Control method and device and vehicle

Abstract

According to the control method, when a collision possibility exists between a target vehicle and a target object, the target vehicle and the target object are divided into an active party and a passive party, and the active party has a priority passing right relative to the passive party; acquiring a first strategy set which can be driven by the active party, wherein the first strategy set comprises at least one first driving strategy; according to the first strategy set, determining a second driving strategy of the passive party under each first driving strategy in the first strategy set to obtain a second strategy set; the execution cost of each feasible strategy obtained by the first strategy set and the second strategy set is analyzed to obtain a first cost set, and each feasible strategy pair is composed of a first driving strategy and a second driving strategy, the first cost set comprises the cost associated with each feasible strategy pair and used for indicating the cost of executing the feasible strategy pair; and controlling the target vehicle according to the driving strategy corresponding to the lowest execution cost in the first cost set. And the driving experience is improved.

Description

[0001] This application is a divisional application. The application number of the original application is 202211077102.4, and the original application date is September 5, 2022. The entire contents of the original application are incorporated into this application by reference. Technical Field

[0002] The present application relates to the field of artificial intelligence (AI) technology, and in particular to a control method, device and vehicle. Background Art

[0003] Autonomous driving is a mainstream application in the field of artificial intelligence. Autonomous driving technology relies on the collaboration of computer vision, radar, monitoring devices and global positioning systems, allowing vehicles to achieve autonomous driving without the need for active human operation. In the field of autonomous driving, vehicles can execute corresponding driving strategies based on actual driving scenarios to ensure safe driving of the vehicle. However, at present, when there is a trajectory conflict between multiple vehicles, vehicles often execute driving strategies such as erroneous deceleration and erroneous acceleration, affecting safe acceleration and driving experience. Summary of the invention

[0004] The present application provides a control method, device, vehicle, computer storage medium and computer product, which can enable the vehicle to continuously test the driving intentions of other objects until the driving intentions of other objects are clear, and then make the final decision to overtake or give way, thereby achieving the effect of slowly accelerating to overtake or slowly decelerating to give way, and improving the driving experience.

[0005] In a first aspect, the present application provides a control method, which includes: dividing a target vehicle and a target object into an active party and a passive party, wherein the active party has priority over the passive party, and there is a possibility of collision between the target vehicle and the target object; obtaining a feasible first strategy set for the active party, wherein the first strategy set includes at least one first driving strategy; according to each first driving strategy in the first strategy set, the driving parameters of the active party at the current moment, and the driving parameters of the passive party at the current moment, obtaining a second driving strategy for the passive party under each first driving strategy in the first strategy set, so as to obtain a second strategy set, wherein the second driving strategy is any one of the following: the passive party only overtakes the active party, the passive party The passive party can only give way to the active party, or the passive party can both overtake the active party and give way to the active party; according to the first strategy set and the second strategy set, determine the target strategy pair set, the target strategy pair set includes at least one feasible strategy pair, and each feasible strategy pair consists of a first driving strategy and a second driving strategy; determine the execution cost of each feasible strategy pair in the target strategy pair set to obtain a first cost set, the first cost set includes the execution cost of each feasible strategy pair; according to the first cost set, determine the target driving strategy, the target driving strategy is the driving strategy of the target vehicle associated with the lowest execution cost in the first cost set; according to the target driving strategy, control the target vehicle. Exemplarily, the driving parameters at the current moment may refer to, but are not limited to: the driving parameters observed when obtaining the first strategy set, or the driving parameters observed when solving the second strategy set, or the driving parameters most recently observed before executing the method.

[0006] In this way, when there is a possibility of conflict between the target vehicle and the target object, the two can be divided into active and passive parties, and the feasible strategy of the active party can be used to solve the feasible strategy of the passive party, and then the execution cost of executing the feasible strategies of the two can be calculated, and finally a feasible strategy with the lowest cost can be selected to control the target vehicle. In this way, the target vehicle can continuously test the driving intention of other objects until the driving intention of other objects is clear, and then make the final decision of rushing or giving way, so as to achieve the effect of slow acceleration to rush or slow deceleration to give way, and improve the driving experience.

[0007] In a possible implementation, if the target vehicle is the active party and the target object is the passive party; according to the first cost set, the target driving strategy is determined, specifically including: if the second driving strategy in the feasible strategy pair corresponding to the target cost is: the passive party only overtakes the active party, then the target driving strategy is determined to be: the target vehicle gives way to the target object, wherein the target cost is the lowest execution cost in the first cost set; if the second driving strategy in the feasible strategy pair corresponding to the target cost is: the passive party only gives way to the active party, then the target driving strategy is determined to be: the target vehicle overtakes the target object; if the second driving strategy in the feasible strategy pair corresponding to the target cost is: the passive party can both overtake the active party and give way to the active party, then the target driving strategy is determined to be: the first driving strategy in the feasible strategy pair corresponding to the target cost.

[0008] In this way, if the target vehicle is the active party and the target object is the passive party, when the driving strategy of the target object is one of grabbing or giving way to the target vehicle, it indicates that the driving intention of the target object is clear. At this time, it can be determined that the driving strategy of the target vehicle is opposite to the driving strategy of the target object, that is, when the driving strategy of the target object is to grab the target vehicle, the driving strategy of the target vehicle is determined to give way to the target object, and when the driving strategy of the target object is to give way to the target vehicle, the driving strategy of the target vehicle is determined to grab the target object. When the driving strategy of the target object is to both grab and give way to the target vehicle, it indicates that the driving intention of the target object is not clear. At this time, the target vehicle can be controlled to test the driving intention of the target object; at the same time, since the target vehicle is the active party at this time, and the road right of the active party is higher than the road right of the passive party, in the driving process, it is often the party with lower road right that needs to give way to the party with lower road right. Therefore, at this time, the target vehicle can be controlled to execute the first driving strategy in the feasible strategy pair corresponding to the target cost, that is, the driving strategy of the target object is determined to be the first driving strategy in the feasible strategy pair corresponding to the target cost.

[0009] In a possible implementation, if the target vehicle is the passive party and the target object is the active party; according to the first cost set, the target driving strategy is determined, specifically including: if the second driving strategy in the feasible strategy pair corresponding to the target cost is: the passive party only overtakes the active party, then the target driving strategy is determined to be: the target vehicle overtakes the target object, wherein the target cost is the lowest execution cost in the first cost set; if the second driving strategy in the feasible strategy pair corresponding to the target cost is: the passive party only gives way to the active party, then the target driving strategy is determined to be: the target vehicle gives way to the target object; if the second driving strategy in the feasible strategy pair corresponding to the target cost is: the passive party can both overtake the active party and give way to the active party, then the target driving strategy is determined to be: the target vehicle gives way to the target object.

[0010] In this way, if the target vehicle is the passive party and the target object is the active party, when the target vehicle's driving strategy is to grab the target object, it indicates that the target vehicle has only one driving strategy to choose from, so it can be determined that the driving strategy is the driving strategy that the target vehicle needs to execute. Similarly, when the target vehicle's driving strategy is to give way to the target object, it indicates that the target vehicle has only one driving strategy to choose from, so it can be determined that the driving strategy is the driving strategy that the target vehicle needs to execute. When the target vehicle's driving strategy is to both grab and give way to the target object, it indicates that the target object's driving intention is still unclear. At this time, if the target vehicle rashly executes the decision to grab or give way, it is easy to cause heavy braking / point braking or even take over, and the driving experience is poor. In addition, since the target vehicle is the passive party at this time, the target vehicle's right of way is lower than the target object's right of way. At the same time, since it is often the party with lower right of way that needs to give way to the party with lower right of way during driving, the target vehicle can be controlled to slow down to test the target object's driving intention, that is, to determine the target vehicle's driving strategy as the give way target object.

[0011] In one possible implementation, the execution cost associated with the feasible strategy pair includes one or more of the following: a comfort cost, which is used to characterize the comfort level when executing the feasible strategy pair; a passability cost, which is used to characterize the efficiency of the active party and / or the passive party in passing the conflict point between the two; an offset cost, which is used to characterize the evaluation of the offset of the active party and / or the passive party when executing the corresponding driving strategy; an inconsistency cost, which is used to characterize the evaluation of the deviation between the driving behavior of the target object in the feasible strategy pair and the actual driving behavior of the target object; or a decision penalty cost, which is used to characterize the evaluation of whether the intention of the passive party is clear.

[0012] In a possible implementation, for any first strategy pair among all feasible strategy pairs, the comfort cost associated with the first strategy pair is determined, specifically including: determining the first comfort cost of the active party when executing the first driving strategy in the first strategy pair according to the acceleration corresponding to the first driving strategy in the first strategy pair and the current acceleration of the active party; determining the second comfort cost of the passive party when executing the second driving strategy in the first strategy pair according to the acceleration corresponding to the second driving strategy in the first strategy pair and the current acceleration of the passive party; determining the comfort cost associated with the first strategy pair according to the first comfort cost and the second comfort cost. Exemplarily, the current acceleration of the active party may refer to, but is not limited to: the acceleration of the active party observed when acquiring the first strategy set, or the acceleration of the active party observed when solving the second strategy set, or the latest observed acceleration of the active party before executing the method.

[0013] In a possible implementation, for any first strategy pair among all feasible strategy pairs, the passability cost associated with the first strategy pair is determined, specifically including: determining the first passability cost of the active party when executing the first driving strategy in the first strategy pair according to the first time and the second time, wherein the first time is the time when the active party passes the target point when executing the first driving strategy in the first strategy pair, and the second time is the time when the active party passes the target point with its current speed and acceleration, and the target point is the conflict point between the driving path of the active party and the driving path of the passive party; determining the second passability cost of the passive party when executing the second driving strategy in the first strategy pair according to the third time and the fourth time, wherein the third time is the time when the passive party passes the target point when executing the second driving strategy in the first strategy pair, and the fourth time is the time when the passive party passes the target point with its current speed and acceleration; determining the passability cost associated with the first strategy pair according to the first passability cost and the second passability cost.

