Vehicle control methods, devices, and autonomous vehicles in interactive scenarios

Abstract

This disclosure provides a vehicle control method, device, and autonomous vehicle in an interactive scenario, relating to the field of computer technology, specifically the field of autonomous driving technology. The specific implementation scheme is as follows: determining the interaction level between a first vehicle and a second vehicle at the current moment; if the interaction level is strong, determining the motion characteristics of the second vehicle at the current moment, and performing autonomous driving decisions on the first vehicle based on the motion characteristics of the second vehicle at the current moment; if the interaction level is weak, performing autonomous driving decisions on the first vehicle based on the interaction level.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, specifically to the field of autonomous driving technology, and in particular to vehicle control methods, devices, and autonomous vehicles in interactive scenarios. Background Technology

[0002] With the continuous development of technology, autonomous vehicles have gradually penetrated into the actual road traffic environment, bringing great convenience to people's lives. Inevitably, there are many interaction scenarios in the process of autonomous driving. Autonomous vehicles will interact with surrounding vehicles, and the aggressiveness of autonomous vehicle movement will change with changes in the surrounding environment (such as the interaction with surrounding vehicles); among them, the aggressiveness of autonomous vehicle movement is the motion characteristic of autonomous vehicle. Summary of the Invention

[0003] This disclosure provides a vehicle control method, device, and autonomous vehicle in an interactive scenario.

[0004] According to a first aspect of this disclosure, a vehicle control method in an interactive scenario is provided, applied to a first vehicle for autonomous driving, comprising:

[0005] Determine the level of interaction between the first vehicle and the second vehicle at the current moment; the second vehicle refers to the vehicles surrounding the first vehicle; the level of interaction is used to characterize the likelihood of the first vehicle interacting with the second vehicle during autonomous driving.

[0006] When the interaction level is strong, the motion characteristics of the second vehicle at the current moment are determined, and the first vehicle is made an autonomous driving decision based on the motion characteristics of the second vehicle at the current moment; strong interaction is used to characterize that the probability of the first vehicle interacting with the second vehicle during the autonomous driving process is greater than a preset threshold; the motion characteristics of the second vehicle are used to characterize the driving intention of the second vehicle.

[0007] When the interaction level is weak, an autonomous driving decision is made for the first vehicle based on the interaction level; the autonomous driving decision is used to determine the driving state of the first vehicle; weak interaction is used to characterize that the probability of the first vehicle interacting with the second vehicle during the autonomous driving process is less than a preset threshold.

[0008] According to a second aspect of this disclosure, a vehicle control device for an interactive scenario is provided, applied to a first vehicle for autonomous driving, comprising:

[0009] The determination module is used to determine the degree of interaction between the first vehicle and the second vehicle at the current moment; the second vehicle refers to the vehicles surrounding the first vehicle; the degree of interaction is used to characterize the likelihood of the first vehicle interacting with the second vehicle during the autonomous driving process.

[0010] The first decision module is used to determine the motion characteristics of the second vehicle at the current moment when the interaction level is strong interaction, and to make autonomous driving decisions for the first vehicle based on the motion characteristics of the second vehicle at the current moment; strong interaction is used to characterize that the probability of the first vehicle interacting with the second vehicle during the autonomous driving process is greater than a preset threshold; the motion characteristics of the second vehicle are used to characterize the driving intention of the second vehicle.

[0011] The second decision module is used to make autonomous driving decisions for the first vehicle based on the level of interaction when the level of interaction is weak. The autonomous driving decision is used to determine the driving state of the first vehicle. Weak interaction is used to indicate that the probability of the first vehicle interacting with the second vehicle during the autonomous driving process is less than a preset threshold.

[0012] According to a third aspect of this disclosure, an electronic device is provided, comprising:

[0013] At least one processor; and

[0014] A memory that is communicatively connected to at least one processor; wherein,

[0015] The memory stores instructions that can be executed by at least one processor, such that the at least one processor is able to perform any of the methods in the first aspect.

[0016] According to a fourth aspect of this disclosure, an autonomous vehicle is provided, including a vehicle control device for interactive scenarios as described in the second aspect or an electronic device as described in the third aspect.

[0017] According to a fifth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause a computer to perform any of the methods in the first aspect.

[0018] According to a sixth aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements any of the methods in the first aspect.

[0019] The technology disclosed herein solves the problem in related technologies where autonomous vehicles have difficulty accurately judging the motion characteristics of surrounding vehicles, improves the accuracy of autonomous vehicles in judging the motion characteristics of surrounding vehicles, and enables autonomous vehicles to adjust their driving behavior in a timely manner based on the motion characteristics of surrounding vehicles.

[0020] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0021] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0022] Figure 1 This is an application scenario diagram that can realize the vehicle control method in an interactive scenario disclosed herein;

[0023] Figure 2 This is a flowchart of a vehicle control method in an interactive scenario provided in this disclosure;

[0024] Figure 3 This is a flowchart of a vehicle control method in another interactive scenario provided in this disclosure;

[0025] Figure 4 This is a schematic diagram of the interaction between a first vehicle and a second vehicle provided in this disclosure;

[0026] Figure 5 This is another interactive diagram of the first vehicle and the second vehicle provided in this disclosure;

[0027] Figure 6 This is a schematic diagram of a vehicle control device in an interactive scenario provided in this disclosure;

[0028] Figure 7 This is a block diagram of an electronic device used to implement the vehicle control method in an interactive scenario according to the embodiments of this disclosure. Detailed Implementation

[0029] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0030] Figure 1 An application scenario diagram is shown, illustrating an embodiment of a vehicle control method applicable to an interactive scenario of this disclosure. For example... Figure 1 As shown, this application scenario may include a first vehicle 101 and a second vehicle 102; wherein, the first vehicle 101 is an autonomous driving vehicle, and the second vehicle 102 is a vehicle surrounding the first vehicle 101. Optionally, the second vehicle 102 may be a vehicle among the vehicles surrounding the first vehicle 101 that is less than a preset distance from the first vehicle 101 (i.e., a vehicle that is relatively close to the first vehicle 101). During driving, the first vehicle 101 and the second vehicle 102 may interact.

[0031] It should be understood that the interaction described in this application can be alternatively described as collision or contact, etc.

[0032] The first vehicle 101 and the second vehicle 102 may include an in-vehicle system, such as the first vehicle 101 may include an in-vehicle system 103.

[0033] In one optional implementation, after the vehicle system 103 of the first vehicle 101 obtains the current interaction scenario information, the vehicle information of the first vehicle 101 (including speed, acceleration and position information), and the vehicle information of the second vehicle 102, it can determine the degree of interaction between the first vehicle and the second vehicle based on the received information. If it is determined that the degree of interaction between the first vehicle 101 and the second vehicle 102 is strong, it can further determine the motion characteristics of the second vehicle at the current moment, and then perform autonomous driving decisions for the first vehicle based on the motion characteristics of the second vehicle at the current moment.

[0034] In another optional implementation, after acquiring the current interaction scenario information, vehicle information of the first vehicle 101 (including speed, acceleration, and position information), and vehicle information of the second vehicle 102, the on-board system 103 of the first vehicle 101 can send the acquired information to the server 105 via the network 104. This allows the server 105 to determine the degree of interaction between the first and second vehicles based on the received information. If the server determines that the interaction between the first vehicle 101 and the second vehicle 102 is strong, it further determines the motion characteristics of the second vehicle at the current moment and then executes an autonomous driving decision for the first vehicle based on the motion characteristics of the second vehicle at the current moment.

