 0.

[0094] When performing force analysis on the backward moving object 0 , the moving object 1 and the moving object 2 may be analyzed first to determine the backward repulsive forces exerted by the moving object 1 and the moving object 2 on the backward moving object 0 , respectively.

[0095] For moving object 1, the net force it receives is in, is the mass of moving object 1, is the acceleration (or deceleration) of the moving object 1. The moving object 1 is subject to the forward gravitational force The forward repulsion of the backward moving object 0 And the backward repulsion generated by moving object 2 You can use the formula Calculated.

[0096] For moving object 2, the net force it receives is in, is the mass of moving object 2, is the acceleration (or deceleration) of the moving object 2. The moving object 2 is subject to the forward gravitational force The forward repulsion of the backward moving object 0 And the backward repulsion generated by moving object 1 in, You can use the formula Calculated, and It is a pair of forces of equal magnitude and opposite direction.

[0097] Solve the force models of moving object 1 and moving object 2 respectively, and we can calculate 5 and The value of .

[0098] For the backward moving object 0, the resultant force it receives is ,in, is the mass of the backward moving object 0, is the acceleration (or deceleration) of the backward moving object 0. The backward moving object 0 is subject to the forward gravitational force The backward repulsion generated by moving object 1 , the backward repulsion generated by moving object 2 And the forward repulsion generated by the target moving object in, You can use the formula Calculated, and are a pair of forces of equal magnitude and opposite direction. and It is a pair of forces of equal magnitude and opposite direction. Solving the force model of the backward moving object 0, its forward repulsive force can be calculated

[0099] Figure 8 FIG. 1 is a schematic diagram of force analysis when there are multiple backward moving objects behind the backward moving object provided by the embodiment of the present application. Figure 8 As shown. The backward moving object 0 also includes m backward moving objects, moving object 1 to moving object m, and the force radius of each moving object is r0, r1, ... r m Among them, moving object m is the last moving object, and backward moving object 0 and the other m backward moving objects are all on a straight line.

[0100] At this point, we can first analyze the force on the moving object m. The resultant force on the moving object m is in, is the mass of the moving object m, is the acceleration (or deceleration) of the moving object m. The moving object m is subject to the forward gravitational force and the forward repulsion exerted by the moving object m-1 on it in, You can use the formula Solve the force model of the moving object m and you can calculate

[0101] Next, we analyze the force on the moving object m-1. The resultant force on the moving object m-1 is in, is the mass of the moving object m-1, is the acceleration (or deceleration) of the moving object m-1. The moving object m-1 is subject to the forward gravitational force The backward repulsion exerted by the moving object m on it and the forward repulsion exerted by the moving object m-2 on it in, You can use the formula Calculated, and is a pair of forces of equal magnitude and opposite direction. Solving the force model of the moving object m-1, we can calculate

[0102] Iteratively calculate the forward repulsive force exerted on the moving objects m-2, m-3, ... by the previous moving object, and finally calculate the forward repulsive force exerted on the 0th backward moving object by the target moving object.

[0103] That is, when iterating to moving object 1, the resultant force on moving object 1 is in, is the mass of moving object 1, is the acceleration (or deceleration) of the moving object 1. The moving object 1 is subject to the forward gravitational force The backward repulsion generated by moving object 2 And the forward repulsion of moving object 0 in, You can use the formula Calculated, and is a pair of forces of equal magnitude and opposite direction. Solving the force model of the moving object 1, we can calculate

[0104] For the backward moving object 0, the resultant force it receives is in, is the mass of the moving object 0, is the acceleration (or deceleration) of the moving object 0. The moving object 0 is subject to the forward gravitational force The backward repulsion generated by moving object 1 and the forward repulsive force exerted by the target moving object on it in, You can use the formula Calculated, and is a pair of forces of equal magnitude and opposite direction. Solving the force model of the moving object 0, we can calculate

[0105] The embodiments of the present application provide a method for calculating the forward repulsion generated by a target moving object on a backward moving object under various circumstances, and can select a suitable method to calculate the optimal forward repulsion according to the current road traffic conditions. Furthermore, the backward repulsion of the target moving object can be determined using the forward repulsion, and the resultant force can be obtained by combining the forward attraction of the target moving object and the surrounding repulsion. Finally, the resultant force is divided by the mass of the target moving object to obtain the expected deceleration of the target moving object, and the yield strategy of the target moving object is determined using the expected deceleration.