[0014] In a possible implementation, for any first strategy pair among all feasible strategy pairs, the offset cost associated with the first strategy pair is determined, specifically including: based on a mapping relationship between a preset offset and an offset cost, and an offset when the active party executes the first driving strategy in the first strategy pair, determining a first offset cost when the active party executes the first driving strategy in the first strategy pair; based on a mapping relationship between a preset offset and an offset cost, and an offset when the passive party executes the second driving strategy in the first strategy pair, determining a second offset cost when the passive party executes the second driving strategy in the first strategy pair; and determining the offset cost associated with the first strategy pair based on the first offset cost and the second offset cost.

[0015] In a possible implementation, for any first strategy pair among all feasible strategy pairs, the inconsistency cost associated with the first strategy pair is determined, specifically including: when the driving strategy of the target object in the first strategy pair is to only overtake the target vehicle, or to only give way to the target vehicle, determining the target probability of the target object overtaking the target vehicle, and, based on the target probability, determining the inconsistency cost; when the driving strategy of the target object in the first strategy pair is to both overtake the target vehicle and give way to the target vehicle, determining the inconsistency cost as a pre-set cost value.

[0016] In one possible implementation, for any first strategy pair among all feasible strategy pairs, a decision penalty cost associated with the first strategy pair is determined, specifically including: based on a pre-set decision penalty rule and the second driving strategy in the first strategy pair, determining the decision penalty cost associated with the first strategy pair.

[0017] In one possible implementation, the second driving strategy in the first strategy pair is: the passive party can both overtake the active party and give way to the active party; based on a pre-set decision penalty rule and the second driving strategy in the first strategy pair, the decision penalty cost associated with the first strategy pair is determined, specifically including: based on the decision penalty rule and the second driving strategy in the first strategy pair, the first decision penalty cost is determined; according to the acceleration corresponding to the first driving strategy in the first strategy pair and the current acceleration of the active party, the second decision penalty cost of the active party when executing the first driving strategy in the first strategy pair is determined; according to the first decision penalty cost and the second decision penalty cost, the decision penalty cost associated with the first strategy pair is determined.

[0018] In a second aspect, the present application provides a control device, which includes: a division module and a processing module. The division module is used to divide the target vehicle and the target object into an active party and a passive party, wherein the active party has a priority right of way relative to the passive party, and there is a possibility of collision between the target vehicle and the target object. The processing module is used to obtain a feasible first strategy set for the active party, and the first strategy set includes at least one first driving strategy. The processing module is also used to obtain the second driving strategy of the passive party under each first driving strategy in the first strategy set according to each first driving strategy in the first strategy set, the driving parameters of the active party at the current moment, and the driving parameters of the passive party at the current moment, so as to obtain a second strategy set, wherein the second driving strategy is any one of the following: the passive party only rushes to the active party, the passive party only gives way to the active party, or the passive party can both rush to the active party and give way to the active party. The processing module is also used to determine a target strategy pair set according to the first strategy set and the second strategy set, and the target strategy pair set includes at least one feasible strategy pair, and each feasible strategy pair consists of a first driving strategy and a second driving strategy. The processing module is also used to determine the execution cost of each feasible strategy pair in the target strategy pair set to obtain a first cost set, wherein the first cost set includes the execution cost of each feasible strategy pair. The processing module is also used to determine a target driving strategy based on the first cost set, wherein the target driving strategy is the driving strategy of the target vehicle associated with the lowest execution cost in the first cost set. The processing module is also used to control the target vehicle based on the target driving strategy.

[0019] In a possible implementation, if the target vehicle is the active party and the target object is the passive party; when the processing module determines the target driving strategy based on the first cost set, it is specifically used to: if the second driving strategy in the feasible strategy pair corresponding to the target cost is: the passive party only overtakes the active party, then the target driving strategy is determined to be: the target vehicle gives way to the target object, wherein the target cost is the lowest execution cost in the first cost set; if the second driving strategy in the feasible strategy pair corresponding to the target cost is: the passive party only gives way to the active party, then the target driving strategy is determined to be: the target vehicle overtakes the target object; if the second driving strategy in the feasible strategy pair corresponding to the target cost is: the passive party can both overtake the active party and give way to the active party, then the target driving strategy is determined to be: the first driving strategy in the feasible strategy pair corresponding to the target cost.

[0020] In a possible implementation, if the target vehicle is the passive party and the target object is the active party; when the processing module determines the target driving strategy based on the first cost set, it is specifically used to: if the second driving strategy in the feasible strategy pair corresponding to the target cost is: the passive party only overtakes the active party, then the target driving strategy is determined to be: the target vehicle overtakes the target object, wherein the target cost is the lowest execution cost in the first cost set; if the second driving strategy in the feasible strategy pair corresponding to the target cost is: the passive party only gives way to the active party, then the target driving strategy is determined to be: the target vehicle gives way to the target object; if the second driving strategy in the feasible strategy pair corresponding to the target cost is: the passive party can both overtake the active party and give way to the active party, then the target driving strategy is determined to be: the target vehicle gives way to the target object.

[0021] In one possible implementation, the execution cost associated with the feasible strategy pair includes one or more of the following: a comfort cost, which is used to characterize the comfort level when executing the feasible strategy pair; a passability cost, which is used to characterize the efficiency of the active party and / or the passive party in passing the conflict point between the two; an offset cost, which is used to characterize the evaluation of the offset of the active party and / or the passive party when executing the corresponding driving strategy; an inconsistency cost, which is used to characterize the evaluation of the deviation between the driving behavior of the target object in the feasible strategy pair and the actual driving behavior of the target object; or a decision penalty cost, which is used to characterize the evaluation of whether the intention of the passive party is clear.

[0022] In a possible implementation, for any first strategy pair among all feasible strategy pairs, when determining the comfort cost associated with the first strategy pair, the processing module is specifically used to: determine a first comfort cost of the active party when executing the first driving strategy in the first strategy pair according to the acceleration corresponding to the first driving strategy in the first strategy pair and the current acceleration of the active party; determine a second comfort cost of the passive party when executing the second driving strategy in the first strategy pair according to the acceleration corresponding to the second driving strategy in the first strategy pair and the current acceleration of the passive party; determine the comfort cost associated with the first strategy pair according to the first comfort cost and the second comfort cost.

[0023] In a possible implementation, for any first strategy pair among all feasible strategy pairs, when determining the passability cost associated with the first strategy pair, the processing module is specifically used to: determine the first passability cost of the active party when executing the first driving strategy in the first strategy pair based on the first time and the second time, wherein the first time is the time when the active party passes the target point when executing the first driving strategy in the first strategy pair, and the second time is the time when the active party passes the target point with its current speed and acceleration, and the target point is the conflict point between the driving path of the active party and the driving path of the passive party; determine the second passability cost of the passive party when executing the second driving strategy in the first strategy pair based on the third time and the fourth time, wherein the third time is the time when the passive party passes the target point when executing the second driving strategy in the first strategy pair, and the fourth time is the time when the passive party passes the target point with its current speed and acceleration; determine the passability cost associated with the first strategy pair based on the first passability cost and the second passability cost.

[0024] In a possible implementation, for any first strategy pair among all feasible strategy pairs, when determining the offset cost associated with the first strategy pair, the processing module is specifically used to: determine the first offset cost of the active party when executing the first driving strategy in the first strategy pair based on a mapping relationship between a preset offset and an offset cost, and an offset when the active party executes the first driving strategy in the first strategy pair; determine the second offset cost of the passive party when executing the second driving strategy in the first strategy pair based on a mapping relationship between a preset offset and an offset cost, and an offset when the passive party executes the second driving strategy in the first strategy pair; determine the offset cost associated with the first strategy pair based on the first offset cost and the second offset cost.

[0025] In one possible implementation, for any first strategy pair among all feasible strategy pairs, when determining the inconsistency cost associated with the first strategy pair, the processing module is specifically used to: when the driving strategy of the target object in the first strategy pair is to only overtake the target vehicle, or to only give way to the target vehicle, determine the target probability of the target object overtaking the target vehicle, and, based on the target probability, determine the inconsistency cost; when the driving strategy of the target object in the first strategy pair is to both overtake the target vehicle and give way to the target vehicle, determine the inconsistency cost as a pre-set cost value.

[0026] In one possible implementation, for any first strategy pair among all feasible strategy pairs, when determining the decision penalty cost associated with the first strategy pair, the processing module is specifically used to: determine the decision penalty cost associated with the first strategy pair based on a pre-set decision penalty rule and the second driving strategy in the first strategy pair.

[0027] In one possible implementation, the second driving strategy in the first strategy pair is: the passive party can both overtake the active party and give way to the active party; when the processing module determines the decision penalty cost associated with the first strategy pair based on a pre-set decision penalty rule and the second driving strategy in the first strategy pair, it is specifically used to: determine the first decision penalty cost based on the decision penalty rule and the second driving strategy in the first strategy pair; determine the second decision penalty cost of the active party when executing the first driving strategy in the first strategy pair according to the acceleration corresponding to the first driving strategy in the first strategy pair and the current acceleration of the active party; determine the decision penalty cost associated with the first strategy pair according to the first decision penalty cost and the second decision penalty cost.

[0028] In a third aspect, the present application provides a vehicle, comprising the control device described in the second aspect or any possible implementation of the second aspect.

[0029] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a processor, the processor executes the method described in the first aspect or any possible implementation of the first aspect.

[0030] In a fifth aspect, the present application provides a computer program product. When the computer program product runs on a processor, the processor executes the method described in the first aspect or any possible implementation of the first aspect.