[0035] The in-vehicle system 103 can be either hardware or software. Here, the autonomous vehicle refers to a vehicle with autonomous driving capabilities. When the in-vehicle system 103 is hardware, it can be an in-vehicle electronic device installed in the autonomous vehicle. When the in-vehicle system 103 is software, it can be installed in the aforementioned in-vehicle electronic device. It can be implemented as multiple software programs or software modules (e.g., multiple software programs or software modules used to provide distributed services) or as a single software program or software module. No specific limitations are made here.

[0036] Network 104 can provide a communication link between vehicle system 103 and server 105. Network 104 can include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0037] Server 105 can be a server that provides various services, such as a backend server that supports the vehicle system 103. The backend server can analyze and process the data received from the autonomous vehicle and feed the processing results back to the vehicle system 103.

[0038] It should be noted that the vehicle control method for interactive scenarios of autonomous vehicles provided in this disclosure can be executed by the server 105 or the vehicle system 103, and correspondingly, it can be executed by the vehicle control device for interactive scenarios set in the server 105 or the vehicle system 103.

[0039] It should be understood that Figure 1 The number of vehicles, networks, and servers shown is merely an example. Any number of in-vehicle systems, networks, and servers can be included depending on implementation needs.

[0040] First Embodiment

[0041] based on Figure 1 The application scenarios shown are as follows. Figure 2 This disclosure presents a flowchart of a vehicle control method in an interactive scenario, as shown below. Figure 2 As shown, the method includes:

[0042] Step S201: Determine the level of interaction between the first vehicle and the second vehicle at the current moment.

[0043] In this context, the first vehicle is an autonomous vehicle, and the second vehicle refers to vehicles surrounding the first vehicle. The second vehicle can be either a human-driven vehicle or an autonomous vehicle. The level of interaction characterizes the likelihood of the first vehicle interacting with the second vehicle during autonomous driving, such as the probability of a collision or other interactive event.

[0044] For example, the degree of interaction between the first vehicle and the second vehicle at the current moment can be determined based on at least one parameter, such as the interaction scenario information of the first vehicle and the second vehicle, the relative interaction time between the first vehicle and the second vehicle (i.e., the first relative interaction time described in this disclosure), and the relative interaction time between the first vehicle and the endpoint of the interaction area (i.e., the second relative interaction time described in this disclosure). Specifically, the implementation process of step S201 can be referred to the following... Figure 3 As described in steps S301-S308.

[0045] Step S202: When the interaction level is strong, determine the motion characteristics of the second vehicle at the current moment, and make an autonomous driving decision for the first vehicle based on the motion characteristics of the second vehicle at the current moment.

[0046] Among them, strong interaction is used to characterize that the probability of the first vehicle interacting with the second vehicle during the autonomous driving process is greater than a preset threshold, that is, there is a high probability that interaction or collision will occur.

[0047] Among them, the motion characteristics of the second vehicle are used to characterize the driving intention of the second vehicle, such as the driving intention of the second vehicle to move laterally and / or the driving intention of the second vehicle to seize the right-of-way, etc.

[0048] The autonomous driving decision-making process is used to determine the driving state of the first vehicle. This decision-making process can be pre-set in the first vehicle as needed, such as within its decision-making module. Executing autonomous driving decisions for the first vehicle based on the motion characteristics of the second vehicle at the current moment can refer to determining the driving state of the first vehicle at the next moment based on / referencing the motion characteristics of the second vehicle, such as speed, acceleration, direction, and whether to change lanes. It should be understood that the reference factors for autonomous driving decisions may include, but are not limited to, the motion characteristics of the second vehicle, and may also include other parameters.

[0049] Specifically, after determining in step S201 that the interaction level between the first vehicle and the second vehicle at the current moment is strong interaction, that is, after determining that the probability of the first vehicle interacting with the second vehicle during the autonomous driving process is greater than a preset threshold, the motion characteristics of the second vehicle at the current moment can be further determined, and the determined motion characteristics of the second vehicle at the current moment can be sent to the decision module of the first vehicle, so that the decision module of the first vehicle can perform autonomous driving decisions for the first vehicle, that is, adjust the driving state (e.g., driving speed, driving direction, etc.) of the first vehicle according to the motion characteristics of the second vehicle at the current moment.

[0050] In one embodiment, the motion characteristics of the second vehicle may include longitudinal motion characteristics and lateral motion characteristics. Therefore, the longitudinal motion characteristics of the second vehicle at the current moment can be determined based on the first time series and the second time series, and the lateral motion characteristics of the second vehicle at the current moment can be determined based on the speed series and the distance series. Specifically, this process can be referred to as follows: Figure 3 The corresponding embodiment describes step S311.

[0051] Subsequently, autonomous driving decisions can be made directly based on the determined motion characteristics of the second vehicle at the current moment. Alternatively, in another embodiment, the following can be referred to first. Figure 3 Step S311 determines the motion characteristics of the second vehicle at the current moment, then corrects the motion characteristics of the second vehicle at the current moment based on the actual driving behavior of the second vehicle at the previous moment adjacent to the current moment, obtaining the corrected motion characteristics, and then determines the corrected motion characteristics as the motion characteristics of the second vehicle at the current moment. Specifically, this process is as follows: Figure 3 As described in S312 of the corresponding embodiment.

[0052] Step S203: When the interaction level is weak, perform an autonomous driving decision for the first vehicle based on the interaction level.

[0053] Among them, weak interaction is used to characterize that the probability of the first vehicle interacting with the second vehicle during the autonomous driving process is less than a preset threshold, that is, there is a high probability that interaction or collision will not occur.

[0054] Specifically, after determining in step S201 that the interaction level between the first vehicle and the second vehicle at the current moment is weak, that is, after determining that the first vehicle will not be affected by the second vehicle during the autonomous driving process, the determined interaction level between the first vehicle and the second vehicle can be sent to the decision module of the first vehicle so that the decision module of the first vehicle can execute autonomous driving decisions for the first vehicle. For example, after determining that the interaction level is weak, the existing driving speed, acceleration, driving direction, etc. can be maintained without changing lanes; or the existing driving speed, acceleration, driving direction, lane change, etc. can be changed.

[0055] In this way, the first vehicle (i.e., the autonomous vehicle) can accurately judge the motion characteristics of the second vehicle with which it has a strong level of interaction, and execute corresponding autonomous driving decisions based on the motion characteristics of the second vehicle. Therefore, the rationality of the autonomous vehicle's decisions can be effectively improved, thereby ensuring the safety of the autonomous vehicle during operation.

[0056] Second Embodiment

[0057] Figure 3 A flowchart of another vehicle control method in an interactive scenario provided in this disclosure is shown, such as... Figure 3 As shown, the method includes:

[0058] Step S301: Obtain interaction scene information.

[0059] Among them, the interaction scenario information is used to characterize the interaction scenario between the first vehicle and the second vehicle.

[0060] In the embodiments of this disclosure, the interactive scene information can be obtained by sensors installed in the autonomous vehicle (i.e., the first vehicle) or by cameras installed in the autonomous vehicle; this disclosure does not limit the information.