[0106] The technical solution of the embodiment of the present application proposes a simple and effective method for risk identification and defensive deceleration calculation for parallel driving. The method can identify potential risks in parallel driving and reduce the probability of potential accidents through timely deceleration measures, providing more reliable safety protection for the autonomous driving system.

[0107] Furthermore, the technical solution provided by the embodiment of the present application, on the basis of considering the safety of surrounding vehicles, transforms the local yielding problem into a global optimization problem, thus realizing the effective application of the defensive deceleration strategy. By incorporating yielding behavior into the optimization consideration of the overall traffic flow, the ability of autonomous driving vehicles to cope with complex road conditions is effectively improved, further enhancing driving safety and traffic efficiency.

[0108] Fig. 9 FIG. 1 is a flow chart of another method for determining a yield strategy based on parallel risk provided in an embodiment of the present application. Fig. 9As shown in the figure, if the target moving object is an unmanned vehicle, the surrounding and self-vehicle information can be obtained first, which can include the vehicle information in front of the self-vehicle, the vehicle information behind the self-vehicle, the side vehicle information traveling side by side, and the self-vehicle information, and the self-vehicle planning path information is obtained at the same time. Next, identify the vehicles that are at risk in the side-by-side driving. Then calculate and implement the side-by-side misalignment deceleration strategy, and limit the speed for the side-by-side risk. Further analyze the force of the rear following vehicle, infer the reaction force of the rear following vehicle to the self-vehicle, and perform forward recursive calculation to obtain the rear expected maximum braking, speed limit repulsion and forward following vehicle attraction. Finally, perform force analysis to determine the expected longitudinal motion of the self-vehicle.

[0109] All the above optional technical solutions can be arbitrarily combined to form optional embodiments of the present application, which will not be described one by one here.

[0110] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method of the present application.

[0111] Fig.10 Schematic diagram of a device for determining a yield strategy based on parallel risk provided in an embodiment of the present application. Fig.10 As shown, the device comprises:

[0112] The acquisition module 1001 is configured to acquire the planned path information and environment information of the target mobile object.

[0113] The determination module 1002 is configured to determine a risky mobile object based on the planned path information and the environmental information. The risky mobile object is a mobile object that has a similar driving direction to the target mobile object and has a conflict risk.

[0114] The determination module 1002 is further configured to determine a defensive deceleration of the target mobile object relative to the risk mobile object.

[0115] The construction module 1003 is configured to construct a force model of the target moving object based at least on the defensive deceleration and the expected motion parameters of the target moving object.

[0116] The determination module 1002 is further configured to determine an expected deceleration of the target moving object based on the force model, and determine a yielding strategy of the target moving object based on the expected deceleration.

[0117] According to the technical solution provided in the embodiments of the present application, by acquiring the planned path information and environmental information of the target mobile object, determining the risky mobile object based on the planned path information and environmental information, determining the defensive deceleration of the target mobile object relative to the risky mobile object, constructing a force model of the target mobile object based at least on the defensive deceleration and the expected motion parameters of the target mobile object, and determining the expected deceleration of the target mobile object based on the force model, and finally determining the yielding strategy of the target mobile object based on the expected deceleration, an effective yielding strategy for autonomous driving vehicles for parallel risks is proposed, which further improves the decision-making efficiency of autonomous driving vehicles.

[0118] In some embodiments, the environmental information at least includes mobile objects traveling side by side with the target mobile object, and the mobile objects traveling side by side are mobile objects whose moving direction has an angle with the moving direction of the target mobile object that is less than a preset angle threshold; determining the risky mobile object based on the planned path information and the environmental information includes: representing the target mobile object with n decomposition circles with the same radius, where n is a positive integer; starting from the center of each decomposition circle, drawing n line segments along the normal direction of the driving direction of the target mobile object, and the length of each line segment is a preset distance threshold; determining the mobile object whose outer contour line intersects with at least one of the n line segments as the risky mobile object.