[0031] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a schematic diagram of an application scenario provided by an embodiment of the present application;

[0033] Figure 2 It is a hardware structure of a vehicle provided in an embodiment of the present application;

[0034] Figure 3 It is a flow chart of a control method provided in an embodiment of the present application;

[0035] Figure 4 is a schematic diagram of a vehicle-to-vehicle intersection provided by an embodiment of the present application;

[0036] Figure 5 is a schematic diagram of a comfort cost function provided in an embodiment of the present application;

[0037] Figure 6 is a schematic diagram of a passability cost function provided in an embodiment of the present application;

[0038] Figure 7 is a schematic diagram of a decision penalty cost function provided in an embodiment of the present application;

[0039] Figure 8 It is a structural schematic diagram of a control device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0040] The term "and / or" in this article is a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The symbol " / " in this article indicates that the associated objects are in an or relationship, for example, A / B means A or B.

[0041] The terms "first" and "second" in the specification and claims herein are used to distinguish different objects rather than to describe a specific order of the objects. For example, a first response message and a second response message are used to distinguish different response messages rather than to describe a specific order of the response messages.

[0042] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0043] In the description of the embodiments of the present application, unless otherwise specified, "multiple" means two or more than two. For example, multiple processing units refer to two or more processing units, etc.; multiple elements refer to two or more elements, etc.

[0044] For example, Figure 1 An application scenario is shown. Figure 1 As shown in (A), vehicles 100 and 200 travel to a T-shaped road condition, with vehicle 100 traveling in the direction indicated by line segment x and vehicle 200 moving in the direction indicated by line segment y. Figure 1 In (B), vehicle 200 merges into the road where vehicle 100 is located, and vehicle 100 is traveling in the direction indicated by line segment x, while vehicle 200 is moving in the direction indicated by line segment y. Figure 1 In (A) or (B), since line segments x and y intersect, that is, the driving trajectories of vehicles 100 and 200 conflict, there is a possibility of collision between vehicles 100 and 200. It should be understood that Figure 1 Only the situation where there is a possibility of collision between two vehicles is shown. Other situations where there is a possibility of collision between vehicles due to conflicts in the driving trajectories between the vehicles are still within the protection scope of this application.

[0045] In addition, Figure 1 In the illustrated scenario, vehicle 100 can be retained, while vehicle 200 can be replaced by other objects, such as a moving object or a stationary object, etc., and the scheme after the replacement is still within the protection scope of the present application. Similarly, vehicle 200 can be retained, while vehicle 100 can be replaced by other objects, such as a moving object or a stationary object, etc., and the scheme after the replacement is still within the protection scope of the present application. For ease of description, the following description will be based on retaining vehicle 100 as an example.

[0046] Generally, when there is a conflict between the driving trajectory of a vehicle and other objects (such as a moving object or a stationary object, etc.), the only two strategies that are often determined are to rush over or give way. However, this "black or white" rush-and-give-way decision may result in decision jumps, causing the vehicle to brake hard / slightly or even take over, resulting in a poor driving experience. Exemplarily, the driving trajectory of other objects can be but is not limited to the driving trajectory predicted for the vehicle. For example, when the other object is a stationary object, the vehicle can predict a motion trajectory for the object; when the other object is a moving object, the vehicle can also predict a motion trajectory for the object.

[0047] In view of this, an embodiment of the present application provides a control method. When there is a possibility of collision between the driving trajectory of a vehicle and other objects (such as a moving object, or a stationary object, etc.), the vehicle and other objects can be divided into active and passive parties, and the active party has the right of way priority over the passive party. Then, the vehicle can be controlled to test the intentions of other objects. When it is determined that the intentions of other objects are obvious, the final decision to rush in or give way is made. Thereby, the effect of slowly accelerating to rush in or slowly decelerating to give way is achieved, and the driving experience is improved.

[0048] For example, Figure 2 FIG. 1 shows a hardware structure of a vehicle. Figure 2 As shown, the vehicle 100 may include: a sensor component 110, a fusion unit 120 and an intelligent driving function component 130. The sensor component 110 and the fusion unit 120 are connected via an interface 140, and the fusion unit 120 and the intelligent driving function component 130 are connected via an interface 150.

[0049] The sensor assembly 110 may include a vehicle posture sensor and / or a perception sensor. The data collected by the sensor assembly 110 may be transmitted to the fusion unit 120 through the interface 140. The vehicle posture sensor may realize the acquisition of driving state information of the vehicle 100, such as speed, acceleration, heading angle, road topology, etc., and the acquisition of external environment information of the vehicle 100, such as road condition information. The perception sensor may realize the acquisition of information of other objects outside the vehicle 100, such as: driving state information, such as speed, heading angle, position, orientation, acceleration, road topology, etc. Optionally, the vehicle posture sensor may include one or more of a gyroscope sensor, a radar sensor, an ultrasonic sensor, a camera, a computer vision system, etc. Among them, the radar sensor may include a laser radar sensor and / or a millimeter wave radar sensor, etc. The perception sensor may include one or more of a camera, a radar sensor, an ultrasonic sensor, etc.

[0050] The radar sensor may be used to sense objects in the surrounding environment of the vehicle 100 using radio signals, and may also sense the speed and / or direction of travel of the objects, etc.

[0051] The camera can be used to capture multiple images of the vehicle's surroundings. The camera can be a still camera or a video camera.

[0052] The computer vision system can be operated to process and analyze the images captured by the camera to identify objects and / or features in the vehicle's surrounding environment. The objects and / or features may include traffic signs, road boundaries, obstacles, other objects, etc. The computer vision system may use object recognition algorithms, Structure from Motion (SFM) algorithms, video tracking, and other computer vision techniques.

[0053] The fusion unit 120 can transmit the data collected by the sensor component 110 to the intelligent driving function component 130 through the interface 150 , so that the intelligent driving function component 130 can implement the intelligent driving function based on the data collected by the sensor component 110 .

[0054] The intelligent driving function component 130 can receive data collected by the sensor component 110 and transmitted by the fusion unit 120 through the interface 150, and then predict the driving trajectory of other objects based on the received data, and / or make driving decisions to realize intelligent driving functions, such as adaptive cruise control (ACC), lane keeping assist (LKA), highway assist HWA (HWA), traffic jam assistant (TJA) and other different intelligent driving / autonomous driving functions.

[0055] The interface 140 can realize data transmission between the sensor component 110 and the fusion unit 120, which can be an interface between the sensor and the fusion unit specified in ISO130150. The interface 150 can realize data transmission between the fusion unit 120 and the intelligent driving function component 130. The message content transmitted by the interface 150 may include one or more of the following: the speed, heading angle, historical trajectory information, acceleration, road topology of the vehicle 100; the type, speed, heading angle, position, orientation, acceleration, road topology, etc. of other objects; the collision time between the vehicle 100 and other objects, etc.

[0056] In some embodiments, the intelligent driving function component 130 may include an object decision module and a motion planning module. The object decision module may determine whether the vehicle 100 will collide with other traffic participants when traveling along the reference path based on the data collected by the sensor component 110. Figure 1 , there is a collision between vehicles 100 and 200. For example, the reference path may refer to a reference benchmark used by the vehicle for object decision making, such as the center line of the current road, etc. The path mainly reflects real map information and can guide the driving direction of the vehicle.

[0057] In addition, the object decision module can also classify the conflict between the vehicle 100 and other traffic participants as game objects or non-game objects. Game objects refer to the mutual influence between the two. For example, continue to refer to Figure 1 , the driving decision of vehicle 100 (such as rushing or giving way, etc.) will affect the driving decision of vehicle 200. At the same time, the driving decision of vehicle 200 (such as rushing or giving way, etc.) will also affect the driving decision of vehicle 100. Therefore, vehicles 100 and 200 are game objects. Non-game objects refer to the absence of mutual influence between the two. For example, in a scenario where vehicle 100 follows other vehicles, the driving decision of vehicle 100 cannot affect the vehicle in front of it and traveling in the same direction. In the embodiment of the present application, the main problem is how to make driving decisions when the two are game objects to avoid collision conflicts between the two.

[0058] The motion planning module can perform lateral planning and longitudinal planning according to the driving decisions made by the object decision module. Lateral planning refers to the planning made in a direction parallel to the reference path (such as the center line of the lane, etc.), corresponding to the vehicle's obstacle avoidance, detour and other behaviors. Among them, the lateral planning may have coordinate information, but not speed information. Longitudinal planning refers to the planning made in the direction along the reference path, corresponding to the vehicle's acceleration, deceleration and other behaviors. Among them, the longitudinal planning may have speed information, but not coordinate information. Exemplarily, since the vehicle's driving trajectory is mainly composed of coordinate information and speed information, the lateral planning and longitudinal planning can together constitute the vehicle's driving trajectory.

[0059] It is understood that the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the vehicle 100. In other embodiments of the present application, the vehicle 100 may include more or fewer components than shown in the figure, or combine some components, or separate some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0060] Next, based on the above content, the control method provided in the embodiment of the present application is introduced.

[0061] For example, Figure 3 A control method is shown. The vehicle involved in the method may be, but is not limited to, the aforementioned vehicle 100. The scene involved in the method may be, but is not limited to, the aforementioned Figure 1The scenario described in the above description is that there is a possibility of collision between the driving routes of vehicles 100 and 200, that is, there is a certain probability of collision between the two vehicles. Of course, it can also be a scenario where there is a possibility of collision between the driving routes of vehicle 100 and other objects. It can be understood that the method can be executed by any device, equipment, platform, or device cluster with computing and processing capabilities. For example, it can be executed by a processor in vehicle 100 or a vehicle-mounted terminal, etc., which is not limited here. Figure 3 As shown, the control method may include S301 to S307, specifically:

[0062] S301. Divide a target vehicle and a target object into an active party and a passive party, wherein the active party has a right of way over the passive party, and there is a possibility of collision between the target vehicle and the target object.