[0061] In this embodiment, the interaction scene information may include lane information of the lane where the first vehicle is located, and may also include vehicle information around the first vehicle, such as lane information of surrounding vehicles and their relative positions to the first vehicle. This disclosure does not limit this. The interaction scene may include an interaction area, which may be an overlapping area between a preset area centered on the first vehicle and a preset area centered on the second vehicle. The size of the preset area can be set as needed. For example, refer to... Figure 4The preset area centered on the first vehicle can be the area between the midpoint of the first vehicle and the end point P of the interaction area. The preset area centered on the second vehicle can be the area between the midpoint of the second vehicle and the end point P of the interaction area. The interaction area is the overlapping area between the preset area centered on the first vehicle and the preset area centered on the second vehicle, that is, the area between the midpoint of the second vehicle and the end point P of the interaction area is the interaction area.

[0062] Step S302: Based on the interaction scenario information, determine whether the second vehicle has the conditions to move laterally to the lane where the first vehicle is located; if yes, proceed to step S303; if no, proceed to step S307.

[0063] Specifically, based on the lane information of the second and first vehicles contained in the interaction scenario information, it can be determined whether the second vehicle has the conditions to move laterally to the lane where the first vehicle is located. For example, because during travel, a vehicle in the main lane is unlikely to move laterally to the auxiliary lane, while a vehicle in the auxiliary lane is more likely to move laterally to the main lane; therefore, the conditions for the second vehicle to move laterally to the lane where the first vehicle is located can include any of the following: Condition 1. If the first vehicle is in a different lane, for example, the first vehicle is in the main lane and the second vehicle is in the auxiliary lane, then the second vehicle has the conditions to move laterally to the lane where the first vehicle is located; if the second vehicle is in the main lane and the first vehicle is in the auxiliary lane, then the second vehicle does not have the conditions to move laterally to the lane where the first vehicle is located. Here, the main lane refers to the lane located in the middle of the road; the auxiliary lane refers to the lane located on the side of the road. Condition 2. If the second vehicle and the first vehicle are in the same lane, then the second vehicle does not have the conditions to move laterally to the lane where the first vehicle is located.

[0064] Exemplarily, in one embodiment, such as Figure 4 As shown, Figure 4 This is a schematic diagram of an interaction scenario between a first vehicle and a second vehicle provided in this disclosure. Vehicle A is the first vehicle, and vehicle B is the second vehicle. At this time, the first vehicle is in the first lane (auxiliary lane), and the second vehicle is in the second lane (main lane). The second vehicle can move to the lane where the first vehicle is located; therefore, it can be determined that the second vehicle has the condition to move laterally to the lane where the first vehicle is located.

[0065] In another embodiment, such as Figure 5 As shown, Figure 5This is another interactive diagram of the first and second vehicles provided in this disclosure. Vehicle A is the first vehicle, and vehicle B is the second vehicle. At this time, the first vehicle is in the second lane (main lane), and the second vehicle is in the first lane (auxiliary lane). The second vehicle cannot move into the lane where the first vehicle is located. Therefore, it can be determined that the second vehicle does not have the condition to move laterally into the lane where the first vehicle is located.

[0066] Step S303: Is the current time the initial time? If yes, proceed to step S307; otherwise, proceed to step S304.

[0067] The initial moment refers to the moment when the first vehicle first obtains interaction scene information, such as the moment when it obtains the vehicle information of the second vehicle.

[0068] Step S304: Obtain the historical motion characteristics of the second vehicle.

[0069] The historical motion characteristics of the second vehicle are used to characterize the motion characteristics of the second vehicle at the previous moment adjacent to the current moment. For example, assuming the current moment is t, the historical motion characteristics of the second vehicle refer to the motion characteristics of the second vehicle at moment t-1.

[0070] Step S305: Based on the historical motion characteristics of the second vehicle, determine whether the second vehicle has the driving intention to move laterally to the lane where the first vehicle is located; if yes, proceed to step S306; if no, proceed to step S307.

[0071] Step S306: Determine that the interaction level between the first vehicle and the second vehicle at the current moment is strong interaction.

[0072] For example, assuming the current time is time t, if the second vehicle has the driving intention to move laterally to the lane where the first vehicle is located, based on the motion characteristics of the second vehicle at time t-1 (i.e. the historical motion characteristics of the second vehicle), then the interaction level between the first vehicle and the second vehicle at the current time can be directly classified as strong interaction.

[0073] Step S307: Determine the degree of interaction between the first vehicle and the second vehicle at the current moment based on the first relative interaction time and / or the second relative interaction time.

[0074] Wherein, the first relative interaction time is the relative interaction time between the first vehicle and the second vehicle. This disclosure does not limit the naming of the first relative interaction time; the first relative interaction time can also be named the first relative collision time t. collsion1 Specifically, the first relative interaction time can be determined based on the relative speed and relative distance between the first vehicle and the second vehicle, and this determination method can refer to the following formula 1.

[0075] Wherein, the second relative interaction time is the relative interaction time between the first vehicle and the endpoint of the interaction area in the interaction scenario. This disclosure does not limit the naming of the second relative interaction time, and the second relative interaction time can also be named the first relative collision time t. collsion2 Specifically, the second relative interaction time can be determined based on the speed of the first vehicle and its position in its own lane, as shown in Formula 2 below.

[0076] Exemplarily, in one embodiment, such as Figure 4 As shown, P is the endpoint of the interaction area between the first vehicle and the second vehicle in the interaction scenario. In determining the degree of interaction between the first vehicle and the second vehicle at the current moment based on the first relative interaction time and / or the second relative interaction time, the first relative interaction time can be determined according to Formula 1.

[0077]

[0078] Among them, t collsion1 Denotes the first relative interaction time, ΔD ab Δv represents the relative distance between the first and second vehicles. ab This indicates the relative speed between the first vehicle and the second vehicle.

[0079] After determining the first relative interaction time according to Formula 1, if the first relative interaction time is less than a preset first time threshold, then the interaction level between the first vehicle and the second vehicle at the current moment is determined to be strong interaction. If the first relative interaction time is greater than or equal to the preset first time threshold, then the second relative interaction time can be determined according to Formula 2.

[0080]

[0081] Among them, t collsion2 Denotes the second relative interaction time, ΔD a v represents the distance between the first vehicle and the endpoint P of the interaction area in the interaction scene. a This indicates the speed of the first vehicle.

[0082] After determining the second relative interaction time according to Formula 2, if the second relative interaction time is less than the preset second time threshold, the interaction level between the first vehicle and the second vehicle at the current moment is determined to be strong interaction; if the second relative interaction time is greater than or equal to the preset second time threshold, the interaction level between the first vehicle and the second vehicle at the current moment is determined to be weak interaction.

[0083] In another embodiment, during the process of determining the interaction level between the first vehicle and the second vehicle at the current moment based on the first relative interaction time and / or the second relative interaction time, the second relative interaction time can be determined first according to Formula 2. If the second relative interaction time is less than a preset second time threshold, the interaction level between the first vehicle and the second vehicle at the current moment is determined to be strong interaction; if the second relative interaction time is greater than or equal to the preset second time threshold, the first relative interaction time can be determined according to Formula 1. After determining the first relative interaction time according to Formula 1, if the first relative interaction time is less than the preset first time threshold, the interaction level between the first vehicle and the second vehicle at the current moment is determined to be strong interaction; if the first relative interaction time is greater than or equal to the preset first time threshold, the interaction level between the first vehicle and the second vehicle at the current moment is determined to be weak interaction.