[0119] In some embodiments, determining the defensive deceleration of the target moving object relative to the risk moving object includes: determining a target coordinate system, wherein the abscissa axis of the target coordinate system is a tangent to the outer contour line of the tail of the risk moving object after the yield time τ, and the ordinate axis of the target coordinate system is a tangent to the outer contour line of the current tail of the risk moving object; solving the formula Get defensive deceleration a s ; where Δs is the distance from the tail of the current risk moving object to the head of the target moving object in the target coordinate system, v agent is the current speed of the risk moving object, v ego is the current speed of the target moving object, k is the curvature of the current driving path of the target moving object, and d is the lateral distance of the target moving object; Among them, l is the length of the target moving object, w is the width of the target moving object, and r is the radius of the decomposition circle.

[0120]

[0121] In some embodiments, the force model of the target moving object is that the resultant force acting on the target moving object includes the forward attraction, surrounding repulsion and backward repulsion of the target moving object; determining the expected deceleration of the target moving object based on the force model includes: determining that the resultant force acting on the target moving object is the sum of the forward attraction and the backward repulsion minus the difference between the surrounding repulsion; and determining the quotient of the resultant force acting on the target moving object and the mass of the target moving object as the expected deceleration.

[0122] In some embodiments, the forward gravitational force on the target moving object is determined by: obtaining the expected motion parameters of the target moving object, the expected motion parameters at least including the expected velocity v0, the expected acceleration a and the expected deceleration b of the target moving object; using the formula Calculate the forward gravity of the target moving object Among them, m ego is the mass of the target moving object, a f is the forward following deceleration, v is the current speed of the target moving object, Δv is the speed difference between the target moving object and the forward moving object, and the forward moving object is the moving object traveling in front of the target moving object and adjacent to the target moving object.

[0123] In some implementations, the surrounding repulsive force on the target moving object is determined in the following manner: using the formula Calculate the surrounding repulsion of the target moving object Among them, m ego is the mass of the target moving object, a s Defensive deceleration.

[0124] In some embodiments, the backward repulsive force on the target moving object is determined by calculating the forward repulsive force on the target moving object. Determine forward repulsion The reaction force is the backward repulsive force of the target moving object; wherein the backward moving object is a moving object traveling behind the target moving object and adjacent to the target moving object.

[0125] In some embodiments, in response to determining that there is no moving object within a preset distance behind the backward moving object, the forward repulsive force of the backward moving object The determination is carried out in the following manner: determining the resultant force of the backward moving object according to the mass of the backward moving object and the acceleration of the backward moving object; determining the forward gravitational force of the backward moving object; and determining the difference between the forward gravitational force of the backward moving object and the resultant force of the backward moving object as the forward repulsive force of the backward moving object.

[0126] In some embodiments, in response to determining that there are m backward-moving objects within a preset distance behind the backward-moving object, where m is a positive integer, the forward repulsive force of the backward-moving object The determination is carried out in the following manner: determine the forward repulsion of the m-th backward moving object, determine the reaction force of the forward repulsion as the backward repulsion of the m-1th backward moving object; determine the resultant force of the m-1th backward moving object according to the mass of the m-1th backward moving object and the acceleration of the m-1th backward moving object; determine the forward attraction of the m-1th backward moving object; determine the sum of the forward attraction of the m-1th backward moving object and the backward repulsion of the m-1th backward moving object as the forward component; determine the difference between the forward component and the resultant force of the m-1th backward moving object as the forward repulsion of the m-1th backward moving object; adopt the above method for calculating the forward repulsion of the m-1th backward moving object, iteratively calculate the forward repulsion of each backward moving object from back to front in sequence, and obtain the forward repulsion of the backward moving object.