[0063] In this embodiment, after the target vehicle collects information about each traffic participant in the environment, when the target vehicle senses that it has a possibility of collision with other traffic participants (hereinafter referred to as "target objects"), the target vehicle can classify itself and the target objects into active parties and passive parties according to traffic rules, wherein the active party has priority over the passive party. Figure 1 (A), according to traffic rules, left turns must give way to straight-moving vehicles, therefore, vehicle 100 is the active party and vehicle 200 is the passive party. For another example, when the target vehicle is moving straight and the target object is turning, it can be determined that the target vehicle is the active party and the target object is the passive party. When the target vehicle is turning and the target object is moving straight, it can be determined that the target vehicle is the passive party and the target object is the active party. In some embodiments, the traffic participants in the embodiments of the present application can be vehicles or other objects, which are not limited here.

[0064] S302: Obtain a first feasible strategy set for the active party, where the first strategy set includes at least one first driving strategy.

[0065] In this embodiment, the first strategy set can be pre-stored in the target vehicle, or obtained from the network in real time, or calculated in real time, which can be determined according to the actual situation and is not limited here. Among them, the first strategy set includes at least one first driving strategy. Exemplarily, each first driving strategy can be used to characterize at least one feasible information (such as acceleration, etc.) of the active party in the direction perpendicular to the lane where the target vehicle is located and one feasible driving information (such as offset, etc.) in the direction along the lane.

[0066] In some embodiments, the first strategy set can be determined based on at least a preset acceleration sampling space, an allowable range of the acceleration of the active party, and a preset lateral offset range. For example, the intersection of the preset acceleration sampling space and the allowable range of the acceleration of the active party can be used as the acceleration variation range in the first strategy set, and the preset lateral offset range can be used as the lateral offset variation range in the strategy space. For example, when the target vehicle is the active party, if the preset acceleration sampling space is [-4.0,3.0] m / s 2 , the target vehicle’s allowed acceleration range is [-3.0, 2.0] m / s 2 , then the acceleration range in the first strategy set is [-3.0, 2.0] m / s 2 If the preset lateral offset range is [-1, 1] m, the lateral offset variation range in the first strategy set is [-1, 1] m.

[0067] Furthermore, considering the balance between computational complexity and strategy space accuracy, the change interval of acceleration in the first strategy set and the offset interval of lateral offset can be set. For example, the acceleration can be set at an interval of 1 m / s 2 Change once, the lateral offset can be changed every 1m.

[0068] For example, if the acceleration range in the first strategy set is [-3.0, 2.0] m / s 2 , the range of lateral displacement is [-1,1]m. At this time, the acceleration change interval can be set to 1m / s 2 , the lateral offset of the target vehicle can be defined as when it keeps driving in the center of the current lane, it avoids to the left (i.e., deviates to the left from the lane centerline) by 1m, recorded as +1m, and avoids to the right (i.e., deviates to the right from the lane centerline) by 1m, recorded as -1m. Finally, the first strategy set shown in Table 1 can be generated. In the strategy set shown in Table 1, an acceleration and a lateral offset can form a driving strategy. For example, an acceleration of 1m / s 2 The driving strategy composed of the lateral deviation of -1m is: with an acceleration of 1m / s 2 , and drive 1m to the right away from the center line of the lane.

[0069]

[0070] Table 1

[0071] In some embodiments, after obtaining the first strategy set, each driving strategy in the first strategy set can be deduced in the time domain to form a first trajectory set corresponding to the feasible driving strategies of the active party. Exemplarily, when performing the time domain deduction, the system delay of the active party (such as the time for transition from one acceleration to another, etc.), speed limit and other constraints can be observed. When the active party accelerates to the road speed limit, the deduction is maintained at a uniform speed at the road speed limit. When all the driving strategies in the first strategy set are deduced, the first trajectory set can be obtained. Exemplarily, the first trajectory set can include at least one driving trajectory, and each driving strategy in the first strategy set can correspond to a driving trajectory.

[0072] After obtaining the first policy set, S303 may be executed.

[0073] S303. According to each first driving strategy in the first strategy set, the driving parameters of the active party at the current moment, and the driving parameters of the passive party at the current moment, obtain the second driving strategy of the passive party under each first driving strategy in the first strategy set to obtain a second strategy set, wherein the second driving strategy is any one of the following: the passive party only overtakes the active party, the passive party only gives way to the active party, or the passive party can both overtake the active party and give way to the active party.

[0074] In this embodiment, the time when the active party reaches the position where it collides with the passive party can be calculated based on the driving parameters (such as speed, acceleration, position, etc.) of the active party at the current moment and each first driving strategy. Then, under each first driving strategy, it is solved whether the passive party can pass the position where the two collide with each other at a certain time interval and distance interval when driving with its current driving parameters (such as speed, acceleration, position, etc.) as initial parameters, and when it can pass the position where the two collide with each other at a certain time interval and distance interval, the actions that the passive party can make, such as only overtaking the active party, or only giving way to the active party, or both overtaking the active party and giving way to the active party, so as to obtain the second driving strategy of the passive party under each first driving strategy in the first strategy set, thereby obtaining the second strategy set. Among them, the second driving strategy is any one of the following: the passive party only overtakes the active party, the passive party only gives way to the active party, or the passive party can both overtake the active party and give way to the active party. Exemplarily, the driving parameters at the current moment may refer to, but are not limited to: driving parameters observed when acquiring the first strategy set, or driving parameters observed when solving the second strategy set, or driving parameters most recently observed before executing the method.

[0075] In some embodiments, quadratic programming (QP) and other algorithms can be used to solve the driving position, driving speed, acceleration, dynamic kinematic constraints, collision time, and road rules of the active and passive parties to solve the acceleration / deceleration / avoidance driving trajectory of the passive party and determine the driving strategy of the passive party. Exemplarily, the driving speed, position, direction, acceleration, road topology, etc. of the target object can be input into the pre-trained model to predict the driving trajectory and / or driving strategy of the passive party.

[0076] For example, if Figure 4 As shown, when vehicle 100 is the active party and at the current moment, the speed of vehicle 100 is 17 km / h, the current observed acceleration of vehicle 100 is -0.67 m / s 2 , the static speed limit of the road is 60km / h. The acceleration of vehicle 100 is 1m / s 2 , taking the driving strategy with a lateral offset of 0m as an example, the feasible trajectory 46 of vehicle 200 (i.e., the passive party) can be obtained by using QP solution. At this time, the distance from vehicle 100 to the trajectory conflict point 43 is 20.11m. When vehicle 100 adopts an acceleration of 1m / s 2 When driving, the time to reach the conflict point is eTTC = 3.51s.

[0077] A width of 0.5 m on each side of the width of vehicle 100 (i.e., the area formed by lines 41 and 42) is taken as the safety passage of vehicle 100. Vehicle 200 travels along its predicted path (i.e., feasible trajectory 46). The point where vehicle 200 starts to invade the safety passage of vehicle 100 is taken as the invasion point (i.e., when vehicle 200 is at position 44), and the point where vehicle 200 completely leaves the safety passage of vehicle 100 is taken as the exit point (i.e., when vehicle 200 is at position 45).

[0078] The conditions for vehicle 200 to safely overtake vehicle 100 and safely give way to vehicle 100 are: when giving way to vehicle 100, the time when vehicle 200 arrives at the intrusion point needs to be a certain time after vehicle 100 passes through trajectory conflict point 43. When overtaking vehicle 100, the time when vehicle 200 arrives at the departure point needs to be a certain time before vehicle 100 arrives at trajectory conflict point 43. Exemplarily, the time interval for vehicle 200 to safely overtake / give way can be pre-set to use different safety time intervals according to different scenarios. For example: the safety time interval can be 1s, that is, if vehicle 200 overtakes vehicle 100, it needs to leave the safety passage where vehicle 100 is located within 2.41s, and if vehicle 200 gives way to vehicle 100, it needs to enter the safety passage where vehicle 100 is located after 4.41s.

[0079] The distance from vehicle 200 to track intersection 43 is 11.92 m, and the observed acceleration of vehicle 200 is 0.0 m / s 2 , the current speed is 17km / h. Considering the width of the safety passage where vehicle 100 is located and the road topology angle where vehicle 200 is located, it can be obtained that the distance between the intrusion point position 44 of vehicle 200 and the current position of vehicle 200 is 7.63m, and the distance between the departure point position 45 of vehicle 200 and the current position of vehicle 200 is 13.4m. In solving the driving strategy of vehicle 200, if the QP (quadratic programming) method is used, when solving the yielding strategy, all maximum displacement constraints before 4.41s are 7.63m, and when solving the rushing strategy, all minimum displacement constraints after 2.41s are 13.4m. The maximum and minimum acceleration constraints and maximum speed constraints used in the solution process can be set according to the kinematic and dynamic constraints of vehicle 200 and the traffic rules constraints.

[0080] The acceleration of vehicle 100 is 1m / s 2 , the driving strategy with a lateral offset of 0m can simultaneously find the solutions of vehicle 200 giving way to vehicle 100 and overtaking vehicle 100 that meet the above conditions. That is, at this time, vehicle 200 can either overtake vehicle 100 or give way to vehicle 100, and the intention of vehicle 200 is unclear.