[0084] In another embodiment, during the process of determining the interaction level between the first vehicle and the second vehicle at the current moment based on the first relative interaction time and / or the second relative interaction time, the first relative interaction time and the second relative interaction time can also be determined simultaneously using Formula 1 and Formula 2 respectively. If the first relative interaction time is less than a preset first time threshold, or if the second relative interaction time is less than a preset second time threshold, then the interaction level between the first vehicle and the second vehicle at the current moment is determined to be strong interaction; if the first relative interaction time is greater than or equal to the preset first time threshold, and if the second relative interaction time is greater than or equal to the preset second time threshold, then the interaction level between the first vehicle and the second vehicle at the current moment is determined to be weak interaction.

[0085] In the embodiments of this disclosure, the first time threshold and the second time threshold can be obtained statistically from relevant interaction data or determined based on practical experience, and this disclosure does not limit them.

[0086] Step S308: Correct the interaction level between the first vehicle and the second vehicle at the current moment to obtain the corrected interaction level, and use the corrected interaction level as the interaction level between the first vehicle and the second vehicle at the current moment.

[0087] In one optional implementation, during the process of correcting the interaction level between the first vehicle and the second vehicle at the current moment, the interaction level between the first vehicle and the second vehicle at the current moment can be corrected based on the first relative interaction time and the second relative interaction time corresponding to the current moment, as well as the first relative interaction time and the second relative interaction time corresponding to the previous moment adjacent to the current moment.

[0088] Specifically, in some embodiments, a first difference can be determined based on the first relative interaction time corresponding to the current time and the first relative interaction time corresponding to the previous time adjacent to the current time, and a second difference can be determined based on the second relative interaction time corresponding to the current time and the second relative interaction time corresponding to the previous time adjacent to the current time.

[0089] After determining the first difference and the second difference, if the first difference is less than a preset first threshold and the second difference is less than a preset second threshold, then the interaction level between the first vehicle and the second vehicle at the previous time, adjacent to the current time, is used as the corrected interaction level; otherwise, the interaction level between the first vehicle and the second vehicle at the current time is used as the corrected interaction level. Once the corrected interaction level is determined, it can be used as the interaction level between the first vehicle and the second vehicle at the current time.

[0090] It should be understood that Figure 3 For illustrative purposes only, this disclosure does not limit the execution order of steps S301-S308, and can be performed according to... Figure 3 The sequence of steps S301-S308 shown can be executed sequentially, or only some of the steps can be executed to obtain the degree of interaction between the first vehicle and the second vehicle:

[0091] For example, step S303 can be skipped. After step S302 is completed, step S304 can be executed directly. That is, after determining that the second vehicle has the conditions to move laterally to the lane where the first vehicle is located, step S304 (obtaining the historical motion characteristics of the second vehicle) can be executed directly. After determining that the second vehicle does not have the conditions to move laterally to the lane where the first vehicle is located, step S307 (determining the degree of interaction between the first vehicle and the second vehicle at the current moment based on the first relative interaction time and / or the second relative interaction time) can be executed.

[0092] For example, steps S301-S306 can be skipped, and steps S307 or S307-S308 can be executed directly to obtain the interaction level between the first vehicle and the second vehicle; or steps S301-S303 can be skipped, and steps S304-S307 or S304-S308 can be executed directly to obtain the interaction level between the first vehicle and the second vehicle.

[0093] For example, step S303 can be executed first, followed by step S302. That is, after executing step S301, step S303 (whether the current time is the initial time) is executed first. If yes, step S307 is executed. If no, step S302 (determining whether the second vehicle has the conditions to move laterally to the lane where the first vehicle is located based on the interaction scenario information) is executed. If yes, step S304 is executed. If no, step S307 is executed.

[0094] In summary, all feasible solutions applicable to this disclosure are within the scope of protection of this disclosure.

[0095] Step S309: Determine whether the interaction level between the first vehicle and the second vehicle is strong interaction; if yes, proceed to steps S311-S313; if no, proceed to step S310.

[0096] Step S310: Execute an autonomous driving decision for the first vehicle based on the degree of interaction between the first vehicle and the second vehicle.

[0097] Specifically, when step S309 determines that the interaction level between the first vehicle and the second vehicle at the current moment is weak, the determined interaction level between the first vehicle and the second vehicle can be sent to the decision module of the first vehicle so that the decision module of the first vehicle can make autonomous driving decisions for the first vehicle. For example, after determining that the interaction level is weak, the existing driving speed, acceleration, driving direction, etc. can be maintained without changing lanes; or the existing driving speed, acceleration, driving direction, lane change, etc. can be changed.

[0098] Step S311: Determine the motion characteristics of the second vehicle at the current moment.

[0099] The motion characteristics of the second vehicle at the current moment include longitudinal motion characteristics and lateral motion characteristics. The longitudinal motion characteristics of the second vehicle are used to characterize whether the second vehicle has the driving intention to use the right-of-way, that is, whether the second vehicle has the driving intention to compete for the right-of-way. The lateral motion characteristics of the second vehicle are used to characterize the driving intention of the second vehicle to move laterally to the lane where the first vehicle is located, that is, whether the second vehicle has the intention to cut laterally.

[0100] Specifically, in some embodiments, if it is determined in step S302 that the second vehicle has the conditions to move laterally to the lane where the first vehicle is located, then in the process of determining the motion characteristics of the second vehicle at the current moment, the longitudinal motion characteristics and lateral motion characteristics of the second vehicle can be determined separately.

[0101] In other embodiments, if it is determined in step S302 that the second vehicle does not have the conditions to move laterally to the lane where the first vehicle is located, then in the process of determining the motion characteristics of the second vehicle at the current moment, only the longitudinal motion characteristics of the second vehicle can be determined.

[0102] In one alternative implementation, the longitudinal motion characteristics of the second vehicle can be determined by the following method one, and the lateral motion characteristics of the second vehicle can be determined by the following method two:

[0103] Method 1: Input the first time series and the second time series corresponding to the first preset time period into the pre-trained first prediction model to obtain the first result; and determine the longitudinal motion characteristics of the second vehicle based on the first result.

[0104] The first preset time period is a continuous time period including the current moment. For example, the first preset time period may include the current moment and multiple consecutive moments preceding the current moment. The first time series is composed of the first relative interaction time corresponding to each moment included in the first preset time period; the second time series is composed of the third relative interaction time corresponding to each moment included in the first preset time period; the third relative interaction time is determined based on the speed and position of the second vehicle; the first prediction model is used to predict the longitudinal motion characteristics of the vehicle.

[0105] Method 2: Input the velocity sequence and distance sequence corresponding to the second preset time period into the pre-trained second prediction model to obtain the second result; and determine the lateral motion characteristics of the second vehicle based on the second result.

[0106] The second preset time period is a continuous time period including the current moment. For example, the second preset time period may include the current moment and multiple consecutive moments preceding the current moment. The second preset time period may be the same as or different from the first preset time period. The speed sequence consists of the lateral speed of the second vehicle at each moment included in the second preset time period; the distance sequence consists of the lateral distance between the first and second vehicles at each moment included in the second preset time period; the second prediction model is used to predict the lateral motion characteristics of the vehicles.