[0127] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0128] Fig.11 Schematic diagram of an electronic device provided in an embodiment of the present application. Fig.11 As shown, the electronic device 11 of this embodiment includes: a processor 1101, a memory 1102, and a computer program 1103 stored in the memory 1102 and executable on the processor 1101. When the processor 1101 executes the computer program 1103, the steps in the above-mentioned method embodiments are implemented. Alternatively, when the processor 1101 executes the computer program 1103, the functions of the modules / units in the above-mentioned device embodiments are implemented.

[0129] The electronic device 11 may be a desktop computer, a notebook, a PDA, a cloud server, or other electronic device. The electronic device 11 may include, but is not limited to, a processor 1101 and a memory 1102. Those skilled in the art will appreciate that Fig.11 The electronic device 11 is merely an example and does not limit the electronic device 11 , and may include more or less components than those shown in the figure, or different components.

[0130] Processor 1101 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0131] The memory 1102 may be an internal storage unit of the electronic device 11, for example, a hard disk or memory of the electronic device 11. The memory 1102 may also be an external storage device of the electronic device 11, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card (FlashCard), etc. equipped on the electronic device 11. The memory 1102 may also include both an internal storage unit of the electronic device 11 and an external storage device. The memory 1102 is used to store computer programs and other programs and data required by the electronic device.

[0132] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units.

[0133] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. The computer program may include computer program code, which may be in source code form, object code form, executable file or some intermediate form. Computer-readable media may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0134] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for determining a yield strategy based on parallel risk, characterized in that: include: Obtaining the planned path information and environmental information of the target moving object; Determine a risky mobile object based on the planned path information and the environmental information, wherein the risky mobile object is a mobile object whose included angle between the moving direction and the moving direction of the target mobile object is less than a preset angle threshold and whose predicted trajectory conflicts with the planned path of the target mobile object; determining a defensive deceleration of the target moving object relative to the risk moving object; constructing a force model of the target moving object based at least on the defensive deceleration and the expected motion parameters of the target moving object; An expected deceleration of the target moving object is determined based on the force model, and a yield strategy of the target moving object is determined based on the expected deceleration.

2. The method according to claim 1, characterized in that The environmental information at least includes a mobile object traveling side by side with the target mobile object, wherein the mobile object traveling side by side is a mobile object whose moving direction and the moving direction of the target mobile object have an angle less than a preset angle threshold; The determining of the risky mobile object based on the planned path information and the environmental information includes: The target moving object is represented by n decomposition circles with the same radius, where n is a positive integer; Starting from the center of each decomposition circle, n line segments are drawn along the normal direction of the moving direction of the target moving object, and the length of each line segment is a preset distance threshold; A moving object whose outer contour intersects at least one of the n line segments is determined as the risky moving object.

3. The method according to claim 2, characterized in that Determining the defensive deceleration of the target moving object relative to the risk moving object includes: Determine a target coordinate system, wherein the abscissa axis of the target coordinate system is the tangent line of the outer contour line of the tail of the risky moving object after the yield time τ, and the ordinate axis of the target coordinate system is the tangent line of the outer contour line of the current tail of the risky moving object; Solving the formula Get the defensive deceleration a s ; Wherein, Δs is the distance from the tail of the current risky moving object to the head of the target moving object in the target coordinate system, v agent is the current speed of the risk moving object, v ego is the current speed of the target moving object, k is the curvature of the current driving path of the target moving object, and d is the lateral distance of the target moving object; Wherein, l is the length of the target moving object, w is the width of the target moving object, r is the radius of the decomposition circle, 4. The method according to claim 1, characterized in that: The force model of the target moving object is that the resultant force on the target moving object includes the forward attraction, surrounding repulsion and backward repulsion of the target moving object; The determining the expected deceleration of the target moving object based on the force model includes: Determine that the resultant force on the target moving object is the sum of the forward attractive force and the backward repulsive force minus the difference of the surrounding repulsive force; The quotient of the resultant force on the target moving object and the mass of the target moving object is determined as the expected deceleration.