[0081] For the remaining vehicle 100, the driving strategy corresponding to the vehicle 200 is solved. When the driving strategy of the vehicle 100 is: lateral offset 0m and acceleration 2m / s 2 When , the strategy of vehicle 200 giving way to vehicle 100 can be obtained, while the strategy of vehicle 200 overtaking vehicle 100 cannot meet the safe staggering constraint and other constraints regardless of whether vehicle 200 deviates, so it is impossible to find a feasible solution. Therefore, vehicle 200 can only give way to vehicle 100 at this time. The intention of vehicle 200 is clear. When the driving strategy of vehicle 100 is: lateral deviation 0m and acceleration is -3m / s 2 When , we can only find the strategy of vehicle 200 overtaking vehicle 100, so vehicle 200 can only overtake vehicle 100 at this time, and the intention of vehicle 200 is clear. When the driving strategy of vehicle 100 is: lateral offset +1m (offset to the left), and the acceleration is 1m / s 2 , no matter whether vehicle 200 is offset or not, it is impossible to find a strategy for vehicle 200 to overtake or give way to vehicle 100 that satisfies the constraint conditions, so there is no solution at this time, that is, it is impossible to safely overtake or give way to vehicle 100. After solving all the driving strategies of vehicle 200, the obtained second strategy set can be shown in Table 2 below. In Table 2, the content except the first column and the first row is the second strategy set of vehicle 200 (i.e., the passive party). For example, referring to Table 2, the driving strategy of the active party is "to offset 1m laterally and accelerate -3m / s2 When the passive party is driving, the driving strategy is "overtaking the active party", that is, the passive party can only overtake the active party; when the active party's driving strategy is "with a lateral offset of 0m and an acceleration of 1m / s 2 When the passive party is driving, the driving strategy is "overtaking and giving way to the active party", that is, the passive party can both overtake the active party and give way to the active party; when the active party's driving strategy is "laterally offset by 1m and accelerating by 1m / s 2 When the passive party is in a state of "driving", it is impossible to avoid a collision with the active party. At this time, it is impossible to find the driving strategy of the passive party, that is, "there is no solution".

[0082]

[0083] Table 2

[0084] In some embodiments, in the process of obtaining the second strategy set based on the first strategy set, the driving parameters of the active party at the current moment, and the driving parameters of the passive party at the current moment, the driving trajectory of the passive party can be deduced in the time domain according to the driving trajectory corresponding to each driving strategy in the first strategy set, and the conditions that the passive party needs to meet when safely overtaking and / or giving way to the active party, so as to form a second trajectory set corresponding to the feasible driving strategy of the passive party. Exemplarily, when performing time domain deduction, the system delay of the passive party (such as the time of transition from one acceleration to another acceleration, etc.), speed limit and other constraints can be observed. When the passive party accelerates to the road speed limit, the deduction is maintained at a uniform speed deduction at the road speed limit. When all the driving strategies in the second strategy set are deduced, the second trajectory set can be obtained. Exemplarily, the second trajectory set can include at least one driving trajectory, and each driving strategy in the second strategy set can correspond to a driving trajectory.

[0085] After the second policy set is obtained, S304 may be executed.

[0086] S304. Determine a target strategy pair set according to the first strategy set and the second strategy set, wherein the target strategy pair set includes at least one feasible strategy pair, and each feasible strategy pair consists of a first driving strategy and a second driving strategy.

[0087] In this embodiment, after obtaining the first strategy set and the second strategy set, a target strategy pair set can be determined from the two strategy sets, and the target strategy pair set includes at least one feasible strategy pair, and each feasible strategy pair consists of a first driving strategy and a second driving strategy. For example, referring to Table 2, the driving strategy "the active party moves with a lateral offset of 1m and an acceleration of -3m / s 2 The driving strategy "the passive party overtakes the active party" can form a feasible strategy pair. The driving strategy "the active party moves with a lateral displacement of 0m and an acceleration of 1m / s2 The driving strategy of "passive party overtaking and giving way to active party" can form a feasible strategy pair.

[0088] In addition, when the passive party has a safe driving strategy that can both overtake and give way to the active party, the feasible strategy pair composed of this driving strategy can be called a bilateral solution strategy pair. For example, referring to Table 2, the driving strategy "the active party has a lateral displacement of 0m and an acceleration of 1m / s 2 The feasible strategy pair consisting of the driving strategy "the passive party overtakes and gives way to the active party" can be called a bilateral solution strategy pair. When the passive party can only find a safe driving strategy of overtaking or giving way to the active party, the feasible strategy pair consisting of this driving strategy can be called a unilateral solution strategy pair. For example, referring to Table 2, the driving strategy "the active party moves with a lateral offset of 1m and an acceleration of -3m / s 2 The driving strategy "the passive party overtakes the active party" and the driving strategy "the passive party overtakes the active party" form a feasible strategy pair, which can be called a unilateral solution strategy pair.

[0089] S305 : Determine the execution cost of each feasible strategy pair in the target strategy pair set to obtain a first cost set, wherein the first cost set includes the execution cost of each feasible strategy pair.

[0090] In this embodiment, the execution cost of each feasible strategy in the target strategy pair set can be analyzed to obtain a first cost set, wherein the first cost set includes the execution cost associated with each feasible strategy pair. The cost associated with each feasible strategy pair is used to indicate the cost of executing the feasible strategy pair.

[0091] In this embodiment, the execution cost associated with each feasible strategy pair may include one or more of the following: comfort cost, passability cost, deviation cost, inconsistency cost, or decision penalty cost.

[0092] The following is an introduction to each cost.

[0093] (1) Comfort cost

[0094] The comfort cost is used to characterize the comfort level when executing a feasible strategy. The higher the comfort cost, the lower the comfort level. In some embodiments, for the active party or the passive party, the smaller the acceleration change rate, the better the corresponding comfort, and the smaller the comfort cost.

[0095] In this embodiment, for any feasible strategy pair, the acceleration change amount when the active party executes the corresponding driving strategy under its current acceleration can be processed based on the preset comfort cost function to obtain the comfort cost of the active party when executing the corresponding driving strategy. Similarly, the acceleration change amount when the passive party executes the corresponding driving strategy under its current acceleration can be processed based on the preset comfort cost function to obtain the comfort cost of the passive party when executing the corresponding driving strategy. Finally, the comfort cost of the active party and the comfort cost of the passive party can be weighted summed (of course, other calculation methods can also be used, such as selecting one, averaging, etc., which are not limited here) to obtain the comfort cost associated with the corresponding feasible strategy pair. Exemplarily, the current acceleration of the active party can refer to, but is not limited to: the acceleration of the active party observed when obtaining the first strategy set, or the acceleration of the active party observed when solving the second strategy set, or the latest observed acceleration of the active party before executing the method.

[0096] For example, if the preset comfort cost function is Figure 5 As shown, y = 0.1429x, where x is the horizontal axis and y is the vertical axis. Figure 1 The vehicle 100 described in the figure is the active party, the vehicle 200 is the passive party, and the current observed acceleration of the vehicle 100 is -0.67 m / s 2 , the current observed acceleration of vehicle 200 is 0m / s 2 In addition, the first strategy set may be as shown in Table 1, and the second strategy set may be as shown in Table 2. When the acceleration corresponding to the vehicle 100 is 1 m / s 2 , and the driving strategy of lateral offset 0m, the corresponding driving strategy of vehicle 200 is to rush and yield. At the same time, when the driving strategy of vehicle 200 is to rush, its acceleration is 1.45m / s 2 , its corresponding driving strategy is to give way, and its acceleration is 0.69m / s 2 .

[0097] Among them, for vehicle 100, under this feasible strategy pair, its acceleration change is eDeltaAcc=1-(-0.67)=1.67m / s 2 , combined with Figure 5 The comfort cost function shown can determine that the comfort cost of the vehicle 100 is eComfCost=0.92×(1.67÷7)=0.2205. Among them, 0.92 is the weight of the comfort cost of the vehicle 100, and the value can be set based on actual conditions.

[0098] For vehicle 200, since it has a bilateral solution under this feasible strategy pair (i.e., it can either overtake vehicle 100 or give way to vehicle 100), the comfort cost of vehicle 200 is the average of the comfort costs corresponding to the overtaking solution and the giving way solution (of course, other calculation methods can also be used, such as summing, selecting one, etc., which are not limited here). Among them, the acceleration change corresponding to the overtaking solution is oDeltaAcc = 1.45-0 = 1.45m / s 2 , the comfort cost at this time is oComfCost = 1.45÷7 = 0.2071. The corresponding acceleration change of the solution is oDeltaAcc = 0.69-0 = 0.69m / s 2 , the comfort cost at this time is oComfCost=0.69÷7=0.0986. The final comfort cost of vehicle 200 under the feasible strategy is oComfCost=1×(0.2071+0.0986)÷2=0.1529. Among them, 1 is the weight of the comfort cost of vehicle 200, which can be set based on actual conditions.

[0099] Further, it can be determined that the comfort cost associated with the feasible strategy is oComfCost = 0.2205 + 0.1592 = 0.3797. At this time, the weights of the active party and the passive party are both 1, and of course they can be other values, which are not limited here. For the comfort costs associated with other feasible strategy pairs, you can refer to the above calculation method, which will not be repeated here.

[0100] (2) Passability cost

[0101] The passability cost is used to characterize the efficiency of the active party and / or the passive party passing through the conflict point between the two (i.e., the conflict point of the driving paths between the two). The faster the time to pass through the conflict point, the smaller the corresponding passability cost.

[0102] In this embodiment, for any feasible strategy pair, the time when the active party passes through the corresponding conflict point when executing the driving strategy in the feasible strategy pair (also referred to as the "first time") and the time when the active party passes through the corresponding conflict point under the current acceleration and speed (also referred to as the "second time") can be processed based on the preset passability cost function to obtain the passability cost of the active party when executing the corresponding driving strategy. Similarly, the time when the passive party passes through the corresponding conflict point when executing the driving strategy in the feasible strategy pair (also referred to as the "third time") and the time when the passive party passes through the corresponding conflict point under the current acceleration and speed (also referred to as the "fourth time") can be processed based on the preset passability cost function to obtain the passability cost of the passive party when executing the corresponding driving strategy. Finally, the passability cost of the active party and the passability cost of the passive party can be weighted summed (of course, other calculation methods can also be used, such as selecting one, averaging, etc., which are not limited here) to obtain the passability cost associated with the corresponding feasible strategy pair.