[0107] In the embodiments of this disclosure, the first preset time period and the second preset time period may be the same or different, and this disclosure does not limit this.

[0108] For example, assuming the current time is time t, both the first and second preset time periods are (t-Δt:t). Therefore, the first time series consists of the first relative interaction time corresponding to each time point included in (t-Δt:t); the second time series consists of the third relative interaction time corresponding to each time point included in (t-Δt:t); the speed series consists of the lateral speed of the second vehicle at each time point included in (t-Δt:t); and the distance series consists of the lateral distance between the first and second vehicles at each time point included in (t-Δt:t), where the lateral speed of the second vehicle refers to the speed of the second vehicle along the Y-axis, and the lateral distance between the first and second vehicles refers to the relative distance between the first and second vehicles along the Y-axis.

[0109] In one embodiment, during the process of determining the longitudinal motion characteristics of the second vehicle, the first relative interaction time corresponding to each moment included in (t-Δt:t) ​​can be determined according to Formula 1, and the third relative interaction time corresponding to each moment included in (t-Δt:t) ​​can be determined according to Formula 3.

[0110]

[0111] Among them, t collsion3 Denotes the third relative interaction time, ΔD b v represents the distance between the second vehicle and the endpoint P of the interaction area. b This indicates the speed of the second vehicle.

[0112] After determining the first and second time series using Formulas 1 and 3, the first and second time series can be input into a pre-trained first prediction model to obtain a first result. If the first result is 0, it indicates that the second vehicle has no intention to compete with the first vehicle for right-of-way; if the first result is 1, it indicates that the second vehicle has the intention to compete with the first vehicle for right-of-way. The first prediction model is used to predict the longitudinal motion characteristics of the vehicle.

[0113] In one embodiment, during the process of determining the lateral motion characteristics of the second vehicle, the lateral distance between the first and second vehicles corresponding to each time point included in (t-Δt:t) ​​can be determined according to Formula 4.

[0114] ΔD ab-y =|D a-y -D b-y | (Formula 4)

[0115] Where, ΔD ab-y D represents the lateral distance between the first and second vehicles. a-y D represents the distance between the first vehicle and the Y-axis edge of the roadside. b-y This indicates the distance between the second vehicle and the Y-axis along the roadside.

[0116] After determining the lateral distance between the first and second vehicles at each time point included in (t-Δt:t) ​​using Formula 4, the velocity and distance sequences corresponding to (t-Δt:t) ​​can be input into a pre-trained second prediction model to obtain a second result. If the second result is 0, it indicates that the second vehicle has no intention to laterally enter the lane where the first vehicle is located; if the second result is 1, it indicates that the second vehicle has the intention to laterally enter the lane where the first vehicle is located. The second prediction model is used to predict the lateral motion characteristics of the vehicles.

[0117] Step S312: Based on the actual driving behavior of the second vehicle at the previous moment adjacent to the current moment, the motion characteristics of the second vehicle at the current moment are corrected to obtain the corrected motion characteristics, and the corrected motion characteristics are used as the motion characteristics of the second vehicle at the current moment.

[0118] In one optional implementation, if the driving intention represented by the motion characteristics of the second vehicle at the current moment is inconsistent with the actual driving behavior of the second vehicle at the previous moment adjacent to the current moment, then the motion characteristics of the second vehicle at the current moment are modified so that the driving intention represented by the modified motion characteristics of the second vehicle is consistent with the actual driving behavior of the second vehicle at the previous moment, and the modified motion characteristics of the second vehicle are used as the motion characteristics of the second vehicle at the current moment; wherein, the actual driving behavior of the second vehicle is used to represent the driving intention of the second vehicle to use the right-of-way and / or the driving intention to move laterally to the lane where the first vehicle is located.

[0119] Specifically, if the longitudinal motion characteristics of the second vehicle at the current moment indicate that the second vehicle does not intend to use the right-of-way, and the actual driving behavior of the second vehicle at the previous moment adjacent to the current moment indicates that the second vehicle has the intention to use the right-of-way, then the longitudinal motion characteristics of the second vehicle at the current moment are corrected to indicate that the second vehicle has the intention to use the right-of-way; if the lateral motion characteristics of the second vehicle at the current moment indicate that the second vehicle does not intend to move laterally into the lane where the first vehicle is located, and the actual driving behavior of the second vehicle at the previous moment adjacent to the current moment indicates that the second vehicle has the intention to move laterally into the lane where the first vehicle is located, then the lateral motion characteristics of the second vehicle at the current moment are corrected to indicate that the second vehicle has the intention to move laterally into the lane where the first vehicle is located.

[0120] For example, assuming the current time is time t, after determining the motion characteristics of the second vehicle at the current time through step S311, the actual driving behavior of the second vehicle at time t-1 can be obtained.

[0121] In one embodiment, if the actual driving behavior of the second vehicle at time t-1 is that the second vehicle has the intention to cut in laterally, and the motion characteristics of the second vehicle at time t are that the second vehicle does not have the intention to cut in laterally, then the actual motion characteristics of the second vehicle at time t-1 are taken as the corrected motion characteristics, and the corrected motion characteristics are taken as the motion characteristics of the second vehicle at time t.

[0122] In another embodiment, if the actual motion characteristic of the second vehicle at time t-1 is that the second vehicle has no intention to cut in laterally, and the motion characteristic of the second vehicle at time t is that the second vehicle has the intention to cut in laterally, then the motion characteristic of the second vehicle at time t is taken as the corrected motion characteristic, and the corrected motion characteristic is taken as the motion characteristic of the second vehicle at time t.

[0123] In another embodiment, if the actual motion characteristics of the second vehicle at time t-1 indicate that the second vehicle has the driving intention to compete for the right-of-way, and the motion characteristics of the second vehicle at time t indicate that the second vehicle does not have the driving intention to compete for the right-of-way, then the actual motion characteristics of the second vehicle at time t-1 are taken as the corrected motion characteristics, and the corrected motion characteristics are taken as the motion characteristics of the second vehicle at time t.

[0124] In another embodiment, if the actual motion characteristics of the second vehicle at time t-1 indicate that the second vehicle has no intention to compete for the right-of-way, and the motion characteristics of the second vehicle at time t indicate that the second vehicle has the intention to compete for the right-of-way, then the motion characteristics of the second vehicle at time t are taken as the corrected motion characteristics, and the corrected motion characteristics are taken as the motion characteristics of the second vehicle at time t.

[0125] Step S313: Execute an autonomous driving decision for the first vehicle based on the motion characteristics of the second vehicle at the current moment.

[0126] After determining the motion characteristics of the second vehicle at the current moment through step S312, the determined motion characteristics of the second vehicle at the current moment can be sent to the decision module of the first vehicle so that the decision module of the first vehicle can execute autonomous driving decisions for the first vehicle, that is, control the driving state (e.g., driving speed, driving direction, etc.) of the first vehicle according to the motion characteristics of the second vehicle at the current moment.