5. The method according to claim 4, characterized in that The forward gravitational force on the target moving object is determined in the following manner: Acquire expected motion parameters of the target moving object, wherein the expected motion parameters at least include an expected velocity v0, an expected acceleration a, and an expected deceleration b of the target moving object; Using the formula Calculate the forward gravitational force of the target moving object Among them, m ego is the mass of the target moving object, a f is the forward following deceleration, δ is an adjustable parameter, v is the current speed of the target moving object, Δv is the speed difference between the target moving object and the forward moving object, the forward moving object is a moving object traveling in front of and adjacent to the target moving object, and T is the expected following time distance.

6. The method according to claim 4, characterized in that The surrounding repulsive force on the target moving object is determined in the following manner: Using the formula Calculate the surrounding repulsive force of the target moving object Among them, m ego is the mass of the target moving object, a s is the defensive deceleration.

7. The method according to claim 4, characterized in that The backward repulsive force on the target moving object is determined in the following manner: Calculate the forward repulsive force exerted by the target moving object on the backward moving object of the target moving object Determine the forward repulsion The reaction force a backward repulsion force for said target moving object; The backward moving object is a moving object that travels behind the target moving object and is adjacent to the target moving object.

8. The method according to claim 7, characterized in that In response to determining that there is no moving object within a preset distance behind the backward moving object, the forward repulsive force of the backward moving object Determined in the following way: determining the resultant force of the backward moving object according to the mass of the backward moving object and the acceleration of the backward moving object; determining a forward gravitational force of the backward moving object; The difference between the forward attractive force of the backward moving object and the resultant force of the backward moving object is determined as the forward repulsive force of the backward moving object.

9. The method according to claim 7, characterized in that: In response to determining that there are m backward-moving objects within a preset distance behind the backward-moving object, where m is a positive integer, the forward repulsive force of the backward-moving object Determined in the following way: Determine the forward repulsion of the mth backward moving object, and determine the reaction force of the forward repulsion as the backward repulsion of the m-1th backward moving object; determining the m-1th backward moving object resultant force according to the mass of the m-1th backward moving object and the acceleration of the m-1th backward moving object; The forward gravitational force of the m-1th backward moving object; Determine the sum of the forward attraction of the m-1th backward moving object and the backward repulsion of the m-1th backward moving object as the forward component; Determine the difference between the forward component and the resultant force of the m-1th backward moving object as the forward repulsive force of the m-1th backward moving object; The method for calculating the forward repulsion of the m-1th backward moving object is adopted to iteratively calculate the forward repulsion of each backward moving object from back to front in sequence to obtain the forward repulsion of the backward moving object.

10. The method according to claim 9, characterized in that The determining the forward repulsive force of the mth backward moving object comprises: determining a resultant force of the mth backward-moving object according to the mass of the mth backward-moving object and the acceleration of the mth backward-moving object; determining the forward gravitational force of the mth backward-moving object; The difference between the forward attractive force of the m-th backward moving object and the resultant force of the m-th backward moving object is determined as the forward repulsive force of the m-th backward moving object.

11. The method according to any one of claims 8 to 10, determining the forward gravitational force of each backward moving object, comprising: Acquire expected motion parameters of each backward moving object, and determine the forward following deceleration of each backward moving object using the expected motion parameters; Obtaining the mass of each backward moving object, and determining that the product of the mass of the target backward moving object and the forward following vehicle deceleration of the target backward moving object is the forward gravitational force of the target backward moving object; The target backward moving object is any backward moving object.

12. A device for determining a yield strategy based on parallel risk, characterized in that: include: An acquisition module is configured to acquire planning path information and environment information of a target mobile object; A determination module is configured to determine a risky mobile object based on the planned path information and the environmental information, wherein the risky mobile object is a mobile object that has a similar travel direction to the target mobile object and has a conflict risk; The determination module is further configured to determine a defensive deceleration of the target mobile object relative to the risk mobile object; A construction module, configured to construct a force model of the target moving object based at least on the defensive deceleration and the expected motion parameters of the target moving object; The determination module is further configured to determine an expected deceleration of the target moving object based on the force model, and determine a yielding strategy of the target moving object based on the expected deceleration.

Images