[0103] For example, if the preset passability cost function is Figure 6 As shown, that is, y = 0.0833x + 0.5, where x is the horizontal axis and y is the vertical axis, and Figure 6 The middle horizontal axis is the time difference between the time it takes to pass the conflict point when the driving strategy is executed and the time it takes to pass the conflict point normally (i.e., when the driving strategy is not executed). Figure 1 The vehicle 100 described in the above is the active party, and the vehicle 200 is the passive party. In addition, if during the simulation, the time for vehicle 100 to pass the conflict point (also called the "collision point") at the current acceleration and speed is eRealPassTime=4.47s, and the time for vehicle 200 to pass the conflict point at the current acceleration and speed is oRealPassTime=2.52s. In addition, the first strategy set can be as shown in the aforementioned Table 1, and the second strategy set can be as shown in the aforementioned Table 2. When the acceleration corresponding to vehicle 100 is 1m / s 2 , and under the driving strategy with a lateral offset of 0m, the corresponding driving strategy of vehicle 200 is to rush in and give way.

[0104] If during the simulation, the time eSamplePassTime = 3.41s for the vehicle 100 to pass the conflict point under the driving strategy, the time difference between the time it normally passes the conflict point and the time it normally passes the conflict point is eDeltaPassTime = eSamplePassTime - eRealPassTime = 3.41 - 4.47 = -1.06. Figure 6, it can be determined that the passability cost of the vehicle 100 under this feasible strategy is ePassCost = 1 × (0.0833 × (-1.06) + 0.5) = 0.4117. Among them, 1 is the weight of the passability cost of the vehicle 100, and this value can be set based on the actual situation.

[0105] If, during the simulation, the time for vehicle 200 to yield and pass the conflict point under the driving strategy corresponding to vehicle 100 is oSamplePassTime=5.02s, then the time difference between this time and the time it normally passes through the conflict point is oDeltaPassTime=oSamplePassTime-oRealPassTime=5.02-2.52=2.5s, and the passability cost of vehicle 200 when yielding is oPassCost=0.0833×2.5+0.5=0.708. If the time for vehicle 200 to rush through the conflict point is oSamplePassTime=2.3s, then the time difference between this time and the time it normally passes through the conflict point is oDeltaPassTime=oSamplePassTime-oRealPassTime=2.3-2.52=-0.22, and the passability cost of vehicle 200 when rushing through is oPassCost=0.0833×(-0.22)+0.5=0.4817. The final passability cost of vehicle 200 under the feasible strategy pair is oPassCost = 1 × (0.708 + 0.4871) ÷ 2 = 0.5976. Among them, 1 is the weight of the passability cost of vehicle 200, and this value can be set based on the actual situation. It should be understood that when determining the final passability cost of vehicle 200 under the feasible strategy pair based on the passability cost corresponding to the rush-through solution of vehicle 200 and the passability cost corresponding to the yielding solution, other calculation methods can also be used, such as summing, selecting one, etc., which are not limited here.

[0106] Further, it can be determined that the passability cost associated with the feasible strategy pair is oComfCost = 0.4117 + 0.5976 = 1.0093. At this time, the weights of the active party and the passive party are both 1, and of course they can be other values, which are not limited here. For the passability costs associated with other feasible strategy pairs, you can refer to the above calculation method, which will not be repeated here.

[0107] (3) Offset cost

[0108] The offset cost is used to characterize the evaluation of the offset that occurs when the active party and / or the passive party executes the corresponding driving strategy. When no offset is required, the offset cost is 0, and of course other values ​​can be taken, which are not limited here; when an offset is required, the offset cost of the active party when executing the corresponding driving strategy can be determined based on the mapping relationship between the preset offset and the offset cost, and the offset when the active party executes the corresponding driving strategy, and / or the offset cost of the passive party when executing the corresponding driving strategy can be determined based on the mapping relationship between the preset offset and the offset cost, and the offset when the passive party executes the corresponding driving strategy. Finally, the offset cost associated with a feasible strategy pair can be obtained based on the determined offset cost of the active party when executing the corresponding driving strategy and the offset cost of the passive party when executing the corresponding driving strategy.

[0109] For example, if the offset is 0m, the offset cost is 0, and if the offset is 1m or -1m, the offset cost is 0.3. Figure 1 , if vehicle 100 is the active party and vehicle 200 is the passive party, and the driving strategy corresponding to vehicle 100 is the driving strategy in Table 1, and the driving strategy corresponding to vehicle 200 is the driving strategy in Table 2. Then, vehicle 100 accelerates at 1 m / s 2 And under the driving strategy of lateral offset 0m, the offset cost eOffsetCost of vehicle 100 is 0. In the deduction process, if under this driving strategy, vehicle 200 does not need to offset and a bilateral solution can be obtained, then the offset cost oOffsetCost of vehicle 200 is 0.

[0110] Further, it can be determined that the offset cost oComfCost = 0 + 0 = 0 associated with the feasible strategy pair; of course, other calculation methods can also be used, such as selecting one, averaging, etc., which are not limited here. At this time, the weights of the active party and the passive party are both 1, and of course they can be other values, which are not limited here. For the offset costs associated with other feasible strategy pairs, you can refer to the above calculation method, which will not be repeated here.

[0111] (4) Inconsistency Cost

[0112] The inconsistency cost is used to characterize the evaluation of the deviation between the driving behavior of the target object in the feasible strategy and the actual driving behavior of the target object. It is mainly determined by the probability of the passive party overtaking the active party as input. Among them, for the probability of the passive party overtaking the active party, the relative position and relative speed of the passive party and the active party, the speed, position, acceleration of the passive party, historical observation data, etc. can be input into the pre-set model to obtain the probability of the passive party overtaking the active party.

[0113] In this embodiment, when solving the driving strategy of the passive party, if a bilateral solution can be solved, the inconsistency cost can be 0.5, of course, it can also be other values, which are not limited here. When only one solution can be found, and the solution is to rush in, the inconsistency cost can be: 1-the probability of the passive party rushing in the active party. When only one solution can be found, and the solution is to give way, the inconsistency cost can be: the probability of the passive party rushing in the active party. In other words, when the driving strategy of the target object in a certain strategy pair is to only rush in the target vehicle, or to only give way to the target vehicle, the target probability of the target object rushing in the target vehicle can be determined first, and then the inconsistency cost associated with the strategy pair can be determined based on the target probability; when the driving strategy of the target object in a certain strategy pair is to both rush in the target vehicle and give way to the target vehicle, the inconsistency cost associated with the strategy pair can be determined as a pre-set cost value.

[0114] For example, if the probability of the passive player taking over the active player is 0.7, and at the same time, Figure 1 The vehicle 100 described in the figure is the active party, the vehicle 200 is the passive party, and the first strategy set can be as shown in the aforementioned Table 1, and the second strategy set can be as shown in the aforementioned Table 2.

[0115] The corresponding acceleration of vehicle 100 is 1 m / s 2 , and under the driving strategy of lateral offset 0m, the corresponding driving strategy of vehicle 200 is to rush and yield, that is, there is a bilateral solution. Therefore, at this time, the inconsistency cost probCost of vehicle 200 = 0.3 × 0.5 = 0.15. Among them, 0.3 is the inconsistency cost weight, which can be set based on actual conditions.

[0116] The corresponding acceleration of vehicle 100 is 2 m / s 2 , and under the driving strategy of lateral offset 0m, the corresponding driving strategy of vehicle 200 can only be to yield. Therefore, at this time, the inconsistency cost probCost of vehicle 200 = 0.3 × 0.7 = 0.21. Among them, 0.3 is the inconsistency cost weight, which can be set based on actual conditions.

[0117] The corresponding acceleration of vehicle 100 is -2 m / s 2 , and under the driving strategy of lateral offset 0m, the corresponding driving strategy of vehicle 200 can only be to rush. Therefore, at this time, the inconsistency cost probCost of vehicle 200 = 0.3 × (1-0.7) = 0.09. Among them, 0.3 is the inconsistency cost weight, which can be set based on actual conditions.

[0118] (5) Decision-making penalty cost

[0119] The decision penalty cost is used to characterize the evaluation of whether the intention of the active party is clear. It may refer to the penalty cost corresponding to the driving strategy of the passive party obtained based on the driving strategy of the active party, which is a unilateral solution or a bilateral solution. Among them, when there is a bilateral solution in the obtained solution, it indicates that the intention of the passive party is still unclear. Therefore, the penalty can be set to be high when the obtained solution is a unilateral solution, and low when the obtained solution is a bilateral solution. Exemplarily, the decision penalty costs corresponding to the unilateral solution and the bilateral solution can be pre-set, that is, the decision penalty rules can be pre-set, and then the corresponding decision penalty costs can be determined in combination with the driving strategy of the passive party. For example, the decision penalty cost corresponding to the unilateral solution can be set to 1, and the decision penalty cost corresponding to the bilateral solution can be set to 0.

[0120] In addition, when the passive party solves the bilateral solution, if the difference between the acceleration of the active party under the driving strategy and its current acceleration is large, the acceleration change of the active party when executing the driving strategy is large, affecting the driving experience, so the penalty of the bilateral solution can be increased. Exemplarily, the difference between the acceleration of the active party under the driving strategy and its current acceleration can be processed based on a preset penalty cost function to obtain the decision penalty cost associated with the corresponding feasible strategy. Then, the final decision penalty cost is determined based on the determined decision penalty cost and the decision penalty cost corresponding to the passive party.

[0121] For example, if the default penalty cost function is Figure 7 As shown, y = 0.333x, where x is the horizontal axis and y is the vertical axis. Figure 1 The vehicle 100 described in the figure is the active party, the vehicle 200 is the passive party, and the first strategy set can be as shown in the aforementioned Table 1, and the second strategy set can be as shown in the aforementioned Table 2.

[0122] The corresponding acceleration of vehicle 100 is 1 m / s 2 And under the driving strategy of lateral offset 0m, the corresponding driving strategy of vehicle 200 is to rush and yield, that is, there is a bilateral solution. Therefore, the basic penalty is eBasicPunishmentCost=0.

[0123] Furthermore, if the current acceleration of the vehicle 100 is -0.67 m / s 2 , then the acceleration change is eDeltaAcc = 1-(-0.67) = 1.67m / s 2 . Combined Figure 7 , we can get the decision penalty cost eDeltaAccPunishmentCost = 1 × 0.333 × 1.67 = 0.55. Among them, 1 is the weight of the decision penalty cost, and the value can be set based on the actual situation.