[0127] It should be understood that Figure 3 For illustrative purposes only, this disclosure does not limit the execution order of steps S311-S313, and steps S311-S313 can be performed in the following order: Figure 3 The process can be executed in the order shown, or only steps S311 and S313 can be executed without performing the process of modifying the motion characteristics of the second vehicle described in step S312. This disclosure does not limit this process.

[0128] based on Figure 3 The method described allows the first vehicle (autonomous vehicle) to dynamically identify the motion characteristics of a second vehicle with strong interaction with it when passing through an interaction area. This avoids adverse consequences such as sudden braking or collisions to the first vehicle due to the uncertainty of the second vehicle's driving behavior. Furthermore, this application can also correct the motion characteristics of the second vehicle at the current moment based on its historical motion characteristics and actual driving behavior, thereby ensuring the stability and accuracy of the identification of the second vehicle's motion characteristics at the current moment. This effectively improves the rationality of the autonomous vehicle's decision-making and ensures the safety of the autonomous vehicle during operation.

[0129] In this embodiment of the disclosure, before using the first prediction model and the second prediction model, the first prediction model can be trained using the following method three, and the second prediction model can be trained using the following method four, as detailed below:

[0130] Method 3: First, obtain driving data under the same interaction scenario. Then, based on the obtained driving data, determine the first relative interaction time under a fixed time sequence. Then, use C-means clustering to cluster the determined first relative interaction time under a fixed time sequence. The number of clusters is 2, that is, the determined first relative interaction time under a fixed time sequence is divided into two categories: those with competition intention and those without competition intention.

[0131] After clustering is completed, the parameters of the Hidden Markov Network (HMM) with the longitudinal motion characteristics of the second vehicle as the latent variable and the first and third relative interaction times as the observed variables can be learned based on the clustering results until the model converges.

[0132] Method 4: First, acquire driving data under the same interaction scenario. Then, based on the acquired driving data, determine the lateral speed of the second vehicle at a fixed time sequence. Next, classify the lateral speed of the second vehicle at the fixed time sequence according to the relationship between the lateral speed of the second vehicle and a pre-set speed threshold. For example, if the lateral speed of the second vehicle is less than the pre-set speed threshold, it is considered that the second vehicle has no intention to laterally cut in; if the lateral speed of the second vehicle is greater than or equal to the pre-set speed threshold, it is considered that the second vehicle has the intention to laterally cut in.

[0133] After classification, parameters can be learned for the hidden Markov network with the latent variable being the lateral motion characteristics of the second vehicle, the observed variables being the lateral velocity of the second vehicle, and the lateral distance between the first and second vehicles, based on the classification results, until the model converges.

[0134] Thus, after training the first prediction model and the second prediction model based on driving data under the same interaction scenario, the longitudinal and lateral motion characteristics of the second vehicle can be accurately predicted in the above step S311, thereby effectively ensuring the accuracy of identifying the motion characteristics of the second vehicle at the current moment.

[0135] In this embodiment of the disclosure, the motion characteristics at an intermediate moment can also be corrected based on the motion characteristics at multiple adjacent moments to prevent the phenomenon of result jumps or jitters during the process of recognizing the motion characteristics of the second vehicle.

[0136] Specifically, if the motion characteristics of the second vehicle at the first moment are inconsistent with those at the second moment, then the motion characteristics of the second vehicle at the third moment are obtained; where the second moment is the moment immediately preceding the first moment, and the third moment is the moment immediately following the first moment; if the motion characteristics of the second vehicle at the third moment are consistent with those at the second moment, then the motion characteristics of the second vehicle at the second moment are taken as the motion characteristics of the second vehicle at the first moment.

[0137] For example, the motion characteristics at time t can be modified based on the motion characteristics at time t-1, time t, and time t+1. If the motion characteristics at time t are inconsistent with the motion characteristics at time t-1, the motion characteristics at time t+1 can be obtained. If the motion characteristics at time t+1 are consistent with the motion characteristics at time t-1, the motion characteristics at time t-1 can be used as the motion characteristics at time t.

[0138] Thus, by correcting the motion characteristics at intermediate moments based on the motion characteristics at multiple adjacent moments, it is possible to prevent jumps or jitters in the recognition results of the second vehicle's motion characteristics during the recognition process, thereby ensuring the stability of the recognition of the second vehicle's motion characteristics.

[0139] Example 3

[0140] The above method embodiments can be executed by a vehicle control device in an interactive scenario. This vehicle control device can be a functional module or unit in a vehicle used to implement the methods described in the embodiments of this disclosure. Figure 6 As shown, this disclosure provides a vehicle control device 600 for interactive scenarios, including:

[0141] The determination module 601 is used to determine the degree of interaction between the first vehicle and the second vehicle at the current moment; the second vehicle is the vehicle surrounding the first vehicle; the degree of interaction is used to characterize the likelihood of the first vehicle interacting with the second vehicle during the autonomous driving process.

[0142] The first decision module 602 is used to determine the motion characteristics of the second vehicle at the current moment when the interaction level is strong interaction, and to perform autonomous driving decisions on the first vehicle based on the motion characteristics of the second vehicle at the current moment; strong interaction is used to characterize that the probability of the first vehicle interacting with the second vehicle during the autonomous driving process is greater than a preset threshold; the motion characteristics of the second vehicle are used to characterize the driving intention of the second vehicle.

[0143] The second decision module 603 is used to make autonomous driving decisions for the first vehicle based on the level of interaction when the level of interaction is weak. The autonomous driving decision is used to determine the driving state of the first vehicle. Weak interaction is used to indicate that the probability of the first vehicle interacting with the second vehicle during the autonomous driving process is less than a preset threshold.

[0144] Optionally, the determination module 601 is specifically used for:

[0145] Acquire interaction scenario information; the interaction scenario information is used to characterize the interaction scenario between the first vehicle and the second vehicle.

[0146] Based on at least one of the following: interactive scene information, the first relative interaction time corresponding to the current time, and the second relative interaction time corresponding to the current time, the degree of interaction between the first vehicle and the second vehicle at the current time is determined; the first relative interaction time is the relative interaction time between the first vehicle and the second vehicle; the second relative interaction time is the relative interaction time between the first vehicle and the endpoint of the interactive area in the interactive scene.

[0147] Optionally, the determination module 601 is specifically used for:

[0148] If, based on the interaction scenario information, it is determined that the second vehicle does not have the conditions to move laterally to the lane where the first vehicle is located, then the degree of interaction between the first vehicle and the second vehicle at the current moment is determined according to the first relative interaction time and / or the second relative interaction time at the current moment.

[0149] If, based on the interaction scenario information, it is determined that the second vehicle has the conditions to move laterally to the lane where the first vehicle is located, then the degree of interaction between the first and second vehicles at the current moment is determined based on the historical motion characteristics of the second vehicle; or, the degree of interaction between the first and second vehicles at the current moment is determined based on the first relative interaction time and / or the second relative interaction time corresponding to the current moment; the historical motion characteristics of the second vehicle are used to characterize the motion characteristics of the second vehicle at the previous moment adjacent to the current moment.

[0150] Optionally, the determination module 601 is specifically used for:

[0151] If the current time is not the initial time, and the historical motion characteristics of the second vehicle indicate that the second vehicle did not have the driving intention to move laterally to the lane where the first vehicle is located in the previous time, or if the current time is the initial time, then the degree of interaction between the first vehicle and the second vehicle at the current time is determined based on the first relative interaction time and / or the second relative interaction time corresponding to the current time.

[0152] If the current moment is not the initial moment, and the historical motion characteristics of the second vehicle indicate that the second vehicle had the driving intention to move laterally to the lane where the first vehicle was located in the previous moment, then the interaction level between the first vehicle and the second vehicle at the current moment is determined to be strong interaction.

[0153] Optionally, the determination module 601 is specifically used for:

[0154] Based on the first relative interaction time and the second relative interaction time corresponding to the current moment, as well as the first relative interaction time and the second relative interaction time corresponding to the previous moment adjacent to the current moment, the interaction degree between the first vehicle and the second vehicle at the current moment is corrected to obtain the corrected interaction degree, and the corrected interaction degree is used as the interaction degree between the first vehicle and the second vehicle at the current moment.

[0155] Optionally, the determination module 601 is specifically used for:

[0156] Determine the first difference and the second difference; the first difference is determined based on the first relative interaction time corresponding to the current time and the first relative interaction time corresponding to the previous time adjacent to the current time; the second difference is determined based on the second relative interaction time corresponding to the current time and the second relative interaction time corresponding to the previous time adjacent to the current time.

[0157] If the first difference is less than a preset first threshold and the second difference is less than a preset second threshold, then the interaction degree between the first vehicle and the second vehicle in the previous time adjacent to the current time is taken as the corrected interaction degree.

[0158] Optionally, the motion characteristics of the second vehicle at the current moment include longitudinal motion characteristics and lateral motion characteristics; the longitudinal motion characteristics of the second vehicle are used to characterize whether the second vehicle has the driving intention to use the right-of-way; the lateral motion characteristics of the second vehicle are used to characterize the driving intention of the second vehicle to move laterally to the lane where the first vehicle is located.

[0159] Optionally, the first decision module 602 is specifically used for:

[0160] The first time series and the second time series corresponding to the first preset time period are input into the pre-trained first prediction model to obtain the first result; the first time series is composed of the first relative interaction time corresponding to each moment included in the first preset time period; the second time series is composed of the third relative interaction time corresponding to each moment included in the first preset time period; the third relative interaction time is determined according to the speed and position of the second vehicle; the first prediction model is used to predict the longitudinal motion characteristics of the vehicle.

[0161] Based on the first result, the longitudinal motion characteristics of the second vehicle are determined.

[0162] Optionally, the first decision module 602 is specifically used for:

[0163] The velocity sequence and distance sequence corresponding to the second preset time period are input into the pre-trained second prediction model to obtain the second result; the velocity sequence is composed of the lateral velocity of the second vehicle at each moment included in the second preset time period; the distance sequence is composed of the lateral distance between the first vehicle and the second vehicle at each moment included in the second preset time period; the second prediction model is used to predict the lateral motion characteristics of the vehicle.

[0164] Based on the second result, the lateral motion characteristics of the second vehicle are determined.

[0165] Optionally, the first decision module 602 is specifically used for:

[0166] If the driving intention represented by the motion characteristics of the second vehicle at the current moment is inconsistent with the actual driving behavior of the second vehicle at the previous moment adjacent to the current moment, then the motion characteristics of the second vehicle at the current moment are modified so that the driving intention represented by the modified motion characteristics of the second vehicle is consistent with the actual driving behavior of the second vehicle at the previous moment, and the modified motion characteristics of the second vehicle are used as the motion characteristics of the second vehicle at the current moment; the actual driving behavior of the second vehicle is used to represent the driving intention of the second vehicle to use the right-of-way and / or the driving intention to move laterally to the lane where the first vehicle is located.

[0167] The above-described method embodiments are not limited to being executed by the vehicle control device in the interactive scenario, but can also be executed by other devices, such as electronic devices. These electronic devices can be integrated into the vehicle or can be independent of the vehicle. They can be devices that communicate with the vehicle, such as in-vehicle electronic devices or servers. These devices can control the vehicle to achieve autonomous driving based on the method described in this disclosure through their communication link with the vehicle. Figure 7 A schematic block diagram of an example electronic device 700 that can be used to implement embodiments of the present disclosure is shown. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0168] like Figure 7 As shown, the electronic device 700 includes a computing unit 701, which can perform various appropriate actions and processes based on a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 into a random access memory (RAM) 703. The RAM 703 may also store various programs and data required for the operation of the device 700. The computing unit 701, ROM 702, and RAM 703 are interconnected via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0169] Multiple components in electronic device 700 are connected to I / O interface 705, including: input unit 706, such as keyboard, mouse, etc.; output unit 707, such as various types of displays, speakers, etc.; storage unit 708, such as disk, optical disk, etc.; and communication unit 709, such as network card, modem, wireless transceiver, etc. Communication unit 709 allows device 700 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0170] The computing unit 701 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 701 performs the various methods and processes described above, such as the vehicle control method in an interactive scenario. For example, in some embodiments, the vehicle control method in an interactive scenario can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 708. In some embodiments, part or all of the computer program can be loaded and / or installed on device 700 via ROM 702 and / or communication unit 709. When the computer program is loaded into RAM 703 and executed by the computing unit 701, one or more steps of the vehicle control method in an interactive scenario described above can be performed. Alternatively, in other embodiments, the computing unit 701 can be configured to perform the vehicle control method in an interactive scenario by any other suitable means (e.g., by means of firmware).

[0171] In another example, this disclosure also provides a vehicle that may include a vehicle control device 600 for interactive scenarios, or the aforementioned electronic device 700.

[0172] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0173] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0174] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0175] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0176] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0177] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0178] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0179] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A vehicle control method applied to a first vehicle in autonomous driving, comprising: obtaining interaction scenario information; the interaction scenario information is used to represent an interaction scenario corresponding to the first vehicle and a second vehicle; the second vehicle is a vehicle around the first vehicle; determining an interaction degree between the first vehicle and the second vehicle at a current time based on at least one of the interaction scenario information, a first relative interaction time corresponding to the current time, and a second relative interaction time corresponding to the current time; the first relative interaction time is a relative interaction time between the first vehicle and the second vehicle; the second relative interaction time is a relative interaction time between the first vehicle and an end point of an interaction region in the interaction scenario; the interaction degree is used to represent a possibility of interaction between the first vehicle and the second vehicle during autonomous driving; in a case that the interaction degree is a strong interaction, determining a motion characteristic of the second vehicle at the current time, and performing an autonomous driving decision for the first vehicle according to the motion characteristic of the second vehicle at the current time; the strong interaction is used to represent that the possibility of interaction between the first vehicle and the second vehicle during autonomous driving is greater than a preset threshold; the motion characteristic of the second vehicle is used to represent a driving intention of the second vehicle; in a case that the interaction degree is a weak interaction, performing an autonomous driving decision for the first vehicle according to the interaction degree; the autonomous driving decision is used to determine a driving state of the first vehicle; the weak interaction is used to represent that the possibility of interaction between the first vehicle and the second vehicle during autonomous driving is less than the preset threshold.