[0124] Further, it can be determined that the vehicle 100 has an acceleration of 1 m / s 2 And the decision penalty cost under the driving strategy of lateral offset 0m is Cost = 0 + 0.55 = 0.55. Of course, a certain weight value can also be set, for example, the weight of the basic penalty cost is 0.4, the weight of the penalty cost obtained based on the acceleration change is 0.6, etc., which can be determined according to the actual situation and is not limited here.

[0125] It should be understood that the above-described costs can be selected one by one or more, depending on the actual situation, and are not limited here. When multiple costs are selected, these costs can be weighted summed or averaged, and the final result can be used as the cost associated with the corresponding feasible strategy pair. In addition, when the driving strategy in the second strategy set is unsolvable, the cost associated with the feasible strategy pair corresponding to the driving strategy can be set to infinity, that is, the cost of executing the feasible strategy pair is very large.

[0126] For example, taking the five costs described above as an example, by summing up each of the costs, the active party can obtain the acceleration of 1m / s 2 And the final cost associated with the feasible strategy with a lateral offset of 0m is costTotal=0.3797+1.0093+0+0.15+0.55=2.089.

[0127] In addition, the above steps are calculated for each feasible strategy pair composed of Table 1 and Table 2, and the total cost of all feasible strategy pairs can be obtained as shown in Table 3. In Table 3, except for the first strategy set and the second strategy set, the content is the cost associated with each feasible strategy pair.

[0128]

[0129] Table 3

[0130] After the first cost set is obtained, S306 may be executed.

[0131] S306 . Determine a target driving strategy according to the first cost set, where the target driving strategy is a driving strategy of the target vehicle associated with the lowest execution cost in the first cost set.

[0132] In this embodiment, after obtaining the first cost set, the target driving strategy can be determined according to the first cost set. Since the cost of executing the lowest cost in the first cost set is the lowest, the driving strategy of the target vehicle associated with the lowest execution cost in the first cost set can be used as the target driving strategy.

[0133] As a possible implementation, when the second driving strategy in the feasible strategy pair corresponding to the lowest cost in the first cost set is: the passive party only overtakes the active party, or the passive party only gives way to the active party, since at this time, regardless of whether the target object is the active party or the passive party, its driving strategy is very clear, it either overtakes or gives way, therefore, at this time, the target vehicle can be controlled to execute a driving strategy opposite to that of the target object. Exemplarily, when the driving strategy of the target object is to overtake the target vehicle, the target vehicle can be controlled to quickly slow down and give way to the target object, that is, at this time, the driving strategy of the target vehicle is: give way to the target object; when the driving strategy of the target object is to give way to the target vehicle, the target vehicle can be controlled to quickly accelerate to overtake the target object, that is, at this time, the driving strategy of the target vehicle is to overtake the target object, thereby allowing the target vehicle to quickly respond to the driving intention of the target object.

[0134] As another possible implementation method, when the second driving strategy in the feasible strategy pair corresponding to the lowest cost in the first cost set is: the passive party can both overtake the active party and give way to the active party, if the target vehicle is the active party and the target object is the passive party, then the driving intention of the target object is still unclear at this time, that is, the target object can both overtake the target vehicle and give way to the target vehicle. At this time, if the target vehicle rashly executes the decision of overtaking or giving way, it is easy to brake hard / slightly or even take over, and the driving experience is poor. Therefore, at this time, the target vehicle can be controlled according to the first driving strategy in the feasible strategy pair corresponding to the lowest cost in the first cost set to test the driving intention of the target object, that is, the first driving strategy in the feasible strategy pair corresponding to the lowest cost in the first cost set is used as the driving strategy of the target vehicle. Among them, since the target vehicle is the active party at this time, the target vehicle has a higher priority right of way than the target object, that is, the right of way of the target vehicle is higher than that of the target object. At the same time, since the party with lower road right often needs to give way to the party with higher road right during driving, the target vehicle can be controlled to accelerate, decelerate or drive at a constant speed to test the driving intention of the target object. In addition, when controlling the target vehicle to accelerate or decelerate, in order to reduce the discomfort of the people in the vehicle, the change in the speed of the target vehicle can be controlled to be less than the first threshold, so that the target vehicle can accelerate or decelerate slowly, etc.

[0135] As another possible implementation, when the second driving strategy in the feasible strategy pair corresponding to the lowest cost in the first cost set is: the passive party can both overtake the active party and give way to the active party, if the target vehicle is the passive party and the target object is the active party, then the driving intention of the target object is still unclear, that is, the target object can both overtake the target vehicle and give way to the target vehicle. At this time, if the target vehicle rashly executes the decision of overtaking or giving way, it is easy to cause heavy braking / point braking or even take over, and the driving experience is poor. In addition, since the target vehicle is the passive party at this time, the target vehicle has a lower priority right of way relative to the target object, that is, the right of way of the target vehicle is lower than that of the target object. At the same time, since it is often the party with lower right of way that needs to give way to the party with lower right of way during driving, the target vehicle can be controlled to slow down to test the driving intention of the target object. In other words, the driving strategy of the target vehicle at this time is: give way to the target object. In addition, when controlling the target vehicle to slow down, in order to reduce the discomfort of the people in the vehicle, the change in the speed of the target vehicle can be controlled to be less than the second threshold, so that the target vehicle can slow down slowly.

[0136] That is to say, when the feasible strategy corresponding to the lowest cost in the first cost set is a unilateral solution for the driving strategy of the passive party, and it is the active party that is trying to overtake, the longitudinal decision of the active party to the passive party is to give way. When the feasible strategy is a unilateral solution for the driving strategy of the passive party, and it is the active party that is trying to give way, the longitudinal decision of the active party to the passive party is to overtake. When the feasible strategy is a bilateral solution for the driving strategy of the passive party, the longitudinal decision of the active party to the passive party is critical overtaking / giving way, that is, the two parties continue to play the game. Among them, when the feasible strategy is a bilateral solution for the driving strategy of the passive party, the maximum and minimum range of the target vehicle's avoidance can be constrained in the lateral direction, and the maximum and minimum range of the target vehicle's speed can be constrained in the longitudinal direction, that is, bilateral constraints are performed. When the feasible strategy is a unilateral solution for the driving strategy of the passive party, the maximum or minimum range of the target vehicle's avoidance can be constrained in the lateral direction, and the maximum or minimum range of the target vehicle's speed can be constrained in the longitudinal direction, that is, unilateral constraints are performed.

[0137] S307: Control the target vehicle according to the target driving strategy.

[0138] In this embodiment, after the target driving strategy is determined, the target vehicle can be controlled according to the target driving strategy. Exemplarily, when the target driving strategy is: the target vehicle rushes to the target object, the target vehicle is controlled to rush to the target object; when the target driving strategy is: the target vehicle gives way to the target object, the target vehicle is controlled to give way to the target object; when the target driving strategy is: the driving strategy of the target vehicle associated with the lowest execution cost in the first cost set, the target vehicle is controlled to execute the driving strategy, and after a preset time interval, one or more steps of S301 to S307 are executed again, and the cycle continues until it is determined that the driving strategy of the target vehicle is to only rush to the target object or to only give way to the target object. For example, when the target driving strategy is: the driving strategy of the target vehicle associated with the lowest execution cost in the first cost set, and the driving strategy is: the acceleration is 1m / s 2 When the lateral offset is 0m, the target vehicle is controlled to accelerate at 1m / s 2 And the lateral offset is 0m.

[0139] In this way, when the target vehicle is far away from the target object, the target object's driving intention to rush or give way to the target vehicle is unclear. At this time, the target vehicle can make a critical rush-and-give-way decision, that is, the target vehicle can continue to move forward and test the target object's driving intention. When the target object's driving intention is clear, the target vehicle can make corresponding adjustments based on the target object's driving intention, such as rushing to the target object or giving way to the target object.

[0140] Therefore, in the early stage of the game between the active and passive parties or when the intention of one party is unclear, the planning results of the lateral planning / longitudinal planning can be accurately controlled through bilateral constraints, and as the decision constraints change continuously from uncertain bilateral constraints to deterministic unilateral constraints, the autonomous driving system can make human-like, flexible and continuous decisions in the face of game scenarios. It achieves the effect of controlling the target vehicle to slowly accelerate or decelerate when the driving intention of the target object is unclear, and the effect of controlling the target vehicle to quickly respond to the driving intention of the target object when the driving intention of the target object is clear, avoiding the planning jump caused by the decision jump caused by the unilateral decision-making during the interaction process, which in turn causes the entire autonomous driving system to brake incorrectly / heavily or suddenly take over the driving intention, thereby improving the driving experience.

[0141] It is understandable that the size of the sequence number of each step in the above embodiment does not mean the order of execution, and 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 embodiment of the present application. In addition, in some possible implementations, each step in the above embodiment can be selectively executed according to actual conditions, and can be partially executed or fully executed, which is not limited here.

[0142] Based on the method in the above embodiment, an embodiment of the present application provides a control device.

[0143] For example, Figure 8 A control device is shown. Figure 8 As shown, the control device 800 may include: a division module 810 and a processing module 820. The division module 810 is used to divide the target vehicle and the target object into an active party and a passive party, wherein the active party has a priority right of way relative to the passive party, and there is a possibility of collision between the target vehicle and the target object. The processing module 820 is used to obtain a feasible first strategy set for the active party, and the first strategy set includes at least one first driving strategy. The processing module 820 is also used to obtain the second driving strategy of the passive party under each first driving strategy in the first strategy set according to each first driving strategy in the first strategy set, the driving parameters of the active party at the current moment, and the driving parameters of the passive party at the current moment, so as to obtain a second strategy set, wherein the second driving strategy is any one of the following: the passive party only overtakes the active party, the passive party only gives way to the active party, or the passive party can both overtake the active party and give way to the active party. The processing module 820 is also used to determine a target strategy pair set according to the first strategy set and the second strategy set, and the target strategy pair set includes at least one feasible strategy pair, and each feasible strategy pair consists of a first driving strategy and a second driving strategy. The processing module 820 is also used to determine the execution cost of each feasible strategy pair in the target strategy pair set to obtain a first cost set, wherein the first cost set includes the execution cost of each feasible strategy pair. The processing module 820 is also used to determine the target driving strategy based on the first cost set, wherein the target driving strategy is the driving strategy of the target vehicle associated with the lowest execution cost in the first cost set. The processing module 820 is also used to control the target vehicle based on the target driving strategy.

[0144] In some embodiments, if the target vehicle is the active party and the target object is the passive party; when the processing module 820 determines the target driving strategy based on the first cost set, it is specifically used to: if the second driving strategy in the feasible strategy pair corresponding to the target cost is: the passive party only overtakes the active party, then the target driving strategy is determined to be: the target vehicle gives way to the target object, wherein the target cost is the lowest execution cost in the first cost set; if the second driving strategy in the feasible strategy pair corresponding to the target cost is: the passive party only gives way to the active party, then the target driving strategy is determined to be: the target vehicle overtakes the target object; if the second driving strategy in the feasible strategy pair corresponding to the target cost is: the passive party can both overtake the active party and give way to the active party, then the target driving strategy is determined to be: the first driving strategy in the feasible strategy pair corresponding to the target cost.

[0145] In some embodiments, if the target vehicle is the passive party and the target object is the active party; when the processing module 820 determines the target driving strategy based on the first cost set, it is specifically used to: if the second driving strategy in the feasible strategy pair corresponding to the target cost is: the passive party only overtakes the active party, then the target driving strategy is determined to be: the target vehicle overtakes the target object, wherein the target cost is the lowest execution cost in the first cost set; if the second driving strategy in the feasible strategy pair corresponding to the target cost is: the passive party only gives way to the active party, then the target driving strategy is determined to be: the target vehicle gives way to the target object; if the second driving strategy in the feasible strategy pair corresponding to the target cost is: the passive party can both overtake the active party and give way to the active party, then the target driving strategy is determined to be: the target vehicle gives way to the target object.

[0146] In some embodiments, the execution cost associated with the feasible strategy pair includes one or more of the following: a comfort cost, which is used to characterize the comfort level when executing the feasible strategy pair; a passability cost, which is used to characterize the efficiency of the active party and / or the passive party in passing the conflict point between the two; an offset cost, which is used to characterize the evaluation of the offset of the active party and / or the passive party when executing the corresponding driving strategy; an inconsistency cost, which is used to characterize the evaluation of the deviation between the driving behavior of the target object in the feasible strategy pair and the actual driving behavior of the target pair; or a decision penalty cost, which is used to characterize the evaluation of whether the intention of the passive party is clear.

[0147] In some embodiments, for any first strategy pair among all feasible strategy pairs, the processing module 820, when determining the comfort cost associated with the first strategy pair, is specifically used to: determine a first comfort cost of the active party when executing the first driving strategy in the first strategy pair according to the acceleration corresponding to the first driving strategy in the first strategy pair and the current acceleration of the active party; determine a second comfort cost of the passive party when executing the second driving strategy in the first strategy pair according to the acceleration corresponding to the second driving strategy in the first strategy pair and the current acceleration of the passive party; determine the comfort cost associated with the first strategy pair according to the first comfort cost and the second comfort cost.

[0148] In some embodiments, for any first strategy pair among all feasible strategy pairs, the processing module 820, when determining the passability cost associated with the first strategy pair, is specifically used to: determine the first passability cost of the active party when executing the first driving strategy in the first strategy pair based on the first time and the second time, wherein the first time is the time when the active party passes the target point when executing the first driving strategy in the first strategy pair, and the second time is the time when the active party passes the target point with its current speed and acceleration, and the target point is the conflict point between the driving path of the active party and the driving path of the passive party; determine the second passability cost of the passive party when executing the second driving strategy in the first strategy pair based on the third time and the fourth time, wherein the third time is the time when the passive party passes the target point when executing the second driving strategy in the first strategy pair, and the fourth time is the time when the passive party passes the target point with its current speed and acceleration; determine the passability cost associated with the first strategy pair based on the first passability cost and the second passability cost.

[0149] In some embodiments, for any first strategy pair among all feasible strategy pairs, the processing module 820, when determining the offset cost associated with the first strategy pair, is specifically used to: determine the first offset cost of the active party when executing the first driving strategy in the first strategy pair based on a mapping relationship between a preset offset and an offset cost, and the offset when the active party executes the first driving strategy in the first strategy pair; determine the second offset cost of the passive party when executing the second driving strategy in the first strategy pair based on a mapping relationship between a preset offset and an offset cost, and the offset when the passive party executes the second driving strategy in the first strategy pair; determine the offset cost associated with the first strategy pair based on the first offset cost and the second offset cost.

[0150] In some embodiments, for any first strategy pair among all feasible strategy pairs, the processing module 820, when determining the inconsistency cost associated with the first strategy pair, is specifically used to: when the driving strategy of the target object in the first strategy pair is to only overtake the target vehicle, or to only give way to the target vehicle, determine the target probability of the target object overtaking the target vehicle, and, based on the target probability, determine the inconsistency cost; when the driving strategy of the target object in the first strategy pair is to both overtake the target vehicle and give way to the target vehicle, determine the inconsistency cost as a pre-set cost value.

[0151] In some embodiments, for any first strategy pair among all feasible strategy pairs, the processing module 820, when determining the decision penalty cost associated with the first strategy pair, is specifically used to: determine the decision penalty cost associated with the first strategy pair based on a pre-set decision penalty rule and the second driving strategy in the first strategy pair.

[0152] In some embodiments, the second driving strategy in the first strategy pair is: the passive party can both overtake the active party and give way to the active party; when the processing module 820 determines the decision penalty cost associated with the first strategy pair based on a pre-set decision penalty rule and the second driving strategy in the first strategy pair, it is specifically used to: determine the first decision penalty cost based on the decision penalty rule and the second driving strategy in the first strategy pair; determine the second decision penalty cost of the active party when executing the first driving strategy in the first strategy pair according to the acceleration corresponding to the first driving strategy in the first strategy pair and the current acceleration of the active party; determine the decision penalty cost associated with the first strategy pair according to the first decision penalty cost and the second decision penalty cost.

[0153] It should be understood that the above-mentioned device is used to execute the method in the above-mentioned embodiment. The implementation principle and technical effect of the corresponding program module in the device are similar to those described in the above-mentioned method. The working process of the device can refer to the corresponding process in the above-mentioned method, which will not be repeated here.

[0154] Based on the device in the above embodiment, the embodiment of the present application provides a vehicle, which may include Figure 8 The control device 800 shown in FIG.

[0155] Based on the method in the above embodiment, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a processor, the processor executes the method in the above embodiment.

[0156] Based on the method in the above embodiment, an embodiment of the present application provides a computer program product. When the computer program product runs on a processor, the processor executes the method in the above embodiment.

[0157] It is understood that the processor in the embodiments of the present application may 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, transistor logic devices, hardware components or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0158] The method steps in the embodiments of the present application can be implemented by hardware or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, and the software modules can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, mobile hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC.

[0159] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions may be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state disk (SSD)), etc.

[0160] It should be understood that the various numerical numbers involved in the embodiments of the present application are only used for the convenience of description and are not used to limit the scope of the embodiments of the present application.

Claims

1. An intelligent driving method, comprising: The target vehicle obtains target object information; Target vehicles and target objects are divided into active and passive parties based on traffic rules; The target vehicle obtains the first feasible strategy set of the active party; The target vehicle obtains a second strategy set corresponding to the first strategy set by the passive party based on the first strategy set; The target vehicle obtains a driving strategy based on the first strategy set and the second strategy set; The target vehicle is controlled based on the driving strategy.

2. The intelligent driving method according to claim 1, characterized in that: The target vehicle obtains the second driving strategy of the passive party under each first driving strategy in the first strategy set according to each first driving strategy in the first strategy set, the driving parameters of the active party at a current moment, and the driving parameters of the passive party at a current moment, so as to obtain a second strategy set.

3. The intelligent driving method according to claim 2, characterized in that : The second driving strategy is any one of the following: the passive party only overtakes the active party, the passive party only gives way to the active party, or the passive party can both overtake the active party and give way to the active party.

4. The intelligent driving method according to any one of claims 2-3, characterized in that: The target vehicle determines a target strategy pair set based on the first strategy set and the second strategy set, wherein the target strategy pair set includes at least one feasible strategy pair, and each of the feasible strategy pairs consists of one of the first driving strategies and one of the second driving strategies; determines the execution cost of each feasible strategy pair in the target strategy pair set to obtain a first cost set, wherein the first cost set includes the execution cost of each of the feasible strategy pairs; the target vehicle determines a target driving strategy based on the first cost set, and the target driving strategy is the driving strategy of the target vehicle associated with the lowest execution cost in the first cost set.

5. An intelligent driving device, comprising: Module for obtaining target object information; A module for classifying target vehicles and target objects into active and passive parties based on traffic rules; A module for obtaining a first set of strategies feasible for an active party; A module for acquiring, based on the first policy set, a second policy set of a passive party corresponding to the first policy set; A module for obtaining a driving strategy based on the first strategy set and the second strategy set; A module for controlling a target vehicle based on the driving strategy.

6. A vehicle, comprising the intelligent driving device as claimed in claim 5.

7. A computer-readable storage medium, comprising an instruction set, wherein when the instruction set is executed by a processor, the processor executes the method according to any one of claims 1 to 4.

8. A computer program product, characterized in that When the computer program product runs on a processor, the processor is enabled to execute the method according to any one of claims 1 to 4.

Images