2. The method of claim 1, wherein, the determining of the interaction degree between the first vehicle and the second vehicle at the current time based on at least one of the interaction scenario information, the first relative interaction time corresponding to the current time, and the second relative interaction time corresponding to the current time comprises: if it is determined based on the interaction scenario information that the second vehicle does not have a condition to move laterally to a lane where the first vehicle is located, then determining the interaction degree between the first vehicle and the second vehicle at the current time according to the first relative interaction time corresponding to the current time and / or the second relative interaction time corresponding to the current time; if it is determined based on the interaction scenario information that the second vehicle has a condition to move laterally to the lane where the first vehicle is located, then determining the interaction degree between the first vehicle and the second vehicle at the current time based on a historical motion characteristic of the second vehicle, or determining the interaction degree between the first vehicle and the second vehicle at the current time based on the first relative interaction time corresponding to the current time and / or the second relative interaction time corresponding to the current time; the historical motion characteristic of the second vehicle is used to represent a motion characteristic of the second vehicle at a previous time adjacent to the current time.

3. The method of claim 2, wherein, The interaction degree between the first vehicle and the second vehicle at the current time is determined based on historical motion characteristics of the second vehicle; or, the interaction degree between the first vehicle and the second vehicle at the current time is determined based on the first relative interaction time corresponding to the current time and / or the second relative interaction time corresponding to the current time, comprising: If the current time is a non-initial time, and the historical motion characteristics of the second vehicle represent that the second vehicle does not have a driving intention to move laterally to the lane where the first vehicle is located at the previous time, or if the current time is an initial time, the interaction degree between the first vehicle and the second vehicle at the current time is determined based on the first relative interaction time corresponding to the current time and / or the second relative interaction time corresponding to the current time. If the current time is a non-initial time, and the historical motion characteristics of the second vehicle represent that the second vehicle has a driving intention to move laterally to the lane where the first vehicle is located at the previous time, it is determined that the interaction degree between the first vehicle and the second vehicle at the current time is the strong interaction.

4. The method of any one of claims 1-3, wherein, The determination of the interaction degree between the first vehicle and the second vehicle at the current time comprises: The interaction degree between the first vehicle and the second vehicle at the current time is corrected based on the first relative interaction time corresponding to the current time and the second relative interaction time corresponding to the current time, and the first relative interaction time corresponding to the previous time adjacent to the current time and the second relative interaction time corresponding to the previous time adjacent to the current time, to obtain a corrected interaction degree, and the corrected interaction degree is taken as the interaction degree between the first vehicle and the second vehicle at the current time.

5. The method of claim 4, wherein, The correction of the interaction degree between the first vehicle and the second vehicle at the current time based on the first relative interaction time corresponding to the current time and the second relative interaction time corresponding to the current time, and the first relative interaction time corresponding to the previous time adjacent to the current time and the second relative interaction time corresponding to the previous time adjacent to the current time, to obtain a corrected interaction degree, comprises: The first difference and the second difference are determined; the first difference is determined according to the first relative interaction time corresponding to the current time and the first relative interaction time corresponding to the previous time adjacent to the current time; the second difference is determined according to the second relative interaction time corresponding to the current time and the second relative interaction time corresponding to the previous time adjacent to the current time; If the first difference is less than a preset first threshold value, and the second difference is less than a preset second threshold value, the interaction degree between the first vehicle and the second vehicle at the previous time adjacent to the current time is taken as the corrected interaction degree.

6. The method of claim 1, wherein, The motion characteristics of the second vehicle at the current time include longitudinal motion characteristics and lateral motion characteristics; the longitudinal motion characteristics of the second vehicle are used to represent whether the second vehicle has a driving intention to use the right-of-way; The lateral motion characteristics of the second vehicle are used to represent a driving intention of the second vehicle to move laterally to the lane where the first vehicle is located.

7. The method of claim 6, wherein, The determination of the longitudinal motion characteristics of the second vehicle at the current time comprises: inputting a first time sequence corresponding to a first preset time period and a second time sequence into a first prediction model trained in advance to obtain a first result; the first time sequence is composed of first relative interaction times corresponding to each time point included in the first preset time period; the second time sequence is composed of third relative interaction times corresponding to each time point included in the first preset time period; the third relative interaction time is determined according to the speed and position of the second vehicle; the first prediction model is used to predict the longitudinal motion characteristic of the vehicle; determining the longitudinal motion characteristic of the second vehicle according to the first result.

8. The method of claim 6, wherein, determining the lateral motion characteristic of the second vehicle at the current time point, comprising: inputting a speed sequence corresponding to a second preset time period and a distance sequence into a second prediction model trained in advance to obtain a second result; the speed sequence is composed of lateral speeds of the second vehicle at each time point included in the second preset time period; the distance sequence is composed of lateral distances between the first vehicle and the second vehicle at each time point included in the second preset time period; the second prediction model is used to predict the lateral motion characteristic of the vehicle; determining the lateral motion characteristic of the second vehicle according to the second result.

9. The method according to any one of claims 6-8, wherein, the determination of the motion characteristic of the second vehicle at the current time point, comprising: if the driving intention represented by the motion characteristic of the second vehicle at the current time point is inconsistent with the actual driving behavior of the second vehicle at a previous time point adjacent to the current time point, then correcting the motion characteristic of the second vehicle at the current time point, so that the driving intention represented by the corrected motion characteristic of the second vehicle is consistent with the actual driving behavior of the second vehicle at the previous time point; the corrected motion characteristic of the second vehicle is used as the motion characteristic of the second vehicle at the current time point; wherein the actual driving behavior of the second vehicle is used to represent the driving intention of the second vehicle to use the right-of-way and / or the driving intention of the second vehicle to move laterally to the lane where the first vehicle is located. 10.A vehicle control device applied to a first vehicle in automatic driving, comprising: a determination module configured to acquire interaction scene information, and determine an interaction degree between the first vehicle and a second vehicle at a current time point based on at least one of the interaction scene information, a first relative interaction time corresponding to the current time point, and a second relative interaction time corresponding to the current time point; the interaction scene information is used to represent an interaction scene corresponding to the first vehicle and the second vehicle; the second vehicle is a vehicle around the first vehicle; the first relative interaction time is a relative interaction time between the first vehicle and the second vehicle; the second relative interaction time is a relative interaction time between the first vehicle and an end point of an interaction region in the interaction scene; the interaction degree is used to represent a possibility size of interaction between the first vehicle and the second vehicle during automatic driving; a first decision module, configured to determine a motion characteristic of the second vehicle at a current time point when the interaction degree is a strong interaction, and perform automatic driving decision for the first vehicle according to the motion characteristic of the second vehicle at the current time point; the strong interaction is used to represent that a possibility of interaction between the first vehicle and the second vehicle during automatic driving of the first vehicle is greater than a preset threshold; and the motion characteristic of the second vehicle is used to represent a driving intention of the second vehicle; a second decision module, configured to perform automatic driving decision for the first vehicle according to the interaction degree when the interaction degree is a weak interaction; the automatic driving decision is used to determine a driving state of the first vehicle; and the weak interaction is used to represent that a possibility of interaction between the first vehicle and the second vehicle during automatic driving of the first vehicle is less than the preset threshold. 11.An electronic device, comprising: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-9. 12.An autonomous vehicle comprising the vehicle control device of claim 10 or the electronic device of claim 11.

13. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, the computer instructions are used to enable the computer to perform the method of any one of claims 1-9. 14.A computer program product comprising a computer program which, when executed by a processor, implements the method of any one of claims 1-9.

Images